system

Abstract

Provide a system. A method for acquiring attribute information of a target audience; A means for segmenting the acquired attribute information using a clustering technique; means for automatically generating a creative concept based on the segmented data; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern marketing activities, it is extremely difficult to quickly and mass-produce effective creative concepts for a target audience. In particular, creating individually optimized concepts that take into account the diverse attributes and preferences of the target audience requires a great deal of effort and time. Against this background, a challenge facing marketers and advertising creators is the lack of ways to quickly and efficiently obtain creative inspiration. [Means for solving the problem]

[0005] The present invention relates to a system including a means for acquiring attribute information of a target audience, a means for segmenting the acquired attribute information using clustering technology, and a means for automatically generating a creative concept based on the segmented data. The means for generating a creative concept can use a natural language generation model, and the attribute information includes age, gender, region, and interests. This system enables marketers and advertising creators to quickly and efficiently generate creative concepts optimized for the target audience.

[0006] "Target audience" refers to a specific group of consumers targeted by a marketing or advertising campaign.

[0007] "Attribute information" is data that indicates the characteristics of an individual user or consumer, including age, gender, region, hobbies and interests.

[0008] "Clustering technology" is a method of classifying data into multiple groups (clusters), and is a technology that collects similar data points to form groups.

[0009] "Segmentation" refers to grouping users who share common attributes or interests, and is a technique often used in marketing activities.

[0010] "Automatically generated" means generated automatically by a system or algorithm without human intervention.

[0011] A "creative concept" is a consistent idea or theme for marketing or advertising, a creative expression method for effectively conveying a message to a target audience.

[0012] A "natural language generation model" is an advanced machine learning algorithm for understanding and generating human language, and is used for the task of generating text.

[0013] "Age, gender, region, and interests" are basic attribute information for identifying a target audience and are elements that make up a basic user profile. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] 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.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] 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.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] 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.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention relates to a system that acquires target audience attribute information, segments them using clustering technology, and automatically generates creative concepts for each segment. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[0036] System program processing overview

[0037] The system operates in the following stages:

[0038] 1. Set API key:

[0039] The user provides the system with their API key, which allows the system to access external data sources.

[0040] 2. Obtaining target audience data:

[0041] The server retrieves target attribute information (e.g., age, gender, region, interests) through the API based on the specified target audience ID, allowing the system to collect detailed data on the target users.

[0042] 3. Audience segmentation:

[0043] The server segments the acquired user data using a clustering algorithm, which groups users with similar attributes and interests.

[0044] 4. Creative concept generation:

[0045] The server automatically generates creative concepts based on the segmented data, specifically using a natural language generation model (e.g., GPT-3 (registered trademark)) to generate concepts appropriate for each segment.

[0046] 5. Output of generated concepts:

[0047] The creative concept generated by the device is displayed, allowing users to check the marketing concept optimized for each segment.

[0048] Specific examples

[0049] For example, a case where the user specifies the target audience ID "example_id" will be described.

[0050] 1. Obtaining target audience data:

[0051] The server receives data through the API, such as:

[0052] [

[0053] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"]},

[0054] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"]},

[0055] ...

[0056] ]

[0057] 2. Audience segmentation:

[0058] The server uses this data to perform clustering, dividing users into five segments, for example:

[0059] Segment 1: [User 1, User 5, User 9]

[0060] Segment 2: [User 2, User 6, User 10]

[0061] ...

[0062] 3. Creative concept generation:

[0063] The server uses a natural language generation model for each segment and inputs a prompt like this:

[0064] "Generate a creative marketing concept for audience: [Segment 1]"

[0065] "Generate a creative marketing concept for audience: [Segment 2]"

[0066] ...

[0067] This generates the following concepts:

[0068] Segment 1: "Fashion-forward sportswear campaign targeting trendy young women in Tokyo."

[0069] Segment 2: "Innovative tech and finance solutions for middle-aged professionals in Osaka."

[0070] ...

[0071] 4. Output of generated concepts:

[0072] The device displays the generated creative concepts to the user. For example, Segment 1 displays a "trend campaign for young people," while Segment 2 displays a "health promotion campaign for seniors."

[0073] In this way, the system can quickly and efficiently generate creative concepts optimized for the target audience, helping to inspire marketers and advertising creators.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[0077] Step 2:

[0078] The server receives the target audience ID and retrieves the target audience's attribute information via API based on this ID. For example, it collects data such as age, gender, region, and interests based on the ID "example_id."

[0079] Step 3:

[0080] The server processes the acquired user data and extracts the necessary attribute information (age, gender, region, interests).

[0081] Step 4:

[0082] Based on the attribute information extracted by the server, users are segmented using a clustering algorithm (KMeans clustering). For example, all users are divided into five segments.

[0083] Step 5:

[0084] The server generates prompts based on the segmented data. For each segment, it creates a prompt like "Generate a creative marketing concept for segment 1."

[0085] Step 6:

[0086] The server-generated prompts are fed into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment.

[0087] Step 7:

[0088] The server sends the generated creative concepts to the device and displays them to the user. For example, concepts such as "Trendy Sportswear Campaign" are displayed for segment 1, and "Innovative Technology and Financial Solutions" are displayed for segment 2.

[0089] This process flow allows users to quickly and efficiently arrive at creative concepts optimized for their target audience.

[0090] Example 1

[0091] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0092] In current marketing and advertising production, it is difficult to quickly generate creative concepts that match the target audience. In particular, there is a need to streamline the process from segmentation based on attribute information to generating creative concepts. Conventional methods require manual data analysis and creative concept development, which requires a great deal of time and effort. Therefore, there is a need for a system that can automatically generate creative concepts optimized for the target audience.

[0093] 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.

[0094] In this invention, the server includes means for acquiring attribute information of the target audience, means for accessing a data source based on the acquired attribute information, means for segmenting the acquired attribute information using a clustering technique, means for automatically generating a creative concept using a generative AI model based on the segmented data, and means for outputting the generated creative concept to a user's terminal, thereby enabling the rapid and efficient generation of a creative concept suited to the target audience.

[0095] A "target audience" is a group of consumers who are likely to be interested in a particular product or service.

[0096] "Attribute information" is information that characterizes the target audience, such as age, gender, region, and interests.

[0097] "Data Source" is an external system or platform used to collect demographic information about your target audience.

[0098] A "clustering technique" is a technique for dividing data into groups, and classifying data points with similar characteristics into the same group.

[0099] "Segmentation" is the process of dividing a target audience into multiple groups based on attribute information obtained using clustering techniques.

[0100] A "generative AI model" is a model that uses artificial intelligence techniques to generate natural language or other forms of information based on specific input data.

[0101] A "creative concept" is a creative idea or theme that communicates an effective advertising or marketing message to a target audience.

[0102] "User's device" means a device such as a computer or smartphone used to display creative concepts generated by the system.

[0103] A "prompt" is text that is input into a generative AI model, from which a creative concept is generated.

[0104] Above are definitions of important terms.

[0105] The present invention relates to a system that acquires target audience attribute information, segments them using clustering technology, and automatically generates creative concepts for each segment. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[0106] The system is configured as follows:

[0107] First, the user provides the system with their API key, which allows the system to access external data sources. The user completes this process by entering the API key in the settings screen and saving it.

[0108] The server then sends an API request using the target audience ID specified by the user. The API request retrieves target audience attribute information such as age, gender, region, and interests. This data is obtained from a marketing platform such as the "Audience Insights API."

[0109] Based on the acquired attribute information, the server uses a clustering algorithm to segment users. For example, Scikit-learn's K-means clustering algorithm is used to cluster the data. Through clustering, users with similar attributes and interests are grouped into the same segment.

[0110] Next, the server generates creative concepts based on the segmented data using the generative AI model GPT-3. Specifically, it generates appropriate prompts for each segment and inputs these prompts into GPT-3. Examples of prompts include:

[0111] "Create a creative marketing concept for audience: [Segment 1]"

[0112] "Create a creative marketing concept for audience: [Segment 2]"

[0113] This automatically generates creative concepts for each segment: for example, for segment 1, a concept like "Fashion-forward sportswear campaign targeting trendy young women in Tokyo" might be generated, and for segment 2, a concept like "Innovative tech and finance solutions for middle-aged professionals in Osaka" might be generated.

[0114] Finally, the generated creative concepts are displayed on the user's device, allowing the user to check the marketing concepts optimized for each segment. Specifically, they are displayed in list format on the dashboard of the web application.

[0115] In this way, the system streamlines the work of marketers and advertising creators, enabling them to quickly provide creative concepts that suit the target audience.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1:

[0118] The user provides the API key to the system.

[0119] Input: The user enters the API key into the settings screen and clicks the "Save" button.

[0120] How it works: The user navigates to the settings screen, enters their API key in the provided field, and clicks the "Save" button, which saves the API key as a credential in the system.

[0121] Output: The system is able to access external data sources and an API key is stored in the system.

[0122] Step 2:

[0123] The server accesses the data source based on the target audience ID.

[0124] Input: User-specified target audience ID.

[0125] How it works: The server generates an API request and sends the target audience ID as a parameter to an external data source, specifically calling the marketing platform's API to retrieve the target audience's attributes.

[0126] Output: The acquired attribute information (e.g., age, gender, region, interests) is stored in a database.

[0127] Step 3:

[0128] The server uses a clustering technique to segment the attribute information.

[0129] Input: The target audience demographic information obtained.

[0130] How it works: The server applies a clustering algorithm (e.g., Scikit-learn's K-means clustering) to classify the target audience into segments based on their attributes, e.g., grouping users with similar interests or attributes.

[0131] Output: Segmented target audience data is generated.

[0132] Step 4:

[0133] The server uses generative AI models to generate creative concepts for each segment.

[0134] Input: Segmented target audience data.

[0135] How it works: The server creates an appropriate prompt for each segment and inputs it into a generative AI model (e.g., GPT-3). An example of a specific prompt might be, "Create a creative marketing concept for audience: [Segment 1]."

[0136] Output: A creative concept optimized for each segment is generated.

[0137] Step 5:

[0138] The terminal outputs the generated creative concept to the user.

[0139] Input: Generated creative concepts.

[0140] How it works: The device displays the generated creative concepts. Specifically, they are displayed in a list format on the web application dashboard. The user can access the dashboard to view the generated concepts.

[0141] Output: Users can visualize creative concepts optimized for each segment.

[0142] (Application example 1)

[0143] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0144] Conventional creative concept generation systems have been unable to effectively utilize the diverse attribute information of target audiences, resulting in the time-consuming and labor-intensive process of segmenting and generating creative concepts. Furthermore, the quality of the generated creative concepts often lacks uniformity, potentially reducing marketing efficiency. There is a need for a system that can solve these issues and generate high-quality creative concepts quickly.

[0145] 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.

[0146] In this invention, the server includes means for acquiring attribute information of the target audience, means for segmenting the acquired attribute information using clustering technology, means for automatically generating a creative concept based on the segmented data, and means for displaying the generated creative concept on a terminal. This allows the target audience attribute information to be effectively utilized to quickly and efficiently generate a creative concept, enabling marketers and advertising creators to quickly obtain high-quality concepts.

[0147] A "target audience" is a group of recipients with specific attributes that you focus on when conducting a particular marketing or promotional activity.

[0148] "Attribute information" refers to characteristic data about the target audience, such as age, gender, region, and interests.

[0149] "Clustering technology" is a machine learning technique for grouping data with similar characteristics.

[0150] "Segmentation" is the process of grouping target audience demographic information using clustering techniques.

[0151] A "creative concept" is an idea for an advertising or marketing strategy generated for a specific target audience.

[0152] A "natural language generation model" is an artificial intelligence model for generating natural language text based on given data and prompts.

[0153] A "Device" is a device, such as a computer or smartphone, that a User uses to display Creative Concepts or other information.

[0154] A system for implementing the present invention acquires attribute information of a target audience, segments them using clustering technology, automatically generates creative concepts for each segment, and displays the generated concepts on a terminal.

[0155] The operation of the system is as follows.

[0156] First, the user provides the server with an API key, which allows the server to access external data sources. Next, the server retrieves target demographic information via the API based on the target audience ID. This demographic information includes data such as age, gender, region, and interests.

[0157] The server segments the data based on the acquired attribute information using a clustering algorithm, such as the K-Means algorithm, which groups audiences with similar attributes.

[0158] Based on the segmented data, the server uses a natural language generation model (e.g., GPT-3) to generate creative concepts appropriate for each segment. In this generation process, prompts are set for each segment, and creative concepts are automatically generated based on the prompts.

[0159] For example, you can use prompts like the following to generate different creative concepts for each segment:

[0160] "Generate a creative marketing concept for audience: Segment 1"

[0161] "Generate a creative marketing concept for audience: Segment 2"

[0162] The generated creative concept is displayed to the user via the terminal, allowing the user to check and use the marketing concept optimized for each segment quickly and efficiently.

[0163] As a specific example, if you use the target audience ID "example_id", the server may obtain the following attribute information:

[0164] 「age: 25, gender: female, location: Tokyo, interests: fashion, sports」

[0165] "age: 40, gender: male, location: Osaka, interests: technology, finance"

[0166] Clustering is performed based on this data and segmented as follows:

[0167] Segment 1: For young people

[0168] Segment 2: Middle-aged people

[0169] Then, for each, set the prompts to generate creative concepts as follows:

[0170] "Generate a creative marketing concept for audience: Young people"

[0171] "Generate a creative marketing concept for audience: middle-aged people"

[0172] The generated creative concept may look something like this:

[0173] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo"

[0174] "Innovative tech and finance solutions for middle-aged professionals in Osaka"

[0175] In this way, the server can effectively utilize the attribute information of the target audience, quickly generate high-quality creative concepts, and provide them in a format that is easy for users to use.

[0176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0177] Step 1:

[0178] The user provides an API key.

[0179] Input: The user enters an API key.

[0180] What it does: Stores the user-provided API key on the server, allowing access to external data sources.

[0181] Output: An API key is saved on the server, granting access to the external data source.

[0182] Step 2:

[0183] The server retrieves the target audience data.

[0184] Input: Target audience ID (e.g. "example_id")

[0185] Processing: The server uses the target audience ID to obtain the target's demographic information (age, gender, region, interests, etc.) via API.

[0186] Output: The target audience's demographic information is retrieved to the server.

[0187] Step 3:

[0188] The server segments the audience data using clustering techniques.

[0189] Input: Attribute information of the target audience obtained

[0190] Processing: The server uses a clustering algorithm (e.g. K-Means) to group similar audiences based on their attributes.

[0191] Output: Segmented audience data.

[0192] Step 4:

[0193] The server generates creative concepts based on the segmented data.

[0194] Input: Segmented audience data

[0195] Processing: The server uses a natural language generation model (e.g., GPT-3) to generate creative concepts appropriate for each segment. For each segment, a prompt is set and a creative concept is generated based on the prompt.

[0196] Output: The generated creative concepts are saved on the server.

[0197] Step 5:

[0198] The server displays the generated creative concept on the terminal.

[0199] Input: Generated creative concept

[0200] Processing: The server sends the generated creative concept to the user's device.

[0201] Output: The creative concept is displayed on the user's device.

[0202] As a concrete example, we will show how to set a prompt sentence. For example, we set the following prompt for segment 1:

[0203] "Generate a creative marketing concept for audience: Young people"

[0204] A creative concept generated based on this prompt might be, for example, "Fashion-forward sportswear campaign targeting trendy young women in Tokyo." This creative concept is displayed on the user's device, allowing the user to review and use it.

[0205] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0206] This invention combines a system that acquires target audience attribute information and segments them using clustering technology with an emotion engine that recognizes user emotions, enabling the generation of more advanced marketing concepts. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[0207] System program processing overview

[0208] The system operates in the following stages:

[0209] 1. Set API key:

[0210] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[0211] 2. Obtaining target audience data:

[0212] Based on the specified target audience ID, the server obtains target attribute information (e.g., age, gender, region, interests, and emotional data) through the API, allowing the system to collect detailed data on the target users.

[0213] 3. Acquiring emotion data:

[0214] The server acquires the user's emotional data through an emotion engine, which uses one or more of voice recognition, facial expression recognition, and text analysis technologies to understand the user's emotional state.

[0215] 4. Integrating audience demographics and sentiment data:

[0216] The server integrates the acquired attribute information and emotional data and updates the user's profile based on this data.

[0217] 5. Audience segmentation:

[0218] The server segments users based on the integrated data using a clustering algorithm (KMeans clustering), which groups users with similar attributes, hobbies, and emotions.

[0219] 6. Creative concept generation:

[0220] The server generates prompts based on the segmented data. For each segment, it creates a prompt like "Generate a creative marketing concept for segment 1."

[0221] 7. Using Natural Language Generation Models:

[0222] The server-generated prompts are fed into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment.

[0223] 8. Output of generated concepts:

[0224] The creative concept generated by the device is displayed, allowing users to check the marketing concept optimized for each segment.

[0225] Specific examples

[0226] For example, a case where the user specifies the target audience ID "example_id" will be described.

[0227] 1. Obtaining target audience data:

[0228] The server receives data through the API, such as:

[0229] [

[0230] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"], "emotion": "happy"},

[0231] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"], "emotion": "neutral"},

[0232] ...

[0233] ]

[0234] 2. Acquiring emotion data:

[0235] The server uses an emotion engine to extract emotion data from the user's voice, facial expressions, and text, and adds it to each attribute information.

[0236] 3. Integrating audience demographics and sentiment data:

[0237] The server integrates the acquired attribute information and emotional data and creates an updated user profile based on them.

[0238] 4. Audience segmentation:

[0239] The server performs clustering based on the combined data, dividing users into five segments, for example:

[0240] Segment 1: [User 1, User 5, User 9]

[0241] Segment 2: [User 2, User 6, User 10]

[0242] ...

[0243] 5. Creative concept generation:

[0244] For each segment, the server inputs the following prompts into the NLG model:

[0245] "Generate a creative marketing concept for audience: [Segment 1]"

[0246] "Generate a creative marketing concept for audience: [Segment 2]"

[0247] ...

[0248] This generates the following concepts:

[0249] Segment 1: "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[0250] Segment 2: "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[0251] ...

[0252] 6. Output of generated concepts:

[0253] The device displays the generated creative concepts to the user, for example, "Trendy Sportswear Campaign" for Segment 1 and "Innovative Technology and Financial Solutions" for Segment 2.

[0254] This process flow allows users to quickly and efficiently generate creative concepts optimized for their target audience. The introduction of the emotion engine enables segmentation using more detailed user profiles, which is expected to lead to the generation of more effective marketing concepts.

[0255] The processing flow will be explained below.

[0256] Step 1:

[0257] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[0258] Step 2:

[0259] The server receives the target audience ID and retrieves the target audience's attribute information via API based on this ID. For example, it collects data such as age, gender, region, and interests based on the ID "example_id."

[0260] Step 3:

[0261] The server uses an emotion engine to obtain additional emotion data, which uses voice recognition, facial expression recognition, and text analysis to understand the user's emotional state, for example, by inputting facial expressions and voice through a webcam or microphone.

[0262] Step 4:

[0263] The server combines the acquired attribute information with the emotional data to create a detailed profile of the user, including, for example, the user's age, gender, region, interests, and emotional state such as "happy" or "neutral."

[0264] Step 5:

[0265] The server uses the aggregated data to segment users using a clustering algorithm (KMeans clustering). For example, it divides all users into five segments.

[0266] Step 6:

[0267] The server generates prompts for each segment based on the segmented data, for example, "Generate a creative marketing concept for segment 1."

[0268] Step 7:

[0269] The server-generated prompts are input into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment. For example, for segment 1, it generates a "sportswear campaign for trend-conscious young women living in Tokyo."

[0270] Step 8:

[0271] The server sends the generated creative concepts to the device and displays them to the user. For example, concepts such as "Fashion-forward sportswear campaign" are displayed for segment 1, and "Innovative technology and financial solutions" are displayed for segment 2.

[0272] This process flow allows users to quickly and efficiently generate creative concepts optimized for their target audience. The introduction of the emotion engine enables segmentation using more detailed user profiles, which is expected to lead to the generation of more effective marketing concepts.

[0273] Example 2

[0274] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0275] Conventional marketing systems have difficulty not only obtaining target audience attribute information but also utilizing user sentiment data. Furthermore, they lack the means to efficiently and effectively segment the obtained information and generate creative marketing concepts for each segment. This makes it difficult for marketers and advertising creators to quickly find inspiration, preventing them from maximizing the effectiveness of their marketing campaigns.

[0276] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring attribute information of the target audience, means for integrating the acquired attribute information and emotion data to update a user profile, means for segmenting the integrated data using a clustering technique, means for automatically generating a creative concept based on the segmented data, and means for displaying the generated creative concept. This enables effective segmentation based on a detailed profile of the target audience and rapid generation of a creative concept based on the segmented data.

[0277] "Target audience" refers to a group of people with specific attributes who are the target of marketing and advertising activities.

[0278] "Attribute information" refers to data that indicates the characteristics of your target audience, such as age, gender, region, interests, and emotional data.

[0279] "Emotion data" is data that indicates the emotional state of a user, obtained from voice, facial expression, text, etc.

[0280] "User profile" refers to detailed personal information that integrates demographic and emotional data of a target audience.

[0281] "Clustering technology" refers to a general algorithm that divides data into groups based on similarity, and includes KMeans clustering as an example here.

[0282] "Segmentation" refers to the use of clustering techniques to divide a target audience based on attribute information and emotional data.

[0283] "Creative Concept" refers to an idea or theme created for a specific marketing purpose.

[0284] "Generative AI model" refers to artificial intelligence technology that uses natural language processing technology to automatically generate text based on input prompts.

[0285] A "prompt" refers to a question or instruction input to a generative AI model.

[0286] A "database" refers to a collection of information that allows for efficient storage and retrieval of large amounts of data.

[0287] "Speech recognition" is a technology that analyzes voice data and converts it into text and emotions.

[0288] "Facial expression recognition" is a technology that analyzes facial expressions from image data and identifies the emotional state of a person.

[0289] "Text analysis" is a technology that analyzes text data and understands and classifies its content and sentiment.

[0290] This invention is a system that acquires attribute information of a target audience, segments them using clustering technology, and combines it with an emotion engine that recognizes user emotions to generate a creative concept. Specific embodiments of this invention are described below.

[0291] Hardware and software used

[0292] The implementation of this system utilizes the following hardware and software:

[0293] Server: Responsible for cloud-based data processing and storage. It operates as the core of the system, generating, processing, and managing various data.

[0294] Terminal: A device that provides an interface for users to access. This includes computers and smartphones.

[0295] Emotion engine: A tool such as Google® Cloud Speech-to-Text or AWS® Rekognition that analyzes a user's voice, facial expressions, and text to obtain emotional data.

[0296] Natural Language Generation Models: Tools that use generative AI models to generate creative concepts, such as OpenAI® GPT-3.

[0297] Clustering algorithm: An algorithm for clustering data (e.g., KMeans clustering) using Python's scikit-learn library.

[0298] Program processing overview

[0299] Obtaining target audience data

[0300] The server uses external APIs based on the target audience ID specified by the user to obtain audience attribute information. Target APIs include Facebook Graph API and Twitter API. The obtained data includes information such as age, gender, region, and interests.

[0301] Acquiring emotion data

[0302] The server acquires the user's emotional data using an emotion engine. The emotional data is extracted from the user's voice, facial expressions, and text. For example, Google Cloud Speech-to-Text is used to analyze the voice data and identify the emotion.

[0303] Integrating audience demographics and sentiment data

[0304] The server integrates the acquired attribute information and emotion data to update a detailed profile for each user, which is then stored in a database on the server.

[0305] Audience segmentation

[0306] The server performs clustering on the combined data, using the Python scikit-learn library and applying the KMeans clustering algorithm, which categorizes audiences into groups with common attributes and sentiments.

[0307] Creative concept generation

[0308] The server generates appropriate prompts for each segment and feeds them into the natural language generation model. The prompts have the following format:

[0309] "Generate a creative marketing concept for audience: [Segment 1]"

[0310] "Generate a creative marketing concept for audience: [Segment 2]"

[0311] This allows the generated creative concepts to be optimized for each segment.

[0312] Generative Concept Output

[0313] The device displays the generated creative concepts to the user. Specifically, the user interface displays a list of marketing concepts for each segment, including the following concepts:

[0314] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[0315] "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[0316] The above process flow allows users to quickly generate creative concepts that are effectively segmented for their target audience, and the introduction of an emotion engine makes it possible to make the most of detailed user profiles.

[0317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0318] Step 1:

[0319] Setting an API key

[0320] The user enters their API key into the system settings screen. This is the input.

[0321] The server receives the user's API key and stores it as authentication information, which is the output.

[0322] Specifically, the user enters the API key into the web interface and clicks the "Save" button.

[0323] Step 2:

[0324] Obtaining target audience data

[0325] The server sends an HTTP request to the external API using the target audience ID "example_id" specified by the user. This is the input.

[0326] The server receives target audience attribute information (e.g., age, gender, region, interests) obtained from an external API. This is the output.

[0327] Specifically, the server executes an API request and retrieves the following JSON data:

[0328] json

[0329] [

[0330] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"], "emotion": "happy"},

[0331] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"], "emotion": "neutral"},

[0332] ...

[0333] ]

[0334] Step 3:

[0335] Acquiring emotion data

[0336] The server sends data to the emotion engine based on the collected attribute information, which becomes the input.

[0337] The server receives emotion data from an emotion engine (e.g., Google Cloud Speech-to-Text, AWS Rekognition) and integrates it into attribute information, which becomes the output.

[0338] Specifically, the server sends each audience member's social media posts and voice data to the emotion engine and obtains the emotion classification results.

[0339] Step 4:

[0340] Integrating audience demographics and sentiment data

[0341] The server integrates the acquired attribute information and emotion data to update the user profile, which serves as input.

[0342] The server stores the integrated detailed user profile in a database, which is the output.

[0343] Specifically, the server executes an INSERT or UPDATE query on a specific table in the database.

[0344] Step 5:

[0345] Audience segmentation

[0346] The server applies a clustering algorithm (e.g., KMeans clustering) based on the combined profile data, which is the input.

[0347] The server generates a clustering result, a segment for each audience, which is the output.

[0348] Specifically, we use the Python scikit-learn library to perform clustering. For example, we segment the data as follows:

[0349] json

[0350] Segment 1: [User 1, User 5, User 9]

[0351] Segment 2: [User 2, User 6, User 10]

[0352] Step 6:

[0353] Creative concept generation

[0354] The server generates a prompt based on the generated segment, which becomes the input.

[0355] The server sends prompts to a generative AI model (e.g., OpenAI GPT-3) to generate a creative concept, which is the output.

[0356] Specifically, it generates the following prompt:

[0357] "Generate a creative marketing concept for audience: [Segment 1]"

[0358] "Generate a creative marketing concept for audience: [Segment 2]"

[0359] Step 7:

[0360] Generative Concept Output

[0361] The device displays the generated creative concept to the user, which serves as input.

[0362] The terminal displays a list of marketing concepts for each segment on the user interface, which is the output.

[0363] Specifically, the UI displays the following concepts:

[0364] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[0365] "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[0366] Through these processing steps, users can quickly obtain creative concepts that are effectively segmented for their target audience. The introduction of an emotion engine makes it possible to make full use of detailed user profiles.

[0367] (Application example 2)

[0368] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0369] Conventional marketing systems based on target audience attribute information have the problem of difficulty in generating personalized advertisements and marketing concepts that take into account the user's emotional state. This makes it difficult to develop effective marketing strategies that accurately capture the target audience's emotional responses, potentially reducing marketing effectiveness.

[0370] 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.

[0371] In this invention, the server includes means for acquiring attribute information of the target audience, means for adding emotional information to the acquired attribute information, means for integrating the added attribute information and emotional information and segmenting using clustering technology, means for generating prompts for generating creative concepts based on the segmented data, and means for inputting the generated prompts into a natural language generation model to automatically generate creative concepts, thereby enabling the generation of personalized marketing concepts that reflect the emotional state of the target audience.

[0372] A "target audience" refers to a group of consumers who are likely to be interested in a particular product or service.

[0373] "Attribute information" refers to basic information such as a user's age, gender, region, and interests.

[0374] "Emotional information" refers to data that reflects the user's emotional state, and includes information obtained from voice, facial expressions, text analysis, etc.

[0375] "Clustering technology" refers to algorithms that group data based on similarities or patterns.

[0376] "Segmentation" refers to the process of dividing users into groups based on attributes or emotional states using collected data.

[0377] A "prompt" refers to an instruction or question that is input into a natural language generation model.

[0378] "Natural language generation model" refers to a machine learning model for understanding and generating human language, specifically including generative AI models such as GPT.

[0379] "Creative Concepts" refers to the creative ideas and strategies generated for marketing and advertising campaigns.

[0380] A system for implementing this invention acquires attribute information and emotion information of a target audience, integrates and segments them, and generates creative concepts using a generative AI model. The system configuration includes a server, an attribute information acquisition API, an emotion information acquisition engine, a clustering algorithm, and a natural language generation model (i.e., a generative AI model).

[0381] Hardware and software configuration

[0382] Hardware

[0383] Server: Collects, processes, analyzes data, and manages the generated creative concepts.

[0384] software

[0385] The main software used is as follows:

[0386] Python: A programming language for creating entire programs.

[0387] The requests library: Used to retrieve data through an API.

[0388] sklearn library: Used for clustering algorithms (KMeans clustering).

[0389] The transformers library: used for text generation using natural language generation models (e.g., GPT-2).

[0390] Data processing and calculation

[0391] Acquiring attribute and emotion information

[0392] The server first obtains the target audience's demographic information, including basic data such as age, gender, region, and interests. Then, it obtains the user's emotional state through an emotional information acquisition engine. This emotional information is collected using one or more technologies: voice recognition, facial expression recognition, and text analysis.

[0393] Data Integration and Clustering

[0394] The acquired attribute information and emotion information are integrated on the server to create a user profile, and then a clustering algorithm (KMeans clustering) is used to segment users based on similar attributes, interests, and emotional states.

[0395] Creative concept generation

[0396] Based on the segmented data, the server uses a generative AI model to create prompts to generate creative concepts, such as "Generate a creative marketing concept for the following audience: [Segment 1]." The prompts are then fed into a natural language generation model to generate the optimal creative concepts for each segment.

[0397] Specific examples

[0398] For example, the prompt for segment 1 is:

[0399] "Generate a creative marketing concept for the following audience: [{'age': 25, 'gender': 'female', 'location': 'Tokyo', 'interests': ['fashion', 'sports'], 'emotion': 'happy'}]"

[0400] By feeding this prompt into a natural language generation model, we can generate creative concepts like this:

[0401] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[0402] This makes it possible to effectively generate personalized marketing concepts that reflect the emotional state of the target audience.

[0403] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0404] Step 1:

[0405] The server uses a means to obtain target audience attribute information to obtain attribute information such as the user's age, gender, region, and interests from an external API. This process makes an API request based on the specified target audience ID and receives attribute information in JSON format. The input is the target audience ID, and the output is JSON data containing attribute information.

[0406] Step 2:

[0407] The server uses the emotion engine to add emotional information to the acquired user attribute information. In this process, the emotion engine analyzes the user's voice, facial expression, and text data, and adds each user's emotional state as data. The input is the attribute information acquired in step 1, and the output is updated user data with the added emotional information.

[0408] Step 3:

[0409] The server integrates the attribute information and emotion information and segments users using clustering techniques (KMeans clustering). In this process, the attribute information and emotion information are input into a clustering algorithm to group users based on similar attributes, interests, and emotional states. The input is the user data integrated in step 2, and the output is user data categorized into multiple segments.

[0410] Step 4:

[0411] The server creates prompts for generating creative concepts based on the segmented data. This process generates instructions for generating marketing concepts for each segment. The input is the segment data generated in step 3, and the output is the prompt.

[0412] Step 5:

[0413] The server inputs the generated prompt into a natural language generation model (e.g., GPT-2) to automatically generate creative concepts. In this process, the generative AI model receives the prompt and generates marketing concepts in natural language. The input is the prompt sentence generated in step 4, and the output is a creative concept appropriate for each segment.

[0414] Step 6:

[0415] The device displays the generated creative concept to the user. In this process, the device displays the creative concept received from the server on the screen for the user to view. The input is the creative concept generated in step 5, and the output is a viewable representation for the user.

[0416] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0417] 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 engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0418] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0419] [Second embodiment]

[0420] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0421] 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.

[0422] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0423] 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.

[0424] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0426] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0427] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0432] The present invention relates to a system that acquires target audience attribute information, segments them using clustering technology, and automatically generates creative concepts for each segment. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[0433] System program processing overview

[0434] The system operates in the following stages:

[0435] 1. Set API key:

[0436] The user provides the system with their API key, which allows the system to access external data sources.

[0437] 2. Obtaining target audience data:

[0438] The server retrieves target attribute information (e.g., age, gender, region, interests) through the API based on the specified target audience ID, allowing the system to collect detailed data on the target users.

[0439] 3. Audience segmentation:

[0440] The server segments the acquired user data using a clustering algorithm, which groups users with similar attributes and interests.

[0441] 4. Creative concept generation:

[0442] The server automatically generates creative concepts based on the segmented data, specifically using a natural language generation model (e.g., GPT-3) to generate concepts appropriate for each segment.

[0443] 5. Output of generated concepts:

[0444] The creative concept generated by the device is displayed, allowing users to check the marketing concept optimized for each segment.

[0445] Specific examples

[0446] For example, a case where the user specifies the target audience ID "example_id" will be described.

[0447] 1. Obtaining target audience data:

[0448] The server receives data through the API, such as:

[0449] [

[0450] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"]},

[0451] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"]},

[0452] ...

[0453] ]

[0454] 2. Audience segmentation:

[0455] The server uses this data to perform clustering, dividing users into five segments, for example:

[0456] Segment 1: [User 1, User 5, User 9]

[0457] Segment 2: [User 2, User 6, User 10]

[0458] ...

[0459] 3. Creative concept generation:

[0460] The server uses a natural language generation model for each segment and inputs a prompt like this:

[0461] "Generate a creative marketing concept for audience: [Segment 1]"

[0462] "Generate a creative marketing concept for audience: [Segment 2]"

[0463] ...

[0464] This generates the following concepts:

[0465] Segment 1: "Fashion-forward sportswear campaign targeting trendy young women in Tokyo."

[0466] Segment 2: "Innovative tech and finance solutions for middle-aged professionals in Osaka."

[0467] ...

[0468] 4. Output of generated concepts:

[0469] The device displays the generated creative concepts to the user. For example, Segment 1 displays a "trend campaign for young people," while Segment 2 displays a "health promotion campaign for seniors."

[0470] In this way, the system can quickly and efficiently generate creative concepts optimized for the target audience, helping to inspire marketers and advertising creators.

[0471] The processing flow will be explained below.

[0472] Step 1:

[0473] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[0474] Step 2:

[0475] The server receives the target audience ID and retrieves the target audience's attribute information via API based on this ID. For example, it collects data such as age, gender, region, and interests based on the ID "example_id."

[0476] Step 3:

[0477] The server processes the acquired user data and extracts the necessary attribute information (age, gender, region, interests).

[0478] Step 4:

[0479] Based on the attribute information extracted by the server, users are segmented using a clustering algorithm (KMeans clustering). For example, all users are divided into five segments.

[0480] Step 5:

[0481] The server generates prompts based on the segmented data. For each segment, it creates a prompt like "Generate a creative marketing concept for segment 1."

[0482] Step 6:

[0483] The server-generated prompts are fed into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment.

[0484] Step 7:

[0485] The server sends the generated creative concepts to the device and displays them to the user. For example, concepts such as "Trendy Sportswear Campaign" are displayed for segment 1, and "Innovative Technology and Financial Solutions" are displayed for segment 2.

[0486] This process flow allows users to quickly and efficiently arrive at creative concepts optimized for their target audience.

[0487] Example 1

[0488] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0489] In current marketing and advertising production, it is difficult to quickly generate creative concepts that match the target audience. In particular, there is a need to streamline the process from segmentation based on attribute information to generating creative concepts. Conventional methods require manual data analysis and creative concept development, which requires a great deal of time and effort. Therefore, there is a need for a system that can automatically generate creative concepts optimized for the target audience.

[0490] 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.

[0491] In this invention, the server includes means for acquiring attribute information of the target audience, means for accessing a data source based on the acquired attribute information, means for segmenting the acquired attribute information using a clustering technique, means for automatically generating a creative concept using a generative AI model based on the segmented data, and means for outputting the generated creative concept to a user's terminal, thereby enabling the rapid and efficient generation of a creative concept suited to the target audience.

[0492] A "target audience" is a group of consumers who are likely to be interested in a particular product or service.

[0493] "Attribute information" is information that characterizes the target audience, such as age, gender, region, and interests.

[0494] "Data Source" is an external system or platform used to collect demographic information about your target audience.

[0495] A "clustering technique" is a technique for dividing data into groups, and classifying data points with similar characteristics into the same group.

[0496] "Segmentation" is the process of dividing a target audience into multiple groups based on attribute information obtained using clustering techniques.

[0497] A "generative AI model" is a model that uses artificial intelligence techniques to generate natural language or other forms of information based on specific input data.

[0498] A "creative concept" is a creative idea or theme that communicates an effective advertising or marketing message to a target audience.

[0499] "User's device" means a device such as a computer or smartphone used to display creative concepts generated by the system.

[0500] A "prompt" is text that is input into a generative AI model, from which a creative concept is generated.

[0501] Above are definitions of important terms.

[0502] The present invention relates to a system that acquires target audience attribute information, segments them using clustering technology, and automatically generates creative concepts for each segment. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[0503] The system is configured as follows:

[0504] First, the user provides the system with their API key, which allows the system to access external data sources. The user completes this process by entering the API key in the settings screen and saving it.

[0505] The server then sends an API request using the target audience ID specified by the user. The API request retrieves target audience attribute information such as age, gender, region, and interests. This data is obtained from a marketing platform such as the "Audience Insights API."

[0506] Based on the acquired attribute information, the server uses a clustering algorithm to segment users. For example, Scikit-learn's K-means clustering algorithm is used to cluster the data. Through clustering, users with similar attributes and interests are grouped into the same segment.

[0507] Next, the server generates creative concepts based on the segmented data using the generative AI model GPT-3. Specifically, it generates appropriate prompts for each segment and inputs these prompts into GPT-3. Examples of prompts include:

[0508] "Create a creative marketing concept for audience: [Segment 1]"

[0509] "Create a creative marketing concept for audience: [Segment 2]"

[0510] This automatically generates creative concepts for each segment: for example, for segment 1, a concept like "Fashion-forward sportswear campaign targeting trendy young women in Tokyo" might be generated, and for segment 2, a concept like "Innovative tech and finance solutions for middle-aged professionals in Osaka" might be generated.

[0511] Finally, the generated creative concepts are displayed on the user's device, allowing the user to check the marketing concepts optimized for each segment. Specifically, they are displayed in list format on the dashboard of the web application.

[0512] In this way, the system streamlines the work of marketers and advertising creators, enabling them to quickly provide creative concepts that suit the target audience.

[0513] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0514] Step 1:

[0515] The user provides the API key to the system.

[0516] Input: The user enters the API key into the settings screen and clicks the "Save" button.

[0517] How it works: The user navigates to the settings screen, enters their API key in the provided field, and clicks the "Save" button, which saves the API key as a credential in the system.

[0518] Output: The system is able to access external data sources and an API key is stored in the system.

[0519] Step 2:

[0520] The server accesses the data source based on the target audience ID.

[0521] Input: User-specified target audience ID.

[0522] How it works: The server generates an API request and sends the target audience ID as a parameter to an external data source, specifically calling the marketing platform's API to retrieve the target audience's attributes.

[0523] Output: The acquired attribute information (e.g., age, gender, region, interests) is stored in a database.

[0524] Step 3:

[0525] The server uses a clustering technique to segment the attribute information.

[0526] Input: The target audience demographic information obtained.

[0527] How it works: The server applies a clustering algorithm (e.g., Scikit-learn's K-means clustering) to classify the target audience into segments based on their attributes, e.g., grouping users with similar interests or attributes.

[0528] Output: Segmented target audience data is generated.

[0529] Step 4:

[0530] The server uses generative AI models to generate creative concepts for each segment.

[0531] Input: Segmented target audience data.

[0532] How it works: The server creates an appropriate prompt for each segment and inputs it into a generative AI model (e.g., GPT-3). An example of a specific prompt might be, "Create a creative marketing concept for audience: [Segment 1]."

[0533] Output: A creative concept optimized for each segment is generated.

[0534] Step 5:

[0535] The terminal outputs the generated creative concept to the user.

[0536] Input: Generated creative concepts.

[0537] How it works: The device displays the generated creative concepts. Specifically, they are displayed in a list format on the web application dashboard. The user can access the dashboard to view the generated concepts.

[0538] Output: Users can visualize creative concepts optimized for each segment.

[0539] (Application example 1)

[0540] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0541] Conventional creative concept generation systems have been unable to effectively utilize the diverse attribute information of target audiences, resulting in the time-consuming and labor-intensive process of segmenting and generating creative concepts. Furthermore, the quality of the generated creative concepts often lacks uniformity, potentially reducing marketing efficiency. There is a need for a system that can solve these issues and generate high-quality creative concepts quickly.

[0542] 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.

[0543] In this invention, the server includes means for acquiring attribute information of the target audience, means for segmenting the acquired attribute information using clustering technology, means for automatically generating a creative concept based on the segmented data, and means for displaying the generated creative concept on a terminal. This allows the target audience attribute information to be effectively utilized to quickly and efficiently generate a creative concept, enabling marketers and advertising creators to quickly obtain high-quality concepts.

[0544] A "target audience" is a group of recipients with specific attributes that you focus on when conducting a particular marketing or promotional activity.

[0545] "Attribute information" refers to characteristic data about the target audience, such as age, gender, region, and interests.

[0546] "Clustering technology" is a machine learning technique for grouping data with similar characteristics.

[0547] "Segmentation" is the process of grouping target audience demographic information using clustering techniques.

[0548] A "creative concept" is an idea for an advertising or marketing strategy generated for a specific target audience.

[0549] A "natural language generation model" is an artificial intelligence model for generating natural language text based on given data and prompts.

[0550] A "Device" is a device, such as a computer or smartphone, that a User uses to display Creative Concepts or other information.

[0551] A system for implementing the present invention acquires attribute information of a target audience, segments them using clustering technology, automatically generates creative concepts for each segment, and displays the generated concepts on a terminal.

[0552] The operation of the system is as follows.

[0553] First, the user provides the server with an API key, which allows the server to access external data sources. Next, the server retrieves target demographic information via the API based on the target audience ID. This demographic information includes data such as age, gender, region, and interests.

[0554] The server segments the data based on the acquired attribute information using a clustering algorithm, such as the K-Means algorithm, which groups audiences with similar attributes.

[0555] Based on the segmented data, the server uses a natural language generation model (e.g., GPT-3) to generate creative concepts appropriate for each segment. In this generation process, prompts are set for each segment, and creative concepts are automatically generated based on the prompts.

[0556] For example, you can use prompts like the following to generate different creative concepts for each segment:

[0557] "Generate a creative marketing concept for audience: Segment 1"

[0558] "Generate a creative marketing concept for audience: Segment 2"

[0559] The generated creative concept is displayed to the user via the terminal, allowing the user to check and use the marketing concept optimized for each segment quickly and efficiently.

[0560] As a specific example, if you use the target audience ID "example_id", the server may obtain the following attribute information:

[0561] 「age: 25, gender: female, location: Tokyo, interests: fashion, sports」

[0562] "age: 40, gender: male, location: Osaka, interests: technology, finance"

[0563] Clustering is performed based on this data and segmented as follows:

[0564] Segment 1: For young people

[0565] Segment 2: Middle-aged people

[0566] Then, for each, set the prompts to generate creative concepts as follows:

[0567] "Generate a creative marketing concept for audience: Young people"

[0568] "Generate a creative marketing concept for audience: middle-aged people"

[0569] The generated creative concept may look something like this:

[0570] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo"

[0571] "Innovative tech and finance solutions for middle-aged professionals in Osaka"

[0572] In this way, the server can effectively utilize the attribute information of the target audience, quickly generate high-quality creative concepts, and provide them in a format that is easy for users to use.

[0573] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0574] Step 1:

[0575] The user provides an API key.

[0576] Input: The user enters an API key.

[0577] What it does: Stores the user-provided API key on the server, allowing access to external data sources.

[0578] Output: An API key is saved on the server, granting access to the external data source.

[0579] Step 2:

[0580] The server retrieves the target audience data.

[0581] Input: Target audience ID (e.g. "example_id")

[0582] Processing: The server uses the target audience ID to obtain the target's demographic information (age, gender, region, interests, etc.) via API.

[0583] Output: The target audience's demographic information is retrieved to the server.

[0584] Step 3:

[0585] The server segments the audience data using clustering techniques.

[0586] Input: Attribute information of the target audience obtained

[0587] Processing: The server uses a clustering algorithm (e.g. K-Means) to group similar audiences based on their attributes.

[0588] Output: Segmented audience data.

[0589] Step 4:

[0590] The server generates creative concepts based on the segmented data.

[0591] Input: Segmented audience data

[0592] Processing: The server uses a natural language generation model (e.g., GPT-3) to generate creative concepts appropriate for each segment. For each segment, a prompt is set and a creative concept is generated based on the prompt.

[0593] Output: The generated creative concepts are saved on the server.

[0594] Step 5:

[0595] The server displays the generated creative concept on the terminal.

[0596] Input: Generated creative concept

[0597] Processing: The server sends the generated creative concept to the user's device.

[0598] Output: The creative concept is displayed on the user's device.

[0599] As a concrete example, we will show how to set a prompt sentence. For example, we set the following prompt for segment 1:

[0600] "Generate a creative marketing concept for audience: Young people"

[0601] A creative concept generated based on this prompt might be, for example, "Fashion-forward sportswear campaign targeting trendy young women in Tokyo." This creative concept is displayed on the user's device, allowing the user to review and use it.

[0602] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0603] This invention combines a system that acquires target audience attribute information and segments them using clustering technology with an emotion engine that recognizes user emotions, enabling the generation of more advanced marketing concepts. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[0604] System program processing overview

[0605] The system operates in the following stages:

[0606] 1. Set API key:

[0607] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[0608] 2. Obtaining target audience data:

[0609] Based on the specified target audience ID, the server obtains target attribute information (e.g., age, gender, region, interests, and emotional data) through the API, allowing the system to collect detailed data on the target users.

[0610] 3. Acquiring emotion data:

[0611] The server acquires the user's emotional data through an emotion engine, which uses one or more of voice recognition, facial expression recognition, and text analysis technologies to understand the user's emotional state.

[0612] 4. Integrating audience demographics and sentiment data:

[0613] The server integrates the acquired attribute information and emotional data and updates the user's profile based on this data.

[0614] 5. Audience segmentation:

[0615] The server segments users based on the integrated data using a clustering algorithm (KMeans clustering), which groups users with similar attributes, hobbies, and emotions.

[0616] 6. Creative concept generation:

[0617] The server generates prompts based on the segmented data. For each segment, it creates a prompt like "Generate a creative marketing concept for segment 1."

[0618] 7. Using Natural Language Generation Models:

[0619] The server-generated prompts are fed into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment.

[0620] 8. Output of generated concepts:

[0621] The creative concept generated by the device is displayed, allowing users to check the marketing concept optimized for each segment.

[0622] Specific examples

[0623] For example, a case where the user specifies the target audience ID "example_id" will be described.

[0624] 1. Obtaining target audience data:

[0625] The server receives data through the API, such as:

[0626] [

[0627] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"], "emotion": "happy"},

[0628] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"], "emotion": "neutral"},

[0629] ...

[0630] ]

[0631] 2. Acquiring emotion data:

[0632] The server uses an emotion engine to extract emotion data from the user's voice, facial expressions, and text, and adds it to each attribute information.

[0633] 3. Integrating audience demographics and sentiment data:

[0634] The server integrates the acquired attribute information and emotional data and creates an updated user profile based on them.

[0635] 4. Audience segmentation:

[0636] The server performs clustering based on the combined data, dividing users into five segments, for example:

[0637] Segment 1: [User 1, User 5, User 9]

[0638] Segment 2: [User 2, User 6, User 10]

[0639] ...

[0640] 5. Creative concept generation:

[0641] For each segment, the server inputs the following prompts into the NLG model:

[0642] "Generate a creative marketing concept for audience: [Segment 1]"

[0643] "Generate a creative marketing concept for audience: [Segment 2]"

[0644] ...

[0645] This generates the following concepts:

[0646] Segment 1: "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[0647] Segment 2: "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[0648] ...

[0649] 6. Output of generated concepts:

[0650] The device displays the generated creative concepts to the user, for example, "Trendy Sportswear Campaign" for Segment 1 and "Innovative Technology and Financial Solutions" for Segment 2.

[0651] This process flow allows users to quickly and efficiently generate creative concepts optimized for their target audience. The introduction of the emotion engine enables segmentation using more detailed user profiles, which is expected to lead to the generation of more effective marketing concepts.

[0652] The processing flow will be explained below.

[0653] Step 1:

[0654] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[0655] Step 2:

[0656] The server receives the target audience ID and retrieves the target audience's attribute information via API based on this ID. For example, it collects data such as age, gender, region, and interests based on the ID "example_id."

[0657] Step 3:

[0658] The server uses an emotion engine to obtain additional emotion data, which uses voice recognition, facial expression recognition, and text analysis to understand the user's emotional state, for example, by inputting facial expressions and voice through a webcam or microphone.

[0659] Step 4:

[0660] The server combines the acquired attribute information with the emotional data to create a detailed profile of the user, including, for example, the user's age, gender, region, interests, and emotional state such as "happy" or "neutral."

[0661] Step 5:

[0662] The server uses the aggregated data to segment users using a clustering algorithm (KMeans clustering). For example, it divides all users into five segments.

[0663] Step 6:

[0664] The server generates prompts for each segment based on the segmented data, for example, "Generate a creative marketing concept for segment 1."

[0665] Step 7:

[0666] The server-generated prompts are input into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment. For example, for segment 1, it generates a "sportswear campaign for trend-conscious young women living in Tokyo."

[0667] Step 8:

[0668] The server sends the generated creative concepts to the device and displays them to the user. For example, concepts such as "Fashion-forward sportswear campaign" are displayed for segment 1, and "Innovative technology and financial solutions" are displayed for segment 2.

[0669] This process flow allows users to quickly and efficiently generate creative concepts optimized for their target audience. The introduction of the emotion engine enables segmentation using more detailed user profiles, which is expected to lead to the generation of more effective marketing concepts.

[0670] Example 2

[0671] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0672] Conventional marketing systems have difficulty not only obtaining target audience attribute information but also utilizing user sentiment data. Furthermore, they lack the means to efficiently and effectively segment the obtained information and generate creative marketing concepts for each segment. This makes it difficult for marketers and advertising creators to quickly find inspiration, preventing them from maximizing the effectiveness of their marketing campaigns.

[0673] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring attribute information of the target audience, means for integrating the acquired attribute information and emotion data to update a user profile, means for segmenting the integrated data using a clustering technique, means for automatically generating a creative concept based on the segmented data, and means for displaying the generated creative concept. This enables effective segmentation based on a detailed profile of the target audience and rapid generation of a creative concept based on the segmented data.

[0674] "Target audience" refers to a group of people with specific attributes who are the target of marketing and advertising activities.

[0675] "Attribute information" refers to data that indicates the characteristics of your target audience, such as age, gender, region, interests, and emotional data.

[0676] "Emotion data" is data that indicates the emotional state of a user, obtained from voice, facial expression, text, etc.

[0677] "User profile" refers to detailed personal information that integrates demographic and emotional data of a target audience.

[0678] "Clustering technology" refers to a general algorithm that divides data into groups based on similarity, and includes KMeans clustering as an example here.

[0679] "Segmentation" refers to the use of clustering techniques to divide a target audience based on attribute information and emotional data.

[0680] "Creative Concept" refers to an idea or theme created for a specific marketing purpose.

[0681] "Generative AI model" refers to artificial intelligence technology that uses natural language processing technology to automatically generate text based on input prompts.

[0682] A "prompt" refers to a question or instruction input to a generative AI model.

[0683] A "database" refers to a collection of information that allows for efficient storage and retrieval of large amounts of data.

[0684] "Speech recognition" is a technology that analyzes voice data and converts it into text and emotions.

[0685] "Facial expression recognition" is a technology that analyzes facial expressions from image data and identifies the emotional state of a person.

[0686] "Text analysis" is a technology that analyzes text data and understands and classifies its content and sentiment.

[0687] This invention is a system that acquires attribute information of a target audience, segments them using clustering technology, and combines it with an emotion engine that recognizes user emotions to generate a creative concept. Specific embodiments of this invention are described below.

[0688] Hardware and software used

[0689] The implementation of this system utilizes the following hardware and software:

[0690] Server: Responsible for cloud-based data processing and storage. It operates as the core of the system, generating, processing, and managing various data.

[0691] Terminal: A device that provides an interface for users to access. This includes computers and smartphones.

[0692] Emotion engine: A tool such as Google Cloud Speech-to-Text or AWS Rekognition that analyzes a user's voice, facial expressions, and text to obtain emotional data.

[0693] Natural Language Generation Models: Tools that use generative AI models, such as OpenAI GPT-3, to generate creative concepts.

[0694] Clustering algorithm: An algorithm for clustering data (e.g., KMeans clustering) using Python's scikit-learn library.

[0695] Program processing overview

[0696] Obtaining target audience data

[0697] The server uses external APIs based on the target audience ID specified by the user to obtain audience attribute information. Target APIs include Facebook Graph API and Twitter API. The obtained data includes information such as age, gender, region, and interests.

[0698] Acquiring emotion data

[0699] The server acquires the user's emotional data using an emotion engine. The emotional data is extracted from the user's voice, facial expressions, and text. For example, Google Cloud Speech-to-Text is used to analyze the voice data and identify the emotion.

[0700] Integrating audience demographics and sentiment data

[0701] The server integrates the acquired attribute information and emotion data to update a detailed profile for each user, which is then stored in a database on the server.

[0702] Audience segmentation

[0703] The server performs clustering on the combined data, using the Python scikit-learn library and applying the KMeans clustering algorithm, which categorizes audiences into groups with common attributes and sentiments.

[0704] Creative concept generation

[0705] The server generates appropriate prompts for each segment and feeds them into the natural language generation model. The prompts have the following format:

[0706] "Generate a creative marketing concept for audience: [Segment 1]"

[0707] "Generate a creative marketing concept for audience: [Segment 2]"

[0708] This allows the generated creative concepts to be optimized for each segment.

[0709] Generative Concept Output

[0710] The device displays the generated creative concepts to the user. Specifically, the user interface displays a list of marketing concepts for each segment, including the following concepts:

[0711] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[0712] "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[0713] The above process flow allows users to quickly generate creative concepts that are effectively segmented for their target audience, and the introduction of an emotion engine makes it possible to make the most of detailed user profiles.

[0714] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0715] Step 1:

[0716] Setting an API key

[0717] The user enters their API key into the system settings screen. This is the input.

[0718] The server receives the user's API key and stores it as authentication information, which is the output.

[0719] Specifically, the user enters the API key into the web interface and clicks the "Save" button.

[0720] Step 2:

[0721] Obtaining target audience data

[0722] The server sends an HTTP request to the external API using the target audience ID "example_id" specified by the user. This is the input.

[0723] The server receives target audience attribute information (e.g., age, gender, region, interests) obtained from an external API. This is the output.

[0724] Specifically, the server executes an API request and retrieves the following JSON data:

[0725] json

[0726] [

[0727] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"], "emotion": "happy"},

[0728] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"], "emotion": "neutral"},

[0729] ...

[0730] ]

[0731] Step 3:

[0732] Acquiring emotion data

[0733] The server sends data to the emotion engine based on the collected attribute information, which becomes the input.

[0734] The server receives emotion data from an emotion engine (e.g., Google Cloud Speech-to-Text, AWS Rekognition) and integrates it into attribute information, which becomes the output.

[0735] Specifically, the server sends each audience member's social media posts and voice data to the emotion engine and obtains the emotion classification results.

[0736] Step 4:

[0737] Integrating audience demographics and sentiment data

[0738] The server integrates the acquired attribute information and emotion data to update the user profile, which serves as input.

[0739] The server stores the integrated detailed user profile in a database, which is the output.

[0740] Specifically, the server executes an INSERT or UPDATE query on a specific table in the database.

[0741] Step 5:

[0742] Audience segmentation

[0743] The server applies a clustering algorithm (e.g., KMeans clustering) based on the combined profile data, which is the input.

[0744] The server generates a clustering result, a segment for each audience, which is the output.

[0745] Specifically, we use the Python scikit-learn library to perform clustering. For example, we segment the data as follows:

[0746] json

[0747] Segment 1: [User 1, User 5, User 9]

[0748] Segment 2: [User 2, User 6, User 10]

[0749] Step 6:

[0750] Creative concept generation

[0751] The server generates a prompt based on the generated segment, which becomes the input.

[0752] The server sends prompts to a generative AI model (e.g., OpenAI GPT-3) to generate a creative concept, which is the output.

[0753] Specifically, it generates the following prompt:

[0754] "Generate a creative marketing concept for audience: [Segment 1]"

[0755] "Generate a creative marketing concept for audience: [Segment 2]"

[0756] Step 7:

[0757] Generative Concept Output

[0758] The device displays the generated creative concept to the user, which serves as input.

[0759] The terminal displays a list of marketing concepts for each segment on the user interface, which is the output.

[0760] Specifically, the UI displays the following concepts:

[0761] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[0762] "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[0763] Through these processing steps, users can quickly obtain creative concepts that are effectively segmented for their target audience. The introduction of an emotion engine makes it possible to make full use of detailed user profiles.

[0764] (Application example 2)

[0765] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0766] Conventional marketing systems based on target audience attribute information have the problem of difficulty in generating personalized advertisements and marketing concepts that take into account the user's emotional state. This makes it difficult to develop effective marketing strategies that accurately capture the target audience's emotional responses, potentially reducing marketing effectiveness.

[0767] 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.

[0768] In this invention, the server includes means for acquiring attribute information of the target audience, means for adding emotional information to the acquired attribute information, means for integrating the added attribute information and emotional information and segmenting using clustering technology, means for generating prompts for generating creative concepts based on the segmented data, and means for inputting the generated prompts into a natural language generation model to automatically generate creative concepts, thereby enabling the generation of personalized marketing concepts that reflect the emotional state of the target audience.

[0769] A "target audience" refers to a group of consumers who are likely to be interested in a particular product or service.

[0770] "Attribute information" refers to basic information such as a user's age, gender, region, and interests.

[0771] "Emotional information" refers to data that reflects the user's emotional state, and includes information obtained from voice, facial expressions, text analysis, etc.

[0772] "Clustering technology" refers to algorithms that group data based on similarities or patterns.

[0773] "Segmentation" refers to the process of dividing users into groups based on attributes or emotional states using collected data.

[0774] A "prompt" refers to an instruction or question that is input into a natural language generation model.

[0775] "Natural language generation model" refers to a machine learning model for understanding and generating human language, specifically including generative AI models such as GPT.

[0776] "Creative Concepts" refers to the creative ideas and strategies generated for marketing and advertising campaigns.

[0777] A system for implementing this invention acquires attribute information and emotion information of a target audience, integrates and segments them, and generates creative concepts using a generative AI model. The system configuration includes a server, an attribute information acquisition API, an emotion information acquisition engine, a clustering algorithm, and a natural language generation model (i.e., a generative AI model).

[0778] Hardware and software configuration

[0779] Hardware

[0780] Server: Collects, processes, analyzes data, and manages the generated creative concepts.

[0781] software

[0782] The main software used is as follows:

[0783] Python: A programming language for creating entire programs.

[0784] The requests library: Used to retrieve data through an API.

[0785] sklearn library: Used for clustering algorithms (KMeans clustering).

[0786] The transformers library: used for text generation using natural language generation models (e.g., GPT-2).

[0787] Data processing and calculation

[0788] Acquiring attribute and emotion information

[0789] The server first obtains the target audience's demographic information, including basic data such as age, gender, region, and interests. Then, it obtains the user's emotional state through an emotional information acquisition engine. This emotional information is collected using one or more technologies: voice recognition, facial expression recognition, and text analysis.

[0790] Data Integration and Clustering

[0791] The acquired attribute information and emotion information are integrated on the server to create a user profile, and then a clustering algorithm (KMeans clustering) is used to segment users based on similar attributes, interests, and emotional states.

[0792] Creative concept generation

[0793] Based on the segmented data, the server uses a generative AI model to create prompts to generate creative concepts, such as "Generate a creative marketing concept for the following audience: [Segment 1]." The prompts are then fed into a natural language generation model to generate the optimal creative concepts for each segment.

[0794] Specific examples

[0795] For example, the prompt for segment 1 is:

[0796] "Generate a creative marketing concept for the following audience: [{'age': 25, 'gender': 'female', 'location': 'Tokyo', 'interests': ['fashion', 'sports'], 'emotion': 'happy'}]"

[0797] By feeding this prompt into a natural language generation model, we can generate creative concepts like this:

[0798] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[0799] This makes it possible to effectively generate personalized marketing concepts that reflect the emotional state of the target audience.

[0800] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0801] Step 1:

[0802] The server uses a means to obtain target audience attribute information to obtain attribute information such as the user's age, gender, region, and interests from an external API. This process makes an API request based on the specified target audience ID and receives attribute information in JSON format. The input is the target audience ID, and the output is JSON data containing attribute information.

[0803] Step 2:

[0804] The server uses the emotion engine to add emotional information to the acquired user attribute information. In this process, the emotion engine analyzes the user's voice, facial expression, and text data, and adds each user's emotional state as data. The input is the attribute information acquired in step 1, and the output is updated user data with the added emotional information.

[0805] Step 3:

[0806] The server integrates the attribute information and emotion information and segments users using clustering techniques (KMeans clustering). In this process, the attribute information and emotion information are input into a clustering algorithm to group users based on similar attributes, interests, and emotional states. The input is the user data integrated in step 2, and the output is user data categorized into multiple segments.

[0807] Step 4:

[0808] The server creates prompts for generating creative concepts based on the segmented data. This process generates instructions for generating marketing concepts for each segment. The input is the segment data generated in step 3, and the output is the prompt.

[0809] Step 5:

[0810] The server inputs the generated prompt into a natural language generation model (e.g., GPT-2) to automatically generate creative concepts. In this process, the generative AI model receives the prompt and generates marketing concepts in natural language. The input is the prompt sentence generated in step 4, and the output is a creative concept appropriate for each segment.

[0811] Step 6:

[0812] The device displays the generated creative concept to the user. In this process, the device displays the creative concept received from the server on the screen for the user to view. The input is the creative concept generated in step 5, and the output is a viewable representation for the user.

[0813] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0814] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0815] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0816] [Third embodiment]

[0817] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0818] 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.

[0819] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0820] 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.

[0821] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0822] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0823] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0824] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0825] 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.

[0826] 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.

[0827] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0828] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0829] The present invention relates to a system that acquires target audience attribute information, segments them using clustering technology, and automatically generates creative concepts for each segment. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[0830] System program processing overview

[0831] The system operates in the following stages:

[0832] 1. Set API key:

[0833] The user provides the system with their API key, which allows the system to access external data sources.

[0834] 2. Obtaining target audience data:

[0835] The server retrieves target attribute information (e.g., age, gender, region, interests) through the API based on the specified target audience ID, allowing the system to collect detailed data on the target users.

[0836] 3. Audience segmentation:

[0837] The server segments the acquired user data using a clustering algorithm, which groups users with similar attributes and interests.

[0838] 4. Creative concept generation:

[0839] The server automatically generates creative concepts based on the segmented data, specifically using a natural language generation model (e.g., GPT-3) to generate concepts appropriate for each segment.

[0840] 5. Output of generated concepts:

[0841] The creative concept generated by the device is displayed, allowing users to check the marketing concept optimized for each segment.

[0842] Specific examples

[0843] For example, a case where the user specifies the target audience ID "example_id" will be described.

[0844] 1. Obtaining target audience data:

[0845] The server receives data through the API, such as:

[0846] [

[0847] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"]},

[0848] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"]},

[0849] ...

[0850] ]

[0851] 2. Audience segmentation:

[0852] The server uses this data to perform clustering, dividing users into five segments, for example:

[0853] Segment 1: [User 1, User 5, User 9]

[0854] Segment 2: [User 2, User 6, User 10]

[0855] ...

[0856] 3. Creative concept generation:

[0857] The server uses a natural language generation model for each segment and inputs a prompt like this:

[0858] "Generate a creative marketing concept for audience: [Segment 1]"

[0859] "Generate a creative marketing concept for audience: [Segment 2]"

[0860] ...

[0861] This generates the following concepts:

[0862] Segment 1: "Fashion-forward sportswear campaign targeting trendy young women in Tokyo."

[0863] Segment 2: "Innovative tech and finance solutions for middle-aged professionals in Osaka."

[0864] ...

[0865] 4. Output of generated concepts:

[0866] The device displays the generated creative concepts to the user. For example, Segment 1 displays a "trend campaign for young people," while Segment 2 displays a "health promotion campaign for seniors."

[0867] In this way, the system can quickly and efficiently generate creative concepts optimized for the target audience, helping to inspire marketers and advertising creators.

[0868] The processing flow will be explained below.

[0869] Step 1:

[0870] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[0871] Step 2:

[0872] The server receives the target audience ID and retrieves the target audience's attribute information via API based on this ID. For example, it collects data such as age, gender, region, and interests based on the ID "example_id."

[0873] Step 3:

[0874] The server processes the acquired user data and extracts the necessary attribute information (age, gender, region, interests).

[0875] Step 4:

[0876] Based on the attribute information extracted by the server, users are segmented using a clustering algorithm (KMeans clustering). For example, all users are divided into five segments.

[0877] Step 5:

[0878] The server generates prompts based on the segmented data. For each segment, it creates a prompt like "Generate a creative marketing concept for segment 1."

[0879] Step 6:

[0880] The server-generated prompts are fed into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment.

[0881] Step 7:

[0882] The server sends the generated creative concepts to the device and displays them to the user. For example, concepts such as "Trendy Sportswear Campaign" are displayed for segment 1, and "Innovative Technology and Financial Solutions" are displayed for segment 2.

[0883] This process flow allows users to quickly and efficiently arrive at creative concepts optimized for their target audience.

[0884] Example 1

[0885] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0886] In current marketing and advertising production, it is difficult to quickly generate creative concepts that match the target audience. In particular, there is a need to streamline the process from segmentation based on attribute information to generating creative concepts. Conventional methods require manual data analysis and creative concept development, which requires a great deal of time and effort. Therefore, there is a need for a system that can automatically generate creative concepts optimized for the target audience.

[0887] 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.

[0888] In this invention, the server includes means for acquiring attribute information of the target audience, means for accessing a data source based on the acquired attribute information, means for segmenting the acquired attribute information using a clustering technique, means for automatically generating a creative concept using a generative AI model based on the segmented data, and means for outputting the generated creative concept to a user's terminal, thereby enabling the rapid and efficient generation of a creative concept suited to the target audience.

[0889] A "target audience" is a group of consumers who are likely to be interested in a particular product or service.

[0890] "Attribute information" is information that characterizes the target audience, such as age, gender, region, and interests.

[0891] "Data Source" is an external system or platform used to collect demographic information about your target audience.

[0892] A "clustering technique" is a technique for dividing data into groups, and classifying data points with similar characteristics into the same group.

[0893] "Segmentation" is the process of dividing a target audience into multiple groups based on attribute information obtained using clustering techniques.

[0894] A "generative AI model" is a model that uses artificial intelligence techniques to generate natural language or other forms of information based on specific input data.

[0895] A "creative concept" is a creative idea or theme that communicates an effective advertising or marketing message to a target audience.

[0896] "User's device" means a device such as a computer or smartphone used to display creative concepts generated by the system.

[0897] A "prompt" is text that is input into a generative AI model, from which a creative concept is generated.

[0898] Above are definitions of important terms.

[0899] The present invention relates to a system that acquires target audience attribute information, segments them using clustering technology, and automatically generates creative concepts for each segment. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[0900] The system is configured as follows:

[0901] First, the user provides the system with their API key, which allows the system to access external data sources. The user completes this process by entering the API key in the settings screen and saving it.

[0902] The server then sends an API request using the target audience ID specified by the user. The API request retrieves target audience attribute information such as age, gender, region, and interests. This data is obtained from a marketing platform such as the "Audience Insights API."

[0903] Based on the acquired attribute information, the server uses a clustering algorithm to segment users. For example, Scikit-learn's K-means clustering algorithm is used to cluster the data. Through clustering, users with similar attributes and interests are grouped into the same segment.

[0904] Next, the server generates creative concepts based on the segmented data using the generative AI model GPT-3. Specifically, it generates appropriate prompts for each segment and inputs these prompts into GPT-3. Examples of prompts include:

[0905] "Create a creative marketing concept for audience: [Segment 1]"

[0906] "Create a creative marketing concept for audience: [Segment 2]"

[0907] This automatically generates creative concepts for each segment: for example, for segment 1, a concept like "Fashion-forward sportswear campaign targeting trendy young women in Tokyo" might be generated, and for segment 2, a concept like "Innovative tech and finance solutions for middle-aged professionals in Osaka" might be generated.

[0908] Finally, the generated creative concepts are displayed on the user's device, allowing the user to check the marketing concepts optimized for each segment. Specifically, they are displayed in list format on the dashboard of the web application.

[0909] In this way, the system streamlines the work of marketers and advertising creators, enabling them to quickly provide creative concepts that suit the target audience.

[0910] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0911] Step 1:

[0912] The user provides the API key to the system.

[0913] Input: The user enters the API key into the settings screen and clicks the "Save" button.

[0914] How it works: The user navigates to the settings screen, enters their API key in the provided field, and clicks the "Save" button, which saves the API key as a credential in the system.

[0915] Output: The system is able to access external data sources and an API key is stored in the system.

[0916] Step 2:

[0917] The server accesses the data source based on the target audience ID.

[0918] Input: User-specified target audience ID.

[0919] How it works: The server generates an API request and sends the target audience ID as a parameter to an external data source, specifically calling the marketing platform's API to retrieve the target audience's attributes.

[0920] Output: The acquired attribute information (e.g., age, gender, region, interests) is stored in a database.

[0921] Step 3:

[0922] The server uses a clustering technique to segment the attribute information.

[0923] Input: The target audience demographic information obtained.

[0924] How it works: The server applies a clustering algorithm (e.g., Scikit-learn's K-means clustering) to classify the target audience into segments based on their attributes, e.g., grouping users with similar interests or attributes.

[0925] Output: Segmented target audience data is generated.

[0926] Step 4:

[0927] The server uses generative AI models to generate creative concepts for each segment.

[0928] Input: Segmented target audience data.

[0929] How it works: The server creates an appropriate prompt for each segment and inputs it into a generative AI model (e.g., GPT-3). An example of a specific prompt might be, "Create a creative marketing concept for audience: [Segment 1]."

[0930] Output: A creative concept optimized for each segment is generated.

[0931] Step 5:

[0932] The terminal outputs the generated creative concept to the user.

[0933] Input: Generated creative concepts.

[0934] How it works: The device displays the generated creative concepts. Specifically, they are displayed in a list format on the web application dashboard. The user can access the dashboard to view the generated concepts.

[0935] Output: Users can visualize creative concepts optimized for each segment.

[0936] (Application example 1)

[0937] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0938] Conventional creative concept generation systems have been unable to effectively utilize the diverse attribute information of target audiences, resulting in the time-consuming and labor-intensive process of segmenting and generating creative concepts. Furthermore, the quality of the generated creative concepts often lacks uniformity, potentially reducing marketing efficiency. There is a need for a system that can solve these issues and generate high-quality creative concepts quickly.

[0939] 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.

[0940] In this invention, the server includes means for acquiring attribute information of the target audience, means for segmenting the acquired attribute information using clustering technology, means for automatically generating a creative concept based on the segmented data, and means for displaying the generated creative concept on a terminal. This allows the target audience attribute information to be effectively utilized to quickly and efficiently generate a creative concept, enabling marketers and advertising creators to quickly obtain high-quality concepts.

[0941] A "target audience" is a group of recipients with specific attributes that you focus on when conducting a particular marketing or promotional activity.

[0942] "Attribute information" refers to characteristic data about the target audience, such as age, gender, region, and interests.

[0943] "Clustering technology" is a machine learning technique for grouping data with similar characteristics.

[0944] "Segmentation" is the process of grouping target audience demographic information using clustering techniques.

[0945] A "creative concept" is an idea for an advertising or marketing strategy generated for a specific target audience.

[0946] A "natural language generation model" is an artificial intelligence model for generating natural language text based on given data and prompts.

[0947] A "Device" is a device, such as a computer or smartphone, that a User uses to display Creative Concepts or other information.

[0948] A system for implementing the present invention acquires attribute information of a target audience, segments them using clustering technology, automatically generates creative concepts for each segment, and displays the generated concepts on a terminal.

[0949] The operation of the system is as follows.

[0950] First, the user provides the server with an API key, which allows the server to access external data sources. Next, the server retrieves target demographic information via the API based on the target audience ID. This demographic information includes data such as age, gender, region, and interests.

[0951] The server segments the data based on the acquired attribute information using a clustering algorithm, such as the K-Means algorithm, which groups audiences with similar attributes.

[0952] Based on the segmented data, the server uses a natural language generation model (e.g., GPT-3) to generate creative concepts appropriate for each segment. In this generation process, prompts are set for each segment, and creative concepts are automatically generated based on the prompts.

[0953] For example, you can use prompts like the following to generate different creative concepts for each segment:

[0954] "Generate a creative marketing concept for audience: Segment 1"

[0955] "Generate a creative marketing concept for audience: Segment 2"

[0956] The generated creative concept is displayed to the user via the terminal, allowing the user to check and use the marketing concept optimized for each segment quickly and efficiently.

[0957] As a specific example, if you use the target audience ID "example_id", the server may obtain the following attribute information:

[0958] 「age: 25, gender: female, location: Tokyo, interests: fashion, sports」

[0959] "age: 40, gender: male, location: Osaka, interests: technology, finance"

[0960] Clustering is performed based on this data and segmented as follows:

[0961] Segment 1: For young people

[0962] Segment 2: Middle-aged people

[0963] Then, for each, set the prompts to generate creative concepts as follows:

[0964] "Generate a creative marketing concept for audience: Young people"

[0965] "Generate a creative marketing concept for audience: middle-aged people"

[0966] The generated creative concept may look something like this:

[0967] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo"

[0968] "Innovative tech and finance solutions for middle-aged professionals in Osaka"

[0969] In this way, the server can effectively utilize the attribute information of the target audience, quickly generate high-quality creative concepts, and provide them in a format that is easy for users to use.

[0970] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0971] Step 1:

[0972] The user provides an API key.

[0973] Input: The user enters an API key.

[0974] What it does: Stores the user-provided API key on the server, allowing access to external data sources.

[0975] Output: An API key is saved on the server, granting access to the external data source.

[0976] Step 2:

[0977] The server retrieves the target audience data.

[0978] Input: Target audience ID (e.g. "example_id")

[0979] Processing: The server uses the target audience ID to obtain the target's demographic information (age, gender, region, interests, etc.) via API.

[0980] Output: The target audience's demographic information is retrieved to the server.

[0981] Step 3:

[0982] The server segments the audience data using clustering techniques.

[0983] Input: Attribute information of the target audience obtained

[0984] Processing: The server uses a clustering algorithm (e.g. K-Means) to group similar audiences based on their attributes.

[0985] Output: Segmented audience data.

[0986] Step 4:

[0987] The server generates creative concepts based on the segmented data.

[0988] Input: Segmented audience data

[0989] Processing: The server uses a natural language generation model (e.g., GPT-3) to generate creative concepts appropriate for each segment. For each segment, a prompt is set and a creative concept is generated based on the prompt.

[0990] Output: The generated creative concepts are saved on the server.

[0991] Step 5:

[0992] The server displays the generated creative concept on the terminal.

[0993] Input: Generated creative concept

[0994] Processing: The server sends the generated creative concept to the user's device.

[0995] Output: The creative concept is displayed on the user's device.

[0996] As a concrete example, we will show how to set a prompt sentence. For example, we set the following prompt for segment 1:

[0997] "Generate a creative marketing concept for audience: Young people"

[0998] A creative concept generated based on this prompt might be, for example, "Fashion-forward sportswear campaign targeting trendy young women in Tokyo." This creative concept is displayed on the user's device, allowing the user to review and use it.

[0999] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1000] This invention combines a system that acquires target audience attribute information and segments them using clustering technology with an emotion engine that recognizes user emotions, enabling the generation of more advanced marketing concepts. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[1001] System program processing overview

[1002] The system operates in the following stages:

[1003] 1. Set API key:

[1004] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[1005] 2. Obtaining target audience data:

[1006] Based on the specified target audience ID, the server obtains target attribute information (e.g., age, gender, region, interests, and emotional data) through the API, allowing the system to collect detailed data on the target users.

[1007] 3. Acquiring emotion data:

[1008] The server acquires the user's emotional data through an emotion engine, which uses one or more of voice recognition, facial expression recognition, and text analysis technologies to understand the user's emotional state.

[1009] 4. Integrating audience demographics and sentiment data:

[1010] The server integrates the acquired attribute information and emotional data and updates the user's profile based on this data.

[1011] 5. Audience segmentation:

[1012] The server segments users based on the integrated data using a clustering algorithm (KMeans clustering), which groups users with similar attributes, hobbies, and emotions.

[1013] 6. Creative concept generation:

[1014] The server generates prompts based on the segmented data. For each segment, it creates a prompt like "Generate a creative marketing concept for segment 1."

[1015] 7. Using Natural Language Generation Models:

[1016] The server-generated prompts are fed into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment.

[1017] 8. Output of generated concepts:

[1018] The creative concept generated by the device is displayed, allowing users to check the marketing concept optimized for each segment.

[1019] Specific examples

[1020] For example, a case where the user specifies the target audience ID "example_id" will be described.

[1021] 1. Obtaining target audience data:

[1022] The server receives data through the API, such as:

[1023] [

[1024] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"], "emotion": "happy"},

[1025] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"], "emotion": "neutral"},

[1026] ...

[1027] ]

[1028] 2. Acquiring emotion data:

[1029] The server uses an emotion engine to extract emotion data from the user's voice, facial expressions, and text, and adds it to each attribute information.

[1030] 3. Integrating audience demographics and sentiment data:

[1031] The server integrates the acquired attribute information and emotional data and creates an updated user profile based on them.

[1032] 4. Audience segmentation:

[1033] The server performs clustering based on the combined data, dividing users into five segments, for example:

[1034] Segment 1: [User 1, User 5, User 9]

[1035] Segment 2: [User 2, User 6, User 10]

[1036] ...

[1037] 5. Creative concept generation:

[1038] For each segment, the server inputs the following prompts into the NLG model:

[1039] "Generate a creative marketing concept for audience: [Segment 1]"

[1040] "Generate a creative marketing concept for audience: [Segment 2]"

[1041] ...

[1042] This generates the following concepts:

[1043] Segment 1: "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[1044] Segment 2: "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[1045] ...

[1046] 6. Output of generated concepts:

[1047] The device displays the generated creative concepts to the user, for example, "Trendy Sportswear Campaign" for Segment 1 and "Innovative Technology and Financial Solutions" for Segment 2.

[1048] This process flow allows users to quickly and efficiently generate creative concepts optimized for their target audience. The introduction of the emotion engine enables segmentation using more detailed user profiles, which is expected to lead to the generation of more effective marketing concepts.

[1049] The processing flow will be explained below.

[1050] Step 1:

[1051] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[1052] Step 2:

[1053] The server receives the target audience ID and retrieves the target audience's attribute information via API based on this ID. For example, it collects data such as age, gender, region, and interests based on the ID "example_id."

[1054] Step 3:

[1055] The server uses an emotion engine to obtain additional emotion data, which uses voice recognition, facial expression recognition, and text analysis to understand the user's emotional state, for example, by inputting facial expressions and voice through a webcam or microphone.

[1056] Step 4:

[1057] The server combines the acquired attribute information with the emotional data to create a detailed profile of the user, including, for example, the user's age, gender, region, interests, and emotional state such as "happy" or "neutral."

[1058] Step 5:

[1059] The server uses the aggregated data to segment users using a clustering algorithm (KMeans clustering). For example, it divides all users into five segments.

[1060] Step 6:

[1061] The server generates prompts for each segment based on the segmented data, for example, "Generate a creative marketing concept for segment 1."

[1062] Step 7:

[1063] The server-generated prompts are input into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment. For example, for segment 1, it generates a "sportswear campaign for trend-conscious young women living in Tokyo."

[1064] Step 8:

[1065] The server sends the generated creative concepts to the device and displays them to the user. For example, concepts such as "Fashion-forward sportswear campaign" are displayed for segment 1, and "Innovative technology and financial solutions" are displayed for segment 2.

[1066] This process flow allows users to quickly and efficiently generate creative concepts optimized for their target audience. The introduction of the emotion engine enables segmentation using more detailed user profiles, which is expected to lead to the generation of more effective marketing concepts.

[1067] Example 2

[1068] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1069] Conventional marketing systems have difficulty not only obtaining target audience attribute information but also utilizing user sentiment data. Furthermore, they lack the means to efficiently and effectively segment the obtained information and generate creative marketing concepts for each segment. This makes it difficult for marketers and advertising creators to quickly find inspiration, preventing them from maximizing the effectiveness of their marketing campaigns.

[1070] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring attribute information of the target audience, means for integrating the acquired attribute information and emotion data to update a user profile, means for segmenting the integrated data using a clustering technique, means for automatically generating a creative concept based on the segmented data, and means for displaying the generated creative concept. This enables effective segmentation based on a detailed profile of the target audience and rapid generation of a creative concept based on the segmented data.

[1071] "Target audience" refers to a group of people with specific attributes who are the target of marketing and advertising activities.

[1072] "Attribute information" refers to data that indicates the characteristics of your target audience, such as age, gender, region, interests, and emotional data.

[1073] "Emotion data" is data that indicates the emotional state of a user, obtained from voice, facial expression, text, etc.

[1074] "User profile" refers to detailed personal information that integrates demographic and emotional data of a target audience.

[1075] "Clustering technology" refers to a general algorithm that divides data into groups based on similarity, and includes KMeans clustering as an example here.

[1076] "Segmentation" refers to the use of clustering techniques to divide a target audience based on attribute information and emotional data.

[1077] "Creative Concept" refers to an idea or theme created for a specific marketing purpose.

[1078] "Generative AI model" refers to artificial intelligence technology that uses natural language processing technology to automatically generate text based on input prompts.

[1079] A "prompt" refers to a question or instruction input to a generative AI model.

[1080] A "database" refers to a collection of information that allows for efficient storage and retrieval of large amounts of data.

[1081] "Speech recognition" is a technology that analyzes voice data and converts it into text and emotions.

[1082] "Facial expression recognition" is a technology that analyzes facial expressions from image data and identifies the emotional state of a person.

[1083] "Text analysis" is a technology that analyzes text data and understands and classifies its content and sentiment.

[1084] This invention is a system that acquires attribute information of a target audience, segments them using clustering technology, and combines it with an emotion engine that recognizes user emotions to generate a creative concept. Specific embodiments of this invention are described below.

[1085] Hardware and software used

[1086] The implementation of this system utilizes the following hardware and software:

[1087] Server: Responsible for cloud-based data processing and storage. It operates as the core of the system, generating, processing, and managing various data.

[1088] Terminal: A device that provides an interface for users to access. This includes computers and smartphones.

[1089] Emotion engine: A tool such as Google Cloud Speech-to-Text or AWS Rekognition that analyzes a user's voice, facial expressions, and text to obtain emotional data.

[1090] Natural Language Generation Models: Tools that use generative AI models, such as OpenAI GPT-3, to generate creative concepts.

[1091] Clustering algorithm: An algorithm for clustering data (e.g., KMeans clustering) using Python's scikit-learn library.

[1092] Program processing overview

[1093] Obtaining target audience data

[1094] The server uses external APIs based on the target audience ID specified by the user to obtain audience attribute information. Target APIs include Facebook Graph API and Twitter API. The obtained data includes information such as age, gender, region, and interests.

[1095] Acquiring emotion data

[1096] The server acquires the user's emotional data using an emotion engine. The emotional data is extracted from the user's voice, facial expressions, and text. For example, Google Cloud Speech-to-Text is used to analyze the voice data and identify the emotion.

[1097] Integrating audience demographics and sentiment data

[1098] The server integrates the acquired attribute information and emotion data to update a detailed profile for each user, which is then stored in a database on the server.

[1099] Audience segmentation

[1100] The server performs clustering on the combined data, using the Python scikit-learn library and applying the KMeans clustering algorithm, which categorizes audiences into groups with common attributes and sentiments.

[1101] Creative concept generation

[1102] The server generates appropriate prompts for each segment and feeds them into the natural language generation model. The prompts have the following format:

[1103] "Generate a creative marketing concept for audience: [Segment 1]"

[1104] "Generate a creative marketing concept for audience: [Segment 2]"

[1105] This allows the generated creative concepts to be optimized for each segment.

[1106] Generative Concept Output

[1107] The device displays the generated creative concepts to the user. Specifically, the user interface displays a list of marketing concepts for each segment, including the following concepts:

[1108] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[1109] "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[1110] The above process flow allows users to quickly generate creative concepts that are effectively segmented for their target audience, and the introduction of an emotion engine makes it possible to make the most of detailed user profiles.

[1111] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1112] Step 1:

[1113] Setting an API key

[1114] The user enters their API key into the system settings screen. This is the input.

[1115] The server receives the user's API key and stores it as authentication information, which is the output.

[1116] Specifically, the user enters the API key into the web interface and clicks the "Save" button.

[1117] Step 2:

[1118] Obtaining target audience data

[1119] The server sends an HTTP request to the external API using the target audience ID "example_id" specified by the user. This is the input.

[1120] The server receives target audience attribute information (e.g., age, gender, region, interests) obtained from an external API. This is the output.

[1121] Specifically, the server executes an API request and retrieves the following JSON data:

[1122] json

[1123] [

[1124] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"], "emotion": "happy"},

[1125] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"], "emotion": "neutral"},

[1126] ...

[1127] ]

[1128] Step 3:

[1129] Acquiring emotion data

[1130] The server sends data to the emotion engine based on the collected attribute information, which becomes the input.

[1131] The server receives emotion data from an emotion engine (e.g., Google Cloud Speech-to-Text, AWS Rekognition) and integrates it into attribute information, which becomes the output.

[1132] Specifically, the server sends each audience member's social media posts and voice data to the emotion engine and obtains the emotion classification results.

[1133] Step 4:

[1134] Integrating audience demographics and sentiment data

[1135] The server integrates the acquired attribute information and emotion data to update the user profile, which serves as input.

[1136] The server stores the integrated detailed user profile in a database, which is the output.

[1137] Specifically, the server executes an INSERT or UPDATE query on a specific table in the database.

[1138] Step 5:

[1139] Audience segmentation

[1140] The server applies a clustering algorithm (e.g., KMeans clustering) based on the combined profile data, which is the input.

[1141] The server generates a clustering result, a segment for each audience, which is the output.

[1142] Specifically, we use the Python scikit-learn library to perform clustering. For example, we segment the data as follows:

[1143] json

[1144] Segment 1: [User 1, User 5, User 9]

[1145] Segment 2: [User 2, User 6, User 10]

[1146] Step 6:

[1147] Creative concept generation

[1148] The server generates a prompt based on the generated segment, which becomes the input.

[1149] The server sends prompts to a generative AI model (e.g., OpenAI GPT-3) to generate a creative concept, which is the output.

[1150] Specifically, it generates the following prompt:

[1151] "Generate a creative marketing concept for audience: [Segment 1]"

[1152] "Generate a creative marketing concept for audience: [Segment 2]"

[1153] Step 7:

[1154] Generative Concept Output

[1155] The device displays the generated creative concept to the user, which serves as input.

[1156] The terminal displays a list of marketing concepts for each segment on the user interface, which is the output.

[1157] Specifically, the UI displays the following concepts:

[1158] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[1159] "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[1160] Through these processing steps, users can quickly obtain creative concepts that are effectively segmented for their target audience. The introduction of an emotion engine makes it possible to make full use of detailed user profiles.

[1161] (Application example 2)

[1162] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1163] Conventional marketing systems based on target audience attribute information have the problem of difficulty in generating personalized advertisements and marketing concepts that take into account the user's emotional state. This makes it difficult to develop effective marketing strategies that accurately capture the target audience's emotional responses, potentially reducing marketing effectiveness.

[1164] 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.

[1165] In this invention, the server includes means for acquiring attribute information of the target audience, means for adding emotional information to the acquired attribute information, means for integrating the added attribute information and emotional information and segmenting using clustering technology, means for generating prompts for generating creative concepts based on the segmented data, and means for inputting the generated prompts into a natural language generation model to automatically generate creative concepts, thereby enabling the generation of personalized marketing concepts that reflect the emotional state of the target audience.

[1166] A "target audience" refers to a group of consumers who are likely to be interested in a particular product or service.

[1167] "Attribute information" refers to basic information such as a user's age, gender, region, and interests.

[1168] "Emotional information" refers to data that reflects the user's emotional state, and includes information obtained from voice, facial expressions, text analysis, etc.

[1169] "Clustering technology" refers to algorithms that group data based on similarities or patterns.

[1170] "Segmentation" refers to the process of dividing users into groups based on attributes or emotional states using collected data.

[1171] A "prompt" refers to an instruction or question that is input into a natural language generation model.

[1172] "Natural language generation model" refers to a machine learning model for understanding and generating human language, specifically including generative AI models such as GPT.

[1173] "Creative Concepts" refers to the creative ideas and strategies generated for marketing and advertising campaigns.

[1174] A system for implementing this invention acquires attribute information and emotion information of a target audience, integrates and segments them, and generates creative concepts using a generative AI model. The system configuration includes a server, an attribute information acquisition API, an emotion information acquisition engine, a clustering algorithm, and a natural language generation model (i.e., a generative AI model).

[1175] Hardware and software configuration

[1176] Hardware

[1177] Server: Collects, processes, analyzes data, and manages the generated creative concepts.

[1178] software

[1179] The main software used is as follows:

[1180] Python: A programming language for creating entire programs.

[1181] The requests library: Used to retrieve data through an API.

[1182] sklearn library: Used for clustering algorithms (KMeans clustering).

[1183] The transformers library: used for text generation using natural language generation models (e.g., GPT-2).

[1184] Data processing and calculation

[1185] Acquiring attribute and emotion information

[1186] The server first obtains the target audience's demographic information, including basic data such as age, gender, region, and interests. Then, it obtains the user's emotional state through an emotional information acquisition engine. This emotional information is collected using one or more technologies: voice recognition, facial expression recognition, and text analysis.

[1187] Data Integration and Clustering

[1188] The acquired attribute information and emotion information are integrated on the server to create a user profile, and then a clustering algorithm (KMeans clustering) is used to segment users based on similar attributes, interests, and emotional states.

[1189] Creative concept generation

[1190] Based on the segmented data, the server uses a generative AI model to create prompts to generate creative concepts, such as "Generate a creative marketing concept for the following audience: [Segment 1]." The prompts are then fed into a natural language generation model to generate the optimal creative concepts for each segment.

[1191] Specific examples

[1192] For example, the prompt for segment 1 is:

[1193] "Generate a creative marketing concept for the following audience: [{'age': 25, 'gender': 'female', 'location': 'Tokyo', 'interests': ['fashion', 'sports'], 'emotion': 'happy'}]"

[1194] By feeding this prompt into a natural language generation model, we can generate creative concepts like this:

[1195] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[1196] This makes it possible to effectively generate personalized marketing concepts that reflect the emotional state of the target audience.

[1197] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1198] Step 1:

[1199] The server uses a means to obtain target audience attribute information to obtain attribute information such as the user's age, gender, region, and interests from an external API. This process makes an API request based on the specified target audience ID and receives attribute information in JSON format. The input is the target audience ID, and the output is JSON data containing attribute information.

[1200] Step 2:

[1201] The server uses the emotion engine to add emotional information to the acquired user attribute information. In this process, the emotion engine analyzes the user's voice, facial expression, and text data, and adds each user's emotional state as data. The input is the attribute information acquired in step 1, and the output is updated user data with the added emotional information.

[1202] Step 3:

[1203] The server integrates the attribute information and emotion information and segments users using clustering techniques (KMeans clustering). In this process, the attribute information and emotion information are input into a clustering algorithm to group users based on similar attributes, interests, and emotional states. The input is the user data integrated in step 2, and the output is user data categorized into multiple segments.

[1204] Step 4:

[1205] The server creates prompts for generating creative concepts based on the segmented data. This process generates instructions for generating marketing concepts for each segment. The input is the segment data generated in step 3, and the output is the prompt.

[1206] Step 5:

[1207] The server inputs the generated prompt into a natural language generation model (e.g., GPT-2) to automatically generate creative concepts. In this process, the generative AI model receives the prompt and generates marketing concepts in natural language. The input is the prompt sentence generated in step 4, and the output is a creative concept appropriate for each segment.

[1208] Step 6:

[1209] The device displays the generated creative concept to the user. In this process, the device displays the creative concept received from the server on the screen for the user to view. The input is the creative concept generated in step 5, and the output is a viewable representation for the user.

[1210] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1211] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1212] 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.

[1213] [Fourth embodiment]

[1214] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1215] 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.

[1216] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1217] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1218] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1219] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1220] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1221] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1222] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1223] 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.

[1224] 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.

[1225] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1226] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1227] The present invention relates to a system that acquires target audience attribute information, segments them using clustering technology, and automatically generates creative concepts for each segment. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[1228] System program processing overview

[1229] The system operates in the following stages:

[1230] 1. Set API key:

[1231] The user provides the system with their API key, which allows the system to access external data sources.

[1232] 2. Obtaining target audience data:

[1233] The server retrieves target attribute information (e.g., age, gender, region, interests) through the API based on the specified target audience ID, allowing the system to collect detailed data on the target users.

[1234] 3. Audience segmentation:

[1235] The server segments the acquired user data using a clustering algorithm, which groups users with similar attributes and interests.

[1236] 4. Creative concept generation:

[1237] The server automatically generates creative concepts based on the segmented data, specifically using a natural language generation model (e.g., GPT-3) to generate concepts appropriate for each segment.

[1238] 5. Output of generated concepts:

[1239] The creative concept generated by the device is displayed, allowing users to check the marketing concept optimized for each segment.

[1240] Specific examples

[1241] For example, a case where the user specifies the target audience ID "example_id" will be described.

[1242] 1. Obtaining target audience data:

[1243] The server receives data through the API, such as:

[1244] [

[1245] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"]},

[1246] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"]},

[1247] ...

[1248] ]

[1249] 2. Audience segmentation:

[1250] The server uses this data to perform clustering, dividing users into five segments, for example:

[1251] Segment 1: [User 1, User 5, User 9]

[1252] Segment 2: [User 2, User 6, User 10]

[1253] ...

[1254] 3. Creative concept generation:

[1255] The server uses a natural language generation model for each segment and inputs a prompt like this:

[1256] "Generate a creative marketing concept for audience: [Segment 1]"

[1257] "Generate a creative marketing concept for audience: [Segment 2]"

[1258] ...

[1259] This generates the following concepts:

[1260] Segment 1: "Fashion-forward sportswear campaign targeting trendy young women in Tokyo."

[1261] Segment 2: "Innovative tech and finance solutions for middle-aged professionals in Osaka."

[1262] ...

[1263] 4. Output of generated concepts:

[1264] The device displays the generated creative concepts to the user. For example, Segment 1 displays a "trend campaign for young people," while Segment 2 displays a "health promotion campaign for seniors."

[1265] In this way, the system can quickly and efficiently generate creative concepts optimized for the target audience, helping to inspire marketers and advertising creators.

[1266] The processing flow will be explained below.

[1267] Step 1:

[1268] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[1269] Step 2:

[1270] The server receives the target audience ID and retrieves the target audience's attribute information via API based on this ID. For example, it collects data such as age, gender, region, and interests based on the ID "example_id."

[1271] Step 3:

[1272] The server processes the acquired user data and extracts the necessary attribute information (age, gender, region, interests).

[1273] Step 4:

[1274] Based on the attribute information extracted by the server, users are segmented using a clustering algorithm (KMeans clustering). For example, all users are divided into five segments.

[1275] Step 5:

[1276] The server generates prompts based on the segmented data. For each segment, it creates a prompt like "Generate a creative marketing concept for segment 1."

[1277] Step 6:

[1278] The server-generated prompts are fed into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment.

[1279] Step 7:

[1280] The server sends the generated creative concepts to the device and displays them to the user. For example, concepts such as "Trendy Sportswear Campaign" are displayed for segment 1, and "Innovative Technology and Financial Solutions" are displayed for segment 2.

[1281] This process flow allows users to quickly and efficiently arrive at creative concepts optimized for their target audience.

[1282] Example 1

[1283] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1284] In current marketing and advertising production, it is difficult to quickly generate creative concepts that match the target audience. In particular, there is a need to streamline the process from segmentation based on attribute information to generating creative concepts. Conventional methods require manual data analysis and creative concept development, which requires a great deal of time and effort. Therefore, there is a need for a system that can automatically generate creative concepts optimized for the target audience.

[1285] 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.

[1286] In this invention, the server includes means for acquiring attribute information of the target audience, means for accessing a data source based on the acquired attribute information, means for segmenting the acquired attribute information using a clustering technique, means for automatically generating a creative concept using a generative AI model based on the segmented data, and means for outputting the generated creative concept to a user's terminal, thereby enabling the rapid and efficient generation of a creative concept suited to the target audience.

[1287] A "target audience" is a group of consumers who are likely to be interested in a particular product or service.

[1288] "Attribute information" is information that characterizes the target audience, such as age, gender, region, and interests.

[1289] "Data Source" is an external system or platform used to collect demographic information about your target audience.

[1290] A "clustering technique" is a technique for dividing data into groups, and classifying data points with similar characteristics into the same group.

[1291] "Segmentation" is the process of dividing a target audience into multiple groups based on attribute information obtained using clustering techniques.

[1292] A "generative AI model" is a model that uses artificial intelligence techniques to generate natural language or other forms of information based on specific input data.

[1293] A "creative concept" is a creative idea or theme that communicates an effective advertising or marketing message to a target audience.

[1294] "User's device" means a device such as a computer or smartphone used to display creative concepts generated by the system.

[1295] A "prompt" is text that is input into a generative AI model, from which a creative concept is generated.

[1296] Above are definitions of important terms.

[1297] The present invention relates to a system that acquires target audience attribute information, segments them using clustering technology, and automatically generates creative concepts for each segment. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[1298] The system is configured as follows:

[1299] First, the user provides the system with their API key, which allows the system to access external data sources. The user completes this process by entering the API key in the settings screen and saving it.

[1300] The server then sends an API request using the target audience ID specified by the user. The API request retrieves target audience attribute information such as age, gender, region, and interests. This data is obtained from a marketing platform such as the "Audience Insights API."

[1301] Based on the acquired attribute information, the server uses a clustering algorithm to segment users. For example, Scikit-learn's K-means clustering algorithm is used to cluster the data. Through clustering, users with similar attributes and interests are grouped into the same segment.

[1302] Next, the server generates creative concepts based on the segmented data using the generative AI model GPT-3. Specifically, it generates appropriate prompts for each segment and inputs these prompts into GPT-3. Examples of prompts include:

[1303] "Create a creative marketing concept for audience: [Segment 1]"

[1304] "Create a creative marketing concept for audience: [Segment 2]"

[1305] This automatically generates creative concepts for each segment: for example, for segment 1, a concept like "Fashion-forward sportswear campaign targeting trendy young women in Tokyo" might be generated, and for segment 2, a concept like "Innovative tech and finance solutions for middle-aged professionals in Osaka" might be generated.

[1306] Finally, the generated creative concepts are displayed on the user's device, allowing the user to check the marketing concepts optimized for each segment. Specifically, they are displayed in list format on the dashboard of the web application.

[1307] In this way, the system streamlines the work of marketers and advertising creators, enabling them to quickly provide creative concepts that suit the target audience.

[1308] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1309] Step 1:

[1310] The user provides the API key to the system.

[1311] Input: The user enters the API key into the settings screen and clicks the "Save" button.

[1312] How it works: The user navigates to the settings screen, enters their API key in the provided field, and clicks the "Save" button, which saves the API key as a credential in the system.

[1313] Output: The system is able to access external data sources and an API key is stored in the system.

[1314] Step 2:

[1315] The server accesses the data source based on the target audience ID.

[1316] Input: User-specified target audience ID.

[1317] How it works: The server generates an API request and sends the target audience ID as a parameter to an external data source, specifically calling the marketing platform's API to retrieve the target audience's attributes.

[1318] Output: The acquired attribute information (e.g., age, gender, region, interests) is stored in a database.

[1319] Step 3:

[1320] The server uses a clustering technique to segment the attribute information.

[1321] Input: The target audience demographic information obtained.

[1322] How it works: The server applies a clustering algorithm (e.g., Scikit-learn's K-means clustering) to classify the target audience into segments based on their attributes, e.g., grouping users with similar interests or attributes.

[1323] Output: Segmented target audience data is generated.

[1324] Step 4:

[1325] The server uses generative AI models to generate creative concepts for each segment.

[1326] Input: Segmented target audience data.

[1327] How it works: The server creates an appropriate prompt for each segment and inputs it into a generative AI model (e.g., GPT-3). An example of a specific prompt might be, "Create a creative marketing concept for audience: [Segment 1]."

[1328] Output: A creative concept optimized for each segment is generated.

[1329] Step 5:

[1330] The terminal outputs the generated creative concept to the user.

[1331] Input: Generated creative concepts.

[1332] How it works: The device displays the generated creative concepts. Specifically, they are displayed in a list format on the web application dashboard. The user can access the dashboard to view the generated concepts.

[1333] Output: Users can visualize creative concepts optimized for each segment.

[1334] (Application example 1)

[1335] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1336] Conventional creative concept generation systems have been unable to effectively utilize the diverse attribute information of target audiences, resulting in the time-consuming and labor-intensive process of segmenting and generating creative concepts. Furthermore, the quality of the generated creative concepts often lacks uniformity, potentially reducing marketing efficiency. There is a need for a system that can solve these issues and generate high-quality creative concepts quickly.

[1337] 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.

[1338] In this invention, the server includes means for acquiring attribute information of the target audience, means for segmenting the acquired attribute information using clustering technology, means for automatically generating a creative concept based on the segmented data, and means for displaying the generated creative concept on a terminal. This allows the target audience attribute information to be effectively utilized to quickly and efficiently generate a creative concept, enabling marketers and advertising creators to quickly obtain high-quality concepts.

[1339] A "target audience" is a group of recipients with specific attributes that you focus on when conducting a particular marketing or promotional activity.

[1340] "Attribute information" refers to characteristic data about the target audience, such as age, gender, region, and interests.

[1341] "Clustering technology" is a machine learning technique for grouping data with similar characteristics.

[1342] "Segmentation" is the process of grouping target audience demographic information using clustering techniques.

[1343] A "creative concept" is an idea for an advertising or marketing strategy generated for a specific target audience.

[1344] A "natural language generation model" is an artificial intelligence model for generating natural language text based on given data and prompts.

[1345] A "Device" is a device, such as a computer or smartphone, that a User uses to display Creative Concepts or other information.

[1346] A system for implementing the present invention acquires attribute information of a target audience, segments them using clustering technology, automatically generates creative concepts for each segment, and displays the generated concepts on a terminal.

[1347] The operation of the system is as follows.

[1348] First, the user provides the server with an API key, which allows the server to access external data sources. Next, the server retrieves target demographic information via the API based on the target audience ID. This demographic information includes data such as age, gender, region, and interests.

[1349] The server segments the data based on the acquired attribute information using a clustering algorithm, such as the K-Means algorithm, which groups audiences with similar attributes.

[1350] Based on the segmented data, the server uses a natural language generation model (e.g., GPT-3) to generate creative concepts appropriate for each segment. In this generation process, prompts are set for each segment, and creative concepts are automatically generated based on the prompts.

[1351] For example, you can use prompts like the following to generate different creative concepts for each segment:

[1352] "Generate a creative marketing concept for audience: Segment 1"

[1353] "Generate a creative marketing concept for audience: Segment 2"

[1354] The generated creative concept is displayed to the user via the terminal, allowing the user to check and use the marketing concept optimized for each segment quickly and efficiently.

[1355] As a specific example, if you use the target audience ID "example_id", the server may obtain the following attribute information:

[1356] 「age: 25, gender: female, location: Tokyo, interests: fashion, sports」

[1357] "age: 40, gender: male, location: Osaka, interests: technology, finance"

[1358] Clustering is performed based on this data and segmented as follows:

[1359] Segment 1: For young people

[1360] Segment 2: Middle-aged people

[1361] Then, for each, set the prompts to generate creative concepts as follows:

[1362] "Generate a creative marketing concept for audience: Young people"

[1363] "Generate a creative marketing concept for audience: middle-aged people"

[1364] The generated creative concept may look something like this:

[1365] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo"

[1366] "Innovative tech and finance solutions for middle-aged professionals in Osaka"

[1367] In this way, the server can effectively utilize the attribute information of the target audience, quickly generate high-quality creative concepts, and provide them in a format that is easy for users to use.

[1368] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1369] Step 1:

[1370] The user provides an API key.

[1371] Input: The user enters an API key.

[1372] What it does: Stores the user-provided API key on the server, allowing access to external data sources.

[1373] Output: An API key is saved on the server, granting access to the external data source.

[1374] Step 2:

[1375] The server retrieves the target audience data.

[1376] Input: Target audience ID (e.g. "example_id")

[1377] Processing: The server uses the target audience ID to obtain the target's demographic information (age, gender, region, interests, etc.) via API.

[1378] Output: The target audience's demographic information is retrieved to the server.

[1379] Step 3:

[1380] The server segments the audience data using clustering techniques.

[1381] Input: Attribute information of the target audience obtained

[1382] Processing: The server uses a clustering algorithm (e.g. K-Means) to group similar audiences based on their attributes.

[1383] Output: Segmented audience data.

[1384] Step 4:

[1385] The server generates creative concepts based on the segmented data.

[1386] Input: Segmented audience data

[1387] Processing: The server uses a natural language generation model (e.g., GPT-3) to generate creative concepts appropriate for each segment. For each segment, a prompt is set and a creative concept is generated based on the prompt.

[1388] Output: The generated creative concepts are saved on the server.

[1389] Step 5:

[1390] The server displays the generated creative concept on the terminal.

[1391] Input: Generated creative concept

[1392] Processing: The server sends the generated creative concept to the user's device.

[1393] Output: The creative concept is displayed on the user's device.

[1394] As a concrete example, we will show how to set a prompt sentence. For example, we set the following prompt for segment 1:

[1395] "Generate a creative marketing concept for audience: Young people"

[1396] A creative concept generated based on this prompt might be, for example, "Fashion-forward sportswear campaign targeting trendy young women in Tokyo." This creative concept is displayed on the user's device, allowing the user to review and use it.

[1397] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1398] This invention combines a system that acquires target audience attribute information and segments them using clustering technology with an emotion engine that recognizes user emotions, enabling the generation of more advanced marketing concepts. This system provides marketers and advertising creators with a means to quickly and efficiently obtain creative inspiration.

[1399] System program processing overview

[1400] The system operates in the following stages:

[1401] 1. Set API key:

[1402] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[1403] 2. Obtaining target audience data:

[1404] Based on the specified target audience ID, the server obtains target attribute information (e.g., age, gender, region, interests, and emotional data) through the API, allowing the system to collect detailed data on the target users.

[1405] 3. Acquiring emotion data:

[1406] The server acquires the user's emotional data through an emotion engine, which uses one or more of voice recognition, facial expression recognition, and text analysis technologies to understand the user's emotional state.

[1407] 4. Integrating audience demographics and sentiment data:

[1408] The server integrates the acquired attribute information and emotional data and updates the user's profile based on this data.

[1409] 5. Audience segmentation:

[1410] The server segments users based on the integrated data using a clustering algorithm (KMeans clustering), which groups users with similar attributes, hobbies, and emotions.

[1411] 6. Creative concept generation:

[1412] The server generates prompts based on the segmented data. For each segment, it creates a prompt like "Generate a creative marketing concept for segment 1."

[1413] 7. Using Natural Language Generation Models:

[1414] The server-generated prompts are fed into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment.

[1415] 8. Output of generated concepts:

[1416] The creative concept generated by the device is displayed, allowing users to check the marketing concept optimized for each segment.

[1417] Specific examples

[1418] For example, a case where the user specifies the target audience ID "example_id" will be described.

[1419] 1. Obtaining target audience data:

[1420] The server receives data through the API, such as:

[1421] [

[1422] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"], "emotion": "happy"},

[1423] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"], "emotion": "neutral"},

[1424] ...

[1425] ]

[1426] 2. Acquiring emotion data:

[1427] The server uses an emotion engine to extract emotion data from the user's voice, facial expressions, and text, and adds it to each attribute information.

[1428] 3. Integrating audience demographics and sentiment data:

[1429] The server integrates the acquired attribute information and emotional data and creates an updated user profile based on them.

[1430] 4. Audience segmentation:

[1431] The server performs clustering based on the combined data, dividing users into five segments, for example:

[1432] Segment 1: [User 1, User 5, User 9]

[1433] Segment 2: [User 2, User 6, User 10]

[1434] ...

[1435] 5. Creative concept generation:

[1436] For each segment, the server inputs the following prompts into the NLG model:

[1437] "Generate a creative marketing concept for audience: [Segment 1]"

[1438] "Generate a creative marketing concept for audience: [Segment 2]"

[1439] ...

[1440] This generates the following concepts:

[1441] Segment 1: "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[1442] Segment 2: "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[1443] ...

[1444] 6. Output of generated concepts:

[1445] The device displays the generated creative concepts to the user, for example, "Trendy Sportswear Campaign" for Segment 1 and "Innovative Technology and Financial Solutions" for Segment 2.

[1446] This process flow allows users to quickly and efficiently generate creative concepts optimized for their target audience. The introduction of the emotion engine enables segmentation using more detailed user profiles, which is expected to lead to the generation of more effective marketing concepts.

[1447] The processing flow will be explained below.

[1448] Step 1:

[1449] The user provides their API key to the system, which allows the server to authenticate to the external data source and retrieve data.

[1450] Step 2:

[1451] The server receives the target audience ID and retrieves the target audience's attribute information via API based on this ID. For example, it collects data such as age, gender, region, and interests based on the ID "example_id."

[1452] Step 3:

[1453] The server uses an emotion engine to obtain additional emotion data, which uses voice recognition, facial expression recognition, and text analysis to understand the user's emotional state, for example, by inputting facial expressions and voice through a webcam or microphone.

[1454] Step 4:

[1455] The server combines the acquired attribute information with the emotional data to create a detailed profile of the user, including, for example, the user's age, gender, region, interests, and emotional state such as "happy" or "neutral."

[1456] Step 5:

[1457] The server uses the aggregated data to segment users using a clustering algorithm (KMeans clustering). For example, it divides all users into five segments.

[1458] Step 6:

[1459] The server generates prompts for each segment based on the segmented data, for example, "Generate a creative marketing concept for segment 1."

[1460] Step 7:

[1461] The server-generated prompts are input into a natural language generation model (e.g., GPT-3) to automatically generate creative concepts appropriate for each segment. For example, for segment 1, it generates a "sportswear campaign for trend-conscious young women living in Tokyo."

[1462] Step 8:

[1463] The server sends the generated creative concepts to the device and displays them to the user. For example, concepts such as "Fashion-forward sportswear campaign" are displayed for segment 1, and "Innovative technology and financial solutions" are displayed for segment 2.

[1464] This process flow allows users to quickly and efficiently generate creative concepts optimized for their target audience. The introduction of the emotion engine enables segmentation using more detailed user profiles, which is expected to lead to the generation of more effective marketing concepts.

[1465] Example 2

[1466] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1467] Conventional marketing systems have difficulty not only obtaining target audience attribute information but also utilizing user sentiment data. Furthermore, they lack the means to efficiently and effectively segment the obtained information and generate creative marketing concepts for each segment. This makes it difficult for marketers and advertising creators to quickly find inspiration, preventing them from maximizing the effectiveness of their marketing campaigns.

[1468] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring attribute information of the target audience, means for integrating the acquired attribute information and emotion data to update a user profile, means for segmenting the integrated data using a clustering technique, means for automatically generating a creative concept based on the segmented data, and means for displaying the generated creative concept. This enables effective segmentation based on a detailed profile of the target audience and rapid generation of a creative concept based on the segmented data.

[1469] "Target audience" refers to a group of people with specific attributes who are the target of marketing and advertising activities.

[1470] "Attribute information" refers to data that indicates the characteristics of your target audience, such as age, gender, region, interests, and emotional data.

[1471] "Emotion data" is data that indicates the emotional state of a user, obtained from voice, facial expression, text, etc.

[1472] "User profile" refers to detailed personal information that integrates demographic and emotional data of a target audience.

[1473] "Clustering technology" refers to a general algorithm that divides data into groups based on similarity, and includes KMeans clustering as an example here.

[1474] "Segmentation" refers to the use of clustering techniques to divide a target audience based on attribute information and emotional data.

[1475] "Creative Concept" refers to an idea or theme created for a specific marketing purpose.

[1476] "Generative AI model" refers to artificial intelligence technology that uses natural language processing technology to automatically generate text based on input prompts.

[1477] A "prompt" refers to a question or instruction input to a generative AI model.

[1478] A "database" refers to a collection of information that allows for efficient storage and retrieval of large amounts of data.

[1479] "Speech recognition" is a technology that analyzes voice data and converts it into text and emotions.

[1480] "Facial expression recognition" is a technology that analyzes facial expressions from image data and identifies the emotional state of a person.

[1481] "Text analysis" is a technology that analyzes text data and understands and classifies its content and sentiment.

[1482] This invention is a system that acquires attribute information of a target audience, segments them using clustering technology, and combines it with an emotion engine that recognizes user emotions to generate a creative concept. Specific embodiments of this invention are described below.

[1483] Hardware and software used

[1484] The implementation of this system utilizes the following hardware and software:

[1485] Server: Responsible for cloud-based data processing and storage. It operates as the core of the system, generating, processing, and managing various data.

[1486] Terminal: A device that provides an interface for users to access. This includes computers and smartphones.

[1487] Emotion engine: A tool such as Google Cloud Speech-to-Text or AWS Rekognition that analyzes a user's voice, facial expressions, and text to obtain emotional data.

[1488] Natural Language Generation Models: Tools that use generative AI models, such as OpenAI GPT-3, to generate creative concepts.

[1489] Clustering algorithm: An algorithm for clustering data (e.g., KMeans clustering) using Python's scikit-learn library.

[1490] Program processing overview

[1491] Obtaining target audience data

[1492] The server uses external APIs based on the target audience ID specified by the user to obtain audience attribute information. Target APIs include Facebook Graph API and Twitter API. The obtained data includes information such as age, gender, region, and interests.

[1493] Acquiring emotion data

[1494] The server acquires the user's emotional data using an emotion engine. The emotional data is extracted from the user's voice, facial expressions, and text. For example, Google Cloud Speech-to-Text is used to analyze the voice data and identify the emotion.

[1495] Integrating audience demographics and sentiment data

[1496] The server integrates the acquired attribute information and emotion data to update a detailed profile for each user, which is then stored in a database on the server.

[1497] Audience segmentation

[1498] The server performs clustering on the combined data, using the Python scikit-learn library and applying the KMeans clustering algorithm, which categorizes audiences into groups with common attributes and sentiments.

[1499] Creative concept generation

[1500] The server generates appropriate prompts for each segment and feeds them into the natural language generation model. The prompts have the following format:

[1501] "Generate a creative marketing concept for audience: [Segment 1]"

[1502] "Generate a creative marketing concept for audience: [Segment 2]"

[1503] This allows the generated creative concepts to be optimized for each segment.

[1504] Generative Concept Output

[1505] The device displays the generated creative concepts to the user. Specifically, the user interface displays a list of marketing concepts for each segment, including the following concepts:

[1506] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[1507] "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[1508] The above process flow allows users to quickly generate creative concepts that are effectively segmented for their target audience, and the introduction of an emotion engine makes it possible to make the most of detailed user profiles.

[1509] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1510] Step 1:

[1511] Setting an API key

[1512] The user enters their API key into the system settings screen. This is the input.

[1513] The server receives the user's API key and stores it as authentication information, which is the output.

[1514] Specifically, the user enters the API key into the web interface and clicks the "Save" button.

[1515] Step 2:

[1516] Obtaining target audience data

[1517] The server sends an HTTP request to the external API using the target audience ID "example_id" specified by the user. This is the input.

[1518] The server receives target audience attribute information (e.g., age, gender, region, interests) obtained from an external API. This is the output.

[1519] Specifically, the server executes an API request and retrieves the following JSON data:

[1520] json

[1521] [

[1522] {"age": 25, "gender": "female", "location": "Tokyo", "interests": ["fashion", "sports"], "emotion": "happy"},

[1523] {"age": 40, "gender": "male", "location": "Osaka", "interests": ["technology", "finance"], "emotion": "neutral"},

[1524] ...

[1525] ]

[1526] Step 3:

[1527] Acquiring emotion data

[1528] The server sends data to the emotion engine based on the collected attribute information, which becomes the input.

[1529] The server receives emotion data from an emotion engine (e.g., Google Cloud Speech-to-Text, AWS Rekognition) and integrates it into attribute information, which becomes the output.

[1530] Specifically, the server sends each audience member's social media posts and voice data to the emotion engine and obtains the emotion classification results.

[1531] Step 4:

[1532] Integrating audience demographics and sentiment data

[1533] The server integrates the acquired attribute information and emotion data to update the user profile, which serves as input.

[1534] The server stores the integrated detailed user profile in a database, which is the output.

[1535] Specifically, the server executes an INSERT or UPDATE query on a specific table in the database.

[1536] Step 5:

[1537] Audience segmentation

[1538] The server applies a clustering algorithm (e.g., KMeans clustering) based on the combined profile data, which is the input.

[1539] The server generates a clustering result, a segment for each audience, which is the output.

[1540] Specifically, we use the Python scikit-learn library to perform clustering. For example, we segment the data as follows:

[1541] json

[1542] Segment 1: [User 1, User 5, User 9]

[1543] Segment 2: [User 2, User 6, User 10]

[1544] Step 6:

[1545] Creative concept generation

[1546] The server generates a prompt based on the generated segment, which becomes the input.

[1547] The server sends prompts to a generative AI model (e.g., OpenAI GPT-3) to generate a creative concept, which is the output.

[1548] Specifically, it generates the following prompt:

[1549] "Generate a creative marketing concept for audience: [Segment 1]"

[1550] "Generate a creative marketing concept for audience: [Segment 2]"

[1551] Step 7:

[1552] Generative Concept Output

[1553] The device displays the generated creative concept to the user, which serves as input.

[1554] The terminal displays a list of marketing concepts for each segment on the user interface, which is the output.

[1555] Specifically, the UI displays the following concepts:

[1556] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[1557] "Innovative tech and finance solutions for middle-aged professionals in Osaka who are feeling neutral."

[1558] Through these processing steps, users can quickly obtain creative concepts that are effectively segmented for their target audience. The introduction of an emotion engine makes it possible to make full use of detailed user profiles.

[1559] (Application example 2)

[1560] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1561] Conventional marketing systems based on target audience attribute information have the problem of difficulty in generating personalized advertisements and marketing concepts that take into account the user's emotional state. This makes it difficult to develop effective marketing strategies that accurately capture the target audience's emotional responses, potentially reducing marketing effectiveness.

[1562] 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.

[1563] In this invention, the server includes means for acquiring attribute information of the target audience, means for adding emotional information to the acquired attribute information, means for integrating the added attribute information and emotional information and segmenting using clustering technology, means for generating prompts for generating creative concepts based on the segmented data, and means for inputting the generated prompts into a natural language generation model to automatically generate creative concepts, thereby enabling the generation of personalized marketing concepts that reflect the emotional state of the target audience.

[1564] A "target audience" refers to a group of consumers who are likely to be interested in a particular product or service.

[1565] "Attribute information" refers to basic information such as a user's age, gender, region, and interests.

[1566] "Emotional information" refers to data that reflects the user's emotional state, and includes information obtained from voice, facial expressions, text analysis, etc.

[1567] "Clustering technology" refers to algorithms that group data based on similarities or patterns.

[1568] "Segmentation" refers to the process of dividing users into groups based on attributes or emotional states using collected data.

[1569] A "prompt" refers to an instruction or question that is input into a natural language generation model.

[1570] "Natural language generation model" refers to a machine learning model for understanding and generating human language, specifically including generative AI models such as GPT.

[1571] "Creative Concepts" refers to the creative ideas and strategies generated for marketing and advertising campaigns.

[1572] A system for implementing this invention acquires attribute information and emotion information of a target audience, integrates and segments them, and generates creative concepts using a generative AI model. The system configuration includes a server, an attribute information acquisition API, an emotion information acquisition engine, a clustering algorithm, and a natural language generation model (i.e., a generative AI model).

[1573] Hardware and software configuration

[1574] Hardware

[1575] Server: Collects, processes, analyzes data, and manages the generated creative concepts.

[1576] software

[1577] The main software used is as follows:

[1578] Python: A programming language for creating entire programs.

[1579] The requests library: Used to retrieve data through an API.

[1580] sklearn library: Used for clustering algorithms (KMeans clustering).

[1581] The transformers library: used for text generation using natural language generation models (e.g., GPT-2).

[1582] Data processing and calculation

[1583] Acquiring attribute and emotion information

[1584] The server first obtains the target audience's demographic information, including basic data such as age, gender, region, and interests. Then, it obtains the user's emotional state through an emotional information acquisition engine. This emotional information is collected using one or more technologies: voice recognition, facial expression recognition, and text analysis.

[1585] Data Integration and Clustering

[1586] The acquired attribute information and emotion information are integrated on the server to create a user profile, and then a clustering algorithm (KMeans clustering) is used to segment users based on similar attributes, interests, and emotional states.

[1587] Creative concept generation

[1588] Based on the segmented data, the server uses a generative AI model to create prompts to generate creative concepts, such as "Generate a creative marketing concept for the following audience: [Segment 1]." The prompts are then fed into a natural language generation model to generate the optimal creative concepts for each segment.

[1589] Specific examples

[1590] For example, the prompt for segment 1 is:

[1591] "Generate a creative marketing concept for the following audience: [{'age': 25, 'gender': 'female', 'location': 'Tokyo', 'interests': ['fashion', 'sports'], 'emotion': 'happy'}]"

[1592] By feeding this prompt into a natural language generation model, we can generate creative concepts like this:

[1593] "Fashion-forward sportswear campaign targeting trendy young women in Tokyo who are feeling happy."

[1594] This makes it possible to effectively generate personalized marketing concepts that reflect the emotional state of the target audience.

[1595] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1596] Step 1:

[1597] The server uses a means to obtain target audience attribute information to obtain attribute information such as the user's age, gender, region, and interests from an external API. This process makes an API request based on the specified target audience ID and receives attribute information in JSON format. The input is the target audience ID, and the output is JSON data containing attribute information.

[1598] Step 2:

[1599] The server uses the emotion engine to add emotional information to the acquired user attribute information. In this process, the emotion engine analyzes the user's voice, facial expression, and text data, and adds each user's emotional state as data. The input is the attribute information acquired in step 1, and the output is updated user data with the added emotional information.

[1600] Step 3:

[1601] The server integrates the attribute information and emotion information and segments users using clustering techniques (KMeans clustering). In this process, the attribute information and emotion information are input into a clustering algorithm to group users based on similar attributes, interests, and emotional states. The input is the user data integrated in step 2, and the output is user data categorized into multiple segments.

[1602] Step 4:

[1603] The server creates prompts for generating creative concepts based on the segmented data. This process generates instructions for generating marketing concepts for each segment. The input is the segment data generated in step 3, and the output is the prompt.

[1604] Step 5:

[1605] The server inputs the generated prompt into a natural language generation model (e.g., GPT-2) to automatically generate creative concepts. In this process, the generative AI model receives the prompt and generates marketing concepts in natural language. The input is the prompt sentence generated in step 4, and the output is a creative concept appropriate for each segment.

[1606] Step 6:

[1607] The device displays the generated creative concept to the user. In this process, the device displays the creative concept received from the server on the screen for the user to view. The input is the creative concept generated in step 5, and the output is a viewable representation for the user.

[1608] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding 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.

[1609] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1610] 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 robot 414.

[1611] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1612] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1613] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1614] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1615] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1616] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1617] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1618] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1619] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1620] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1621] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1622] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1623] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1624] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1625] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1626] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1627] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1628] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1629] The following is further disclosed regarding the above embodiment.

[1630] (Claim 1)

[1631] A means for obtaining demographic information of the target audience;

[1632] A means for segmenting the acquired attribute information using a clustering technique;

[1633] means for automatically generating a creative concept based on the segmented data;

[1634] A system including:

[1635] (Claim 2)

[1636] 10. The system of claim 1, wherein the means for generating a creative concept uses a natural language generation model.

[1637] (Claim 3)

[1638] The system according to claim 1, wherein the attribute information includes age, gender, region, and interests.

[1639] "Example 1"

[1640] (Claim 1)

[1641] A means for obtaining demographic information of the target audience;

[1642] a means for accessing a data source based on the acquired attribute information;

[1643] A means for segmenting the acquired attribute information using a clustering technique;

[1644] means for automatically generating creative concepts using a generative AI model based on the segmented data;

[1645] means for outputting the generated creative concept to a user's terminal;

[1646] A system including:

[1647] (Claim 2)

[1648] 2. The system of claim 1, wherein the means for generating a creative concept uses a generative AI model by inputting a prompt sentence.

[1649] (Claim 3)

[1650] The system according to claim 1, wherein the attribute information includes age, gender, region, and interests.

[1651] "Application Example 1"

[1652] (Claim 1)

[1653] A means for obtaining demographic information of the target audience;

[1654] A means for segmenting the acquired attribute information using a clustering technique;

[1655] means for automatically generating a creative concept based on the segmented data;

[1656] a means for displaying the generated creative concept on a terminal;

[1657] A system including:

[1658] (Claim 2)

[1659] 10. The system of claim 1, wherein the means for generating a creative concept uses a natural language generation model.

[1660] (Claim 3)

[1661] The system according to claim 1, wherein the attribute information includes age, gender, region, and interests.

[1662] "Example 2: Combining Emotion Engines"

[1663] (Claim 1)

[1664] A means for obtaining demographic information of the target audience;

[1665] a means for integrating the acquired attribute information and emotion data to update a user profile;

[1666] means for segmenting the integrated data using clustering techniques;

[1667] means for automatically generating a creative concept based on the segmented data;

[1668] a means for displaying the generated creative concepts;

[1669] A system including:

[1670] (Claim 2)

[1671] 10. The system of claim 1, wherein the means for generating a creative concept uses a generative AI model.

[1672] (Claim 3)

[1673] The system according to claim 1, wherein the attribute information includes age, gender, region, interests, and emotion data.

[1674] "Application example 2 when combining emotion engines"

[1675] (Claim 1)

[1676] A means for obtaining demographic information of the target audience;

[1677] a means for adding emotion information to the acquired attribute information;

[1678] A means for integrating the added attribute information and emotion information and segmenting them using clustering technology;

[1679] means for generating prompts for generating creative concepts based on the segmented data;

[1680] a means for inputting the generated prompts into a natural language generation model to automatically generate creative concepts;

[1681] A system including:

[1682] (Claim 2)

[1683] 10. The system of claim 1, wherein the means for generating a creative concept uses a generative AI model.

[1684] (Claim 3)

[1685] The system according to claim 1 , wherein the attribute information includes age, gender, region, interest, and emotion information. [Explanation of symbols]

[1686] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for obtaining demographic information of the target audience; A means for segmenting the acquired attribute information using a clustering technique; means for automatically generating a creative concept based on the segmented data; A system including:

2. 10. The system of claim 1, wherein the means for generating creative concepts uses a natural language generation model.

3. The system according to claim 1 , wherein the attribute information includes age, gender, region, and interests.

Images