System

Abstract

To provide a system.SOLUTION: A system includes the means for: acquiring requirements to be satisfied or a necessary condition being reference in generating a new project idea or marketing content provided from a user; generating a prompt sentence to be inputted to a generative AI model on the basis of the necessary condition; transmitting content generated by the generative AI model to the user by inputting the prompt sentence in the generative AI model; receiving a feedback including a correction point or an improvement point from the user to the content; and acquiring the improved content generated by using the generative AI model on the basis of the feedback.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] The issue is the decline in planning quality due to a lack of resources in the planning department. [Means for solving the problem]

[0005] As a means of solving this problem, a system is proposed that provides an AI generation means that generates concepts and marketing content for new project ideas that meet the necessary conditions, and a testing means that performs concept testing in market research and AB testing on the web to ensure the quality of the generated content. Specifically, the AI ​​generation means generates content using creative answers, and the testing means selects content that will appeal to customers, improving the quality of the project and increasing the probability of sales. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16]FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, a system including an AI generation means and a testing means is provided. The AI ​​generation means generates concepts and marketing content for new planning ideas that satisfy necessary conditions. Specifically, the AI ​​generation means generates content by utilizing creative answers based on necessary conditions set by the planning department. For example, when generating planning ideas for a new product, the AI ​​generation means generates planning ideas that satisfy necessary conditions such as the target customer segment, the market environment, and the characteristics of the product.

[0029] "Example 2"

[0030] In addition, a testing method is provided to ensure the quality of the generated content. The testing method involves market research concept testing and web AB testing, and by selecting content that will appeal to customers, the quality of the plan is improved and the probability of sales is increased. For example, market research concept testing is conducted on multiple plan ideas generated by the AI ​​generation method, and the plan idea with the highest evaluation based on customer evaluation is selected. In addition, web AB testing is conducted, and the plan idea with the best response is selected based on actual customer reactions.

[0031] The process flow of each embodiment will be described below.

[0032] "Example 1"

[0033] Step 1: The planning department sets the requirements, including the target customer group, market environment, product characteristics, etc.

[0034] Step 2: The AI ​​generator uses creative answers to generate new business idea concepts and marketing content based on the set requirements.

[0035] Step 3: The planning department reviews the generated planning ideas and makes corrections or additions as necessary.

[0036] "Example 2"

[0037] Step 1: Conduct market research concept testing on multiple planning ideas generated by the AI ​​generation method.

[0038] Step 2: Select the most highly rated project idea based on customer evaluations.

[0039] Step 3: Conduct online AB testing of the selected project ideas.

[0040] Step 4: Based on actual customer reactions, the project idea with the best response is finally selected.

[0041] Example 1

[0042] Next, a description will be given of Example 1 of the embodiment 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".

[0043] In conventional systems for generating new project ideas and marketing content, the process from when the user inputs the necessary conditions to when the generated content is evaluated and improved is complicated, making it difficult to efficiently generate high-quality content. In addition, market research and web AB testing to ensure the quality of the generated content are often done manually, which is time-consuming and labor-intensive.

[0044] 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.

[0045] In this invention, the server includes a generating means for generating concepts and marketing content for new project ideas that satisfy necessary conditions, an evaluating means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an input means for a user to input necessary conditions, a generating means for generating a prompt sentence based on the input necessary conditions, a generating means for inputting the generated prompt sentence into a generative AI model to generate content, a transmitting means for transmitting the generated content to a user's terminal, and an evaluating means for receiving feedback from the user and evaluating and improving the content. This makes it possible to streamline the process from when the user inputs necessary conditions to when the generated content is evaluated and improved, and to generate high-quality content quickly.

[0046] "Requirements" are requirements or standards that must be met when a user generates a new project idea or marketing content.

[0047] A "new project idea" is a proposal or concept that adds new value or features to an existing product or service.

[0048] "Marketing Content" means information or messages intended to promote or sell a product or service.

[0049] The "generation means" refers to a method or device for generating new project ideas and marketing content based on necessary conditions.

[0050] An "assessment means" is a method or device for assessing the quality of the generated content and improving it if necessary.

[0051] An "input means" is a method or device by which a user inputs requirements into the system.

[0052] A "prompt sentence" is an instruction sentence input into a generative AI model and is generated based on necessary conditions.

[0053] A "generative AI model" is an algorithm or program that uses artificial intelligence to generate new planning ideas and marketing content.

[0054] The "transmitting means" refers to a method or device for transmitting the generated content to a user's terminal.

[0055] "Feedback" refers to information about corrections or improvements provided by a user to generated content.

[0056] The present invention relates to a system for generating new project ideas and marketing contents that satisfy necessary conditions, and evaluating and improving the quality of the generated ideas and contents. The system includes a generating means, an evaluating means, an inputting means, a transmitting means, and a feedback means.

[0057] The server hosts a generative AI model as a generating means. Specifically, the server uses a generative AI model such as GPT-4 (registered trademark) by OpenAI (registered trademark). When a user inputs a necessary condition through an input means, the server receives it and generates a prompt sentence. The generated prompt sentence is input to the generative AI model, and new project ideas and marketing content are generated.

[0058] Users access the system using a terminal (PC or tablet) and input their requirements. Requirements include target customer segments, market environment, product characteristics, etc. For example, a user may input the following requirements:

[0059] Target customer demographic: Young people in their 20s

[0060] Market environment: Online shopping is mainstream

[0061] Product features: Eco-friendly materials used

[0062] Based on these requirements, the server will generate a prompt like this:

[0063] "Generate product ideas for new products using eco-friendly materials to be sold on the online shopping market, targeting young people in their 20s."

[0064] The server inputs this prompt into the generative AI model and receives the generated content, such as the following:

[0065] "We are proposing a stylish backpack made from recycled materials for young people in their 20s. This backpack will be sold exclusively online, and customers who purchase it will receive eco points as a special perk."

[0066] The server transmits the generated content to the user's terminal. The terminal displays the received content to the user. The user checks the generated content and provides feedback, if necessary. The feedback may include corrections or improvements.

[0067] The server receives feedback from users and evaluates and improves the content using the evaluation means, which improves the quality of the generated content and allows it to meet user requirements with greater accuracy.

[0068] This system streamlines the process from when users input their requirements to when they evaluate and improve the generated content, making it possible to quickly generate high-quality content.

[0069] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0070] Step 1:

[0071] A user logs into the system using a terminal. The user inputs requirements such as target customer demographics, market environment, and product characteristics. The input requirements are sent to the server. Specifically, the user enters requirements into the input form and clicks the "Submit" button. Input: Requirements. Output: Requirements sent to the server.

[0072] Step 2:

[0073] The server receives the requirements sent by the user. The server generates a prompt sentence based on the received requirements. Specifically, the server analyzes the requirements and creates a prompt sentence in a format suitable for the generative AI model. Input: Requirements from the user. Output: Generated prompt sentence.

[0074] Step 3:

[0075] The server inputs the generated prompt sentence into the generative AI model. The server waits for the generative AI model to generate content based on the prompt sentence. Specifically, the server sends the prompt sentence to the generative AI model through the API and receives the generated content. Input: Generated prompt sentence. Output: Generated content from the generative AI model.

[0076] Step 4:

[0077] The server sends the content received from the generative AI model to the user's device. The device displays the received content to the user. In concrete terms, the server sends the generated content to the user's device in real time, and the device displays the content on its screen. Input: Generated content from the generative AI model. Output: Content displayed on the user's device.

[0078] Step 5:

[0079] The user checks the generated content displayed on the terminal. If necessary, the user inputs feedback on corrections and improvements. Specifically, the user enters comments in the feedback form and clicks the "Submit" button. Input: Generated content. Output: Feedback from the user.

[0080] Step 6:

[0081] The server receives feedback from the user. The server evaluates the generated content based on the feedback and makes improvements if necessary. Specifically, the server analyzes the feedback and sends the prompt sentence to the generative AI model again to generate improved content. Input: User feedback. Output: Improved generated content.

[0082] (Application example 1)

[0083] Next, a description will be given of Application Example 1 of Form 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."

[0084] Conventional advertising content generation systems have had difficulty generating effective advertising content based on conditions such as target customer segments, market environment, and product characteristics. In addition, there was a lack of market research and testing methods to ensure the quality of the generated content, making it impossible to maximize the effectiveness of advertising. This resulted in a problem of reduced advertising effectiveness and the inability to expect an increase in sales.

[0085] 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.

[0086] In this invention, the server includes an AI generation means for generating new project idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a smartphone application for generating advertising content based on conditions such as target customer segments, market environment, product characteristics, etc. This makes it possible to generate effective advertising content and ensure its quality.

[0087] "Requirements" are conditions that must be met when generating advertising content, such as target customer segments, market environment, and product characteristics.

[0088] A "new project idea" is a new concept or marketing strategy that has never been seen before.

[0089] "Marketing content" refers to materials such as text, images, and videos used to promote products and services.

[0090] "AI generation means" refers to a means of using artificial intelligence to generate new planning ideas and marketing content that meets necessary conditions.

[0091] "Testing methods" refer to the means of conducting market research concept tests and AB tests on the web to ensure the quality of the generated content.

[0092] A "target demographic" is a particular group of customers to whom an advertisement or product is primarily directed.

[0093] "Market environment" refers to external factors such as the competitive situation and trends in the market in which the advertisement or product is developed.

[0094] "Product features" are the specific characteristics or benefits of an advertisement or product.

[0095] A "smartphone application" is a software program that runs on a smartphone.

[0096] "Advertising content" refers to materials such as text, images, and videos created to promote a specific product or service.

[0097] The following system configuration is necessary to implement this invention. The system includes an AI generation means for generating new project idea concepts and marketing content that meet required conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a smartphone application for generating advertising content based on conditions such as the target customer demographic, market environment, and product characteristics.

[0098] The server uses a generative AI model such as OpenAI's GPT-3 (registered trademark) to generate advertising content based on the requirements entered by the user, such as the target customer demographic, market environment, and product characteristics. Specifically, when the user enters the requirements through a smartphone application, the server converts them into a prompt text and sends it to the generative AI model. The generative AI model generates creative advertising content based on the prompt text and returns it to the user.

[0099] For example, if the target customer group is set as "women in their 20s," the market environment is set as "highly competitive cosmetics market," and the product characteristics are set as "highly moisturizing," the following prompt sentence will be generated.

[0100] Example prompt:

[0101] Target customer group: Women in their 20s

[0102] Market environment: Highly competitive cosmetics market

[0103] Product Features: High moisturizing effect

[0104] Please generate advertising content that meets the above criteria.

[0105] For example, the generated advertising content might be, "Recommended for women in their 20s! A new product that's attracting attention in the highly competitive cosmetics market. It has high moisturizing effects and is perfect for those who suffer from dry skin. Try it now!"

[0106] Furthermore, to ensure the quality of the generated advertising content, the server performs concept testing for market research and AB testing on the web, which allows it to predict the effectiveness of advertising and propose optimal advertising ideas to users.

[0107] In this way, it becomes possible to generate effective advertising content and ensure its quality.

[0108] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0109] Step 1:

[0110] The user launches the smartphone application and inputs necessary conditions such as the target customer group, market environment, and product characteristics.

[0111] Input: Target customer group, market environment, product characteristics

[0112] Output: Prerequisites entered

[0113] Specific operation: The user enters the target customer group (e.g., women in their 20s), market environment (e.g., highly competitive cosmetics market), and product characteristics (e.g., high moisturizing effect) into the application's input form.

[0114] Step 2:

[0115] The terminal converts the input requirements into a prompt text and sends it to the server.

[0116] Input: Requirements

[0117] Output: Prompt statement

[0118] Specific behavior: The application converts the entered requirements into a prompt like this:

[0119] Target customer group: Women in their 20s

[0120] Market environment: Highly competitive cosmetics market

[0121] Product Features: High moisturizing effect

[0122] Please generate advertising content that meets the above criteria.

[0123] This prompt is sent to the server.

[0124] Step 3:

[0125] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate advertising content based on the prompt text.

[0126] Input: prompt statement

[0127] Output: Ad content

[0128] Specific operation: The server inputs the prompt text into the AI ​​model and obtains the generated ad content. For example, the ad content generated is "Recommended for women in their 20s! A new product that is attracting attention in the highly competitive cosmetics market. Highly moisturizing, perfect for those who suffer from dry skin. Try it now!"

[0129] Step 4:

[0130] The server sends the generated advertising content back to the terminal.

[0131] Input: Ad content

[0132] Output: Ad content sent to the device

[0133] Specific operations: The server transmits the generated advertising content to the terminal.

[0134] Step 5:

[0135] The terminal displays the received advertisement content to the user.

[0136] Input: Ad content

[0137] Output: Ad content displayed

[0138] Specific behavior: The application displays the received advertising content to the user.

[0139] Step 6:

[0140] The user reviews the quality of the generated advertising content and corrects or regenerates it as necessary.

[0141] Input: Ad content

[0142] Output: The modified or regenerated ad content.

[0143] What happens: The user reviews the displayed ad content and, if necessary, corrects it or requests that it be regenerated.

[0144] Step 7:

[0145] In order to ensure the quality of the advertising content generated by the server, we conduct concept tests for market research and A / B tests on the web.

[0146] Input: Ad content

[0147] Output: Test results

[0148] Specific operation: The server subjects the generated advertising content to market research concept testing and web-based AB testing and obtains the results.

[0149] Step 8:

[0150] The server proposes optimal advertising ideas to the user based on the test results.

[0151] Input: Test result

[0152] Output: Best ad recommendation

[0153] What happens: The server analyzes the test results and suggests optimal ads to the user.

[0154] Example 2

[0155] Next, a second embodiment of the second embodiment will be described. 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."

[0156] With conventional planning idea generation and evaluation systems, it was difficult to accurately evaluate the quality of the generated ideas and their response in the market. As a result, it was not possible to select planning ideas that would appeal to customers, and there was a problem that sales could not be expected to increase. Furthermore, there was also the issue that it was difficult to quickly bring ideas to market because the evaluation process of the generated ideas was complicated and time-consuming.

[0157] 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.

[0158] In this invention, the server includes a means for generating new planning ideas using a generative AI model, a means for conducting market research concept testing on the generated planning ideas, and a means for conducting AB testing on the web on the generated planning ideas, which makes it possible to quickly and accurately evaluate the quality of the generated planning ideas and select the optimal planning ideas that will appeal to customers.

[0159] A "generative AI model" is a type of artificial intelligence that uses natural language processing technology to generate new project ideas.

[0160] "New project ideas" are novel concepts and marketing content generated by generative AI models.

[0161] "Market research concept testing" is a method of collecting customer evaluations of generated planning ideas and verifying the validity of the ideas based on that evaluation data.

[0162] "Web AB testing" is a method of selecting the most effective idea by displaying different project ideas to actual customers and collecting and analyzing their response data.

[0163] "Server" refers to a computer system that executes the generative AI model and evaluates and selects the generated project ideas.

[0164] "Reaching the customer" means that the generated planning ideas will pique the customer's interest and stimulate their desire to purchase.

[0165] "Planning quality" is an index showing the market acceptability and effectiveness of the generated planning ideas.

[0166] The "probability of selling" is an index showing the possibility that the generated planning idea will be successful in the market and actually generate sales.

[0167] This invention is a system that generates new project ideas using a generative AI model and evaluates the ideas through concept testing in market research and AB testing on the web. A specific embodiment of this system will be described below.

[0168] The server generates new project ideas using a generative AI model (e.g., an advanced artificial intelligence model using natural language processing technology). An example of a generative AI model that can be used is OpenAI's GPT-4. The server inputs a prompt sentence into the generative AI model to generate multiple project ideas. An example of a specific prompt sentence is "Please generate five project ideas for a new smartphone app."

[0169] The generated project ideas are stored in a database by the server. The server then conducts market research concept testing. In the market research concept testing, market research tools such as SurveyMonkey and Qualtrics are used to collect customer evaluations of the generated project ideas. Specifically, the server creates a survey that includes the following question: "How interested are you in this app idea? (Please rate on a scale of 1-5)." Users answer the survey using their devices, and the server collects and analyzes the evaluation data.

[0170] Next, the server conducts AB testing on the web. In AB testing, different project ideas are displayed to actual customers using tools such as Google (registered trademark) Optimize and Optimizely, and reaction data is collected. Specifically, the server sets up the following test: "Show idea 1 to group A and idea 2 to group B, and compare which group makes more clicks." Users use their devices to view web pages and react to the displayed project ideas. The server analyzes the collected click data and selects the project idea with the best reaction.

[0171] Finally, the server comprehensively evaluates the results of the market research concept tests and the web-based AB tests to select the most highly rated and appealing plan idea. This selected plan idea is stored in a database and notified to the user.

[0172] This system makes it possible to quickly and accurately evaluate the quality of the generated planning ideas and select the most suitable planning idea that will appeal to customers, thereby improving the quality of the plan and increasing the probability of it selling.

[0173] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0174] Step 1:

[0175] The server generates new project ideas using the generative AI model. Specifically, the server inputs a prompt sentence, "Please generate five project ideas for a new smartphone app," into the generative AI model. The generative AI model generates five different project ideas based on this prompt sentence and returns them to the server. The server stores the generated project ideas in a database. The input is the prompt sentence, and the output is the generated project ideas.

[0176] Step 2:

[0177] The server conducts market research concept testing on the generated project ideas. Specifically, the server creates a survey using a market research tool (e.g., SurveyMonkey or Qualtrics). The survey includes questions such as, "How interested are you in this app idea? (Please rate on a scale of 1-5)." Users answer the survey using their terminals. The server collects evaluation data from users and stores it in a database. The input is the generated project idea and the survey responses, and the output is the evaluation data.

[0178] Step 3:

[0179] The server analyzes the collected evaluation data and selects the project idea with the highest evaluation. Specifically, the server statistically processes the evaluation data and calculates the average evaluation score of each project idea. The project idea with the highest score is selected and proceeds to the next step. The input is the evaluation data, and the output is the project idea with the highest evaluation.

[0180] Step 4:

[0181] The server conducts AB testing on the web for the selected project ideas. Specifically, the server uses an AB testing tool (e.g., Google Optimize or Optimizely) to display different project ideas to actual customers. For example, idea 1 is displayed to group A and idea 2 is displayed to group B, and a comparison is made to see which group makes more clicks. Users use their devices to view web pages and react to the displayed project ideas. The server saves the collected click data in a database. The input is the selected project idea and customer response data, and the output is click data.

[0182] Step 5:

[0183] The server analyzes the collected click data and selects the project idea with the best response. Specifically, the server statistically processes the click data and calculates the click rate of each project idea. The project idea with the highest click rate is finally selected. The input is the click data, and the output is the project idea with the best response.

[0184] Step 6:

[0185] The server saves the final selected project idea in a database and notifies the user. Specifically, the server saves the selected project idea in a database and notifies the user of the result via email or a notification system. The input is the project idea with the best response, and the output is the notification to the user.

[0186] (Application example 2)

[0187] Next, a description will be given of Application Example 2 of Form 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."

[0188] Traditionally, planning advertising campaigns and generating marketing content is often done manually, which is time-consuming and labor-intensive, and there is a lack of objective evaluation methods for selecting effective content. This makes the effectiveness of advertising campaigns uncertain, and may not lead to increased sales. Furthermore, market research and AB testing to ensure the quality of the generated content are also cumbersome, making it difficult to obtain rapid feedback.

[0189] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0190] In this invention, the server includes a generating AI model means for generating new planning idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing of market research and AB testing on the web to ensure the quality of the generated content, a means for generating planning ideas for advertising campaigns, calculating evaluations and click rates, and a means for selecting the most highly rated advertising campaign and proposing it to the advertiser. This makes it possible to consistently automate the process from planning to evaluation, selection, and proposal of advertising campaigns, and quickly implement effective advertising campaigns.

[0191] A "generative AI model means" is a means that uses artificial intelligence technology to generate new project idea concepts and marketing content that meet required conditions.

[0192] "Testing methods" refer to the means of conducting market research concept tests and AB tests on the web to ensure the quality of the generated content.

[0193] The "means for generating advertising campaign planning ideas" refers to means for generating new ideas for advertising campaigns and calculating ratings and click-through rates for those ideas.

[0194] The "means of proposing to advertisers" refers to the means of selecting the most highly rated advertising campaign and proposing the results to advertisers.

[0195] A system for implementing the present invention includes a generative AI model means, a testing means, a means for generating planning ideas for advertising campaigns, and a means for proposing ideas to advertisers.

[0196] The server generates new project idea concepts and marketing content that meet the requirements using a generative AI model means, which generates creative answers based on the prompt sentence, for example, using an OpenAI API.

[0197] Next, to ensure the quality of the generated content, we use testing methods to conduct concept tests for market research and AB tests on the web. From the multiple generated project ideas, we select the one with the highest evaluation based on customer evaluations and actual click rates.

[0198] The means for generating advertising campaign planning ideas uses a generative AI model means to generate new advertising campaign ideas and calculate ratings and click-through rates for the ideas, the means being implemented using a programming language such as Python.

[0199] Finally, the most highly evaluated advertising campaign is selected using a means for proposing to the advertiser, and the result is proposed to the advertiser. This means generates a report for proposing the optimal advertising campaign to the advertiser based on the evaluation result and the click-through rate data.

[0200] As a specific example, when considering an advertising campaign for a new beverage, the prompt sentence is "Generate ideas for an advertising campaign for a new beverage." Based on this prompt sentence, the generative AI model means generates multiple advertising campaign ideas, and by conducting concept tests in market research and AB tests on the web for those ideas, the most effective advertising campaign can be selected and proposed to the advertiser.

[0201] This system automates the entire process of advertising campaigns, from planning to evaluation, selection and proposal, making it possible to quickly implement effective advertising campaigns.

[0202] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0203] Step 1:

[0204] The server uses a generative AI model means to generate concepts and marketing content for new project ideas. Specifically, the server sends a prompt sentence, "Please generate an idea for a new beverage advertising campaign," as an input to a generative AI model (e.g., OpenAI's API), and receives the generated multiple advertising campaign ideas as an output.

[0205] Step 2:

[0206] The server performs market research concept testing on the generated advertising campaign ideas. Specifically, the server inputs the generated ideas into a market research tool, collects evaluation data from customers, calculates an evaluation score for each idea based on the evaluation data, and obtains the evaluation score as an output.

[0207] Step 3:

[0208] The server selects the best-rated advertising campaign idea based on the rating scores, by comparing the rating scores, selecting the idea with the highest score, and obtaining the idea as an output.

[0209] Step 4:

[0210] The server performs AB testing on the web for the selected advertising campaign ideas. Specifically, the selected ideas are input into an AB testing tool, and actual click-through rate data is collected. Based on the click-through rate data, the click-through rate for each idea is calculated, and the click-through rate is obtained as output.

[0211] Step 5:

[0212] The server selects the advertising campaign idea that has the best response based on the click-through rate, by comparing the click-through rates, selecting the idea with the highest click-through rate, and obtaining the idea as an output.

[0213] Step 6:

[0214] The server proposes the most highly rated and most responsive advertising campaign ideas to the advertiser. Specifically, the server compiles the selected ideas, their evaluation scores, and click-through rates in a report format and sends it to the advertiser. The server obtains the report as an output.

[0215] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0216] "Example 1"

[0217] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system recognizes the emotion of a user and generates new project idea concepts and marketing content according to the emotion. Specifically, the emotion engine recognizes the emotion of the user, and the AI ​​generation means generates content by utilizing creative answers based on the emotion. For example, when the user expresses an emotion of joy, the AI ​​generation means generates a project idea according to the emotion of joy. This makes it possible to generate project ideas corresponding to the emotion of the user.

[0218] "Example 2"

[0219] A testing method using an emotion engine is also provided. This testing method improves the quality of the plan and increases the probability of sales by recognizing the user's emotions and selecting content that will appeal to customers according to those emotions. Specifically, the emotion engine recognizes the user's emotions and performs concept testing for market research and AB testing on the web based on those emotions. For example, if a user expresses an emotion of joy, the testing method selects content that corresponds to that emotion and performs market research and AB testing for that content. This makes it possible to select content that corresponds to the user's emotions and improve the quality.

[0220] The process flow of each embodiment will be described below.

[0221] "Example 1"

[0222] Step 1: Recognize the user's emotion using the emotion engine.

[0223] Step 2: Based on the recognized sentiment, the AI ​​generator uses the creative answers to generate new project idea concepts and marketing content.

[0224] Step 3: Present the generated planning ideas and marketing content to the user.

[0225] "Example 2"

[0226] Step 1: Recognize the user's emotion using the emotion engine.

[0227] Step 2: Based on the emotions identified, conduct market research concept testing and web-based A / B testing.

[0228] Step 3: Based on the test results, select content that will resonate with customers, improve the quality of the plan, and increase the probability of sales.

[0229] Example 1

[0230] Next, a description will be given of Example 1 of the embodiment 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".

[0231] In conventional systems, it was difficult to take users' emotions into account when generating new project ideas and marketing content, and the generated content did not necessarily match the user's emotions. In addition, there was a lack of evaluation methods to ensure the quality of the generated content, making it difficult to maximize the effectiveness of the content.

[0232] 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.

[0233] In this invention, the server includes a generating means for generating new project idea concepts and marketing content that satisfy the necessary conditions, an evaluating means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognizing means for recognizing the emotion of a user and generating content according to the emotion, and a control means for generating a prompt sentence based on the emotion data obtained from the emotion recognizing means and the necessary conditions and sending it to the generating means. This makes it possible to generate new project ideas and marketing content that match the emotion of the user, and further to evaluate and improve the quality of the generated content.

[0234] The "generation means" refers to a means for generating concepts for new project ideas and marketing content that meet the necessary conditions.

[0235] "Evaluation methods" refer to methods used for conducting market research concept tests and web-based A / B tests to ensure the quality of the generated content.

[0236] The "emotion recognition means" is a means for recognizing the user's emotion and generating content in accordance with that emotion.

[0237] The "control means" is a means for generating a prompt sentence based on the emotion data obtained from the emotion recognition means and the necessary conditions, and sending the prompt sentence to the generation means.

[0238] A "prompt sentence" is an instruction sentence used by the generating means when generating new project ideas and marketing content.

[0239] A "new business idea" is a concept for a new product or service that is not yet on the market.

[0240] "Marketing content" refers to advertising and promotional materials used to promote products and services to the market.

[0241] "Requirements" are conditions that the generated content must satisfy, such as the target customer group, market environment, and product characteristics.

[0242] The present invention relates to a system for generating concepts and marketing contents for new project ideas that satisfy requirements. The system includes a generating unit, an evaluating unit, an emotion recognizing unit, and a controlling unit.

[0243] Hardware and Software Used

[0244] Hardware: Servers, terminals

[0245] Software: Generative AI models (e.g. GPT-4), emotion engines (e.g. Affectiva)

[0246] Specific operation of the system

[0247] User Emotion Recognition

[0248] A user accesses the system using a terminal. The terminal's camera and microphone capture the user's facial expressions and voice in real time. The terminal sends the captured data to the emotion engine. The emotion engine analyzes the characteristics of the user's facial expressions and voice and recognizes emotions. For example, when a user smiles, the emotion engine recognizes the emotion of "happiness."

[0249] Setting Prerequisites

[0250] The planning department logs into the server and inputs the necessary conditions. The server saves the input necessary conditions in a database. The necessary conditions include the target customer group, the market environment, and the characteristics of the product. For example, the target customer group can be set as "young people in their 20s," the market environment as "health-conscious," and the product characteristic as "low calorie."

[0251] Content Generation

[0252] The server sends the user's emotion data obtained from the emotion engine and the requirements provided by the planning department to the generation means. The generation means uses a generative AI model (e.g. GPT-4) to generate creative content based on the requirements and the user's emotions. The generative AI model receives the prompt sentence and generates content based on it.

[0253] Examples of prompt statements

[0254] The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low calorie. Users show happy emotions. Based on these conditions, generate planning ideas for a new beverage product.

[0255] For example, if the prompt is, "The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low calorie. Users are expressing feelings of joy. Based on these conditions, please generate planning ideas for a new beverage product," the generative AI model would generate ideas such as, "Propose low-calorie, vitamin-rich fruit juice for young people in their 20s."

[0256] Testing and Feedback

[0257] The server sends the generated content to the evaluator. The evaluator evaluates the generated content and provides feedback. The server receives the test results and modifies the content as necessary. For example, if the evaluator provides feedback such as "The idea for the proposed fruit juice is good, but more specific ingredient information is needed," the server resends the prompt sentence to the generative AI model based on the feedback to generate modified content.

[0258] In this way, new project ideas and marketing content are generated based on the user's emotions and requirements.

[0259] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0260] Step 1:

[0261] User Emotion Recognition

[0262] Input: A user logs in to a device and allows access to the camera and microphone.

[0263] Specific operation: The device captures the user's facial expressions and voice in real time.

[0264] Data processing: The device sends the captured data to the emotion engine, which analyzes the user's facial expressions and voice characteristics to recognize emotions.

[0265] Output: The emotion engine sends the recognized emotion data to the server. For example, if the user smiles, the emotion engine recognizes the emotion of "happiness" and sends the data to the server.

[0266] Step 2:

[0267] Setting Prerequisites

[0268] Input: The planning department logs into the server and enters their requirements.

[0269] Specific Actions: The server stores the entered requirements in a database.

[0270] Data processing: Requirements include target customer demographics, market environment, product characteristics, etc.

[0271] Output: The server sends the saved requirements to the generator. For example, the target customer group is set as "young people in their 20s," the market environment is set as "health-conscious," and the product characteristic is set as "low calorie."

[0272] Step 3:

[0273] Content Generation

[0274] Input: The server sends the user's emotion data obtained from the emotion engine and the requirements provided by the planning department to the generator.

[0275] Specific operation: The generator uses a generative AI model (e.g., GPT-4) to generate creative content based on the requirements and user emotions.

[0276] Data processing: The generative AI model receives a prompt and generates content based on it.

[0277] Output: The generated content is sent to the server. For example, if the prompt is "The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low-calorie. The user shows an emotion of joy. Based on these conditions, please generate a planning idea for a new beverage product," the generative AI model will generate an idea such as "Propose a low-calorie, vitamin-rich fruit juice for young people in their 20s."

[0278] Step 4:

[0279] Testing and Feedback

[0280] Input: The server sends the generated content to the evaluator.

[0281] What to do: The evaluation tool evaluates the generated content and provides feedback.

[0282] Data processing: Evaluation measures assess the quality of content and identify areas for improvement.

[0283] Output: The server receives the test results and modifies the content as necessary. For example, if the evaluator gives feedback such as "The idea of ​​the proposed fruit juice is good, but more specific information on the ingredients is needed," the server sends the prompt sentence to the generative AI model again based on the feedback, and generates the modified content.

[0284] In this way, new project ideas and marketing content are generated based on the user's emotions and requirements.

[0285] (Application example 1)

[0286] Next, a description will be given of Application Example 1 of Form 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."

[0287] Conventional marketing content generation systems provide uniform content without considering the user's feelings, making it difficult to attract the user's interest. In addition, there was a lack of testing methods to ensure the quality of the generated content, which made it difficult to achieve effective marketing.

[0288] 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.

[0289] In this invention, the server includes an AI generation means for generating new project idea concepts and marketing content that meet the necessary conditions, a test means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognition means for recognizing the emotion of a user and generating content according to the emotion, and a display means for displaying the generated content in real time. This makes it possible to generate effective marketing content according to the emotion of a user and ensure its quality.

[0290] A "requirement" is a criterion or requirement that must be met in order to achieve a particular purpose or goal.

[0291] A "new project idea" is a new idea or plan that has never been seen before.

[0292] A "concept" is the basic idea or philosophy behind a project or product.

[0293] "Marketing Content" means information and materials used to promote and sell products and services.

[0294] An "AI generation means" refers to a function or device that uses artificial intelligence to automatically generate new planning ideas and marketing content.

[0295] "Testing Means" means any method or device for evaluating or verifying the quality of the Produced Content.

[0296] "Market research" refers to research activities conducted to understand consumer needs and market trends.

[0297] A "concept test" is a test conducted to evaluate whether a new plan or product concept will be accepted in the market.

[0298] "AB testing on the web" refers to the comparison of different versions of a web page or piece of content to evaluate which one is more effective.

[0299] "Emotion recognition means" refers to technology or devices for detecting and recognizing a user's emotions.

[0300] A "display means" refers to a method or device for visually presenting the generated content to a user.

[0301] As an embodiment of the present invention, an emotion-responsive advertisement generation system will be described as an example. This system includes an AI generation means for generating concepts and marketing content for new project ideas that satisfy necessary conditions, a testing means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognition means for recognizing the emotion of a user and generating content corresponding to the emotion, and a display means for displaying the generated content in real time.

[0302] Hardware and Software Used

[0303] Hardware: Smartphone camera

[0304] Software: OpenCV, Keras, Transformers libraries

[0305] Processing flow

[0306] 1. Camera image capture: Capture images in real time from the smartphone camera, which gives an image of the user's face.

[0307] 2. Face detection and emotion recognition: Detect faces using OpenCV and recognize the user's emotions using an emotion recognition model trained with Keras. Specifically, the face area is cut out, converted to grayscale, and then input to the emotion recognition model.

[0308] 3. Advertising content generation: Based on the recognized emotion, generate appropriate advertising content using the GPT-3 model. For example, if the user shows the emotion of happiness, input the prompt sentence "Generate advertising content appropriate for when the user shows the emotion of happiness" to the GPT-3 model.

[0309] 4. Display of advertising content: The generated advertising content is displayed on the camera footage in real time, allowing users to visually confirm the advertisements that correspond to their own emotions.

[0310] Examples

[0311] For example, if the user is expressing an emotion of joy, the following prompt sentence is input to the generative AI model:

[0312] Examples of prompt statements

[0313] Generate appropriate ad content when users are expressing the emotion of happiness.

[0314] When this prompt sentence is input into the GPT-3 model, advertising content such as "Why not try our new ice cream? It's on sale now at a special discount!" is generated. This advertising content is displayed in real time on the smartphone screen, attracting the user's interest.

[0315] The above is an embodiment of the present invention. This system makes it possible to generate effective marketing content in response to the user's emotions and to guarantee the quality of the content.

[0316] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0317] Step 1:

[0318] Capture video from a smartphone camera in real time. The input is the camera video and the output is the captured frames. Specifically, start the smartphone camera and continuously capture video.

[0319] Step 2:

[0320] Detect faces from captured frames. The input is the captured frame and the output is the detected face area. Specifically, we use OpenCV to detect faces in the frame and get the face position information.

[0321] Step 3:

[0322] The detected face area is converted to grayscale and input to the emotion recognition model. The input is the face area, and the output is the recognized emotion. Specifically, the face area is cut out, converted to grayscale, and then input to the emotion recognition model trained with Keras.

[0323] Step 4:

[0324] Based on the recognized emotion, appropriate advertising content is generated. The input is the recognized emotion, and the output is the generated advertising content. Specifically, a prompt sentence is generated according to the recognized emotion, and input to the GPT-3 model to generate advertising content.

[0325] Step 5:

[0326] The generated advertising content is displayed on the camera image in real time. The input is the generated advertising content, and the output is the advertising content displayed to the user. Specifically, the generated advertising content is superimposed on the captured frame and displayed on the smartphone screen.

[0327] The above are the specific processing steps of this system.

[0328] Example 2

[0329] Next, a second embodiment of the second embodiment will be described. 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."

[0330] Conventional marketing content generation systems make it difficult to select content that fully considers customer emotions and reactions, making it difficult to develop effective marketing strategies. In addition, there is a lack of testing methods to ensure the quality of the generated content, and specific methods to increase the probability of sales are required.

[0331] 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.

[0332] In this invention, the server includes a means for inputting a prompt sentence, a means for generating new project ideas and marketing content using a generative AI model, a means for conducting concept testing of market research to ensure the quality of the generated content, a means for conducting AB testing on the web, a means for using an emotion engine to recognize user emotions, and a means for selecting content based on emotion data. This makes it possible to generate and select effective marketing content that takes into account the emotions and reactions of customers.

[0333] A "prompt sentence" is a sentence of instructions or questions that is input to a generative AI model.

[0334] A "generative AI model" is an artificial intelligence algorithm that generates new project ideas and marketing content based on input prompt text.

[0335] "Market research concept testing" is a research instrument that gathers feedback from customers to evaluate the quality of the content generated.

[0336] "Web AB testing" is a testing method in which different versions of content are presented to actual website visitors and their reactions are compared.

[0337] An "emotion engine" is a technology that recognizes and analyzes emotions from a user's facial expressions, tone of voice, etc.

[0338] "Emotion data" is information regarding the user's emotions recognized by the emotion engine.

[0339] "Content selection method" is the process of selecting the most appropriate content based on generated content, test results, and sentiment data.

[0340] This invention is a system that uses a generative AI model to generate new project ideas and marketing content, and conducts market research and AB testing on the web to ensure the quality of the content. Furthermore, it is possible to select optimal content based on emotion data using an emotion engine that recognizes the user's emotions.

[0341] Hardware and Software Used

[0342] Hardware: Servers, terminals

[0343] Software: Generative AI models, emotion engines, web testing tools, online survey tools

[0344] Details of data processing and calculation

[0345] 1. Enter the prompt text

[0346] A user uses the device to input a prompt for the generative AI model, for example, "Generate marketing campaign ideas for a new smartphone."

[0347] 2. Generate project ideas

[0348] The server uses a generative AI model to generate multiple marketing campaign ideas based on the input prompt, and the generated ideas are stored in a database.

[0349] 3. Market research concept testing

[0350] The server inputs the generated project ideas into an online survey tool and conducts a survey of customers. For example, a survey form including a question such as "Are you interested in this campaign?" is created.

[0351] 4. Analysis of concept test results

[0352] The server compiles the survey results, calculates the evaluation score for each idea, and selects the idea with the highest evaluation.

[0353] 5. Web-based A / B testing

[0354] The server then feeds the selected ideas into an A / B testing tool to create different versions of advertising banners that are displayed to real website visitors.

[0355] 6. Analyzing AB test results

[0356] The server collects the results of the AB tests, analyzes the click-through rates and conversion rates of each version, and selects the version with the best performance.

[0357] 7. User emotion recognition by emotion engine

[0358] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, which are then analyzed by an emotion engine, for example to analyze facial expressions in real time while the user is viewing an advertisement.

[0359] 8. Emotion-Based Content Selection

[0360] The server selects content according to the user's emotion based on the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server selects a campaign idea that corresponds to that emotion.

[0361] 9. Emotion-Based Market Research and A / B Testing

[0362] The server then subjects the selected content to market research concept testing and web AB testing. For example, it creates an advertising banner that corresponds to the emotion of joy and conducts the test again.

[0363] 10. Selection of the final result

[0364] The server comprehensively analyzes all test results and ultimately selects the campaign idea that is most highly rated and best suited to user emotions.

[0365] Examples

[0366] For example, consider a generative AI model that receives the following prompt sentence as input:

[0367] Example prompt:

[0368] "Generate ideas for a marketing campaign for a new smartphone."

[0369] 1. The server inputs this prompt into a generative AI model to generate multiple marketing campaign ideas.

[0370] 2. The server uses online survey tools to conduct market research concept testing of the generated ideas. For example, it creates a survey form and asks customers, "Are you interested in this campaign?"

[0371] 3. The server compiles the survey results and selects the most highly rated campaign idea.

[0372] 4. The server uses an AB testing tool to perform AB testing on the web for the selected campaign ideas, for example, creating different versions of advertising banners and displaying them to actual website visitors.

[0373] 5. The server analyzes the results of the AB tests and selects the version with the highest click-through rate.

[0374] 6. The device uses an emotion engine to recognize the user's emotions. For example, the device captures the user's facial expression while viewing an advertisement on the smartphone and performs emotion analysis.

[0375] 7. Based on the emotion data, if the user shows an emotion of happiness, the server selects a campaign idea that corresponds to that emotion.

[0376] 8. The server will then conduct market research concept testing and online AB testing on the selected campaign ideas.

[0377] 9. The server analyzes the test results and finally selects the best campaign idea that corresponds to the user's emotions.

[0378] In this way, the system selects content that will appeal to customers and improves the quality of planning through the roles of the server, terminal, and user.

[0379] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0380] Step 1: Enter the prompt statement

[0381] The user uses the terminal to input a prompt sentence to the generative AI model. For example, the user might input, "Please generate an idea for a marketing campaign for a new smartphone." This prompt sentence becomes the input data.

[0382] Step 2: Generate planning ideas

[0383] The server uses the generative AI model to generate multiple marketing campaign ideas based on the input prompt sentence, and the generated ideas are stored in a database, where the prompt sentence is the input data and the generated ideas are the output data.

[0384] Step 3: Market research concept testing

[0385] The server inputs the generated project ideas into an online survey tool and conducts a survey of customers. For example, a survey form is created that includes the question, "Are you interested in this campaign?" The survey results become the input data, and the evaluation scores become the output data.

[0386] Step 4: Analyzing the concept test results

[0387] The server tally up the survey results, calculate an evaluation score for each idea, and select the idea with the highest evaluation. The survey results are the input data, and the evaluation scores are the output data.

[0388] Step 5: AB testing on the web

[0389] The server inputs the selected ideas into the AB testing tool to create different versions of ad banners. These banners are displayed to real website visitors. The selected ideas are the input data, and the ad banners are the output data.

[0390] Step 6: Analyze the A / B test results

[0391] The server collects the results of the AB tests, analyzes the click-through rate and conversion rate of each version, and selects the version with the best performance. The AB test results are the input data, and the optimal version is the output data.

[0392] Step 7: Recognizing user emotions with the emotion engine

[0393] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and analyzes them with an emotion engine. For example, the device analyzes the user's facial expressions in real time while the user is watching an advertisement. The captured facial expressions and voice are the input data, and the analyzed emotion data is the output data.

[0394] Step 8: Select content based on emotion

[0395] The server selects content according to the user's emotion based on the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server selects a campaign idea that corresponds to that emotion. The emotion data is the input data, and the selected content is the output data.

[0396] Step 9: Emotion-based market research and A / B testing

[0397] The server then subjects the selected content to market research concept testing or web AB testing. For example, it creates an advertising banner that corresponds to the emotion of joy and conducts the test again. The selected content is the input data, and the test results are the output data.

[0398] Step 10: Select the final result

[0399] The server comprehensively analyzes all the test results and finally selects the campaign idea that is the most highly rated and best suited to the user's emotions. The test results are the input data, and the best campaign idea is the output data.

[0400] (Application example 2)

[0401] Next, a description will be given of Application Example 2 of Form 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."

[0402] In conventional marketing content generation systems, there were insufficient testing methods to ensure the quality of the generated content, making it difficult to efficiently select content that would appeal to customers. In addition, content selection did not take into account user emotions, making it impossible to maximize customer response. This reduced the probability of sales and limited marketing effectiveness.

[0403] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0404] In this invention, the server includes a generating means using a generating AI model to generate new project idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a testing means using an emotion engine that recognizes the user's emotions and selects content that will appeal to customers according to the emotions. This makes it possible to improve the quality of the generated content, efficiently select content that will appeal to customers, and increase the probability of sales.

[0405] A "generative AI model" is an algorithm or system that uses artificial intelligence to automatically generate new planning ideas and marketing content.

[0406] "Generation means" refers to a function or device that uses a generative AI model to generate new planning ideas and marketing content that meets necessary conditions.

[0407] "Testing means" refers to functions or devices used for conducting concept testing for market research or AB testing on the web in order to ensure the quality of the generated content.

[0408] An "emotion engine" is an algorithm or system that recognizes a user's emotions and selects content that will resonate with customers based on those emotions.

[0409] "Market research concept testing" is a research methodology used to evaluate the market acceptability of generated content or project ideas.

[0410] "AB testing on the web" is a testing method in which different versions of content are published simultaneously on the web and the most effective content is selected by comparing actual customer reactions.

[0411] In order to implement the present invention, the following system configuration and processing procedures are required.

[0412] First, the server uses a generative AI model to generate new project ideas and marketing content. The generative AI model can use advanced natural language processing models such as GPT-3 and BERT. The generative AI model generates specific content by inputting a prompt sentence such as the following:

[0413] Example prompt:

[0414] "Generate ideas for a new marketing campaign. The target audience will be young people in their 20s, with a focus on promotion using social media."

[0415] The generated content is then evaluated by testing methods such as market research concept testing and web AB testing. In market research concept testing, methods such as questionnaire surveys and focus group interviews can be used to evaluate how well the generated content is accepted in the market. In web AB testing, different versions of the content are published simultaneously on the web and actual customer reactions are compared.

[0416] In addition, a testing method using an emotion engine is also built in. The emotion engine recognizes the user's emotions and selects content that will appeal to customers based on those emotions. For example, if a user expresses joy, it selects content that corresponds to that emotion and conducts market research and A / B testing of that content.

[0417] For example, when a user is using a smartphone, the smartphone's camera and microphone are used to analyze the user's facial expressions and tone of voice, and the emotion engine recognizes the user's emotions. Based on the recognized emotions, optimal content is selected and presented to the user.

[0418] This system makes it possible to improve the quality of generated content, efficiently select content that will appeal to customers, and increase the probability of sales.

[0419] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0420] Step 1:

[0421] The server inputs a prompt text to the generative AI model. For example, the prompt text might be, "Please generate ideas for a new marketing campaign. The target audience is young people in their 20s, and we will place emphasis on promotion using social media." The generative AI model generates new project ideas and marketing content based on this prompt text. The input is the prompt text, and the output is the generated content.

[0422] Step 2:

[0423] The server subjects the generated content to market research concept testing, which uses methods such as questionnaire surveys and focus group interviews to evaluate how well the generated content will be received in the market. The input is the generated content and the output is the results of the market research.

[0424] Step 3:

[0425] The server subjects the generated content to AB testing on the web. In AB testing on the web, different versions of content are published simultaneously on the web and actual customer reactions are compared. The input is the generated content, and the output is the result of the AB test.

[0426] Step 4:

[0427] The device uses the smartphone's camera and microphone to recognize the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotions. The input is the user's facial expression and voice data, and the output is the recognized emotion.

[0428] Step 5:

[0429] The server selects the optimal content based on the recognized emotion. For example, if the user indicates an emotion of happiness, the server selects the content according to the emotion. The input is the recognized emotion and the generated content, and the output is the selected optimal content.

[0430] Step 6:

[0431] The terminal presents the selected optimal content to the user. The user checks the presented content and provides feedback as necessary. The input is the selected content, and the output is the user's feedback.

[0432] In this way, it is possible to improve the quality of the generated content, efficiently select content that appeals to customers, and increase the probability of sales.

[0433] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0434] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0435] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0436] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0437] [Second embodiment]

[0438] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0439] 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.

[0440] 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 wide area network (WAN) and / or a local area network (LAN).

[0441] 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.

[0442] 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 the voice according to instructions from the processor 46.

[0443] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0444] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0445] Fig. 4 shows an example of 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0450] "Example 1"

[0451] In one embodiment of the present invention, a system including an AI generation means and a testing means is provided. The AI ​​generation means generates concepts and marketing content for new planning ideas that satisfy necessary conditions. Specifically, the AI ​​generation means generates content by utilizing creative answers based on necessary conditions set by the planning department. For example, when generating planning ideas for a new product, the AI ​​generation means generates planning ideas that satisfy necessary conditions such as the target customer segment, the market environment, and the characteristics of the product.

[0452] "Example 2"

[0453] In addition, a testing method is provided to ensure the quality of the generated content. The testing method involves market research concept testing and web AB testing, and by selecting content that will appeal to customers, the quality of the plan is improved and the probability of sales is increased. For example, market research concept testing is conducted on multiple plan ideas generated by the AI ​​generation method, and the plan idea with the highest evaluation based on customer evaluation is selected. In addition, web AB testing is conducted, and the plan idea with the best response is selected based on actual customer reactions.

[0454] The process flow of each embodiment will be described below.

[0455] "Example 1"

[0456] Step 1: The planning department sets the requirements, including the target customer group, market environment, product characteristics, etc.

[0457] Step 2: The AI ​​generator uses creative answers to generate new business idea concepts and marketing content based on the set requirements.

[0458] Step 3: The planning department reviews the generated planning ideas and makes corrections or additions as necessary.

[0459] "Example 2"

[0460] Step 1: Conduct market research concept testing on multiple planning ideas generated by the AI ​​generation method.

[0461] Step 2: Select the most highly rated project idea based on customer evaluations.

[0462] Step 3: Conduct online AB testing of the selected project ideas.

[0463] Step 4: Based on actual customer reactions, the project idea with the best response is finally selected.

[0464] Example 1

[0465] Next, a description will be given of Example 1 of Form 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".

[0466] In conventional systems for generating new project ideas and marketing content, the process from when the user inputs the necessary conditions to when the generated content is evaluated and improved is complicated, making it difficult to efficiently generate high-quality content. In addition, market research and web AB testing to ensure the quality of the generated content are often done manually, which is time-consuming and labor-intensive.

[0467] 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.

[0468] In this invention, the server includes a generating means for generating concepts and marketing content for new project ideas that satisfy necessary conditions, an evaluating means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an input means for a user to input necessary conditions, a generating means for generating a prompt sentence based on the input necessary conditions, a generating means for inputting the generated prompt sentence into a generative AI model to generate content, a transmitting means for transmitting the generated content to a user's terminal, and an evaluating means for receiving feedback from the user and evaluating and improving the content. This makes it possible to streamline the process from when the user inputs necessary conditions to when the generated content is evaluated and improved, and to generate high-quality content quickly.

[0469] "Requirements" are requirements or standards that must be met when a user generates a new project idea or marketing content.

[0470] A "new project idea" is a proposal or concept that adds new value or features to an existing product or service.

[0471] "Marketing Content" means information or messages intended to promote or sell a product or service.

[0472] The "generation means" refers to a method or device for generating new project ideas and marketing content based on necessary conditions.

[0473] An "assessment means" is a method or device for assessing the quality of the generated content and improving it if necessary.

[0474] An "input means" is a method or device by which a user inputs requirements into the system.

[0475] A "prompt sentence" is an instruction sentence input into a generative AI model and is generated based on necessary conditions.

[0476] A "generative AI model" is an algorithm or program that uses artificial intelligence to generate new planning ideas and marketing content.

[0477] The "transmitting means" refers to a method or device for transmitting the generated content to a user's terminal.

[0478] "Feedback" refers to information about corrections or improvements provided by a user to generated content.

[0479] The present invention relates to a system for generating new project ideas and marketing contents that satisfy necessary conditions, and evaluating and improving the quality of the generated ideas and contents. The system includes a generating means, an evaluating means, an inputting means, a transmitting means, and a feedback means.

[0480] The server hosts a generative AI model as a generation means. Specifically, the server uses a generative AI model such as OpenAI's GPT-4. When a user inputs the necessary conditions through an input means, the server receives it and generates a prompt sentence. The generated prompt sentence is input to the generative AI model, and new project ideas and marketing content are generated.

[0481] Users access the system using a terminal (PC or tablet) and input their requirements. Requirements include target customer segments, market environment, product characteristics, etc. For example, a user may input the following requirements:

[0482] Target customer demographic: Young people in their 20s

[0483] Market environment: Online shopping is mainstream

[0484] Product features: Eco-friendly materials used

[0485] Based on these requirements, the server will generate a prompt like this:

[0486] "Generate product ideas for new products using eco-friendly materials to be sold on the online shopping market, targeting young people in their 20s."

[0487] The server inputs this prompt into the generative AI model and receives the generated content, such as the following:

[0488] "We are proposing a stylish backpack made from recycled materials for young people in their 20s. This backpack will be sold exclusively online, and customers who purchase it will receive eco points as a special perk."

[0489] The server transmits the generated content to the user's terminal. The terminal displays the received content to the user. The user checks the generated content and provides feedback, if necessary. The feedback may include corrections or improvements.

[0490] The server receives feedback from users and evaluates and improves the content using the evaluation means, which improves the quality of the generated content and allows it to meet user requirements with greater accuracy.

[0491] This system streamlines the process from when users input their requirements to when they evaluate and improve the generated content, making it possible to quickly generate high-quality content.

[0492] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0493] Step 1:

[0494] A user logs into the system using a terminal. The user inputs requirements such as target customer demographics, market environment, and product characteristics. The input requirements are sent to the server. Specifically, the user enters requirements into the input form and clicks the "Submit" button. Input: Requirements. Output: Requirements sent to the server.

[0495] Step 2:

[0496] The server receives the requirements sent by the user. The server generates a prompt sentence based on the received requirements. Specifically, the server analyzes the requirements and creates a prompt sentence in a format suitable for the generative AI model. Input: Requirements from the user. Output: Generated prompt sentence.

[0497] Step 3:

[0498] The server inputs the generated prompt sentence into the generative AI model. The server waits for the generative AI model to generate content based on the prompt sentence. Specifically, the server sends the prompt sentence to the generative AI model through the API and receives the generated content. Input: Generated prompt sentence. Output: Generated content from the generative AI model.

[0499] Step 4:

[0500] The server sends the content received from the generative AI model to the user's device. The device displays the received content to the user. In concrete terms, the server sends the generated content to the user's device in real time, and the device displays the content on its screen. Input: Generated content from the generative AI model. Output: Content displayed on the user's device.

[0501] Step 5:

[0502] The user checks the generated content displayed on the terminal. If necessary, the user inputs feedback on corrections and improvements. Specifically, the user enters comments in the feedback form and clicks the "Submit" button. Input: Generated content. Output: Feedback from the user.

[0503] Step 6:

[0504] The server receives feedback from the user. The server evaluates the generated content based on the feedback and makes improvements if necessary. Specifically, the server analyzes the feedback and sends the prompt sentence to the generative AI model again to generate improved content. Input: User feedback. Output: Improved generated content.

[0505] (Application example 1)

[0506] Next, a description will be given of Application Example 1 of Form 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".

[0507] Conventional advertising content generation systems have had difficulty generating effective advertising content based on conditions such as target customer segments, market environment, and product characteristics. In addition, there was a lack of market research and testing methods to ensure the quality of the generated content, making it impossible to maximize the effectiveness of advertising. This resulted in a problem of reduced advertising effectiveness and the inability to expect an increase in sales.

[0508] 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.

[0509] In this invention, the server includes an AI generation means for generating new project idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a smartphone application for generating advertising content based on conditions such as target customer segments, market environment, product characteristics, etc. This makes it possible to generate effective advertising content and ensure its quality.

[0510] "Requirements" are conditions that must be met when generating advertising content, such as target customer segments, market environment, and product characteristics.

[0511] A "new project idea" is a new concept or marketing strategy that has never been seen before.

[0512] "Marketing content" refers to materials such as text, images, and videos used to promote products and services.

[0513] "AI generation means" refers to a means of using artificial intelligence to generate new planning ideas and marketing content that meets necessary conditions.

[0514] "Testing methods" refer to the means of conducting market research concept tests and AB tests on the web to ensure the quality of the generated content.

[0515] A "target demographic" is a particular group of customers to whom an advertisement or product is primarily directed.

[0516] "Market environment" refers to external factors such as the competitive situation and trends in the market in which the advertisement or product is developed.

[0517] "Product features" are the specific characteristics or benefits of an advertisement or product.

[0518] A "smartphone application" is a software program that runs on a smartphone.

[0519] "Advertising content" refers to materials such as text, images, and videos created to promote a specific product or service.

[0520] The following system configuration is necessary to implement this invention. The system includes an AI generation means for generating new project idea concepts and marketing content that meet required conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a smartphone application for generating advertising content based on conditions such as the target customer demographic, market environment, and product characteristics.

[0521] The server uses a generative AI model such as OpenAI's GPT-3 to generate advertising content based on the requirements entered by the user, such as the target customer demographic, market environment, and product characteristics. Specifically, when the user enters the requirements through a smartphone application, the server converts them into a prompt text and sends it to the generative AI model. The generative AI model generates creative advertising content based on the prompt text and returns it to the user.

[0522] For example, if the target customer group is set as "women in their 20s," the market environment is set as "highly competitive cosmetics market," and the product characteristics are set as "highly moisturizing," the following prompt sentence will be generated.

[0523] Example prompt:

[0524] Target customer group: Women in their 20s

[0525] Market environment: Highly competitive cosmetics market

[0526] Product Features: High moisturizing effect

[0527] Please generate advertising content that meets the above criteria.

[0528] For example, the generated advertising content might be, "Recommended for women in their 20s! A new product that's attracting attention in the highly competitive cosmetics market. It has high moisturizing effects and is perfect for those who suffer from dry skin. Try it now!"

[0529] Furthermore, to ensure the quality of the generated advertising content, the server performs concept testing for market research and AB testing on the web, which allows it to predict the effectiveness of advertising and propose optimal advertising ideas to users.

[0530] In this way, it becomes possible to generate effective advertising content and ensure its quality.

[0531] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0532] Step 1:

[0533] The user launches the smartphone application and inputs necessary conditions such as the target customer group, market environment, and product characteristics.

[0534] Input: Target customer group, market environment, product characteristics

[0535] Output: Prerequisites entered

[0536] Specific operation: The user enters the target customer group (e.g., women in their 20s), market environment (e.g., highly competitive cosmetics market), and product characteristics (e.g., high moisturizing effect) into the application's input form.

[0537] Step 2:

[0538] The terminal converts the input requirements into a prompt text and sends it to the server.

[0539] Input: Requirements

[0540] Output: Prompt statement

[0541] Specific behavior: The application converts the entered requirements into a prompt like this:

[0542] Target customer group: Women in their 20s

[0543] Market environment: Highly competitive cosmetics market

[0544] Product Features: High moisturizing effect

[0545] Please generate advertising content that meets the above criteria.

[0546] This prompt is sent to the server.

[0547] Step 3:

[0548] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate advertising content based on the prompt text.

[0549] Input: prompt statement

[0550] Output: Ad content

[0551] Specific operation: The server inputs the prompt text into the AI ​​model and obtains the generated ad content. For example, the ad content generated is "Recommended for women in their 20s! A new product that is attracting attention in the highly competitive cosmetics market. Highly moisturizing, perfect for those who suffer from dry skin. Try it now!"

[0552] Step 4:

[0553] The server sends the generated advertising content back to the terminal.

[0554] Input: Ad content

[0555] Output: Ad content sent to the device

[0556] Specific operations: The server transmits the generated advertising content to the terminal.

[0557] Step 5:

[0558] The terminal displays the received advertisement content to the user.

[0559] Input: Ad content

[0560] Output: Ad content displayed

[0561] Specific behavior: The application displays the received advertising content to the user.

[0562] Step 6:

[0563] The user reviews the quality of the generated advertising content and corrects or regenerates it as necessary.

[0564] Input: Ad content

[0565] Output: The modified or regenerated ad content.

[0566] What happens: The user reviews the displayed ad content and, if necessary, corrects it or requests that it be regenerated.

[0567] Step 7:

[0568] In order to ensure the quality of the advertising content generated by the server, we conduct concept tests for market research and A / B tests on the web.

[0569] Input: Ad content

[0570] Output: Test results

[0571] Specific operation: The server subjects the generated advertising content to market research concept testing and web-based AB testing and obtains the results.

[0572] Step 8:

[0573] The server proposes optimal advertising ideas to the user based on the test results.

[0574] Input: Test result

[0575] Output: Best ad recommendation

[0576] What happens: The server analyzes the test results and suggests optimal ads to the user.

[0577] Example 2

[0578] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0579] With conventional planning idea generation and evaluation systems, it was difficult to accurately evaluate the quality of the generated ideas and their response in the market. As a result, it was not possible to select planning ideas that would appeal to customers, and there was a problem that sales could not be expected to increase. Furthermore, there was also the issue that it was difficult to quickly bring ideas to market because the evaluation process of the generated ideas was complicated and time-consuming.

[0580] 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.

[0581] In this invention, the server includes a means for generating new planning ideas using a generative AI model, a means for conducting market research concept testing on the generated planning ideas, and a means for conducting AB testing on the web on the generated planning ideas, which makes it possible to quickly and accurately evaluate the quality of the generated planning ideas and select the optimal planning ideas that will appeal to customers.

[0582] A "generative AI model" is a type of artificial intelligence that uses natural language processing technology to generate new project ideas.

[0583] "New project ideas" are novel concepts and marketing content generated by generative AI models.

[0584] "Market research concept testing" is a method of collecting customer evaluations of generated planning ideas and verifying the validity of the ideas based on that evaluation data.

[0585] "Web AB testing" is a method of selecting the most effective idea by displaying different project ideas to actual customers and collecting and analyzing their response data.

[0586] "Server" refers to a computer system that executes the generative AI model and evaluates and selects the generated project ideas.

[0587] "Reaching the customer" means that the generated planning ideas will pique the customer's interest and stimulate their desire to purchase.

[0588] "Planning quality" is an index showing the market acceptability and effectiveness of the generated planning ideas.

[0589] The "probability of selling" is an index showing the possibility that the generated planning idea will be successful in the market and actually generate sales.

[0590] This invention is a system that generates new project ideas using a generative AI model and evaluates the ideas through concept testing in market research and AB testing on the web. A specific embodiment of this system will be described below.

[0591] The server generates new project ideas using a generative AI model (e.g., an advanced artificial intelligence model using natural language processing technology). An example of a generative AI model that can be used is OpenAI's GPT-4. The server inputs a prompt sentence into the generative AI model to generate multiple project ideas. An example of a specific prompt sentence is "Please generate five project ideas for a new smartphone app."

[0592] The generated project ideas are stored in a database by the server. The server then conducts market research concept testing. In the market research concept testing, market research tools such as SurveyMonkey and Qualtrics are used to collect customer evaluations of the generated project ideas. Specifically, the server creates a survey that includes the following question: "How interested are you in this app idea? (Please rate on a scale of 1-5)." Users answer the survey using their devices, and the server collects and analyzes the evaluation data.

[0593] Next, the server conducts AB testing on the web. In AB testing, tools such as Google Optimize and Optimizely are used to display different project ideas to actual customers and collect response data. Specifically, the server sets up the following test: "Show idea 1 to group A and idea 2 to group B, and compare which group clicks more." Users use their devices to view web pages and respond to the displayed project ideas. The server analyzes the collected click data and selects the project idea with the best response.

[0594] Finally, the server comprehensively evaluates the results of the market research concept tests and the web-based AB tests to select the plan idea that has the highest evaluation and appeals to customers. This selected plan idea is stored in the database and notified to the user.

[0595] This system makes it possible to quickly and accurately evaluate the quality of the generated planning ideas and select the most suitable planning idea that will appeal to customers, thereby improving the quality of the plan and increasing the probability of it selling.

[0596] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0597] Step 1:

[0598] The server generates new project ideas using the generative AI model. Specifically, the server inputs a prompt sentence, "Please generate five project ideas for a new smartphone app," into the generative AI model. The generative AI model generates five different project ideas based on this prompt sentence and returns them to the server. The server stores the generated project ideas in a database. The input is the prompt sentence, and the output is the generated project ideas.

[0599] Step 2:

[0600] The server conducts market research concept testing on the generated project ideas. Specifically, the server creates a survey using a market research tool (e.g., SurveyMonkey or Qualtrics). The survey includes questions such as, "How interested are you in this app idea? (Please rate on a scale of 1-5)." Users answer the survey using their terminals. The server collects evaluation data from users and stores it in a database. The input is the generated project idea and the survey responses, and the output is the evaluation data.

[0601] Step 3:

[0602] The server analyzes the collected evaluation data and selects the project idea with the highest evaluation. Specifically, the server statistically processes the evaluation data and calculates the average evaluation score of each project idea. The project idea with the highest score is selected and proceeds to the next step. The input is the evaluation data, and the output is the project idea with the highest evaluation.

[0603] Step 4:

[0604] The server conducts AB testing on the web for the selected project ideas. Specifically, the server uses an AB testing tool (e.g., Google Optimize or Optimizely) to display different project ideas to actual customers. For example, idea 1 is displayed to group A and idea 2 is displayed to group B, and a comparison is made to see which group makes more clicks. Users use their devices to view web pages and react to the displayed project ideas. The server saves the collected click data in a database. The input is the selected project idea and customer response data, and the output is click data.

[0605] Step 5:

[0606] The server analyzes the collected click data and selects the project idea with the best response. Specifically, the server statistically processes the click data and calculates the click rate of each project idea. The project idea with the highest click rate is finally selected. The input is the click data, and the output is the project idea with the best response.

[0607] Step 6:

[0608] The server saves the final selected project idea in a database and notifies the user. Specifically, the server saves the selected project idea in a database and notifies the user of the result via email or a notification system. The input is the project idea with the best response, and the output is the notification to the user.

[0609] (Application example 2)

[0610] Next, a description will be given of Application Example 2 of Form 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".

[0611] Traditionally, planning advertising campaigns and generating marketing content is often done manually, which is time-consuming and labor-intensive, and there is a lack of objective evaluation methods for selecting effective content. This makes the effectiveness of advertising campaigns uncertain, and may not lead to increased sales. Furthermore, market research and AB testing to ensure the quality of the generated content are also cumbersome, making it difficult to obtain rapid feedback.

[0612] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0613] In this invention, the server includes a generating AI model means for generating new planning idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing of market research and AB testing on the web to ensure the quality of the generated content, a means for generating planning ideas for advertising campaigns, calculating evaluations and click rates, and a means for selecting the most highly rated advertising campaign and proposing it to the advertiser. This makes it possible to consistently automate the process from planning to evaluation, selection, and proposal of advertising campaigns, and quickly implement effective advertising campaigns.

[0614] A "generative AI model means" is a means that uses artificial intelligence technology to generate new project idea concepts and marketing content that meet required conditions.

[0615] "Testing methods" refer to the means of conducting market research concept tests and AB tests on the web to ensure the quality of the generated content.

[0616] The "means for generating advertising campaign planning ideas" refers to means for generating new ideas for advertising campaigns and calculating ratings and click-through rates for those ideas.

[0617] The "means of proposing to advertisers" refers to the means of selecting the most highly rated advertising campaign and proposing the results to advertisers.

[0618] A system for implementing the present invention includes a generative AI model means, a testing means, a means for generating planning ideas for advertising campaigns, and a means for proposing ideas to advertisers.

[0619] The server generates new project idea concepts and marketing content that meet the requirements using a generative AI model means, which generates creative answers based on the prompt sentence, for example, using an OpenAI API.

[0620] Next, to ensure the quality of the generated content, we use testing methods to conduct concept tests for market research and AB tests on the web. From the multiple generated project ideas, we select the one with the highest evaluation based on customer evaluations and actual click rates.

[0621] The means for generating advertising campaign planning ideas uses a generative AI model means to generate new advertising campaign ideas and calculate ratings and click-through rates for the ideas, the means being implemented using a programming language such as Python.

[0622] Finally, the most highly evaluated advertising campaign is selected using a means for proposing to the advertiser, and the result is proposed to the advertiser. This means generates a report for proposing the optimal advertising campaign to the advertiser based on the evaluation result and the click-through rate data.

[0623] As a specific example, when considering an advertising campaign for a new beverage, the prompt sentence is "Generate ideas for an advertising campaign for a new beverage." Based on this prompt sentence, the generative AI model means generates multiple advertising campaign ideas, and by conducting concept tests in market research and AB tests on the web for those ideas, the most effective advertising campaign can be selected and proposed to the advertiser.

[0624] This system automates the entire process of advertising campaigns, from planning to evaluation, selection and proposal, making it possible to quickly implement effective advertising campaigns.

[0625] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0626] Step 1:

[0627] The server uses a generative AI model means to generate concepts and marketing content for new project ideas. Specifically, the server sends a prompt sentence, "Please generate an idea for a new beverage advertising campaign," as an input to a generative AI model (e.g., OpenAI's API), and receives the generated multiple advertising campaign ideas as an output.

[0628] Step 2:

[0629] The server performs market research concept testing on the generated advertising campaign ideas. Specifically, the server inputs the generated ideas into a market research tool, collects evaluation data from customers, calculates an evaluation score for each idea based on the evaluation data, and obtains the evaluation score as an output.

[0630] Step 3:

[0631] The server selects the best-rated advertising campaign idea based on the rating scores, by comparing the rating scores, selecting the idea with the highest score, and obtaining the idea as an output.

[0632] Step 4:

[0633] The server performs AB testing on the web for the selected advertising campaign ideas. Specifically, the selected ideas are input into an AB testing tool, and actual click-through rate data is collected. Based on the click-through rate data, the click-through rate for each idea is calculated, and the click-through rate is obtained as output.

[0634] Step 5:

[0635] The server selects the advertising campaign idea that has the best response based on the click-through rate, by comparing the click-through rates, selecting the idea with the highest click-through rate, and obtaining the idea as an output.

[0636] Step 6:

[0637] The server proposes the most highly rated and most responsive advertising campaign ideas to the advertiser. Specifically, the server compiles the selected ideas, their evaluation scores, and click-through rates in a report format and sends it to the advertiser. The server obtains the report as an output.

[0638] In addition, 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.

[0639] "Example 1"

[0640] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system recognizes the emotion of a user and generates new project idea concepts and marketing content according to the emotion. Specifically, the emotion engine recognizes the emotion of the user, and the AI ​​generation means generates content by utilizing creative answers based on the emotion. For example, when the user expresses an emotion of joy, the AI ​​generation means generates a project idea according to the emotion of joy. This makes it possible to generate project ideas corresponding to the emotion of the user.

[0641] "Example 2"

[0642] A testing method using an emotion engine is also provided. This testing method improves the quality of the plan and increases the probability of sales by recognizing the user's emotions and selecting content that will appeal to customers according to those emotions. Specifically, the emotion engine recognizes the user's emotions and performs concept testing for market research and AB testing on the web based on those emotions. For example, if a user expresses an emotion of joy, the testing method selects content that corresponds to that emotion and performs market research and AB testing for that content. This makes it possible to select content that corresponds to the user's emotions and improve the quality.

[0643] The process flow of each embodiment will be described below.

[0644] "Example 1"

[0645] Step 1: Recognize the user's emotion using the emotion engine.

[0646] Step 2: Based on the recognized sentiment, the AI ​​generator uses the creative answers to generate new project idea concepts and marketing content.

[0647] Step 3: Present the generated planning ideas and marketing content to the user.

[0648] "Example 2"

[0649] Step 1: Recognize the user's emotion using the emotion engine.

[0650] Step 2: Based on the emotions identified, conduct market research concept testing and web-based A / B testing.

[0651] Step 3: Based on the test results, select content that will resonate with customers, improve the quality of the plan, and increase the probability of sales.

[0652] Example 1

[0653] Next, a description will be given of Example 1 of Form 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".

[0654] In conventional systems, it was difficult to take users' emotions into account when generating new project ideas and marketing content, and the generated content did not necessarily match the user's emotions. In addition, there was a lack of evaluation methods to ensure the quality of the generated content, making it difficult to maximize the effectiveness of the content.

[0655] 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.

[0656] In this invention, the server includes a generating means for generating new project idea concepts and marketing content that satisfy the necessary conditions, an evaluating means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognizing means for recognizing the emotion of a user and generating content according to the emotion, and a control means for generating a prompt sentence based on the emotion data obtained from the emotion recognizing means and the necessary conditions and sending it to the generating means. This makes it possible to generate new project ideas and marketing content that match the emotion of the user, and further to evaluate and improve the quality of the generated content.

[0657] The "generation means" refers to a means for generating concepts for new project ideas and marketing content that meet the necessary conditions.

[0658] "Evaluation methods" are methods used to conduct market research concept tests and web-based A / B tests to ensure the quality of the generated content.

[0659] The "emotion recognition means" is a means for recognizing the user's emotion and generating content in accordance with that emotion.

[0660] The "control means" is a means for generating a prompt sentence based on the emotion data obtained from the emotion recognition means and the necessary conditions, and sending the prompt sentence to the generation means.

[0661] A "prompt sentence" is an instruction sentence used by the generating means when generating new project ideas and marketing content.

[0662] A "new business idea" is a concept for a new product or service that is not yet on the market.

[0663] "Marketing content" refers to advertising and promotional materials used to promote products and services to the market.

[0664] "Requirements" are conditions that the generated content must satisfy, such as the target customer group, market environment, and product characteristics.

[0665] The present invention relates to a system for generating concepts and marketing contents for new project ideas that satisfy requirements. The system includes a generating unit, an evaluating unit, an emotion recognizing unit, and a controlling unit.

[0666] Hardware and Software Used

[0667] Hardware: Servers, terminals

[0668] Software: Generative AI models (e.g. GPT-4), emotion engines (e.g. Affectiva)

[0669] Specific operation of the system

[0670] User Emotion Recognition

[0671] A user accesses the system using a terminal. The terminal's camera and microphone capture the user's facial expressions and voice in real time. The terminal sends the captured data to the emotion engine. The emotion engine analyzes the characteristics of the user's facial expressions and voice and recognizes emotions. For example, when a user smiles, the emotion engine recognizes the emotion of "happiness."

[0672] Setting Prerequisites

[0673] The planning department logs into the server and inputs the necessary conditions. The server saves the input necessary conditions in a database. The necessary conditions include the target customer group, the market environment, and the characteristics of the product. For example, the target customer group can be set as "young people in their 20s," the market environment as "health-conscious," and the product characteristic as "low calorie."

[0674] Content Generation

[0675] The server sends the user's emotion data obtained from the emotion engine and the requirements provided by the planning department to the generation means. The generation means uses a generative AI model (e.g. GPT-4) to generate creative content based on the requirements and the user's emotions. The generative AI model receives the prompt sentence and generates content based on it.

[0676] Examples of prompt statements

[0677] The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low calorie. Users show happy emotions. Based on these conditions, generate planning ideas for a new beverage product.

[0678] For example, if the prompt is, "The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low calorie. Users are expressing feelings of joy. Based on these conditions, please generate planning ideas for a new beverage product," the generative AI model would generate ideas such as, "Propose low-calorie, vitamin-rich fruit juice for young people in their 20s."

[0679] Testing and Feedback

[0680] The server sends the generated content to the evaluator. The evaluator evaluates the generated content and provides feedback. The server receives the test results and modifies the content as necessary. For example, if the evaluator provides feedback such as "The idea for the proposed fruit juice is good, but more specific ingredient information is needed," the server resends the prompt sentence to the generative AI model based on the feedback to generate modified content.

[0681] In this way, new project ideas and marketing content are generated based on the user's emotions and requirements.

[0682] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0683] Step 1:

[0684] User Emotion Recognition

[0685] Input: A user logs in to a device and allows access to the camera and microphone.

[0686] Specific operation: The device captures the user's facial expressions and voice in real time.

[0687] Data processing: The device sends the captured data to the emotion engine, which analyzes the user's facial expressions and voice characteristics to recognize emotions.

[0688] Output: The emotion engine sends the recognized emotion data to the server. For example, if the user smiles, the emotion engine recognizes the emotion of "happiness" and sends the data to the server.

[0689] Step 2:

[0690] Setting Prerequisites

[0691] Input: The planning department logs into the server and enters their requirements.

[0692] Specific Actions: The server stores the entered requirements in a database.

[0693] Data processing: Requirements include target customer demographics, market environment, product characteristics, etc.

[0694] Output: The server sends the saved requirements to the generator. For example, the target customer group is set as "young people in their 20s," the market environment is set as "health-conscious," and the product characteristic is set as "low calorie."

[0695] Step 3:

[0696] Content Generation

[0697] Input: The server sends the user's emotion data obtained from the emotion engine and the requirements provided by the planning department to the generator.

[0698] Specific operation: The generator uses a generative AI model (e.g., GPT-4) to generate creative content based on the requirements and user emotions.

[0699] Data processing: The generative AI model receives a prompt and generates content based on it.

[0700] Output: The generated content is sent to the server. For example, if the prompt is "The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low-calorie. The user shows an emotion of joy. Based on these conditions, please generate a planning idea for a new beverage product," the generative AI model will generate an idea such as "Propose a low-calorie, vitamin-rich fruit juice for young people in their 20s."

[0701] Step 4:

[0702] Testing and Feedback

[0703] Input: The server sends the generated content to the evaluator.

[0704] What to do: The evaluation tool evaluates the generated content and provides feedback.

[0705] Data processing: Evaluation measures assess the quality of content and identify areas for improvement.

[0706] Output: The server receives the test results and modifies the content as necessary. For example, if the evaluator gives feedback such as "The idea of ​​the proposed fruit juice is good, but more specific information on the ingredients is needed," the server sends the prompt sentence to the generative AI model again based on the feedback, and generates the modified content.

[0707] In this way, new project ideas and marketing content are generated based on the user's emotions and requirements.

[0708] (Application example 1)

[0709] Next, a description will be given of Application Example 1 of Form 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".

[0710] Conventional marketing content generation systems provide uniform content without considering the user's feelings, making it difficult to attract the user's interest. In addition, there was a lack of testing methods to ensure the quality of the generated content, which made it difficult to achieve effective marketing.

[0711] 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.

[0712] In this invention, the server includes an AI generation means for generating new project idea concepts and marketing content that meet the necessary conditions, a test means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognition means for recognizing the emotion of a user and generating content according to the emotion, and a display means for displaying the generated content in real time. This makes it possible to generate effective marketing content according to the emotion of a user and ensure its quality.

[0713] A "requirement" is a criterion or requirement that must be met in order to achieve a particular purpose or goal.

[0714] A "new project idea" is a new idea or plan that has never been seen before.

[0715] A "concept" is the basic idea or philosophy behind a project or product.

[0716] "Marketing Content" means information and materials used to promote and sell products and services.

[0717] An "AI generation means" refers to a function or device that uses artificial intelligence to automatically generate new planning ideas and marketing content.

[0718] "Testing Means" means any method or device for evaluating or verifying the quality of the Produced Content.

[0719] "Market research" refers to research activities conducted to understand consumer needs and market trends.

[0720] A "concept test" is a test conducted to evaluate whether a new plan or product concept will be accepted in the market.

[0721] "AB testing on the web" refers to the comparison of different versions of a web page or piece of content to evaluate which one is more effective.

[0722] "Emotion recognition means" refers to technology or devices for detecting and recognizing a user's emotions.

[0723] A "display means" refers to a method or device for visually presenting the generated content to a user.

[0724] As an embodiment of the present invention, an emotion-responsive advertisement generation system will be described as an example. This system includes an AI generation means for generating concepts and marketing content for new project ideas that satisfy necessary conditions, a testing means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognition means for recognizing the emotion of a user and generating content corresponding to the emotion, and a display means for displaying the generated content in real time.

[0725] Hardware and Software Used

[0726] Hardware: Smartphone camera

[0727] Software: OpenCV, Keras, Transformers libraries

[0728] Processing flow

[0729] 1. Camera image capture: Capture images in real time from the smartphone camera, which gives an image of the user's face.

[0730] 2. Face detection and emotion recognition: Detect faces using OpenCV and recognize the user's emotions using an emotion recognition model trained with Keras. Specifically, the face area is cut out, converted to grayscale, and then input to the emotion recognition model.

[0731] 3. Advertising content generation: Based on the recognized emotion, generate appropriate advertising content using the GPT-3 model. For example, if the user shows the emotion of happiness, input the prompt sentence "Generate advertising content appropriate for when the user shows the emotion of happiness" to the GPT-3 model.

[0732] 4. Display of advertising content: The generated advertising content is displayed on the camera footage in real time, allowing users to visually confirm the advertisements that correspond to their own emotions.

[0733] Examples

[0734] For example, if the user is expressing an emotion of joy, the following prompt sentence is input to the generative AI model:

[0735] Examples of prompt statements

[0736] Generate appropriate ad content when users are expressing the emotion of happiness.

[0737] When this prompt sentence is input into the GPT-3 model, advertising content such as "Why not try our new ice cream? It's on sale now at a special discount!" is generated. This advertising content is displayed in real time on the smartphone screen, attracting the user's interest.

[0738] The above is an embodiment of the present invention. This system makes it possible to generate effective marketing content in response to the user's emotions and to guarantee the quality of the content.

[0739] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0740] Step 1:

[0741] Capture video from a smartphone camera in real time. The input is the camera video and the output is the captured frames. Specifically, start the smartphone camera and continuously capture video.

[0742] Step 2:

[0743] Detect faces from captured frames. The input is the captured frame and the output is the detected face area. Specifically, we use OpenCV to detect faces in the frame and get the face position information.

[0744] Step 3:

[0745] The detected face area is converted to grayscale and input to the emotion recognition model. The input is the face area, and the output is the recognized emotion. Specifically, the face area is cut out, converted to grayscale, and then input to the emotion recognition model trained with Keras.

[0746] Step 4:

[0747] Based on the recognized emotion, appropriate advertising content is generated. The input is the recognized emotion, and the output is the generated advertising content. Specifically, a prompt sentence is generated according to the recognized emotion, and input to the GPT-3 model to generate advertising content.

[0748] Step 5:

[0749] The generated advertising content is displayed on the camera image in real time. The input is the generated advertising content, and the output is the advertising content displayed to the user. Specifically, the generated advertising content is superimposed on the captured frame and displayed on the smartphone screen.

[0750] The above are the specific processing steps of this system.

[0751] Example 2

[0752] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0753] Conventional marketing content generation systems make it difficult to select content that fully considers customer emotions and reactions, making it difficult to develop effective marketing strategies. In addition, there is a lack of testing methods to ensure the quality of the generated content, and specific methods to increase the probability of sales are required.

[0754] 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.

[0755] In this invention, the server includes a means for inputting a prompt sentence, a means for generating new project ideas and marketing content using a generative AI model, a means for conducting concept testing of market research to ensure the quality of the generated content, a means for conducting AB testing on the web, a means for using an emotion engine to recognize user emotions, and a means for selecting content based on emotion data. This makes it possible to generate and select effective marketing content that takes into account the emotions and reactions of customers.

[0756] A "prompt sentence" is a sentence of instructions or questions that is input to a generative AI model.

[0757] A "generative AI model" is an artificial intelligence algorithm that generates new project ideas and marketing content based on input prompt text.

[0758] "Market research concept testing" is a research instrument that gathers feedback from customers to evaluate the quality of the content generated.

[0759] "Web AB testing" is a testing method in which different versions of content are presented to actual website visitors and their reactions are compared.

[0760] An "emotion engine" is a technology that recognizes and analyzes emotions from a user's facial expressions, tone of voice, etc.

[0761] "Emotion data" is information regarding the user's emotions recognized by the emotion engine.

[0762] "Content selection method" is the process of selecting the most appropriate content based on generated content, test results, and sentiment data.

[0763] This invention is a system that uses a generative AI model to generate new project ideas and marketing content, and conducts market research and AB testing on the web to ensure the quality of the content. Furthermore, it is possible to select optimal content based on emotion data using an emotion engine that recognizes the user's emotions.

[0764] Hardware and Software Used

[0765] Hardware: Servers, terminals

[0766] Software: Generative AI models, emotion engines, web testing tools, online survey tools

[0767] Details of data processing and calculation

[0768] 1. Enter the prompt text

[0769] A user uses the device to input a prompt for the generative AI model, for example, "Generate marketing campaign ideas for a new smartphone."

[0770] 2. Generate project ideas

[0771] The server uses a generative AI model to generate multiple marketing campaign ideas based on the input prompt, and the generated ideas are stored in a database.

[0772] 3. Market research concept testing

[0773] The server inputs the generated project ideas into an online survey tool and conducts a survey of customers. For example, a survey form including a question such as "Are you interested in this campaign?" is created.

[0774] 4. Analysis of concept test results

[0775] The server compiles the survey results, calculates the evaluation score for each idea, and selects the idea with the highest evaluation.

[0776] 5. Web-based A / B testing

[0777] The server then feeds the selected ideas into an A / B testing tool to create different versions of advertising banners that are displayed to real website visitors.

[0778] 6. Analyzing AB test results

[0779] The server collects the results of the AB tests, analyzes the click-through rates and conversion rates of each version, and selects the version with the best performance.

[0780] 7. User emotion recognition by emotion engine

[0781] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, which are then analyzed by an emotion engine, for example to analyze facial expressions in real time while the user is viewing an advertisement.

[0782] 8. Emotion-Based Content Selection

[0783] The server selects content according to the user's emotion based on the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server selects a campaign idea that corresponds to that emotion.

[0784] 9. Emotion-Based Market Research and A / B Testing

[0785] The server then subjects the selected content to market research concept testing and web AB testing. For example, it creates an advertising banner that corresponds to the emotion of joy and conducts the test again.

[0786] 10. Selection of the final result

[0787] The server comprehensively analyzes all test results and ultimately selects the campaign idea that is most highly rated and best suited to user emotions.

[0788] Examples

[0789] For example, consider a generative AI model that receives the following prompt sentence as input:

[0790] Example prompt:

[0791] "Generate ideas for a marketing campaign for a new smartphone."

[0792] 1. The server inputs this prompt into a generative AI model to generate multiple marketing campaign ideas.

[0793] 2. The server uses online survey tools to conduct market research concept testing of the generated ideas. For example, it creates a survey form and asks customers, "Are you interested in this campaign?"

[0794] 3. The server compiles the survey results and selects the most highly rated campaign idea.

[0795] 4. The server uses an AB testing tool to perform AB testing on the web for the selected campaign ideas, for example, creating different versions of advertising banners and displaying them to actual website visitors.

[0796] 5. The server analyzes the results of the AB tests and selects the version with the highest click-through rate.

[0797] 6. The device uses an emotion engine to recognize the user's emotions. For example, the device captures the user's facial expression while viewing an advertisement on the smartphone and performs emotion analysis.

[0798] 7. Based on the emotion data, if the user shows an emotion of happiness, the server selects a campaign idea that corresponds to that emotion.

[0799] 8. The server will then conduct market research concept testing and online AB testing on the selected campaign ideas.

[0800] 9. The server analyzes the test results and finally selects the best campaign idea that corresponds to the user's emotions.

[0801] In this way, the system selects content that will appeal to customers and improves the quality of planning through the roles of the server, terminal, and user.

[0802] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0803] Step 1: Enter the prompt statement

[0804] The user uses the terminal to input a prompt sentence to the generative AI model. For example, the user might input, "Please generate an idea for a marketing campaign for a new smartphone." This prompt sentence becomes the input data.

[0805] Step 2: Generate planning ideas

[0806] The server uses the generative AI model to generate multiple marketing campaign ideas based on the input prompt sentence, and the generated ideas are stored in a database, where the prompt sentence is the input data and the generated ideas are the output data.

[0807] Step 3: Market research concept testing

[0808] The server inputs the generated project ideas into an online survey tool and conducts a survey of customers. For example, a survey form is created that includes the question, "Are you interested in this campaign?" The survey results become the input data, and the evaluation scores become the output data.

[0809] Step 4: Analyzing concept test results

[0810] The server tally up the survey results, calculate an evaluation score for each idea, and select the idea with the highest evaluation. The survey results are the input data, and the evaluation scores are the output data.

[0811] Step 5: AB testing on the web

[0812] The server inputs the selected ideas into the AB testing tool to create different versions of ad banners. These banners are displayed to real website visitors. The selected ideas are the input data, and the ad banners are the output data.

[0813] Step 6: Analyze the A / B test results

[0814] The server collects the results of the AB tests, analyzes the click-through rate and conversion rate of each version, and selects the version with the best performance. The AB test results are the input data, and the optimal version is the output data.

[0815] Step 7: Recognizing user emotions with the emotion engine

[0816] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and analyzes them with an emotion engine. For example, the device analyzes the user's facial expressions in real time while the user is watching an advertisement. The captured facial expressions and voice are the input data, and the analyzed emotion data is the output data.

[0817] Step 8: Select content based on emotion

[0818] The server selects content according to the user's emotion based on the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server selects a campaign idea that corresponds to that emotion. The emotion data is the input data, and the selected content is the output data.

[0819] Step 9: Emotion-based market research and A / B testing

[0820] The server then subjects the selected content to market research concept testing or web AB testing. For example, it creates an advertising banner that corresponds to the emotion of joy and conducts the test again. The selected content is the input data, and the test results are the output data.

[0821] Step 10: Select the final result

[0822] The server comprehensively analyzes all the test results and finally selects the most suitable campaign idea that is the most highly rated and corresponds to the user's emotions. The test results are the input data, and the optimal campaign idea is the output data.

[0823] (Application example 2)

[0824] Next, a description will be given of Application Example 2 of Form 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".

[0825] In conventional marketing content generation systems, there were insufficient testing methods to ensure the quality of the generated content, making it difficult to efficiently select content that would appeal to customers. In addition, content selection did not take into account user emotions, making it impossible to maximize customer response. This reduced the probability of sales and limited marketing effectiveness.

[0826] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0827] In this invention, the server includes a generating means using a generating AI model to generate new project idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a testing means using an emotion engine that recognizes the user's emotions and selects content that will appeal to customers according to the emotions. This makes it possible to improve the quality of the generated content, efficiently select content that will appeal to customers, and increase the probability of sales.

[0828] A "generative AI model" is an algorithm or system that uses artificial intelligence to automatically generate new planning ideas and marketing content.

[0829] "Generation means" refers to a function or device that uses a generative AI model to generate new planning ideas and marketing content that meets necessary conditions.

[0830] "Testing means" refers to functions or devices used for conducting concept testing for market research or AB testing on the web in order to ensure the quality of the generated content.

[0831] An "emotion engine" is an algorithm or system that recognizes a user's emotions and selects content that will resonate with customers based on those emotions.

[0832] "Market research concept testing" is a research methodology used to evaluate the market acceptability of generated content or project ideas.

[0833] "AB testing on the web" is a testing method in which different versions of content are published simultaneously on the web and the most effective content is selected by comparing actual customer reactions.

[0834] In order to implement the present invention, the following system configuration and processing procedures are required.

[0835] First, the server uses a generative AI model to generate new project ideas and marketing content. The generative AI model can use advanced natural language processing models such as GPT-3 and BERT. The generative AI model generates specific content by inputting a prompt sentence such as the following:

[0836] Example prompt:

[0837] "Generate ideas for a new marketing campaign. The target audience will be young people in their 20s, with a focus on promotion using social media."

[0838] The generated content is then evaluated by testing methods such as market research concept testing and web AB testing. In market research concept testing, methods such as questionnaire surveys and focus group interviews can be used to evaluate how well the generated content is accepted in the market. In web AB testing, different versions of the content are published simultaneously on the web and actual customer reactions are compared.

[0839] In addition, a testing method using an emotion engine is also built in. The emotion engine recognizes the user's emotions and selects content that will appeal to customers based on those emotions. For example, if a user expresses joy, it selects content that corresponds to that emotion and conducts market research and A / B testing of that content.

[0840] For example, when a user is using a smartphone, the smartphone's camera and microphone are used to analyze the user's facial expressions and tone of voice, and the emotion engine recognizes the user's emotions. Based on the recognized emotions, optimal content is selected and presented to the user.

[0841] This system makes it possible to improve the quality of generated content, efficiently select content that will appeal to customers, and increase the probability of sales.

[0842] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0843] Step 1:

[0844] The server inputs a prompt text to the generative AI model. For example, the prompt text might be, "Please generate ideas for a new marketing campaign. The target audience is young people in their 20s, and we will place emphasis on promotion using social media." The generative AI model generates new project ideas and marketing content based on this prompt text. The input is the prompt text, and the output is the generated content.

[0845] Step 2:

[0846] The server subjects the generated content to market research concept testing, which uses methods such as questionnaire surveys and focus group interviews to evaluate how well the generated content will be received in the market. The input is the generated content and the output is the results of the market research.

[0847] Step 3:

[0848] The server subjects the generated content to AB testing on the web. In AB testing on the web, different versions of content are published simultaneously on the web and actual customer reactions are compared. The input is the generated content, and the output is the result of the AB test.

[0849] Step 4:

[0850] The device uses the smartphone's camera and microphone to recognize the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotions. The input is the user's facial expression and voice data, and the output is the recognized emotion.

[0851] Step 5:

[0852] The server selects the optimal content based on the recognized emotion. For example, if the user indicates an emotion of happiness, the server selects the content according to the emotion. The input is the recognized emotion and the generated content, and the output is the selected optimal content.

[0853] Step 6:

[0854] The terminal presents the selected optimal content to the user. The user checks the presented content and provides feedback as necessary. The input is the selected content, and the output is the user's feedback.

[0855] In this way, it is possible to improve the quality of the generated content, efficiently select content that appeals to customers, and increase the probability of sales.

[0856] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0857] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0858] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0859] 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 smart glasses 214.

[0860] [Third embodiment]

[0861] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0862] 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.

[0863] 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 wide area network (WAN) and / or a local area network (LAN).

[0864] 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.

[0865] 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 the voice according to instructions from the processor 46.

[0866] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0867] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0868] Fig. 6 shows an example of 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.

[0869] 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.

[0870] 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.

[0871] In the headset type terminal 314, 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.

[0872] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0873] "Example 1"

[0874] In one embodiment of the present invention, a system including an AI generation means and a testing means is provided. The AI ​​generation means generates concepts and marketing content for new planning ideas that satisfy necessary conditions. Specifically, the AI ​​generation means generates content by utilizing creative answers based on necessary conditions set by the planning department. For example, when generating planning ideas for a new product, the AI ​​generation means generates the content by considering necessary conditions such as the target customer base, the market environment, and the characteristics of the product.

[0875] Generate project ideas that meet these needs.

[0876] "Example 2"

[0877] In addition, a testing method is provided to ensure the quality of the generated content. The testing method involves market research concept testing and web AB testing, and by selecting content that will appeal to customers, the quality of the plan is improved and the probability of sales is increased. For example, market research concept testing is conducted on multiple plan ideas generated by the AI ​​generation method, and the plan idea with the highest evaluation based on customer evaluation is selected. In addition, web AB testing is conducted, and the plan idea with the best response is selected based on actual customer reactions.

[0878] The process flow of each embodiment will be described below.

[0879] "Example 1"

[0880] Step 1: The planning department sets the requirements, including the target customer group, market environment, product characteristics, etc.

[0881] Step 2: The AI ​​generator uses creative answers to generate new business idea concepts and marketing content based on the set requirements.

[0882] Step 3: The planning department reviews the generated planning ideas and makes corrections or additions as necessary.

[0883] "Example 2"

[0884] Step 1: Conduct market research concept testing on multiple planning ideas generated by the AI ​​generation method.

[0885] Step 2: Select the most highly rated project idea based on customer evaluations.

[0886] Step 3: Conduct online AB testing of the selected project ideas.

[0887] Step 4: Based on actual customer reactions, the project idea with the best response is finally selected.

[0888] Example 1

[0889] Next, a description will be given of Example 1 of the embodiment 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".

[0890] In conventional systems for generating new project ideas and marketing content, the process from when the user inputs the necessary conditions to when the generated content is evaluated and improved is complicated, making it difficult to efficiently generate high-quality content. In addition, market research and web AB testing to ensure the quality of the generated content are often done manually, which is time-consuming and labor-intensive.

[0891] 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.

[0892] In this invention, the server includes a generating means for generating concepts and marketing content for new project ideas that satisfy necessary conditions, an evaluating means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an input means for a user to input necessary conditions, a generating means for generating a prompt sentence based on the input necessary conditions, a generating means for inputting the generated prompt sentence into a generative AI model to generate content, a transmitting means for transmitting the generated content to a user's terminal, and an evaluating means for receiving feedback from the user and evaluating and improving the content. This makes it possible to streamline the process from when the user inputs necessary conditions to when the generated content is evaluated and improved, and to generate high-quality content quickly.

[0893] "Requirements" are requirements or standards that must be met when a user generates a new project idea or marketing content.

[0894] A "new project idea" is a proposal or concept that adds new value or features to an existing product or service.

[0895] "Marketing Content" means information or messages intended to promote or sell a product or service.

[0896] The "generation means" refers to a method or device for generating new project ideas and marketing content based on necessary conditions.

[0897] An "assessment means" is a method or device for assessing the quality of the generated content and improving it if necessary.

[0898] An "input means" is a method or device by which a user inputs requirements into the system.

[0899] A "prompt sentence" is an instruction sentence input into a generative AI model and is generated based on necessary conditions.

[0900] A "generative AI model" is an algorithm or program that uses artificial intelligence to generate new planning ideas and marketing content.

[0901] The "transmitting means" refers to a method or device for transmitting the generated content to a user's terminal.

[0902] "Feedback" refers to information about corrections or improvements provided by a user to generated content.

[0903] The present invention relates to a system for generating new project ideas and marketing contents that satisfy necessary conditions, and evaluating and improving the quality of the generated ideas and contents. The system includes a generating means, an evaluating means, an inputting means, a transmitting means, and a feedback means.

[0904] The server hosts a generative AI model as a generation means. Specifically, the server uses a generative AI model such as OpenAI's GPT-4. When a user inputs the necessary conditions through an input means, the server receives it and generates a prompt sentence. The generated prompt sentence is input to the generative AI model, and new project ideas and marketing content are generated.

[0905] Users access the system using a terminal (PC or tablet) and input their requirements. Requirements include target customer segments, market environment, product characteristics, etc. For example, a user may input the following requirements:

[0906] Target customer demographic: Young people in their 20s

[0907] Market environment: Online shopping is mainstream

[0908] Product features: Eco-friendly materials used

[0909] Based on these requirements, the server will generate a prompt like this:

[0910] "Generate product ideas for new products using eco-friendly materials to be sold on the online shopping market, targeting young people in their 20s."

[0911] The server inputs this prompt into the generative AI model and receives the generated content, such as the following:

[0912] "We are proposing a stylish backpack made from recycled materials for young people in their 20s. This backpack will be sold exclusively online, and customers who purchase it will receive eco points as a special perk."

[0913] The server transmits the generated content to the user's terminal. The terminal displays the received content to the user. The user checks the generated content and provides feedback, if necessary. The feedback may include corrections or improvements.

[0914] The server receives feedback from users and evaluates and improves the content using the evaluation means, which improves the quality of the generated content and allows it to meet user requirements with greater accuracy.

[0915] This system streamlines the process from when users input their requirements to when they evaluate and improve the generated content, making it possible to quickly generate high-quality content.

[0916] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0917] Step 1:

[0918] A user logs into the system using a terminal. The user inputs requirements such as target customer demographics, market environment, and product characteristics. The input requirements are sent to the server. Specifically, the user enters requirements into the input form and clicks the "Submit" button. Input: Requirements. Output: Requirements sent to the server.

[0919] Step 2:

[0920] The server receives the requirements sent by the user. The server generates a prompt sentence based on the received requirements. Specifically, the server analyzes the requirements and creates a prompt sentence in a format suitable for the generative AI model. Input: Requirements from the user. Output: Generated prompt sentence.

[0921] Step 3:

[0922] The server inputs the generated prompt sentence into the generative AI model. The server waits for the generative AI model to generate content based on the prompt sentence. Specifically, the server sends the prompt sentence to the generative AI model through the API and receives the generated content. Input: Generated prompt sentence. Output: Generated content from the generative AI model.

[0923] Step 4:

[0924] The server sends the content received from the generative AI model to the user's device. The device displays the received content to the user. In concrete terms, the server sends the generated content to the user's device in real time, and the device displays the content on its screen. Input: Generated content from the generative AI model. Output: Content displayed on the user's device.

[0925] Step 5:

[0926] The user checks the generated content displayed on the terminal. If necessary, the user inputs feedback on corrections and improvements. Specifically, the user enters comments in the feedback form and clicks the "Submit" button. Input: Generated content. Output: Feedback from the user.

[0927] Step 6:

[0928] The server receives feedback from the user. The server evaluates the generated content based on the feedback and makes improvements if necessary. Specifically, the server analyzes the feedback and sends the prompt sentence to the generative AI model again to generate improved content. Input: User feedback. Output: Improved generated content.

[0929] (Application example 1)

[0930] Next, a description will be given of Application Example 1 of Form 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".

[0931] Conventional advertising content generation systems have had difficulty generating effective advertising content based on conditions such as target customer segments, market environment, and product characteristics. In addition, there was a lack of market research and testing methods to ensure the quality of the generated content, making it impossible to maximize the effectiveness of advertising. This resulted in a problem of reduced advertising effectiveness and the inability to expect an increase in sales.

[0932] 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.

[0933] In this invention, the server includes an AI generation means for generating new project idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a smartphone application for generating advertising content based on conditions such as target customer segments, market environment, product characteristics, etc. This makes it possible to generate effective advertising content and ensure its quality.

[0934] "Requirements" are conditions that must be met when generating advertising content, such as target customer segments, market environment, and product characteristics.

[0935] A "new project idea" is a new concept or marketing strategy that has never been seen before.

[0936] "Marketing content" refers to materials such as text, images, and videos used to promote products and services.

[0937] "AI generation means" refers to a means of using artificial intelligence to generate new planning ideas and marketing content that meets necessary conditions.

[0938] "Testing methods" refer to the means of conducting market research concept tests and AB tests on the web to ensure the quality of the generated content.

[0939] A "target demographic" is a particular group of customers to whom an advertisement or product is primarily directed.

[0940] "Market environment" refers to external factors such as the competitive situation and trends in the market in which the advertisement or product is developed.

[0941] "Product features" are the specific characteristics or benefits of an advertisement or product.

[0942] A "smartphone application" is a software program that runs on a smartphone.

[0943] "Advertising content" refers to materials such as text, images, and videos created to promote a specific product or service.

[0944] The following system configuration is necessary to implement this invention. The system includes an AI generation means for generating new project idea concepts and marketing content that meet required conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a smartphone application for generating advertising content based on conditions such as the target customer demographic, market environment, and product characteristics.

[0945] The server uses a generative AI model such as OpenAI's GPT-3 to generate advertising content based on the requirements entered by the user, such as the target customer demographic, market environment, and product characteristics. Specifically, when the user enters the requirements through a smartphone application, the server converts them into a prompt text and sends it to the generative AI model. The generative AI model generates creative advertising content based on the prompt text and returns it to the user.

[0946] For example, if the target customer group is set as "women in their 20s," the market environment is set as "highly competitive cosmetics market," and the product characteristics are set as "highly moisturizing," the following prompt sentence will be generated.

[0947] Example prompt:

[0948] Target customer group: Women in their 20s

[0949] Market environment: Highly competitive cosmetics market

[0950] Product Features: High moisturizing effect

[0951] Please generate advertising content that meets the above criteria.

[0952] For example, the generated advertising content might be, "Recommended for women in their 20s! A new product that's attracting attention in the highly competitive cosmetics market. It has high moisturizing effects and is perfect for those who suffer from dry skin. Try it now!"

[0953] Furthermore, to ensure the quality of the generated advertising content, the server performs concept testing for market research and AB testing on the web, which allows it to predict the effectiveness of advertising and propose optimal advertising ideas to users.

[0954] In this way, it becomes possible to generate effective advertising content and ensure its quality.

[0955] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0956] Step 1:

[0957] The user launches the smartphone application and inputs necessary conditions such as the target customer group, market environment, and product characteristics.

[0958] Input: Target customer group, market environment, product characteristics

[0959] Output: Prerequisites entered

[0960] Specific operation: The user enters the target customer group (e.g., women in their 20s), market environment (e.g., highly competitive cosmetics market), and product characteristics (e.g., high moisturizing effect) into the application's input form.

[0961] Step 2:

[0962] The terminal converts the input requirements into a prompt text and sends it to the server.

[0963] Input: Requirements

[0964] Output: Prompt statement

[0965] Specific behavior: The application converts the entered requirements into a prompt like this:

[0966] Target customer group: Women in their 20s

[0967] Market environment: Highly competitive cosmetics market

[0968] Product Features: High moisturizing effect

[0969] Please generate advertising content that meets the above criteria.

[0970] This prompt is sent to the server.

[0971] Step 3:

[0972] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate advertising content based on the prompt text.

[0973] Input: prompt statement

[0974] Output: Ad content

[0975] Specific operation: The server inputs the prompt text into the AI ​​model and obtains the generated ad content. For example, the ad content generated is "Recommended for women in their 20s! A new product that is attracting attention in the highly competitive cosmetics market. Highly moisturizing, perfect for those who suffer from dry skin. Try it now!"

[0976] Step 4:

[0977] The server sends the generated advertising content back to the terminal.

[0978] Input: Ad content

[0979] Output: Ad content sent to the device

[0980] Specific operations: The server transmits the generated advertising content to the terminal.

[0981] Step 5:

[0982] The terminal displays the received advertisement content to the user.

[0983] Input: Ad content

[0984] Output: Ad content displayed

[0985] Specific behavior: The application displays the received advertising content to the user.

[0986] Step 6:

[0987] The user reviews the quality of the generated advertising content and corrects or regenerates it as necessary.

[0988] Input: Ad content

[0989] Output: The modified or regenerated ad content.

[0990] What happens: The user reviews the displayed ad content and, if necessary, corrects it or requests that it be regenerated.

[0991] Step 7:

[0992] In order to ensure the quality of the advertising content generated by the server, we conduct concept tests for market research and A / B tests on the web.

[0993] Input: Ad content

[0994] Output: Test results

[0995] Specific operation: The server subjects the generated advertising content to market research concept testing and web-based AB testing and obtains the results.

[0996] Step 8:

[0997] The server proposes optimal advertising ideas to the user based on the test results.

[0998] Input: Test result

[0999] Output: Best ad recommendation

[1000] What happens: The server analyzes the test results and suggests optimal ads to the user.

[1001] Example 2

[1002] Next, a second embodiment of the second form will be described. 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".

[1003] With conventional planning idea generation and evaluation systems, it was difficult to accurately evaluate the quality of the generated ideas and their response in the market. As a result, it was not possible to select planning ideas that would appeal to customers, and there was a problem that sales could not be expected to increase. Furthermore, there was also the issue that it was difficult to quickly bring ideas to market because the evaluation process of the generated ideas was complicated and time-consuming.

[1004] 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.

[1005] In this invention, the server includes a means for generating new planning ideas using a generative AI model, a means for conducting market research concept testing on the generated planning ideas, and a means for conducting AB testing on the web on the generated planning ideas, which makes it possible to quickly and accurately evaluate the quality of the generated planning ideas and select the optimal planning ideas that will appeal to customers.

[1006] A "generative AI model" is a type of artificial intelligence that uses natural language processing technology to generate new project ideas.

[1007] "New project ideas" are novel concepts and marketing content generated by generative AI models.

[1008] "Market research concept testing" is a method of collecting customer evaluations of generated planning ideas and verifying the validity of the ideas based on that evaluation data.

[1009] "Web AB testing" is a method of selecting the most effective idea by displaying different project ideas to actual customers and collecting and analyzing their response data.

[1010] "Server" refers to a computer system that executes the generative AI model and evaluates and selects the generated project ideas.

[1011] "Reaching the customer" means that the generated planning ideas will pique the customer's interest and stimulate their desire to purchase.

[1012] "Planning quality" is an index showing the market acceptability and effectiveness of the generated planning ideas.

[1013] The "probability of selling" is an index showing the possibility that the generated planning idea will be successful in the market and actually generate sales.

[1014] This invention is a system that generates new project ideas using a generative AI model and evaluates the ideas through concept testing in market research and AB testing on the web. A specific embodiment of this system will be described below.

[1015] The server generates new project ideas using a generative AI model (e.g., an advanced artificial intelligence model using natural language processing technology). An example of a generative AI model that can be used is OpenAI's GPT-4. The server inputs a prompt sentence into the generative AI model to generate multiple project ideas. An example of a specific prompt sentence is "Please generate five project ideas for a new smartphone app."

[1016] The generated project ideas are stored in a database by the server. The server then conducts market research concept testing. In the market research concept testing, market research tools such as SurveyMonkey and Qualtrics are used to collect customer evaluations of the generated project ideas. Specifically, the server creates a survey that includes the following question: "How interested are you in this app idea? (Please rate on a scale of 1-5)." Users answer the survey using their devices, and the server collects and analyzes the evaluation data.

[1017] Next, the server conducts AB testing on the web. In AB testing, tools such as Google Optimize and Optimizely are used to display different project ideas to actual customers and collect response data. Specifically, the server sets up the following test: "Show idea 1 to group A and idea 2 to group B, and compare which group clicks more." Users use their devices to view web pages and respond to the displayed project ideas. The server analyzes the collected click data and selects the project idea with the best response.

[1018] Finally, the server comprehensively evaluates the results of the market research concept tests and the web-based AB tests to select the plan idea that has the highest evaluation and appeals to customers. This selected plan idea is stored in the database and notified to the user.

[1019] This system makes it possible to quickly and accurately evaluate the quality of the generated planning ideas and select the most suitable planning idea that will appeal to customers, thereby improving the quality of the plan and increasing the probability of it selling.

[1020] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1021] Step 1:

[1022] The server generates new project ideas using the generative AI model. Specifically, the server inputs a prompt sentence, "Please generate five project ideas for a new smartphone app," into the generative AI model. The generative AI model generates five different project ideas based on this prompt sentence and returns them to the server. The server stores the generated project ideas in a database. The input is the prompt sentence, and the output is the generated project ideas.

[1023] Step 2:

[1024] The server conducts market research concept testing on the generated project ideas. Specifically, the server creates a survey using a market research tool (e.g., SurveyMonkey or Qualtrics). The survey includes questions such as, "How interested are you in this app idea? (Please rate on a scale of 1-5)." Users answer the survey using their terminals. The server collects evaluation data from users and stores it in a database. The input is the generated project idea and the survey responses, and the output is the evaluation data.

[1025] Step 3:

[1026] The server analyzes the collected evaluation data and selects the project idea with the highest evaluation. Specifically, the server statistically processes the evaluation data and calculates the average evaluation score of each project idea. The project idea with the highest score is selected and proceeds to the next step. The input is the evaluation data, and the output is the project idea with the highest evaluation.

[1027] Step 4:

[1028] The server conducts AB testing on the web for the selected project ideas. Specifically, the server uses an AB testing tool (e.g., Google Optimize or Optimizely) to display different project ideas to actual customers. For example, idea 1 is displayed to group A and idea 2 is displayed to group B, and a comparison is made to see which group makes more clicks. Users use their devices to view web pages and react to the displayed project ideas. The server saves the collected click data in a database. The input is the selected project idea and customer response data, and the output is click data.

[1029] Step 5:

[1030] The server analyzes the collected click data and selects the project idea with the best response. Specifically, the server statistically processes the click data and calculates the click rate of each project idea. The project idea with the highest click rate is finally selected. The input is the click data, and the output is the project idea with the best response.

[1031] Step 6:

[1032] The server saves the final selected project idea in a database and notifies the user. Specifically, the server saves the selected project idea in a database and notifies the user of the result via email or a notification system. The input is the project idea with the best response, and the output is the notification to the user.

[1033] (Application example 2)

[1034] Next, a description will be given of Application Example 2 of Form 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".

[1035] Traditionally, planning advertising campaigns and generating marketing content is often done manually, which is time-consuming and labor-intensive, and there is a lack of objective evaluation methods for selecting effective content. This makes the effectiveness of advertising campaigns uncertain, and may not lead to increased sales. Furthermore, market research and AB testing to ensure the quality of the generated content are also cumbersome, making it difficult to obtain rapid feedback.

[1036] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1037] In this invention, the server includes a generating AI model means for generating new planning idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing of market research and AB testing on the web to ensure the quality of the generated content, a means for generating planning ideas for advertising campaigns, calculating evaluations and click rates, and a means for selecting the most highly rated advertising campaign and proposing it to the advertiser. This makes it possible to consistently automate the process from planning to evaluation, selection, and proposal of advertising campaigns, and quickly implement effective advertising campaigns.

[1038] A "generative AI model means" is a means that uses artificial intelligence technology to generate new project idea concepts and marketing content that meet required conditions.

[1039] "Testing methods" refer to the means of conducting market research concept tests and AB tests on the web to ensure the quality of the generated content.

[1040] The "means for generating advertising campaign planning ideas" refers to means for generating new ideas for advertising campaigns and calculating ratings and click-through rates for those ideas.

[1041] The "means of proposing to advertisers" refers to the means of selecting the most highly rated advertising campaign and proposing the results to advertisers.

[1042] A system for implementing the present invention includes a generative AI model means, a testing means, a means for generating planning ideas for advertising campaigns, and a means for proposing ideas to advertisers.

[1043] The server generates new project idea concepts and marketing content that meet the requirements using a generative AI model means, which generates creative answers based on the prompt sentence, for example, using an OpenAI API.

[1044] Next, to ensure the quality of the generated content, we use testing methods to conduct concept tests for market research and AB tests on the web. From the multiple generated project ideas, we select the one with the highest evaluation based on customer evaluations and actual click rates.

[1045] The means for generating advertising campaign planning ideas uses a generative AI model means to generate new advertising campaign ideas and calculate ratings and click-through rates for the ideas, the means being implemented using a programming language such as Python.

[1046] Finally, the most highly evaluated advertising campaign is selected using a means for proposing to the advertiser, and the result is proposed to the advertiser. This means generates a report for proposing the optimal advertising campaign to the advertiser based on the evaluation result and the click-through rate data.

[1047] As a specific example, when considering an advertising campaign for a new beverage, the prompt sentence is "Generate ideas for an advertising campaign for a new beverage." Based on this prompt sentence, the generative AI model means generates multiple advertising campaign ideas, and by conducting concept tests in market research and AB tests on the web for those ideas, the most effective advertising campaign can be selected and proposed to the advertiser.

[1048] This system automates the entire process of advertising campaigns, from planning to evaluation, selection and proposal, making it possible to quickly implement effective advertising campaigns.

[1049] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1050] Step 1:

[1051] The server uses a generative AI model means to generate concepts and marketing content for new project ideas. Specifically, the server sends a prompt sentence, "Please generate an idea for a new beverage advertising campaign," as an input to a generative AI model (e.g., OpenAI's API), and receives the generated multiple advertising campaign ideas as an output.

[1052] Step 2:

[1053] The server performs market research concept testing on the generated advertising campaign ideas. Specifically, the server inputs the generated ideas into a market research tool, collects evaluation data from customers, calculates an evaluation score for each idea based on the evaluation data, and obtains the evaluation score as an output.

[1054] Step 3:

[1055] The server selects the best-rated advertising campaign idea based on the rating scores, by comparing the rating scores, selecting the idea with the highest score, and obtaining the idea as an output.

[1056] Step 4:

[1057] The server performs AB testing on the web for the selected advertising campaign ideas. Specifically, the selected ideas are input into an AB testing tool, and actual click-through rate data is collected. Based on the click-through rate data, the click-through rate for each idea is calculated, and the click-through rate is obtained as output.

[1058] Step 5:

[1059] The server selects the advertising campaign idea that has the best response based on the click-through rate, by comparing the click-through rates, selecting the idea with the highest click-through rate, and obtaining the idea as an output.

[1060] Step 6:

[1061] The server proposes the most highly rated and most responsive advertising campaign ideas to the advertiser. Specifically, the server compiles the selected ideas, their evaluation scores, and click-through rates in a report format and sends it to the advertiser. The server obtains the report as an output.

[1062] In addition, 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.

[1063] "Example 1"

[1064] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system recognizes the emotion of a user and generates new project idea concepts and marketing content according to the emotion. Specifically, the emotion engine recognizes the emotion of the user, and the AI ​​generation means generates content by utilizing creative answers based on the emotion. For example, when the user expresses an emotion of joy, the AI ​​generation means generates a project idea according to the emotion of joy. This makes it possible to generate project ideas corresponding to the emotion of the user.

[1065] "Example 2"

[1066] A testing method using an emotion engine is also provided. This testing method improves the quality of the plan and increases the probability of sales by recognizing the user's emotions and selecting content that will appeal to customers according to those emotions. Specifically, the emotion engine recognizes the user's emotions and performs concept testing for market research and AB testing on the web based on those emotions. For example, if a user expresses an emotion of joy, the testing method selects content that corresponds to that emotion and performs market research and AB testing for that content. This makes it possible to select content that corresponds to the user's emotions and improve the quality.

[1067] The process flow of each embodiment will be described below.

[1068] "Example 1"

[1069] Step 1: Recognize the user's emotion using the emotion engine.

[1070] Step 2: Based on the recognized sentiment, the AI ​​generator uses the creative answers to generate new project idea concepts and marketing content.

[1071] Step 3: Present the generated planning ideas and marketing content to the user.

[1072] "Example 2"

[1073] Step 1: Recognize the user's emotion using the emotion engine.

[1074] Step 2: Based on the emotions identified, conduct market research concept testing and web-based A / B testing.

[1075] Step 3: Based on the test results, select content that will resonate with customers, improve the quality of the plan, and increase the probability of sales.

[1076] Example 1

[1077] Next, a description will be given of Example 1 of the embodiment 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".

[1078] In conventional systems, it was difficult to take users' emotions into account when generating new project ideas and marketing content, and the generated content did not necessarily match the user's emotions. In addition, there was a lack of evaluation methods to ensure the quality of the generated content, making it difficult to maximize the effectiveness of the content.

[1079] 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.

[1080] In this invention, the server includes a generating means for generating new project idea concepts and marketing content that satisfy the necessary conditions, an evaluating means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognizing means for recognizing the emotion of a user and generating content according to the emotion, and a control means for generating a prompt sentence based on the emotion data obtained from the emotion recognizing means and the necessary conditions and sending it to the generating means. This makes it possible to generate new project ideas and marketing content that match the emotion of the user, and further to evaluate and improve the quality of the generated content.

[1081] The "generation means" refers to a means for generating concepts for new project ideas and marketing content that meet the necessary conditions.

[1082] "Evaluation methods" are methods used to conduct market research concept tests and web-based A / B tests to ensure the quality of the generated content.

[1083] The "emotion recognition means" is a means for recognizing the user's emotion and generating content in accordance with that emotion.

[1084] The "control means" is a means for generating a prompt sentence based on the emotion data obtained from the emotion recognition means and the necessary conditions, and sending the prompt sentence to the generation means.

[1085] A "prompt sentence" is an instruction sentence used by the generating means when generating new project ideas and marketing content.

[1086] A "new business idea" is a concept for a new product or service that is not yet on the market.

[1087] "Marketing content" refers to advertising and promotional materials used to promote products and services to the market.

[1088] "Requirements" are conditions that the generated content must satisfy, such as the target customer group, market environment, and product characteristics.

[1089] The present invention relates to a system for generating concepts and marketing contents for new project ideas that satisfy requirements. The system includes a generating unit, an evaluating unit, an emotion recognizing unit, and a controlling unit.

[1090] Hardware and Software Used

[1091] Hardware: Servers, terminals

[1092] Software: Generative AI models (e.g. GPT-4), emotion engines (e.g. Affectiva)

[1093] Specific operation of the system

[1094] User Emotion Recognition

[1095] A user accesses the system using a terminal. The terminal's camera and microphone capture the user's facial expressions and voice in real time. The terminal sends the captured data to the emotion engine. The emotion engine analyzes the characteristics of the user's facial expressions and voice and recognizes emotions. For example, when a user smiles, the emotion engine recognizes the emotion of "happiness."

[1096] Setting Prerequisites

[1097] The planning department logs into the server and inputs the necessary conditions. The server saves the input necessary conditions in a database. The necessary conditions include the target customer group, the market environment, and the characteristics of the product. For example, the target customer group can be set as "young people in their 20s," the market environment as "health-conscious," and the product characteristic as "low calorie."

[1098] Content Generation

[1099] The server sends the user's emotion data obtained from the emotion engine and the requirements provided by the planning department to the generation means. The generation means uses a generative AI model (e.g. GPT-4) to generate creative content based on the requirements and the user's emotions. The generative AI model receives the prompt sentence and generates content based on it.

[1100] Examples of prompt statements

[1101] The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low calorie. Users show happy emotions. Based on these conditions, generate planning ideas for a new beverage product.

[1102] For example, if the prompt is, "The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low calorie. Users are expressing feelings of joy. Based on these conditions, please generate planning ideas for a new beverage product," the generative AI model would generate ideas such as, "Propose low-calorie, vitamin-rich fruit juice for young people in their 20s."

[1103] Testing and Feedback

[1104] The server sends the generated content to the evaluator. The evaluator evaluates the generated content and provides feedback. The server receives the test results and modifies the content as necessary. For example, if the evaluator provides feedback such as "The idea for the proposed fruit juice is good, but more specific ingredient information is needed," the server resends the prompt sentence to the generative AI model based on the feedback to generate modified content.

[1105] In this way, new project ideas and marketing content are generated based on the user's emotions and requirements.

[1106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1107] Step 1:

[1108] User Emotion Recognition

[1109] Input: A user logs in to a device and allows access to the camera and microphone.

[1110] Specific operation: The device captures the user's facial expressions and voice in real time.

[1111] Data processing: The device sends the captured data to the emotion engine, which analyzes the user's facial expressions and voice characteristics to recognize emotions.

[1112] Output: The emotion engine sends the recognized emotion data to the server. For example, if the user smiles, the emotion engine recognizes the emotion of "happiness" and sends the data to the server.

[1113] Step 2:

[1114] Setting Prerequisites

[1115] Input: The planning department logs into the server and enters their requirements.

[1116] Specific Actions: The server stores the entered requirements in a database.

[1117] Data processing: Requirements include target customer demographics, market environment, product characteristics, etc.

[1118] Output: The server sends the saved requirements to the generator. For example, the target customer group is set as "young people in their 20s," the market environment is set as "health-conscious," and the product characteristic is set as "low calorie."

[1119] Step 3:

[1120] Content Generation

[1121] Input: The server sends the user's emotion data obtained from the emotion engine and the requirements provided by the planning department to the generator.

[1122] Specific operation: The generator uses a generative AI model (e.g., GPT-4) to generate creative content based on the requirements and user emotions.

[1123] Data processing: The generative AI model receives a prompt and generates content based on it.

[1124] Output: The generated content is sent to the server. For example, if the prompt is "The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low-calorie. The user shows an emotion of joy. Based on these conditions, please generate a planning idea for a new beverage product," the generative AI model will generate an idea such as "Propose a low-calorie, vitamin-rich fruit juice for young people in their 20s."

[1125] Step 4:

[1126] Testing and Feedback

[1127] Input: The server sends the generated content to the evaluator.

[1128] What to do: The evaluation tool evaluates the generated content and provides feedback.

[1129] Data processing: Evaluation measures assess the quality of content and identify areas for improvement.

[1130] Output: The server receives the test results and modifies the content as necessary. For example, if the evaluator gives feedback such as "The idea of ​​the proposed fruit juice is good, but more specific information on the ingredients is needed," the server sends the prompt sentence to the generative AI model again based on the feedback, and generates the modified content.

[1131] In this way, new project ideas and marketing content are generated based on the user's emotions and requirements.

[1132] (Application example 1)

[1133] Next, a description will be given of Application Example 1 of Form 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".

[1134] Conventional marketing content generation systems provide uniform content without considering the user's feelings, making it difficult to attract the user's interest. In addition, there was a lack of testing methods to ensure the quality of the generated content, which made it difficult to achieve effective marketing.

[1135] 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.

[1136] In this invention, the server includes an AI generation means for generating new project idea concepts and marketing content that meet the necessary conditions, a test means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognition means for recognizing the emotion of a user and generating content according to the emotion, and a display means for displaying the generated content in real time. This makes it possible to generate effective marketing content according to the emotion of a user and ensure its quality.

[1137] A "requirement" is a criterion or requirement that must be met in order to achieve a particular purpose or goal.

[1138] A "new project idea" is a new idea or plan that has never been seen before.

[1139] A "concept" is the basic idea or philosophy behind a project or product.

[1140] "Marketing Content" means information and materials used to promote and sell products and services.

[1141] An "AI generation means" refers to a function or device that uses artificial intelligence to automatically generate new planning ideas and marketing content.

[1142] "Testing Means" means any method or device for evaluating or verifying the quality of the Produced Content.

[1143] "Market research" refers to research activities conducted to understand consumer needs and market trends.

[1144] A "concept test" is a test conducted to evaluate whether a new plan or product concept will be accepted in the market.

[1145] "AB testing on the web" refers to the comparison of different versions of a web page or piece of content to evaluate which one is more effective.

[1146] "Emotion recognition means" refers to technology or devices for detecting and recognizing a user's emotions.

[1147] A "display means" refers to a method or device for visually presenting the generated content to a user.

[1148] As an embodiment of the present invention, an emotion-responsive advertisement generation system will be described as an example. This system includes an AI generation means for generating concepts and marketing content for new project ideas that satisfy necessary conditions, a testing means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognition means for recognizing the emotion of a user and generating content corresponding to the emotion, and a display means for displaying the generated content in real time.

[1149] Hardware and Software Used

[1150] Hardware: Smartphone camera

[1151] Software: OpenCV, Keras, Transformers libraries

[1152] Processing flow

[1153] 1. Camera image capture: Capture images in real time from the smartphone camera, which gives an image of the user's face.

[1154] 2. Face detection and emotion recognition: Detect faces using OpenCV and recognize the user's emotions using an emotion recognition model trained with Keras. Specifically, the face area is cut out, converted to grayscale, and then input to the emotion recognition model.

[1155] 3. Advertising content generation: Based on the recognized emotion, generate appropriate advertising content using the GPT-3 model. For example, if the user shows the emotion of happiness, input the prompt sentence "Generate advertising content appropriate for when the user shows the emotion of happiness" to the GPT-3 model.

[1156] 4. Display of advertising content: The generated advertising content is displayed on the camera footage in real time, allowing users to visually confirm the advertisements that correspond to their own emotions.

[1157] Examples

[1158] For example, if the user is expressing an emotion of joy, the following prompt sentence is input to the generative AI model:

[1159] Examples of prompt statements

[1160] Generate appropriate ad content when users are expressing the emotion of happiness.

[1161] When this prompt sentence is input into the GPT-3 model, advertising content such as "Why not try our new ice cream? It's on sale now at a special discount!" is generated. This advertising content is displayed in real time on the smartphone screen, attracting the user's interest.

[1162] The above is an embodiment of the present invention. This system makes it possible to generate effective marketing content in response to the user's emotions and to guarantee the quality of the content.

[1163] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1164] Step 1:

[1165] Capture video from a smartphone camera in real time. The input is the camera video and the output is the captured frames. Specifically, start the smartphone camera and continuously capture video.

[1166] Step 2:

[1167] Detect faces from captured frames. The input is the captured frame and the output is the detected face area. Specifically, we use OpenCV to detect faces in the frame and get the face position information.

[1168] Step 3:

[1169] The detected face area is converted to grayscale and input to the emotion recognition model. The input is the face area, and the output is the recognized emotion. Specifically, the face area is cut out, converted to grayscale, and then input to the emotion recognition model trained with Keras.

[1170] Step 4:

[1171] Based on the recognized emotion, appropriate advertising content is generated. The input is the recognized emotion, and the output is the generated advertising content. Specifically, a prompt sentence is generated according to the recognized emotion, and input to the GPT-3 model to generate advertising content.

[1172] Step 5:

[1173] The generated advertising content is displayed on the camera image in real time. The input is the generated advertising content, and the output is the advertising content displayed to the user. Specifically, the generated advertising content is superimposed on the captured frame and displayed on the smartphone screen.

[1174] The above are the specific processing steps of this system.

[1175] Example 2

[1176] Next, a second embodiment of the second form will be described. 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".

[1177] Conventional marketing content generation systems make it difficult to select content that fully considers customer emotions and reactions, making it difficult to develop effective marketing strategies. In addition, there is a lack of testing methods to ensure the quality of the generated content, and specific methods to increase the probability of sales are required.

[1178] 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.

[1179] In this invention, the server includes a means for inputting a prompt sentence, a means for generating new project ideas and marketing content using a generative AI model, a means for conducting concept testing of market research to ensure the quality of the generated content, a means for conducting AB testing on the web, a means for using an emotion engine to recognize user emotions, and a means for selecting content based on emotion data. This makes it possible to generate and select effective marketing content that takes into account the emotions and reactions of customers.

[1180] A "prompt sentence" is a sentence of instructions or questions that is input to a generative AI model.

[1181] A "generative AI model" is an artificial intelligence algorithm that generates new project ideas and marketing content based on input prompt text.

[1182] "Market research concept testing" is a research instrument that gathers feedback from customers to evaluate the quality of the content generated.

[1183] "Web AB testing" is a testing method in which different versions of content are presented to actual website visitors and their reactions are compared.

[1184] An "emotion engine" is a technology that recognizes and analyzes emotions from a user's facial expressions, tone of voice, etc.

[1185] "Emotion data" is information regarding the user's emotions recognized by the emotion engine.

[1186] "Content selection method" is the process of selecting the most appropriate content based on generated content, test results, and sentiment data.

[1187] This invention is a system that uses a generative AI model to generate new project ideas and marketing content, and conducts market research and AB testing on the web to ensure the quality of the content. Furthermore, it is possible to select optimal content based on emotion data using an emotion engine that recognizes the user's emotions.

[1188] Hardware and Software Used

[1189] Hardware: Servers, terminals

[1190] Software: Generative AI models, emotion engines, web testing tools, online survey tools

[1191] Details of data processing and calculation

[1192] 1. Enter the prompt text

[1193] A user uses the device to input a prompt for the generative AI model, for example, "Generate marketing campaign ideas for a new smartphone."

[1194] 2. Generate project ideas

[1195] The server uses a generative AI model to generate multiple marketing campaign ideas based on the input prompt, and the generated ideas are stored in a database.

[1196] 3. Market research concept testing

[1197] The server inputs the generated project ideas into an online survey tool and conducts a survey of customers. For example, a survey form including a question such as "Are you interested in this campaign?" is created.

[1198] 4. Analysis of concept test results

[1199] The server compiles the survey results, calculates the evaluation score for each idea, and selects the idea with the highest evaluation.

[1200] 5. Web-based A / B testing

[1201] The server then feeds the selected ideas into an A / B testing tool to create different versions of advertising banners that are displayed to real website visitors.

[1202] 6. Analyzing AB test results

[1203] The server collects the results of the AB tests, analyzes the click-through rates and conversion rates of each version, and selects the version with the best performance.

[1204] 7. User emotion recognition by emotion engine

[1205] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, which are then analyzed by an emotion engine, for example to analyze facial expressions in real time while the user is viewing an advertisement.

[1206] 8. Emotion-Based Content Selection

[1207] The server selects content according to the user's emotion based on the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server selects a campaign idea that corresponds to that emotion.

[1208] 9. Emotion-Based Market Research and A / B Testing

[1209] The server then subjects the selected content to market research concept testing and web AB testing. For example, it creates an advertising banner that corresponds to the emotion of joy and conducts the test again.

[1210] 10. Selection of the final result

[1211] The server comprehensively analyzes all test results and ultimately selects the campaign idea that is most highly rated and best suited to user emotions.

[1212] Examples

[1213] For example, consider a generative AI model that receives the following prompt sentence as input:

[1214] Example prompt:

[1215] "Generate ideas for a marketing campaign for a new smartphone."

[1216] 1. The server inputs this prompt into a generative AI model to generate multiple marketing campaign ideas.

[1217] 2. The server uses online survey tools to conduct market research concept testing of the generated ideas. For example, it creates a survey form and asks customers, "Are you interested in this campaign?"

[1218] 3. The server compiles the survey results and selects the most highly rated campaign idea.

[1219] 4. The server uses an AB testing tool to perform AB testing on the web for the selected campaign ideas, for example, creating different versions of advertising banners and displaying them to actual website visitors.

[1220] 5. The server analyzes the results of the AB tests and selects the version with the highest click-through rate.

[1221] 6. The device uses an emotion engine to recognize the user's emotions. For example, the device captures the user's facial expression while viewing an advertisement on the smartphone and performs emotion analysis.

[1222] 7. Based on the emotion data, if the user shows an emotion of happiness, the server selects a campaign idea that corresponds to that emotion.

[1223] 8. The server will then conduct market research concept testing and online AB testing on the selected campaign ideas.

[1224] 9. The server analyzes the test results and finally selects the best campaign idea that corresponds to the user's emotions.

[1225] In this way, the system selects content that will appeal to customers and improves the quality of planning through the roles of the server, terminal, and user.

[1226] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1227] Step 1: Enter the prompt statement

[1228] The user uses the terminal to input a prompt sentence to the generative AI model. For example, the user might input, "Please generate an idea for a marketing campaign for a new smartphone." This prompt sentence becomes the input data.

[1229] Step 2: Generate planning ideas

[1230] The server uses the generative AI model to generate multiple marketing campaign ideas based on the input prompt sentence, and the generated ideas are stored in a database, where the prompt sentence is the input data and the generated ideas are the output data.

[1231] Step 3: Market research concept testing

[1232] The server inputs the generated project ideas into an online survey tool and conducts a survey of customers. For example, a survey form is created that includes the question, "Are you interested in this campaign?" The survey results become the input data, and the evaluation scores become the output data.

[1233] Step 4: Analyzing the concept test results

[1234] The server tally up the survey results, calculate an evaluation score for each idea, and select the idea with the highest evaluation. The survey results are the input data, and the evaluation scores are the output data.

[1235] Step 5: AB testing on the web

[1236] The server inputs the selected ideas into the AB testing tool to create different versions of ad banners. These banners are displayed to real website visitors. The selected ideas are the input data, and the ad banners are the output data.

[1237] Step 6: Analyze the A / B test results

[1238] The server collects the results of the AB tests, analyzes the click-through rate and conversion rate of each version, and selects the version with the best performance. The AB test results are the input data, and the optimal version is the output data.

[1239] Step 7: Recognizing user emotions with the emotion engine

[1240] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and analyzes them with an emotion engine. For example, the device analyzes the user's facial expressions in real time while the user is watching an advertisement. The captured facial expressions and voice are the input data, and the analyzed emotion data is the output data.

[1241] Step 8: Select content based on emotion

[1242] The server selects content according to the user's emotion based on the emotion data obtained from the emotion engine. For example, if the user expresses joy, the server selects a campaign idea that corresponds to that emotion. The emotion data is the input data, and the selected content is the output data.

[1243] Step 9: Emotion-based market research and A / B testing

[1244] The server then subjects the selected content to market research concept testing or web AB testing. For example, it creates an advertising banner that corresponds to the emotion of joy and conducts the test again. The selected content is the input data, and the test results are the output data.

[1245] Step 10: Select the final result

[1246] The server comprehensively analyzes all the test results and finally selects the most suitable campaign idea that is the most highly rated and corresponds to the user's emotions. The test results are the input data, and the optimal campaign idea is the output data.

[1247] (Application example 2)

[1248] Next, a description will be given of Application Example 2 of Form 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".

[1249] In conventional marketing content generation systems, there were insufficient testing methods to ensure the quality of the generated content, making it difficult to efficiently select content that would appeal to customers. In addition, content selection did not take into account user emotions, making it impossible to maximize customer response. This reduced the probability of sales and limited marketing effectiveness.

[1250] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1251] In this invention, the server includes a generating means using a generating AI model to generate new project idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a testing means using an emotion engine that recognizes the user's emotions and selects content that will appeal to customers according to the emotions. This makes it possible to improve the quality of the generated content, efficiently select content that will appeal to customers, and increase the probability of sales.

[1252] A "generative AI model" is an algorithm or system that uses artificial intelligence to automatically generate new planning ideas and marketing content.

[1253] "Generation means" refers to a function or device that uses a generative AI model to generate new planning ideas and marketing content that meets necessary conditions.

[1254] "Testing means" refers to functions or devices used for conducting concept testing for market research or AB testing on the web in order to ensure the quality of the generated content.

[1255] An "emotion engine" is an algorithm or system that recognizes a user's emotions and selects content that will resonate with customers based on those emotions.

[1256] "Market research concept testing" is a research methodology used to evaluate the market acceptability of generated content or project ideas.

[1257] "AB testing on the web" is a testing method in which different versions of content are published simultaneously on the web and the most effective content is selected by comparing actual customer reactions.

[1258] In order to implement the present invention, the following system configuration and processing procedures are required.

[1259] First, the server uses a generative AI model to generate new project ideas and marketing content. The generative AI model can use advanced natural language processing models such as GPT-3 and BERT. The generative AI model generates specific content by inputting a prompt sentence such as the following:

[1260] Example prompt:

[1261] "Generate ideas for a new marketing campaign. The target audience will be young people in their 20s, with a focus on promotion using social media."

[1262] The generated content is then evaluated by testing methods such as market research concept testing and web AB testing. In market research concept testing, methods such as questionnaire surveys and focus group interviews can be used to evaluate how well the generated content is accepted in the market. In web AB testing, different versions of the content are published simultaneously on the web and actual customer reactions are compared.

[1263] In addition, a testing method using an emotion engine is also built in. The emotion engine recognizes the user's emotions and selects content that will appeal to customers based on those emotions. For example, if a user expresses joy, it selects content that corresponds to that emotion and conducts market research and A / B testing of that content.

[1264] For example, when a user is using a smartphone, the smartphone's camera and microphone are used to analyze the user's facial expressions and tone of voice, and the emotion engine recognizes the user's emotions. Based on the recognized emotions, optimal content is selected and presented to the user.

[1265] This system makes it possible to improve the quality of generated content, efficiently select content that will appeal to customers, and increase the probability of sales.

[1266] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1267] Step 1:

[1268] The server inputs a prompt text to the generative AI model. For example, the prompt text might be, "Please generate ideas for a new marketing campaign. The target audience is young people in their 20s, and we will place emphasis on promotion using social media." The generative AI model generates new project ideas and marketing content based on this prompt text. The input is the prompt text, and the output is the generated content.

[1269] Step 2:

[1270] The server subjects the generated content to market research concept testing, which uses methods such as questionnaire surveys and focus group interviews to evaluate how well the generated content will be received in the market. The input is the generated content and the output is the results of the market research.

[1271] Step 3:

[1272] The server subjects the generated content to AB testing on the web. In AB testing on the web, different versions of content are published simultaneously on the web and actual customer reactions are compared. The input is the generated content, and the output is the result of the AB test.

[1273] Step 4:

[1274] The device uses the smartphone's camera and microphone to recognize the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice to recognize the user's emotions. The input is the user's facial expression and voice data, and the output is the recognized emotion.

[1275] Step 5:

[1276] The server selects the optimal content based on the recognized emotion. For example, if the user indicates an emotion of happiness, the server selects the content according to the emotion. The input is the recognized emotion and the generated content, and the output is the selected optimal content.

[1277] Step 6:

[1278] The terminal presents the selected optimal content to the user. The user checks the presented content and provides feedback as necessary. The input is the selected content, and the output is the user's feedback.

[1279] In this way, it is possible to improve the quality of the generated content, efficiently select content that appeals to customers, and increase the probability of sales.

[1280] 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 voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice 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 voice data.

[1281] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1282] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1283] 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.

[1284] [Fourth embodiment]

[1285] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1286] 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.

[1287] 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 wide area network (WAN) and / or a local area network (LAN).

[1288] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1289] 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 the voice according to instructions from the processor 46.

[1290] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1291] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1292] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. 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.

[1293] Fig. 8 shows an example of 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.

[1294] 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.

[1295] 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.

[1296] In the robot 414, 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.

[1297] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1298] "Example 1"

[1299] In one embodiment of the present invention, a system including an AI generation means and a testing means is provided. The AI ​​generation means generates concepts and marketing content for new planning ideas that satisfy necessary conditions. Specifically, the AI ​​generation means generates content by utilizing creative answers based on necessary conditions set by the planning department. For example, when generating planning ideas for a new product, the AI ​​generation means generates planning ideas that satisfy necessary conditions such as the target customer segment, the market environment, and the characteristics of the product.

[1300] "Example 2"

[1301] In addition, a testing method is provided to ensure the quality of the generated content. The testing method involves market research concept testing and web AB testing, and by selecting content that will appeal to customers, the quality of the plan is improved and the probability of sales is increased. For example, market research concept testing is conducted on multiple plan ideas generated by the AI ​​generation method, and the plan idea with the highest evaluation based on customer evaluation is selected. In addition, web AB testing is conducted, and the plan idea with the best response is selected based on actual customer reactions.

[1302] The process flow of each embodiment will be described below.

[1303] "Example 1"

[1304] Step 1: The planning department sets the requirements, including the target customer group, market environment, product characteristics, etc.

[1305] Step 2: The AI ​​generator uses creative answers to generate new business idea concepts and marketing content based on the set requirements.

[1306] Step 3: The planning department reviews the generated planning ideas and makes corrections or additions as necessary.

[1307] "Example 2"

[1308] Step 1: Conduct market research concept testing on multiple planning ideas generated by the AI ​​generation method.

[1309] Step 2: Select the most highly rated project idea based on customer evaluations.

[1310] Step 3: Conduct online AB testing of the selected project ideas.

[1311] Step 4: Based on actual customer reactions, the project idea with the best response is finally selected.

[1312] Example 1

[1313] Next, a description will be given of Example 1 of the embodiment 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".

[1314] In conventional systems for generating new project ideas and marketing content, the process from when the user inputs the necessary conditions to when the generated content is evaluated and improved is complicated, making it difficult to efficiently generate high-quality content. In addition, market research and web AB testing to ensure the quality of the generated content are often done manually, which is time-consuming and labor-intensive.

[1315] 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.

[1316] In this invention, the server includes a generating means for generating concepts and marketing content for new project ideas that satisfy necessary conditions, an evaluating means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an input means for a user to input necessary conditions, a generating means for generating a prompt sentence based on the input necessary conditions, a generating means for inputting the generated prompt sentence into a generative AI model to generate content, a transmitting means for transmitting the generated content to a user's terminal, and an evaluating means for receiving feedback from the user and evaluating and improving the content. This makes it possible to streamline the process from when the user inputs necessary conditions to when the generated content is evaluated and improved, and to generate high-quality content quickly.

[1317] "Requirements" are requirements or standards that must be met when a user generates a new project idea or marketing content.

[1318] A "new project idea" is a proposal or concept that adds new value or features to an existing product or service.

[1319] "Marketing Content" means information or messages intended to promote or sell a product or service.

[1320] The "generation means" refers to a method or device for generating new project ideas and marketing content based on necessary conditions.

[1321] An "assessment means" is a method or device for assessing the quality of the generated content and improving it if necessary.

[1322] An "input means" is a method or device by which a user inputs requirements into the system.

[1323] A "prompt sentence" is an instruction sentence input into a generative AI model and is generated based on necessary conditions.

[1324] A "generative AI model" is an algorithm or program that uses artificial intelligence to generate new planning ideas and marketing content.

[1325] The "transmitting means" refers to a method or device for transmitting the generated content to a user's terminal.

[1326] "Feedback" refers to information about corrections or improvements provided by a user to generated content.

[1327] The present invention relates to a system for generating new project ideas and marketing contents that satisfy necessary conditions, and evaluating and improving the quality of the generated ideas and contents. The system includes a generating means, an evaluating means, an inputting means, a transmitting means, and a feedback means.

[1328] The server hosts a generative AI model as a generation means. Specifically, the server uses a generative AI model such as OpenAI's GPT-4. When a user inputs the necessary conditions through an input means, the server receives it and generates a prompt sentence. The generated prompt sentence is input to the generative AI model, and new project ideas and marketing content are generated.

[1329] Users access the system using a terminal (PC or tablet) and input their requirements. Requirements include target customer segments, market environment, product characteristics, etc. For example, a user may input the following requirements:

[1330] Target customer demographic: Young people in their 20s

[1331] Market environment: Online shopping is mainstream

[1332] Product features: Eco-friendly materials used

[1333] Based on these requirements, the server will generate a prompt like this:

[1334] "Generate product ideas for new products using eco-friendly materials to be sold on the online shopping market, targeting young people in their 20s."

[1335] The server inputs this prompt into the generative AI model and receives the generated content, such as the following:

[1336] "We are proposing a stylish backpack made from recycled materials for young people in their 20s. This backpack will be sold exclusively online, and customers who purchase it will receive eco points as a special perk."

[1337] The server transmits the generated content to the user's terminal. The terminal displays the received content to the user. The user checks the generated content and provides feedback, if necessary. The feedback may include corrections or improvements.

[1338] The server receives feedback from users and evaluates and improves the content using the evaluation means, which improves the quality of the generated content and allows it to meet user requirements with greater accuracy.

[1339] This system streamlines the process from when users input their requirements to when they evaluate and improve the generated content, making it possible to quickly generate high-quality content.

[1340] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1341] Step 1:

[1342] A user logs into the system using a terminal. The user inputs requirements such as target customer demographics, market environment, and product characteristics. The input requirements are sent to the server. Specifically, the user enters requirements into the input form and clicks the "Submit" button. Input: Requirements. Output: Requirements sent to the server.

[1343] Step 2:

[1344] The server receives the requirements sent by the user. The server generates a prompt sentence based on the received requirements. Specifically, the server analyzes the requirements and creates a prompt sentence in a format suitable for the generative AI model. Input: Requirements from the user. Output: Generated prompt sentence.

[1345] Step 3:

[1346] The server inputs the generated prompt sentence into the generative AI model. The server waits for the generative AI model to generate content based on the prompt sentence. Specifically, the server sends the prompt sentence to the generative AI model through the API and receives the generated content. Input: Generated prompt sentence. Output: Generated content from the generative AI model.

[1347] Step 4:

[1348] The server sends the content received from the generative AI model to the user's device. The device displays the received content to the user. In concrete terms, the server sends the generated content to the user's device in real time, and the device displays the content on its screen. Input: Generated content from the generative AI model. Output: Content displayed on the user's device.

[1349] Step 5:

[1350] The user checks the generated content displayed on the terminal. If necessary, the user inputs feedback on corrections and improvements. Specifically, the user enters comments in the feedback form and clicks the "Submit" button. Input: Generated content. Output: Feedback from the user.

[1351] Step 6:

[1352] The server receives feedback from the user. The server evaluates the generated content based on the feedback and makes improvements if necessary. Specifically, the server analyzes the feedback and sends the prompt sentence to the generative AI model again to generate improved content. Input: User feedback. Output: Improved generated content.

[1353] (Application example 1)

[1354] Next, a description will be given of Application Example 1 of Form 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".

[1355] Conventional advertising content generation systems have had difficulty generating effective advertising content based on conditions such as target customer segments, market environment, and product characteristics. In addition, there was a lack of market research and testing methods to ensure the quality of the generated content, making it impossible to maximize the effectiveness of advertising. This resulted in a problem of reduced advertising effectiveness and the inability to expect an increase in sales.

[1356] 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.

[1357] In this invention, the server includes an AI generation means for generating new project idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a smartphone application for generating advertising content based on conditions such as target customer segments, market environment, product characteristics, etc. This makes it possible to generate effective advertising content and ensure its quality.

[1358] "Requirements" are conditions that must be met when generating advertising content, such as target customer segments, market environment, and product characteristics.

[1359] A "new project idea" is a new concept or marketing strategy that has never been seen before.

[1360] "Marketing content" refers to materials such as text, images, and videos used to promote products and services.

[1361] "AI generation means" refers to a means of using artificial intelligence to generate new planning ideas and marketing content that meets necessary conditions.

[1362] "Testing methods" refer to the means of conducting market research concept tests and AB tests on the web to ensure the quality of the generated content.

[1363] A "target demographic" is a particular group of customers to whom an advertisement or product is primarily directed.

[1364] "Market environment" refers to external factors such as the competitive situation and trends in the market in which the advertisement or product is developed.

[1365] "Product features" are the specific characteristics or benefits of an advertisement or product.

[1366] A "smartphone application" is a software program that runs on a smartphone.

[1367] "Advertising content" refers to materials such as text, images, and videos created to promote a specific product or service.

[1368] The following system configuration is necessary to implement this invention. The system includes an AI generation means for generating new project idea concepts and marketing content that meet required conditions, a testing means for conducting concept testing for market research and AB testing on the web to ensure the quality of the generated content, and a smartphone application for generating advertising content based on conditions such as the target customer demographic, market environment, and product characteristics.

[1369] The server uses a generative AI model such as OpenAI's GPT-3 to generate advertising content based on the requirements entered by the user, such as the target customer demographic, market environment, and product characteristics. Specifically, when the user enters the requirements through a smartphone application, the server converts them into a prompt text and sends it to the generative AI model. The generative AI model generates creative advertising content based on the prompt text and returns it to the user.

[1370] For example, if the target customer group is set as "women in their 20s," the market environment is set as "highly competitive cosmetics market," and the product characteristics are set as "highly moisturizing," the following prompt sentence will be generated.

[1371] Example prompt:

[1372] Target customer group: Women in their 20s

[1373] Market environment: Highly competitive cosmetics market

[1374] Product Features: High moisturizing effect

[1375] Please generate advertising content that meets the above criteria.

[1376] For example, the generated advertising content might be, "Recommended for women in their 20s! A new product that's attracting attention in the highly competitive cosmetics market. It has high moisturizing effects and is perfect for those who suffer from dry skin. Try it now!"

[1377] Furthermore, to ensure the quality of the generated advertising content, the server performs concept testing for market research and AB testing on the web, which allows it to predict the effectiveness of advertising and propose optimal advertising ideas to users.

[1378] In this way, it becomes possible to generate effective advertising content and ensure its quality.

[1379] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1380] Step 1:

[1381] The user launches the smartphone application and inputs necessary conditions such as the target customer group, market environment, and product characteristics.

[1382] Input: Target customer group, market environment, product characteristics

[1383] Output: Prerequisites entered

[1384] Specific operation: The user enters the target customer group (e.g., women in their 20s), market environment (e.g., highly competitive cosmetics market), and product characteristics (e.g., high moisturizing effect) into the application's input form.

[1385] Step 2:

[1386] The terminal converts the input requirements into a prompt text and sends it to the server.

[1387] Input: Requirements

[1388] Output: Prompt statement

[1389] Specific behavior: The application converts the entered requirements into a prompt like this:

[1390] Target customer group: Women in their 20s

[1391] Market environment: Highly competitive cosmetics market

[1392] Product Features: High moisturizing effect

[1393] Please generate advertising content that meets the above criteria.

[1394] This prompt is sent to the server.

[1395] Step 3:

[1396] The server uses a generative AI model (e.g., OpenAI's GPT-3) to generate advertising content based on the prompt text.

[1397] Input: prompt statement

[1398] Output: Ad content

[1399] Specific operation: The server inputs the prompt text into the AI ​​model and obtains the generated ad content. For example, the ad content generated is "Recommended for women in their 20s! A new product that is attracting attention in the highly competitive cosmetics market. Highly moisturizing, perfect for those who suffer from dry skin. Try it now!"

[1400] Step 4:

[1401] The server sends the generated advertising content back to the terminal.

[1402] Input: Ad content

[1403] Output: Ad content sent to the device

[1404] Specific operations: The server transmits the generated advertising content to the terminal.

[1405] Step 5:

[1406] The terminal displays the received advertisement content to the user.

[1407] Input: Ad content

[1408] Output: Ad content displayed

[1409] Specific behavior: The application displays the received advertising content to the user.

[1410] Step 6:

[1411] The user reviews the quality of the generated advertising content and corrects or regenerates it as necessary.

[1412] Input: Ad content

[1413] Output: The modified or regenerated ad content.

[1414] What happens: The user reviews the displayed ad content and, if necessary, corrects it or requests that it be regenerated.

[1415] Step 7:

[1416] In order to ensure the quality of the advertising content generated by the server, we conduct concept tests for market research and A / B tests on the web.

[1417] Input: Ad content

[1418] Output: Test results

[1419] Specific operation: The server subjects the generated advertising content to market research concept testing and web-based AB testing and obtains the results.

[1420] Step 8:

[1421] The server proposes optimal advertising ideas to the user based on the test results.

[1422] Input: Test result

[1423] Output: Best ad recommendation

[1424] What happens: The server analyzes the test results and suggests optimal ads to the user.

[1425] Example 2

[1426] Next, a second embodiment of the second embodiment will be described. 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".

[1427] With conventional planning idea generation and evaluation systems, it was difficult to accurately evaluate the quality of the generated ideas and their response in the market. As a result, it was not possible to select planning ideas that would appeal to customers, and there was a problem that sales could not be expected to increase. Furthermore, there was also the issue that it was difficult to quickly bring ideas to market because the evaluation process of the generated ideas was complicated and time-consuming.

[1428] 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.

[1429] In this invention, the server includes a means for generating new planning ideas using a generative AI model, a means for conducting market research concept testing on the generated planning ideas, and a means for conducting AB testing on the web on the generated planning ideas, which makes it possible to quickly and accurately evaluate the quality of the generated planning ideas and select the optimal planning ideas that will appeal to customers.

[1430] A "generative AI model" is a type of artificial intelligence that uses natural language processing technology to generate new project ideas.

[1431] "New project ideas" are novel concepts and marketing content generated by generative AI models.

[1432] "Market research concept testing" is a method of collecting customer evaluations of generated planning ideas and verifying the validity of the ideas based on that evaluation data.

[1433] "Web AB testing" is a method of selecting the most effective idea by displaying different project ideas to actual customers and collecting and analyzing their response data.

[1434] "Server" refers to a computer system that executes the generative AI model and evaluates and selects the generated project ideas.

[1435] "Reaching the customer" means that the generated planning ideas will pique the customer's interest and stimulate their desire to purchase.

[1436] "Planning quality" is an index showing the market acceptability and effectiveness of the generated planning ideas.

[1437] The "probability of selling" is an index showing the possibility that the generated planning idea will be successful in the market and actually generate sales.

[1438] This invention is a system that generates new project ideas using a generative AI model and evaluates the ideas through concept testing in market research and AB testing on the web. A specific embodiment of this system will be described below.

[1439] The server generates new project ideas using a generative AI model (e.g., an advanced artificial intelligence model using natural language processing technology). An example of a generative AI model that can be used is OpenAI's GPT-4. The server inputs a prompt sentence into the generative AI model to generate multiple project ideas. An example of a specific prompt sentence is "Please generate five project ideas for a new smartphone app."

[1440] The generated project ideas are stored in a database by the server. The server then conducts market research concept testing. In the market research concept testing, market research tools such as SurveyMonkey and Qualtrics are used to collect customer evaluations of the generated project ideas. Specifically, the server creates a survey that includes the following question: "How interested are you in this app idea? (Please rate on a scale of 1-5)." Users answer the survey using their devices, and the server collects and analyzes the evaluation data.

[1441] Next, the server conducts AB testing on the web. In AB testing, tools such as Google Optimize and Optimizely are used to display different project ideas to actual customers and collect response data. Specifically, the server sets up the following test: "Show idea 1 to group A and idea 2 to group B, and compare which group clicks more." Users use their devices to view web pages and respond to the displayed project ideas. The server analyzes the collected click data and selects the project idea with the best response.

[1442] Finally, the server comprehensively evaluates the results of the market research concept tests and the web-based AB tests to select the most highly rated and appealing plan idea. This selected plan idea is stored in a database and notified to the user.

[1443] This system makes it possible to quickly and accurately evaluate the quality of the generated planning ideas and select the most suitable planning idea that will appeal to customers, thereby improving the quality of the plan and increasing the probability of it selling.

[1444] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1445] Step 1:

[1446] The server generates new project ideas using the generative AI model. Specifically, the server inputs a prompt sentence, "Please generate five project ideas for a new smartphone app," into the generative AI model. The generative AI model generates five different project ideas based on this prompt sentence and returns them to the server. The server stores the generated project ideas in a database. The input is the prompt sentence, and the output is the generated project ideas.

[1447] Step 2:

[1448] The server conducts market research concept testing on the generated project ideas. Specifically, the server creates a survey using a market research tool (e.g., SurveyMonkey or Qualtrics). The survey includes questions such as, "How interested are you in this app idea? (Please rate on a scale of 1-5)." Users answer the survey using their terminals. The server collects evaluation data from users and stores it in a database. The input is the generated project idea and the survey responses, and the output is the evaluation data.

[1449] Step 3:

[1450] The server analyzes the collected evaluation data and selects the project idea with the highest evaluation. Specifically, the server statistically processes the evaluation data and calculates the average evaluation score of each project idea. The project idea with the highest score is selected and proceeds to the next step. The input is the evaluation data, and the output is the project idea with the highest evaluation.

[1451] Step 4:

[1452] The server conducts AB testing on the web for the selected project ideas. Specifically, the server uses an AB testing tool (e.g., Google Optimize or Optimizely) to display different project ideas to actual customers. For example, idea 1 is displayed to group A and idea 2 is displayed to group B, and a comparison is made to see which group makes more clicks. Users use their devices to view web pages and react to the displayed project ideas. The server saves the collected click data in a database. The input is the selected project idea and customer response data, and the output is click data.

[1453] Step 5:

[1454] The server analyzes the collected click data and selects the project idea with the best response. Specifically, the server statistically processes the click data and calculates the click rate of each project idea. The project idea with the highest click rate is finally selected. The input is the click data, and the output is the project idea with the best response.

[1455] Step 6:

[1456] The server saves the final selected project idea in a database and notifies the user. Specifically, the server saves the selected project idea in a database and notifies the user of the result via email or a notification system. The input is the project idea with the best response, and the output is the notification to the user.

[1457] (Application example 2)

[1458] Next, a description will be given of Application Example 2 of Form 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".

[1459] Traditionally, planning advertising campaigns and generating marketing content is often done manually, which is time-consuming and labor-intensive, and there is a lack of objective evaluation methods for selecting effective content. This makes the effectiveness of advertising campaigns uncertain, and may not lead to increased sales. Furthermore, market research and AB testing to ensure the quality of the generated content are also cumbersome, making it difficult to obtain rapid feedback.

[1460] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1461] In this invention, the server includes a generating AI model means for generating new planning idea concepts and marketing content that meet the necessary conditions, a testing means for conducting concept testing of market research and AB testing on the web to ensure the quality of the generated content, a means for generating planning ideas for advertising campaigns, calculating evaluations and click rates, and a means for selecting the most highly rated advertising campaign and proposing it to the advertiser. This makes it possible to consistently automate the process from planning to evaluation, selection, and proposal of advertising campaigns, and quickly implement effective advertising campaigns.

[1462] A "generative AI model means" is a means that uses artificial intelligence technology to generate new project idea concepts and marketing content that meet required conditions.

[1463] "Testing methods" refer to the means of conducting market research concept tests and AB tests on the web to ensure the quality of the generated content.

[1464] The "means for generating advertising campaign planning ideas" refers to means for generating new ideas for advertising campaigns and calculating ratings and click-through rates for those ideas.

[1465] The "means of proposing to advertisers" refers to the means of selecting the most highly rated advertising campaign and proposing the results to advertisers.

[1466] A system for implementing the present invention includes a generative AI model means, a testing means, a means for generating planning ideas for advertising campaigns, and a means for proposing ideas to advertisers.

[1467] The server generates new project idea concepts and marketing content that meet the requirements using a generative AI model means, which generates creative answers based on the prompt sentence, for example, using an OpenAI API.

[1468] Next, to ensure the quality of the generated content, we use testing methods to conduct concept tests for market research and AB tests on the web. From the multiple generated project ideas, we select the one with the highest evaluation based on customer evaluations and actual click rates.

[1469] The means for generating advertising campaign planning ideas uses a generative AI model means to generate new advertising campaign ideas and calculate ratings and click-through rates for the ideas, the means being implemented using a programming language such as Python.

[1470] Finally, the most highly evaluated advertising campaign is selected using a means for proposing to the advertiser, and the result is proposed to the advertiser. This means generates a report for proposing the optimal advertising campaign to the advertiser based on the evaluation result and the click-through rate data.

[1471] As a specific example, when considering an advertising campaign for a new beverage, the prompt sentence is "Generate ideas for an advertising campaign for a new beverage." Based on this prompt sentence, the generative AI model means generates multiple advertising campaign ideas, and by conducting concept tests in market research and AB tests on the web for those ideas, the most effective advertising campaign can be selected and proposed to the advertiser.

[1472] This system automates the entire process of advertising campaigns, from planning to evaluation, selection and proposal, making it possible to quickly implement effective advertising campaigns.

[1473] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1474] Step 1:

[1475] The server uses a generative AI model means to generate concepts and marketing content for new project ideas. Specifically, the server sends a prompt sentence, "Please generate an idea for a new beverage advertising campaign," as an input to a generative AI model (e.g., OpenAI's API), and receives the generated multiple advertising campaign ideas as an output.

[1476] Step 2:

[1477] The server performs market research concept testing on the generated advertising campaign ideas. Specifically, the server inputs the generated ideas into a market research tool, collects evaluation data from customers, calculates an evaluation score for each idea based on the evaluation data, and obtains the evaluation score as an output.

[1478] Step 3:

[1479] The server selects the best-rated advertising campaign idea based on the rating scores, by comparing the rating scores, selecting the idea with the highest score, and obtaining the idea as an output.

[1480] Step 4:

[1481] The server performs AB testing on the web for the selected advertising campaign ideas. Specifically, the selected ideas are input into an AB testing tool, and actual click-through rate data is collected. Based on the click-through rate data, the click-through rate for each idea is calculated, and the click-through rate is obtained as output.

[1482] Step 5:

[1483] The server selects the advertising campaign idea that has the best response based on the click-through rate, by comparing the click-through rates, selecting the idea with the highest click-through rate, and obtaining the idea as an output.

[1484] Step 6:

[1485] The server proposes the most highly rated and most responsive advertising campaign ideas to the advertiser. Specifically, the server compiles the selected ideas, their evaluation scores, and click-through rates in a report format and sends it to the advertiser. The server obtains the report as an output.

[1486] In addition, 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.

[1487] "Example 1"

[1488] As one embodiment of the present invention, a system incorporating an emotion engine is provided. This system recognizes the emotion of a user and generates new project idea concepts and marketing content according to the emotion. Specifically, the emotion engine recognizes the emotion of the user, and the AI ​​generation means generates content by utilizing creative answers based on the emotion. For example, when the user expresses an emotion of joy, the AI ​​generation means generates a project idea according to the emotion of joy. This makes it possible to generate project ideas corresponding to the emotion of the user.

[1489] "Example 2"

[1490] A testing method using an emotion engine is also provided. This testing method improves the quality of the plan and increases the probability of sales by recognizing the user's emotions and selecting content that will appeal to customers according to those emotions. Specifically, the emotion engine recognizes the user's emotions and performs concept testing for market research and AB testing on the web based on those emotions. For example, if a user expresses an emotion of joy, the testing method selects content that corresponds to that emotion and performs market research and AB testing for that content. This makes it possible to select content that corresponds to the user's emotions and improve the quality.

[1491] The process flow of each embodiment will be described below.

[1492] "Example 1"

[1493] Step 1: Recognize the user's emotion using the emotion engine.

[1494] Step 2: Based on the recognized sentiment, the AI ​​generator uses the creative answers to generate new project idea concepts and marketing content.

[1495] Step 3: Present the generated planning ideas and marketing content to the user.

[1496] "Example 2"

[1497] Step 1: Recognize the user's emotion using the emotion engine.

[1498] Step 2: Based on the emotions identified, conduct market research concept testing and web-based A / B testing.

[1499] Step 3: Based on the test results, select content that will resonate with customers, improve the quality of the plan, and increase the probability of sales.

[1500] Example 1

[1501] Next, a description will be given of Example 1 of the embodiment 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".

[1502] In conventional systems, it was difficult to take users' emotions into account when generating new project ideas and marketing content, and the generated content did not necessarily match the user's emotions. In addition, there was a lack of evaluation methods to ensure the quality of the generated content, making it difficult to maximize the effectiveness of the content.

[1503] 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.

[1504] In this invention, the server includes a generating means for generating new project idea concepts and marketing content that satisfy the necessary conditions, an evaluating means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognizing means for recognizing the emotion of a user and generating content according to the emotion, and a control means for generating a prompt sentence based on the emotion data obtained from the emotion recognizing means and the necessary conditions and sending it to the generating means. This makes it possible to generate new project ideas and marketing content that match the emotion of the user, and further to evaluate and improve the quality of the generated content.

[1505] The "generation means" refers to a means for generating concepts for new project ideas and marketing content that meet the necessary conditions.

[1506] "Evaluation methods" are methods used to conduct market research concept tests and web-based A / B tests to ensure the quality of the generated content.

[1507] The "emotion recognition means" is a means for recognizing the user's emotion and generating content in accordance with that emotion.

[1508] The "control means" is a means for generating a prompt sentence based on the emotion data obtained from the emotion recognition means and the necessary conditions, and sending the prompt sentence to the generation means.

[1509] A "prompt sentence" is an instruction sentence used by the generating means when generating new project ideas and marketing content.

[1510] A "new business idea" is a concept for a new product or service that is not yet on the market.

[1511] "Marketing content" refers to advertising and promotional materials used to promote products and services to the market.

[1512] "Requirements" are conditions that the generated content must satisfy, such as the target customer group, market environment, and product characteristics.

[1513] The present invention relates to a system for generating concepts and marketing contents for new project ideas that satisfy requirements. The system includes a generating unit, an evaluating unit, an emotion recognizing unit, and a controlling unit.

[1514] Hardware and Software Used

[1515] Hardware: Servers, terminals

[1516] Software: Generative AI models (e.g. GPT-4), emotion engines (e.g. Affectiva)

[1517] Specific operation of the system

[1518] User Emotion Recognition

[1519] A user accesses the system using a terminal. The terminal's camera and microphone capture the user's facial expressions and voice in real time. The terminal sends the captured data to the emotion engine. The emotion engine analyzes the characteristics of the user's facial expressions and voice and recognizes emotions. For example, when a user smiles, the emotion engine recognizes the emotion of "happiness."

[1520] Setting Prerequisites

[1521] The planning department logs into the server and inputs the necessary conditions. The server saves the input necessary conditions in a database. The necessary conditions include the target customer group, the market environment, and the characteristics of the product. For example, the target customer group can be set as "young people in their 20s," the market environment as "health-conscious," and the product characteristic as "low calorie."

[1522] Content Generation

[1523] The server sends the user's emotion data obtained from the emotion engine and the requirements provided by the planning department to the generation means. The generation means uses a generative AI model (e.g. GPT-4) to generate creative content based on the requirements and the user's emotions. The generative AI model receives the prompt sentence and generates content based on it.

[1524] Examples of prompt statements

[1525] The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low calorie. Users show happy emotions. Based on these conditions, generate planning ideas for a new beverage product.

[1526] For example, if the prompt is, "The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low calorie. Users are expressing feelings of joy. Based on these conditions, please generate planning ideas for a new beverage product," the generative AI model would generate ideas such as, "Propose low-calorie, vitamin-rich fruit juice for young people in their 20s."

[1527] Testing and Feedback

[1528] The server sends the generated content to the evaluator. The evaluator evaluates the generated content and provides feedback. The server receives the test results and modifies the content as necessary. For example, if the evaluator provides feedback such as "The idea for the proposed fruit juice is good, but more specific ingredient information is needed," the server resends the prompt sentence to the generative AI model based on the feedback to generate modified content.

[1529] In this way, new project ideas and marketing content are generated based on the user's emotions and requirements.

[1530] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1531] Step 1:

[1532] User Emotion Recognition

[1533] Input: A user logs in to a device and allows access to the camera and microphone.

[1534] Specific operation: The device captures the user's facial expressions and voice in real time.

[1535] Data processing: The device sends the captured data to the emotion engine, which analyzes the user's facial expressions and voice characteristics to recognize emotions.

[1536] Output: The emotion engine sends the recognized emotion data to the server. For example, if the user smiles, the emotion engine recognizes the emotion of "happiness" and sends the data to the server.

[1537] Step 2:

[1538] Setting Prerequisites

[1539] Input: The planning department logs into the server and enters their requirements.

[1540] Specific Actions: The server stores the entered requirements in a database.

[1541] Data processing: Requirements include target customer demographics, market environment, product characteristics, etc.

[1542] Output: The server sends the saved requirements to the generator. For example, the target customer group is set as "young people in their 20s," the market environment is set as "health-conscious," and the product characteristic is set as "low calorie."

[1543] Step 3:

[1544] Content Generation

[1545] Input: The server sends the user's emotion data obtained from the emotion engine and the requirements provided by the planning department to the generator.

[1546] Specific operation: The generator uses a generative AI model (e.g., GPT-4) to generate creative content based on the requirements and user emotions.

[1547] Data processing: The generative AI model receives a prompt and generates content based on it.

[1548] Output: The generated content is sent to the server. For example, if the prompt is "The target customer base is young people in their 20s, the market environment is health-conscious, and the product characteristics are low-calorie. The user shows an emotion of joy. Based on these conditions, please generate a planning idea for a new beverage product," the generative AI model will generate an idea such as "Propose a low-calorie, vitamin-rich fruit juice for young people in their 20s."

[1549] Step 4:

[1550] Testing and Feedback

[1551] Input: The server sends the generated content to the evaluator.

[1552] What to do: The evaluation tool evaluates the generated content and provides feedback.

[1553] Data processing: Evaluation measures assess the quality of content and identify areas for improvement.

[1554] Output: The server receives the test results and modifies the content as necessary. For example, if the evaluator gives feedback such as "The idea of ​​the proposed fruit juice is good, but more specific information on the ingredients is needed," the server sends the prompt sentence to the generative AI model again based on the feedback, and generates the modified content.

[1555] In this way, new project ideas and marketing content are generated based on the user's emotions and requirements.

[1556] (Application example 1)

[1557] Next, a description will be given of Application Example 1 of Form 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".

[1558] Conventional marketing content generation systems provide uniform content without considering the user's feelings, making it difficult to attract the user's interest. In addition, there was a lack of testing methods to ensure the quality of the generated content, which made it difficult to achieve effective marketing.

[1559] 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.

[1560] In this invention, the server includes an AI generation means for generating new project idea concepts and marketing content that meet the necessary conditions, a test means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognition means for recognizing the emotion of a user and generating content according to the emotion, and a display means for displaying the generated content in real time. This makes it possible to generate effective marketing content according to the emotion of a user and ensure its quality.

[1561] A "requirement" is a criterion or requirement that must be met in order to achieve a particular purpose or goal.

[1562] A "new project idea" is a new idea or plan that has never been seen before.

[1563] A "concept" is the basic idea or philosophy behind a project or product.

[1564] "Marketing Content" means information and materials used to promote and sell products and services.

[1565] An "AI generation means" refers to a function or device that uses artificial intelligence to automatically generate new planning ideas and marketing content.

[1566] "Testing Means" means any method or device for evaluating or verifying the quality of the Produced Content.

[1567] "Market research" refers to research activities conducted to understand consumer needs and market trends.

[1568] A "concept test" is a test conducted to evaluate whether a new plan or product concept will be accepted in the market.

[1569] "AB testing on the web" refers to the comparison of different versions of a web page or piece of content to evaluate which one is more effective.

[1570] "Emotion recognition means" refers to technology or devices for detecting and recognizing a user's emotions.

[1571] A "display means" refers to a method or device for visually presenting the generated content to a user.

[1572] As an embodiment of the present invention, an emotion-responsive advertisement generation system will be described as an example. This system includes an AI generation means for generating concepts and marketing content for new project ideas that satisfy necessary conditions, a testing means for conducting concept tests for market research and AB tests on the web to ensure the quality of the generated content, an emotion recognition means for recognizing the emotion of a user and generating content corresponding to the emotion, and a display means for displaying the generated content in real time.

[1573] Hardware and Software Used

[1574] Hardware: Smartphone camera

[1575] Software: OpenCV, Keras, Transformers libraries

[1576] Processing flow

[1577] 1. Camera image capture: Capture images in real time from the smartphone camera, which gives an image of the user's face.

[1578] 2. Face detection and emotion recognition: Detect faces using OpenCV and recognize the user's emotions using an emotion recognition model trained with Keras. Specifically, the face area is cut out, converted to grayscale, and then input to the emotion recognition model.

[1579] 3. Advertising content generation: Based on the recognized emotion, generate appropriate advertising content using the GPT-3 model. For example, if the user shows the emotion of happiness, input the prompt sentence "Generate advertising content appropriate for when the user shows the emotion of happiness" to the GPT-3 model.

[1580] 4. Display of advertising content: The generated advertising content is displayed on the camera footage in real time, allowing users to visually confirm the advertisements that correspond to their own emotions.

[1581] Examples

[1582] For example, if the user is expressing an emotion of joy, the following prompt sentence is input to the generative AI model:

[1583] Examples of prompt statements

[1584] Generate appropriate ad content when users are expressing the emotion of happiness.

[1585] When this prompt sentence is input into the GPT-3 model, advertising content such as "Why not try our new ice cream? It's on sale now at a special discount!" is generated. This advertising content is displayed in real time on the smartphone screen, attracting the user's interest.

[1586] The above is an embodiment of the present invention. This system makes it possible to generate effective marketing content in response to the user's emotions and to guarantee the quality of the content.

[1587] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1588] Step 1:

[1589] Capture video from a smartphone camera in real time. The input is the camera video and the output is the captured frames. Specifically, start the smartphone camera and continuously capture video.

[1590] Step 2:

[1591] Detect faces from captured frames. The input is the captured frame and the output is the detected face area. Specifically, we use OpenCV to detect faces in the frame and get the face position information.

[1592] Step 3:

[1593] The detected face area is converted to grayscale and input to the emotion recognition model. The input is the face area, and the output is the recognized emotion. Specifically, the face area is cut out, converted to grayscale, and then input to the emotion recognition model trained with Keras.

[1594] Step 4:

[1595] Based on the recognized emotion, appropriate advertising content is generated. The input is the recognized emotion, and the output is the generated advertising content. Specifically, a prompt sentence is generated according to the recognized emotion, and input to the GPT-3 model to generate advertising content.

[1596] Step 5:

[1597] The generated advertising content is displayed on the camera image in real time. The input is the generated advertising content, and the output is the advertising content displayed to the user. Specifically, the generated advertising content is superimposed on the captured frame and displayed on the smartphone screen.

[1598] The above are the specific processing steps of this system.

[1599] Example 2

[1600] Next, a second embodiment of the second embodiment will be described. 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".

[1601] Conventional marketing content generation systems make it difficult to select content that fully considers customer emotions and reactions, making it difficult to develop effective marketing strategies. In addition, there is a lack of testing methods to ensure the quality of the generated content, and specific methods to increase the probability of sales are required.

[1602] 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.

[1603] In this invention, the server includes a means for inputting a prompt sentence, a means for generating new project ideas and marketing content using a generative AI model, a means for conducting concept testing of market research to ensure the quality of the generated content, a means for conducting AB testing on the web, a means for using an emotion engine to recognize user emotions, and a means for selecting content based on emotion data. This makes it possible to generate and select effective marketing content that takes into account the emotions and reactions of customers.

[1604] A "prompt sentence" is a sentence of instructions or questions that is input to a generative AI model.

[1605] A "generative AI model" is an artificial intelligence algorithm that generates new project ideas and marketing content based on input prompt text.

[1606] "Market research concept testing" is a research instrument that gathers feedback from customers to evaluate the quality of the content generated.

[1607] "Web AB testing" is a testing method in which different versions of content are presented to actual website visitors and their reactions are compared.

[1608] An "emotion engine" is a technology that recognizes and analyzes emotions from a user's facial expressions, tone of voice, etc.

[1609] "Emotion data" is information regarding the user's emotions recognized by the emotion engine.

[1610] "Content selection method" is the process of selecting the most appropriate content based on generated content, test results, and sentiment data.

[1611] This invention is a system that uses a generative AI model to generate new project ideas and marketing content, and conducts market research and AB testing on the web to ensure the quality of the content. Furthermore, it is possible to select optimal content based on emotion data using an emotion engine that recognizes the user's emotions.

[1612] Hardware and Software Used

[1613] Hardware: Servers, terminals

[1614] Software: Generative AI models, emotion engines, web testing tools, online survey tools

[1615] Details of data processing and calculation

[1616] 1. Enter the prompt text

[1617] A user uses the device to input a prompt for the generative AI model, for example, "Generate marketing campaign ideas for a new smartphone."

[1618] 2. Generate project ideas

[1619] The server uses a generative AI model to generate multiple marketing campaign ideas based on the input prompt, and the generated ideas are stored in a database.

[1620] 3. Market research concept testing

[1621] The server inputs the generated project ideas into an online survey tool and conducts a survey of custome...

Claims

1. A means for acquiring requirements, which are requirements or standards to be met when generating new project ideas or marketing content provided by a user; A means for generating a prompt sentence to be input to a generative AI model based on the necessary conditions; A means for transmitting content generated by the generative AI model to a user by inputting the prompt sentence into the generative AI model; means for receiving feedback from a user regarding the content, the feedback including corrections or improvements; means for obtaining improved content generated using the generative AI model based on the feedback; A system including:

2. A means for obtaining requirements regarding target customer segments, market conditions or product characteristics; A means for generating a prompt sentence to be input to a generative AI model based on the necessary conditions; A means for obtaining advertising content generated by the generative AI model by inputting the prompt sentence into the generative AI model; A means for conducting market research concept tests or AB tests on the web in order to ensure the quality of the generated advertising content; A system including:

3. A means for generating a prompt sentence to be input to the generative AI model based on the requirements; A means for acquiring a project idea generated by the generative AI model by inputting the prompt sentence into the generative AI model; A means for conducting market research concept testing on the generated planning ideas; A means for collecting evaluation data based on responses from users to the concept tests; A means for selecting project ideas based on the collected evaluation data; A means for conducting A / B testing on the web for the selected project ideas; A means for collecting click data based on responses from users to the concept test; A method to analyze the collected click data and select the project idea with the best response, Including system.

Images