System

Abstract

A system is provided.SOLUTION: The system includes a means for acquiring market trend data, a means for collecting customer behavior data, a means for acquiring competition information, a means for cleansing the acquired data, a means for integrating and analyzing a plurality of data, a means for drafting a marketing strategy based on the generated analysis result, and a means for providing the generated marketing strategy to a user in a report format.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While there is a growing trend for companies to in-house their marketing operations, a lack of data, know-how, and human resources poses challenges. Furthermore, it is difficult to efficiently analyze market trends, customer behavior, and competitors, making it difficult to develop appropriate marketing strategies. Furthermore, creating advertising copy and brand visuals requires creative talent and specialized knowledge, making it difficult to do so in-house. It is also difficult to improve the accuracy of customer acquisition and churn predictions, and formulating countermeasures takes time and effort. Many companies are looking to solve these challenges and carry out their marketing operations efficiently and effectively. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system including the following means: This system includes a means for acquiring market trend data, a means for collecting customer behavior data, a means for acquiring competitive information, a means for cleansing the acquired data, a means for integrating and analyzing multiple data, a means for formulating a marketing strategy based on the generated analysis results, and a means for providing the generated marketing strategy to the user in report format. This system enables efficient analysis of market trends, customer behavior, and competitors, and the formulation of appropriate marketing strategies. Furthermore, this system also enables efficient internal creation of advertising copy and brand visuals by using a generative AI to generate advertising copy based on input concepts and keywords, a means for generating brand visuals based on the generated advertising copy using an image generation AI, and a means for integrating the generated advertising copy and brand visuals and providing them to the user. Furthermore, this system includes a means for collecting and cleansing customer data, a means for analyzing customer acquisition and churn, a means for analyzing churn factors based on the prediction results, a means for generating countermeasures for churn factors, and a means for providing the generated countermeasures to the user. This system also enables highly accurate prediction of customer acquisition and churn and the rapid formulation of appropriate countermeasures.

[0006] "Market trend data" refers to data that indicates market trends and fluctuations, and primarily includes consumer demand, competitive trends, economic indicators, etc.

[0007] "Customer behavior data" refers to data about a customer's behavior, such as their purchasing and usage history of products and services, website visits, and click patterns.

[0008] "Competitive information" is information about other companies or products operating in the same market, including data about those companies' strategies, product features, marketing activities, etc.

[0009] "Cleansing" is the process of correcting and removing errors, inconsistencies, missing values, etc. in order to maintain data quality.

[0010] "Generative AI" refers to artificial intelligence that automatically generates text, images, etc. based on large amounts of data, and includes models designed specifically for specific purposes.

[0011] A "marketing strategy" is a plan or methodology that a company devise to effectively offer products or services in the market and acquire and retain customers.

[0012] "Ad copy" refers to the catchphrases and sentences used in an advertisement, designed to effectively communicate a particular message.

[0013] "Brand visuals" refer to designs and images that visually represent a brand, and are a means of visually conveying the brand's identity and message.

[0014] A "predictive model" is a statistical or machine learning method used to forecast future events or outcomes based on past data.

[0015] "Chuckers" are the causes or reasons why customers stop using a product or service.

[0016] A "solution" is a specific solution or action plan adopted to address a specific problem or issue. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system for streamlining and optimizing corporate marketing activities, and mainly realizes the functions of data collection, data analysis, strategy planning, creative generation, and customer forecasting. This system is mainly composed of a server and user terminals, and implements multiple functions including generation AI.

[0039] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0040] Users collect data through their devices to create marketing strategies. The server first obtains market trend data. This includes data collected from websites and APIs. Next, the server collects customer behavior data. This data is obtained from the company's CRM system and affiliated data providers. Competitive information is also obtained by the server using methods such as web crawlers. This data is then cleansed and integrated into a single, well-organized data set by the server.

[0041] The server then inputs the data into a generative AI model and performs analysis in accordance with marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy for the user and delivers it to the user's device in the form of a report.

[0042] Specific examples

[0043] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior.The user can use this information to find the appropriate target market and determine positioning.

[0044] Brand visuals + copy creation

[0045] The user inputs the campaign concept and keywords through the device. The server provides the input information to the generation AI, which automatically generates the ad copy. At the same time, the server also uses the image generation AI to generate brand visuals. The generated text and visuals are integrated on the server and provided to the user.

[0046] Specific examples

[0047] When a user inputs the concept of "environmentally friendly products" for a new campaign, the server generates the copy "One choice to nurture the future" along with a natural-looking visual that matches it, and delivers it to the user's device. The user then uses this to develop an advertisement.

[0048] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0049] The server collects and cleans customer data from the company's customer database. It then uses a predictive model to predict customer acquisition and churn. Based on the prediction results, the server analyzes the causes of churn and generates appropriate countermeasures. The generated countermeasures are delivered to the user's device in report format.

[0050] Specific examples

[0051] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The causes are identified as price competition and the emergence of new competitors. The server generates a report recommending countermeasures such as "implementing price promotions" or "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[0052] This system allows companies to efficiently in-house their marketing operations, reducing costs and accumulating marketing know-how.

[0053] The processing flow will be explained below.

[0054] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0055] Step 1: Data collection

[0056] 1. Obtaining market trend data

[0057] The server retrieves data about market trends through websites and APIs.

[0058] 2. Collecting customer behavior data

[0059] The server collects customer behavior data from the company's CRM system and affiliated data providers.

[0060] 3. Obtaining Competitive Information

[0061] The server uses web crawlers to gather information about competitors, including news, blogs, and social media data.

[0062] Step 2: Data cleansing

[0063] 1. Data normalization

[0064] The server inspects the collected data and corrects noise and missing values.

[0065] 2. Data integration

[0066] The server aggregates data from different sources into a single, coherent data set.

[0067] Step 3: Data analysis

[0068] 1. Entering data

[0069] The server inputs the prepared data into the generation AI.

[0070] 2. Applying a Marketing Framework

[0071] The server uses generated AI to perform analysis based on marketing frameworks such as 3C, STP, and 4P.

[0072] Step 4: Strategic planning

[0073] 1. Generating strategic proposals

[0074] The server generates marketing strategy proposals based on the analysis results.

[0075] 2. Report creation

[0076] The server prepares a report summarizing strategic proposals.

[0077] Step 5: Delivering results

[0078] 1. Report Distribution

[0079] The server delivers the generated report to the user's terminal.

[0080] 2. Confirm and implement the strategy

[0081] Users can check the reports on their devices and plan and implement specific marketing strategies.

[0082] Brand visuals + copy creation

[0083] Step 1: User Input

[0084] 1. Concept input

[0085] The user enters the campaign concept and keywords into the input form on the device.

[0086] Step 2: Generate a copy

[0087] 1. Concept Processing

[0088] The server analyzes the concepts and keywords entered.

[0089] 2. Generative AI copy creation

[0090] The server generates the ad copy using generation AI.

[0091] Step 3: Generate the visuals

[0092] 1. Use of image generation AI

[0093] The server creates brand visuals based on the copy using image generation AI.

[0094] Step 4: Creative Integration

[0095] 1. Integrate copy and visuals

[0096] The server integrates the generated ad copy with the brand visuals.

[0097] Step 5: Delivering results

[0098] 1. Creative Delivery

[0099] The server delivers the integrated creative to the user's device.

[0100] 2. Final confirmation and adoption

[0101] The user reviews the creative on their device and selects it as the final ad.

[0102] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0103] Step 1: Data collection and cleansing

[0104] 1. Collection of Customer Data

[0105] A server collects customer data from a company's customer database.

[0106] 2. Data cleansing

[0107] The server cleanses the collected data and puts it in a form suitable for analysis.

[0108] Step 2: Predictive analytics

[0109] 1. Data model input

[0110] The server inputs the cleansed data into a predictive model.

[0111] 2. Customer acquisition and churn prediction

[0112] The server uses predictive models to analyze the likelihood of customer acquisition or churn.

[0113] Step 3: Analyze causes and develop countermeasures

[0114] 1. Analysis of dropout factors

[0115] Based on the prediction results, the server analyzes the factors that cause customers to leave.

[0116] 2. Generating countermeasures

[0117] The server generates specific countermeasures based on the analysis results.

[0118] Step 4: Create and deliver the report

[0119] 1. Report creation

[0120] The server creates a report summarizing the cause analysis and proposed countermeasures.

[0121] 2. Report distribution

[0122] The server delivers the generated report to the user's terminal.

[0123] 3. Implementing measures

[0124] The user checks the report on the device and takes specific measures.

[0125] With this detailed processing flow, the system of the present invention can automate and streamline marketing operations, and solve many of the problems that companies face.

[0126] Example 1

[0127] 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."

[0128] In conventional marketing systems, each process, such as data collection, cleansing, analysis, and strategy planning, is performed piecemeal, preventing overall efficiency and optimization. Furthermore, it is often difficult to link individual data analysis tools and ad copy generation tools, resulting in a lack of consistency in marketing activities. The present invention aims to provide a system that comprehensively solves these issues and streamlines and optimizes the entire marketing process.

[0129] 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.

[0130] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple data, means for inputting data into a generative AI model and performing analysis based on a marketing framework, means for formulating a marketing strategy based on the generated analysis results, and means for providing the generated marketing strategy to a user in the form of a report. This makes it possible to consistently and efficiently carry out the marketing process from data collection to analysis, strategy formulation, and report creation.

[0131] "Market trend data" refers to data that shows market trends and demand, competitor trends, consumer preferences, etc. It includes dynamic information collected from websites and APIs and obtained from a variety of sources.

[0132] "Customer behavior data" refers to data that shows how customers behave. This includes data collected internally by a company, such as purchase history, browsing history, and CRM system information, as well as data provided by partner data providers.

[0133] "Competitive information" refers to data that shows competitors' activities, strategies, product information, etc. It includes information collected by crawling websites using methods such as web crawlers.

[0134] "Data cleansing" is the process of correcting or removing inaccurate, missing, or redundant portions of collected data, thereby improving the quality of the data set used for subsequent analysis.

[0135] A "generative AI model" is an AI model that uses artificial intelligence technology to analyze data and perform specific tasks, such as analyzing data based on a marketing framework or generating advertising copy.

[0136] A "marketing framework" refers to the basic frameworks and methods for formulating marketing strategies such as 3C, STP, and 4P. These frameworks provide an important analytical perspective in building a marketing strategy.

[0137] "Ad copy" refers to sentences and phrases that effectively communicate an advertisement or campaign. It is automatically generated using a generative AI model based on input concepts and keywords.

[0138] "Image generation AI" is an artificial intelligence technology that automatically generates visuals (images and designs) based on a specified concept or theme. This allows for the rapid and consistent generation of visuals for branding and advertising.

[0139] The "report format" is a document format that summarizes analysis results, strategic proposals, countermeasures, etc. in an easy-to-understand format. Charts and text are organized so that users can easily grasp the content.

[0140] A "predictive model" is a mathematical model that uses data to forecast future trends and outcomes. It is used to predict things like customer acquisition and churn.

[0141] Strategic planning is the process of devising and formulating the most effective marketing strategy based on collected and analyzed data, which determines the specific approach to achieving a company's goals.

[0142] This invention is a system for streamlining and optimizing corporate marketing activities, and realizes the functions of data collection, data analysis, strategy planning, creative generation, and customer prediction. This system is mainly composed of a server and user terminals, and implements multiple functions including generative AI models.

[0143] Hardware and software used

[0144] Hardware: Servers, user terminals, database servers, web crawlers

[0145] Software: Generative AI models, image generation AI, CRM systems, API integration tools, data cleansing tools, predictive models

[0146] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0147] To help users develop marketing strategies through their devices, the server collects market trend data, customer behavior data, and competitive information. Market trend data is primarily obtained from websites and APIs. Customer behavior data is collected from the company's CRM system and affiliated data providers, while competitive information is obtained from websites using web crawlers.

[0148] The collected data is cleansed by the server and compiled into an integrated dataset. This integrated dataset is input into a generative AI model, which performs analysis based on marketing frameworks such as 3C, STP, and 4P. A marketing strategy is developed based on the generated analysis results and provided to the user's device in report format.

[0149] Specific examples

[0150] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior.The user can use this information to find the appropriate target market and determine positioning.

[0151] Brand visuals + copy creation

[0152] The user inputs the campaign concept and keywords via their device. The server provides this input information to a generative AI model, which automatically generates advertising copy. At the same time, image generation AI is used to generate brand visuals. The generated advertising copy and brand visuals are integrated on the server and provided to the user's device.

[0153] Specific examples

[0154] When a user inputs the concept of "environmentally friendly products" for a new campaign, the server generates the copy "One choice to nurture the future" along with natural-looking visuals that match it, and delivers them to the user's device. The user then uses this to develop an advertisement. "An example of a prompt for the generative AI model is, 'Please generate advertising copy for an environmentally friendly product campaign.'"

[0155] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0156] The server collects and cleans customer data from the company's customer database. It then uses a predictive model to predict customer acquisition and churn, and analyzes the causes of churn based on the prediction results. Finally, it generates appropriate countermeasures and provides them to the user's device in the form of a report.

[0157] Specific examples

[0158] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The causes are identified as price competition and the emergence of new competitors. The server generates a report recommending countermeasures such as "implementing price promotions" or "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[0159] This system allows companies to efficiently in-house their marketing operations, reducing costs and accumulating marketing know-how.

[0160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0161] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0162] Step 1: Data collection request

[0163] The user issues a data collection request from a terminal, specifying the data type (market trends, customer behavior, competitive information) required for formulating a marketing strategy.

[0164] Input: Data collection request details (data type, etc.)

[0165] Output: Data collection instructions to the server

[0166] Step 2: Collect market trend data

[0167] The server sends requests to designated websites or APIs to retrieve market trend data, which is then stored in a database.

[0168] Input: Website or API URL, query parameters

[0169] Output: Raw data (market trend information)

[0170] Specific behavior: The server sends an HTTP request to an API endpoint, receives the response, and stores it in a database.

[0171] Step 3: Collect customer behavior data

[0172] The server collects customer behavior data from the company's CRM system and partner data providers, retrieves the data via API, and stores it in a local database.

[0173] Input: API endpoint, authentication information

[0174] Output: Raw data (customer behavior information)

[0175] What happens: The server executes the API call and writes the returned data to a local database.

[0176] Step 4: Gather competitive intelligence

[0177] The server launches a web crawler to collect data from the websites of the specified competitors, which is then stored in a database.

[0178] Input: Competitor URL list

[0179] Output: Raw data (competitive information)

[0180] What it does: The server runs a web crawler and parses the HTML data to extract useful information.

[0181] Step 5: Data cleansing

[0182] The server cleanses the collected data and corrects or removes inaccuracies, missing parts, or duplicates.

[0183] Input: Raw datasets (market trends, customer behavior, competitive intelligence)

[0184] Output: Cleansed dataset

[0185] What it does: The server uses data cleansing tools to improve data consistency and accuracy.

[0186] Step 6: Data Integration

[0187] The server combines the cleansed data from multiple data sources into a single integrated data set.

[0188] Input: Cleansed dataset

[0189] Output: Unified dataset

[0190] Specific operation: The server performs a database join operation to generate a consolidated dataset.

[0191] Step 7: Data analysis

[0192] The server inputs the integrated data set into a generative AI model and performs analysis based on marketing frameworks such as 3C, STP, and 4P.

[0193] Input: Unified dataset

[0194] Output: Analysis results

[0195] Specific operations: The server runs the generative AI model and performs marketing analysis.

[0196] Step 8: Strategic Planning and Reporting

[0197] The server develops a marketing strategy based on the analysis results, compiles the results in report format, and delivers them to the user's device.

[0198] Input: Analysis results

[0199] Output: Marketing Strategy Report

[0200] What it does: The server uses a reporting tool to document the analysis results in a format that is easy to visualize.

[0201] Brand visuals + copy creation

[0202] Step 1: Concept entry

[0203] The user inputs the campaign concept and keywords into the system via a terminal.

[0204] Input: Campaign concept, keywords

[0205] Output: Input information to the server

[0206] Step 2: Input to the generative AI model

[0207] The server feeds input concepts and keywords into a generative AI model to generate ad copy, while also using image-generating AI to generate brand visuals.

[0208] Input: Campaign concept, keywords

[0209] Output: Advertising copy, brand visuals

[0210] Specific operation: The server passes the prompt sentence to the generative AI model and executes the generative AI model and image generation AI.

[0211] Step 3: Integrate copy and visuals

[0212] The server integrates the generated advertising copy with the brand visuals and provides them to the user's terminal.

[0213] Input: Ad copy, brand visuals

[0214] Output: Integrated marketing materials

[0215] Specific operation: The server combines the copy and visuals into a single file or document and sends it to the user's terminal.

[0216] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0217] Step 1: Collect and cleanse customer data

[0218] The server collects and cleans customer data from the company's customer database.

[0219] Input: Customer database

[0220] Output: Cleansed customer data

[0221] Specific operation: The server extracts data from the database, corrects outliers, and completes the data.

[0222] Step 2: Run the predictive model

[0223] The server inputs the cleansed customer data into a predictive model to predict customer acquisition and churn.

[0224] Input: Cleansed customer data

[0225] Output: Prediction results

[0226] What happens: The server applies the predictive model to predict customer behavior.

[0227] Step 3: Factor analysis

[0228] The server analyzes the reasons for customer abandonment based on the prediction results.

[0229] Input: Prediction result

[0230] Output: Factor analysis results

[0231] Specific actions: The server uses data analysis tools to identify the reasons for abandonment.

[0232] Step 4: Generate countermeasures

[0233] The server generates appropriate countermeasures based on the results of analyzing the reasons for dropout.

[0234] Input: Factor analysis results

[0235] Output: Countermeasures

[0236] Specific operation: The server uses the generative AI model to create countermeasures.

[0237] Step 5: Reporting

[0238] The server compiles the generated countermeasures into a report and provides it to the user's terminal.

[0239] Input: Countermeasures

[0240] Output: Countermeasures report

[0241] What happens: The server uses a reporting tool to document the proposed action and send it to the user.

[0242] (Application example 1)

[0243] 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."

[0244] Conventional marketing systems often require a huge amount of time and resources for data collection, analysis, and marketing strategy planning. Especially for advertising campaigns, specialized knowledge and skills are required to quickly create effective advertising copy and visuals. Furthermore, it is difficult to analyze market trends and obtain competitive information in real time, making it difficult to accurately predict customer behavior and quickly take countermeasures based on that information. To solve these problems, a multifunctional marketing support system is needed.

[0245] 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.

[0246] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple pieces of data, means for generating advertising copy using a generation AI, means for generating brand visuals using an image generation AI, and means for integrating the generated advertising copy and brand visuals and providing them to users. This makes it possible to grasp market trends, customer behavior, and competitive information in real time, and to quickly create and deploy effective advertising campaigns.

[0247] "Market trend data" is data that shows market trends and consumer behavior patterns.

[0248] "Customer behavior data" is data that records the actions of customers when they make purchases, browse, make inquiries, etc.

[0249] "Competitive information" is data about competing companies and products in the same market.

[0250] "Data cleansing" is the process of removing noise, redundancies, and errors from collected data and preparing it for use.

[0251] "Data integration" is the process of combining multiple data sets into a single, coherent data set.

[0252] "Generative AI" is artificial intelligence that automatically generates text, visuals, etc. using natural language processing models, etc.

[0253] "Ad copy" is a short, persuasive sentence or catchphrase used in an advertisement.

[0254] "Image generation AI" is an artificial intelligence that automatically generates images based on a specified concept.

[0255] "Brand visuals" are images and designs that visually express the brand's values ​​and messages.

[0256] "Real-time prediction" is a technology that instantly predicts future results based on current data.

[0257] "Report creation means" is a function that provides analysis results and strategy proposals to users in document format.

[0258] To realize this application example, cooperation between the server, terminals, and users is essential. The system of the present invention is composed of the following main means.

[0259] First, the server acquires market trend data. This data is acquired using tools that collect information from websites and APIs. Next, the server collects customer behavior data. This data is derived from the company's CRM system and partner data providers. Finally, the server uses a web crawler to acquire competitive information. This data is then cleansed on the server and compiled into a single, integrated dataset.

[0260] The integrated data set is analyzed and a generative AI is used to create a marketing strategy. Specifically, based on the concepts and keywords entered by the user, the generative AI generates advertising copy and the image generation AI generates brand visuals. For example, if a user enters the concept "environmentally friendly products," the server sends the following prompt to the generative AI: "Please create advertising copy based on the following concept: environmentally friendly products."

[0261] The generated advertising copy and brand visuals are integrated by the server and provided to the user's device. Based on this, the user can develop an effective advertising campaign. The server also analyzes market trends, competitive information, and customer behavior data in real time to predict the effectiveness of the advertising campaign. The results are fed back to the user in real time, allowing them to adjust their strategy as needed.

[0262] Regarding the hardware and software used, the server is a computer running high-performance data processing and AI models. Also, a Python program uses a generation AI (e.g., GPT-3 (registered trademark)) and an image generation AI (e.g., DALL-E). An application is installed on the user's device to receive and display the generated results.

[0263] This system makes it possible to grasp market trends and competitive information in real time, and quickly create and deploy effective advertising campaigns. Specifically, consider the case where a user inputs the concept of "environmentally friendly products." The server sends a prompt message saying, "Please create an advertising copy based on the following concept: environmentally friendly products," and generates the advertising copy "One choice to nurture the future" along with natural visuals that match it. This allows users to effectively deploy high-quality advertising campaigns.

[0264] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0265] Step 1:

[0266] The server obtains market trend data. Specifically, the server collects information about market trends from designated websites or APIs and stores it in a database. The input is market trend information from websites or APIs, and the output is organized market trend data.

[0267] Step 2:

[0268] The server collects customer behavior data. It retrieves the data from the company's CRM system or partner data providers, cleanses it, and integrates it into a database. The input is customer behavior data retrieved from the company's CRM system or data providers, and the output is cleansed customer behavior data.

[0269] Step 3:

[0270] The server obtains competitive information using a web crawler. This involves collecting competitor websites and public information and converting it into an analyzable format. The input is competitor information collected by the web crawler, and the output is formatted competitive information.

[0271] Step 4:

[0272] The server cleanses the acquired market trend data, customer behavior data, and competitive information to create an integrated dataset. The input is the various data obtained in the previous step, and the output is the integrated, cleansed dataset.

[0273] Step 5:

[0274] The server inputs the integrated dataset into the generative AI model for analysis, including analysis based on marketing frameworks such as 3C, STP, and 4P. The input is the integrated dataset, and the output is the analysis result of the generated marketing strategy.

[0275] Step 6:

[0276] The server uses a generation AI to generate advertising copy based on the concepts and keywords entered by the user. For example, if a user enters the concept "environmentally friendly products," the server sends the prompt "Please create advertising copy based on the following concept: environmentally friendly products" to the generation AI. The input is the user's concept or keywords, and the output is the generated advertising copy.

[0277] Step 7:

[0278] The server generates brand visuals using image generation AI based on the generated advertising copy. For example, it sends a prompt statement, "Please create an advertising visual based on an environmentally friendly product," to the image generation AI. The input is the generated advertising copy, and the output is the generated brand visual.

[0279] Step 8:

[0280] The server integrates the generated advertising copy and brand visuals and provides them to the user. The input is the generated advertising copy and brand visuals, and the output is the integrated advertising campaign materials, which the user can use to develop their advertising campaign.

[0281] Step 9:

[0282] The server analyzes market trends, customer behavior data, and competitive information in real time to predict the effectiveness of advertising campaigns. The inputs are market trend data, customer behavior data, and competitive information collected in real time, and the output is the predicted results of the advertising campaign.

[0283] Step 10:

[0284] The server feeds back the real-time prediction results to the user's device and modifies the strategy as necessary. The input is the real-time prediction results, and the output is a modified marketing strategy.

[0285] Through the above steps, the system of the present invention is able to grasp market trends and competitive information in real time, and quickly create and develop effective advertising campaigns.

[0286] 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.

[0287] This invention is a system for streamlining and optimizing corporate marketing operations, and in particular, by combining an emotion engine, it is possible to understand user emotions and generate marketing strategies and creatives more effectively. This system is mainly composed of a server, terminals, generation AI, and an emotion engine.

[0288] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0289] Users collect data through their devices to create marketing strategies. The server first obtains market trend data. This includes data collected from websites and APIs. Next, the server collects customer behavior data. This data is obtained from the company's CRM system and affiliated data providers. Competitive information is also obtained by the server using methods such as web crawlers. This data is then cleansed and integrated into a single, well-organized data set by the server.

[0290] The server then inputs the data into a generative AI model and performs analysis in accordance with marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy for the user and delivers it to the user's device in report format. Furthermore, by combining it with an emotion engine, it becomes possible to provide personalized strategies that take into account the user's emotional data.

[0291] Specific examples

[0292] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior. Based on user input, the emotion engine analyzes the user's level of excitement and interest, and suggests more appropriate target markets and positioning.

[0293] Brand visuals + copy creation

[0294] The user inputs the campaign concept and keywords via their device. The emotion engine analyzes the user's input and understands their emotional state at the time. The server provides this to the generation AI, which automatically generates advertising copy. At the same time, the server also uses image generation AI to generate brand visuals. The generated text and visuals are integrated on the server and provided to the user.

[0295] Specific examples

[0296] When a user inputs the concept "environmentally friendly products" for a new campaign, the emotion engine recognizes the user's emotion as "excitement." Based on this, the server generates the copy "One choice to nurture the future" along with energetic, natural visuals, which are then delivered to the user's device. The user then uses this to develop an advertisement.

[0297] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0298] The server collects and cleans customer data from a company's customer database. It then uses a predictive model to predict customer acquisition and churn. Based on the prediction results, the server analyzes the causes of churn and generates appropriate countermeasures. The generated countermeasures are delivered in report format to the user's device. Furthermore, by combining it with an emotion engine, it becomes possible to provide countermeasures that take user emotions into account.

[0299] Specific examples

[0300] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The emotion engine analyzes the users' feelings of "anxiety" and "dissatisfaction" and identifies price competition and the emergence of new competitors as the causes. The server generates a report recommending countermeasures such as "implementing price promotions" and "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[0301] This system allows companies to efficiently in-house their marketing operations, and by taking user emotions into account, they can implement even more effective marketing strategies.

[0302] The processing flow will be explained below.

[0303] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0304] Step 1: Data collection

[0305] 1. Obtaining market trend data

[0306] The server retrieves data about market trends through the API, including economic indicators and consumer behavior.

[0307] 2. Collecting customer behavior data

[0308] The server collects customer purchase history and website visit records from the company's CRM system.

[0309] 3. Obtaining Competitive Information

[0310] The server uses a web crawler to collect public information (news, social media posts, etc.) about competitors.

[0311] Step 2: Data cleansing

[0312] 1. Data normalization

[0313] The server cleanses the collected data and corrects inconsistencies and missing values, for example, removing duplicate data and imputing missing values.

[0314] 2. Data integration

[0315] The server consolidates market trend data, customer behavior data, and competitive intelligence, and organizes it into a format suitable for analysis.

[0316] Step 3: Data analysis

[0317] 1. Entering data

[0318] The server inputs the cleansed data into the generation AI.

[0319] 2. Applying a Marketing Framework

[0320] The server uses generated AI to perform analysis based on marketing frameworks such as 3C, STP, and 4P.

[0321] Step 4: Integrating Emotional Data

[0322] 1. Entering emotions

[0323] The user inputs emotion data from the device, and the system recognizes the user's emotion by analyzing the voice and text input.

[0324] 2. Applying the Emotion Engine

[0325] The server uses an emotion engine to analyze the user's emotions and integrates the emotion data into the analysis results.

[0326] Step 5: Strategic planning

[0327] 1. Generating strategic proposals

[0328] The server generates an individually personalized marketing strategy based on the analysis results and sentiment data.

[0329] 2. Report creation

[0330] The server prepares a report summarizing strategic proposals.

[0331] Step 6: Delivering results

[0332] 1. Report Distribution

[0333] The server delivers the generated report to the user's terminal.

[0334] 2. Confirm and implement the strategy

[0335] Users can check the reports on their devices and plan and implement specific marketing strategies.

[0336] Brand visuals + copy creation

[0337] Step 1: User Input

[0338] 1. Concept input

[0339] The user enters the campaign concept and keywords into the input form on the device.

[0340] Step 2: Analyze the emotion data

[0341] 1. Emotion Analysis

[0342] The server uses an emotion engine to analyze emotions from concepts and keywords entered by the user.

[0343] Step 3: Generate a copy

[0344] 1. Concept Processing

[0345] The server provides concepts and keywords along with emotional data to the generation AI.

[0346] 2. Generative AI copy creation

[0347] The server generates the ad copy using generation AI.

[0348] Step 4: Generate the visuals

[0349] 1. Use of image generation AI

[0350] The server uses image generation AI to create brand visuals based on copy and emotional data.

[0351] Step 5: Creative Integration

[0352] 1. Integrate copy and visuals

[0353] The server integrates the generated ad copy with the brand visuals.

[0354] Step 6: Delivering results

[0355] 1. Creative Delivery

[0356] The server delivers the integrated creative to the user's device.

[0357] 2. Final confirmation and adoption

[0358] The user reviews the creative on their device and selects it as the final ad.

[0359] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0360] Step 1: Data collection and cleansing

[0361] 1. Collection of Customer Data

[0362] A server collects customer data from a company's customer database.

[0363] 2. Data cleansing

[0364] The server cleanses the collected data and corrects inconsistencies and missing values.

[0365] Step 2: Run the predictive model

[0366] 1. Data model input

[0367] The server inputs the cleansed data into a predictive model.

[0368] 2. Customer acquisition and churn prediction

[0369] The server uses predictive models to analyze the likelihood of customer acquisition or churn.

[0370] Step 3: Integrating Emotional Data

[0371] 1. Entering emotions

[0372] The user inputs emotion data into the device. The emotion engine analyzes the voice and text input and recognizes the emotion.

[0373] 2. Application of Emotion Data

[0374] The server integrates the emotion data into the prediction results.

[0375] Step 4: Analyze causes and develop countermeasures

[0376] 1. Analysis of dropout factors

[0377] The server analyzes the factors behind customer abandonment based on the prediction results and emotional data.

[0378] 2. Generating countermeasures

[0379] The server generates specific countermeasures based on the analysis results.

[0380] Step 5: Create and deliver the report

[0381] 1. Report creation

[0382] The server creates a report summarizing the cause analysis and proposed countermeasures.

[0383] 2. Report distribution

[0384] The server delivers the generated report to the user's terminal.

[0385] 3. Implementing measures

[0386] The user checks the report on the device and takes specific measures.

[0387] This detailed processing flow enables the system of the present invention to automate and streamline marketing operations, and to solve many of the problems that companies face. In addition, by combining it with an emotion engine, it is possible to implement more effective marketing strategies that take user emotions into account.

[0388] Example 2

[0389] 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."

[0390] To respond to complex and diverse marketing environments, modern companies need to collect large amounts of data and analyze that data to develop effective marketing strategies. However, manually collecting, cleansing, and analyzing massive amounts of data requires time and effort, and the accuracy of the analysis often depends on human subjectivity, making it difficult to develop optimal marketing strategies. Furthermore, conventional marketing analysis methods have difficulty taking user emotions into account, and they have not been able to provide personalized strategies sufficiently. Therefore, there is a need for a system that can efficiently collect and analyze data and automatically generate marketing strategies that take user emotions into account.

[0391] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0392] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple pieces of data, means for analyzing data based on a marketing framework using a generative AI model, means for analyzing user emotion data using an emotion engine, means for formulating a marketing strategy based on the generated analysis results, and means for providing the generated marketing strategy to the user in report form. This enables efficient and accurate collection and analysis of data, and realizes automatic generation of a marketing strategy that takes user emotions into consideration.

[0393] "Market trend data" is information that indicates market trends and consumer behavior patterns, obtained from internet data sources and APIs.

[0394] "Customer behavior data" is information that shows how a company's customers behave, collected from CRM systems and affiliated data providers.

[0395] "Competitive information" refers to information about competitors' activities, products, and services, and is obtained using web crawlers.

[0396] "Data cleansing" is the process of removing missing values ​​and outliers from collected data to improve the quality of the data.

[0397] "Data integration" is the process of combining multiple data sets into a single, coherent data set.

[0398] A "generative AI model" is an artificial intelligence model that performs marketing analysis and text generation based on large amounts of data.

[0399] An "emotion engine" is software that analyzes a user's emotional state based on their input and behavior.

[0400] A "marketing framework" is an analytical tool used to plan marketing strategies, and includes 3C, STP, 4P, etc.

[0401] A "marketing strategy" is a strategy that a company should implement based on market trends, customer behavior, and competitive information.

[0402] A "report format" is a document format designed to communicate analysis results and strategies to users in an easy-to-understand manner.

[0403] "Ad Copy" means text used in a marketing campaign that is generated by a generative AI model.

[0404] "Brand visuals" are visual elements used in advertising and marketing campaigns that are generated by image generation AI.

[0405] A "predictive model" is an algorithm that predicts future customer behavior based on past data.

[0406] "Countermeasures" are specific countermeasures to problems such as customer defection, and are generated based on the analysis results.

[0407] This invention is a system for streamlining and optimizing corporate marketing operations, and in particular, by combining an emotion engine, it is possible to understand user emotions and generate marketing strategies and creatives more effectively. This system is mainly composed of a server, terminals, a generative AI model, and an emotion engine.

[0408] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0409] When a user issues a market research command from their device, the server executes the following steps: First, the server uses the Python requests library to retrieve market trend data from an external API. Next, the server uses an SQL query to collect customer behavior data from the company's CRM system. The server also uses BeautifulSoup to retrieve competitive information using a web crawler and collect that information.

[0410] The server cleanses the collected data using the pandas library and compiles it into a single integrated dataset. The cleansed dataset is input into a generative AI model (using, for example, TENSORFLOW (registered trademark) or PyTorch) and analyzed based on marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy and generates a PDF report using, for example, the PDFKit library.

[0411] Furthermore, the emotion engine analyzes the user's emotional data and personalizes marketing strategies. The report generated in this way is delivered from the server to the user's device, and the user can use it to decide on marketing measures.

[0412] Specific examples

[0413] When a user issues a command from a terminal saying, "Start market research for a new product," the server collects and analyzes market trends, customer behavior, and competitive information. For example, the user might enter the following prompt:

[0414] I'd like to create a marketing strategy for a new product. Can you provide me with an analysis of competitor trends and customer purchasing behavior?

[0415] Brand visuals + copy creation

[0416] When a user inputs a campaign concept or keywords through their device, the emotion engine analyzes the user's emotional state. Based on this emotional information, the server generates advertising copy using a generative AI model (e.g., GPT-3). The server then generates brand visuals using an image generation AI (e.g., DALL-E).

[0417] The generated advertising copy and brand visuals are integrated on the server and delivered to the user's device, where the user can use it to create content for their marketing campaign.

[0418] Specific examples

[0419] When a user enters "eco-friendly products" as their "new campaign concept," the emotion engine analyzes the user's emotion as "excitement." Based on this, the generative AI model generates the following ad copy:

[0420] One choice to nurture the future

[0421] In parallel, image generation AI generates energetic and natural visuals, which are then delivered to the user's device.

[0422] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0423] The server collects data from a company's customer database and cleans it using the pandas library. The server then predicts customer acquisition and churn using a machine learning model from Scikit-learn. Based on the prediction results, the server analyzes the reasons for churn and generates specific countermeasures.

[0424] The emotion engine analyzes the user's emotional data and personalizes countermeasures. The countermeasures are generated in report format and sent from the server to the user's device. The user then implements marketing measures based on this report.

[0425] Specific examples

[0426] The server analyzes customer data and discovers that purchases are declining in a particular segment. The emotion engine analyzes user "anxiety" and "dissatisfaction" and identifies price competition and the emergence of new competitors as the causes. Based on this information, the server generates specific countermeasures such as:

[0427] Implementing price promotions and strengthening loyalty programs

[0428] These proposed solutions are provided to the user in the form of a report.

[0429] As described above, the system of the present invention achieves efficient and accurate collection and analysis of data, and automatically generates marketing strategies and creatives that take user emotions into consideration.

[0430] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0431] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0432] Step 1:

[0433] The user issues market research instructions from the terminal.

[0434] Input: The user types "Start market research for new product" into the terminal and presses the "Collect data" button.

[0435] Output: Market research instructions are sent to the server.

[0436] Step 2:

[0437] The server retrieves market trend data.

[0438] Input: Receive market research instructions.

[0439] Data processing / calculation: The server uses the requests library to retrieve market trend data from external APIs.

[0440] What happens: The server sends a request to a specific API endpoint and receives market trend data in JSON format.

[0441] Output: Obtained market trend data.

[0442] Step 3:

[0443] The server collects customer behavior data.

[0444] Input: Access the CRM system using an SQL query.

[0445] Data processing / calculation: Extract customer behavior data and format it using the pandas library.

[0446] Specific operation: Extract the necessary customer behavior data from the SQL database and convert it into a data frame.

[0447] Output: Collected customer behavior data.

[0448] Step 4:

[0449] The server retrieves the conflict information.

[0450] Input: Scraping instructions using a web crawler.

[0451] Data processing / calculation: Use the BeautifulSoup library to crawl competitors' websites and extract data.

[0452] What it does: The server accesses the web page of each competitor and runs a script to extract the required information.

[0453] Output: The obtained competitive intelligence data.

[0454] Step 5:

[0455] The server performs data cleansing and integration.

[0456] Inputs: Captured market trend data, customer behavior data, and competitive intelligence data.

[0457] Data processing / calculation: Use the pandas library to fill in missing values ​​and remove outliers to create a single integrated dataset.

[0458] Specific actions: Run scripts to impute missing values, remove outliers, merge necessary fields, etc.

[0459] Output: A cleansed, consolidated dataset.

[0460] Step 6:

[0461] The server analyzes the data using the generative AI model.

[0462] Input: The cleansed consolidated dataset.

[0463] Data processing / computation: Use generative AI models (e.g., PyTorch, TensorFlow) to perform analysis based on marketing frameworks.

[0464] How it works: The integrated dataset is fed into a generative AI model to obtain results based on frameworks such as 3C, STP, and 4P.

[0465] Output: Analysis results.

[0466] Step 7:

[0467] The server creates marketing strategies and generates reports.

[0468] Input: Analysis results.

[0469] Data processing / calculation: Use the PDFKit library to visualize the analysis results and create detailed PDF reports.

[0470] What it does: Generate graphs and charts from the analysis results and convert them to PDF format.

[0471] Output: PDF report.

[0472] Step 8:

[0473] The server uses an emotion engine to personalize the marketing strategy.

[0474] Input: PDF report and user sentiment data.

[0475] Data processing / calculation: The emotion engine analyzes the user's past inputs and reactions to customize the report content.

[0476] What it does: Perform real-time analysis using the sentiment engine and adjust some of the reports.

[0477] Output: Personalized PDF report.

[0478] Step 9:

[0479] The server delivers the report to the user.

[0480] Input: A personalized PDF report.

[0481] Output: The report is delivered to the user's device.

[0482] Brand visuals + copy creation

[0483] Step 1:

[0484] The user enters the campaign concept and keywords into the terminal.

[0485] Input: Campaign concept or keywords (e.g. "eco-friendly products").

[0486] Output: The input concepts or keywords.

[0487] Step 2:

[0488] An emotion engine analyzes the user's emotional state.

[0489] Input: The concept or keyword entered.

[0490] Data processing / calculation: The emotion engine analyzes the user's emotions.

[0491] Specific behavior: Analyzes emotional state (e.g., "excited") in real time based on user input.

[0492] Output: Parsed emotion data.

[0493] Step 3:

[0494] The server generates the ad copy using a generative AI model.

[0495] Input: Sentiment data and concepts, keywords.

[0496] Data processing / computation: Using generative AI models (e.g., GPT-3) to generate ad copy based on sentiment data.

[0497] What it does: Concepts and keywords are input as prompts into the generation AI, which then generates ad copy.

[0498] Output: The generated ad copy.

[0499] Step 4:

[0500] The server generates brand visuals using image generation AI.

[0501] Input: ad copy and sentiment data.

[0502] Data processing / calculation: Use image generation AI (e.g., DALL-E) to generate brand visuals based on emotional data.

[0503] What it does: Ad copy is fed into an image generation AI as a prompt to generate a visual.

[0504] Output: Generated brand visuals.

[0505] Step 5:

[0506] The server integrates the generated ad copy with the brand visuals.

[0507] Input: Generated ad copy and brand visuals.

[0508] Data processing / calculation: Integrate copy and visuals into one file in HTML format.

[0509] What it does: Runs a script that embeds ad copy and brand visuals into an HTML template.

[0510] Output: Integrated marketing content.

[0511] Step 6:

[0512] The server provides the aggregated content to the user.

[0513] Input: Integrated marketing content.

[0514] Output: The content is delivered to the user's device.

[0515] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0516] Step 1:

[0517] The server collects and cleanses customer data.

[0518] Input: Instructions to gather customer data from a company database using an SQL query.

[0519] Data processing / calculation: Cleanse the data using the pandas library.

[0520] Specific behavior: Extract data from SQL database and handle missing values ​​and outliers.

[0521] Output: Cleansed customer data.

[0522] Step 2:

[0523] The server uses a predictive model to predict customer acquisition and churn.

[0524] Input: Cleansed customer data.

[0525] Data processing / calculation: Predictions are made using Scikit-learn machine learning models.

[0526] Specific operation: The cleansed data is input into a predictive model to generate acquisition and churn predictions.

[0527] Output: Prediction results.

[0528] Step 3:

[0529] The server analyzes the reasons for dropout based on the prediction results.

[0530] Input: Prediction results.

[0531] Data processing / calculation: Identify reasons for dropout using analytical methods such as Feature Importance.

[0532] Specific operation: Analyze important variables of the model to identify customer abandonment factors from the prediction results.

[0533] Output: Dropout factors.

[0534] Step 4:

[0535] The server generates specific countermeasures.

[0536] Input: Churn factors.

[0537] Data processing / calculation: Consider quantitative and qualitative data to generate countermeasures.

[0538] Specific actions: Based on the reasons for abandonment, we propose countermeasures such as price promotions and strengthening loyalty programs.

[0539] Output: Proposed solution.

[0540] Step 5:

[0541] Use an emotion engine to personalize countermeasures.

[0542] Input: Countermeasure proposal and user sentiment data.

[0543] Data processing / calculation: The emotion engine analyzes the user's emotional data and customizes countermeasures.

[0544] Specific actions: Adjust some of the proposed countermeasures based on the user's past reactions and emotional data.

[0545] Output: Personalized countermeasures.

[0546] Step 6:

[0547] The server generates the report and delivers it to the user.

[0548] Input: personalized countermeasures.

[0549] Data processing / calculation: Use libraries such as PDFKit to create a report of proposed countermeasures.

[0550] Specific operation: A report in PDF format is generated based on the proposed countermeasures and delivered to the user's device.

[0551] Output: A personalized action report.

[0552] The above is the specific processing flow of this system.

[0553] (Application example 2)

[0554] 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."

[0555] Conventional marketing systems developed marketing strategies and generated advertising copy and brand visuals based on market trend data, customer behavior data, and competitive intelligence. However, they were unable to generate personalized strategies and advertisements that took user emotions into account. As a result, marketing effectiveness was insufficient, resulting in a decrease in appeal to target customers. Furthermore, because they were unable to analyze customer emotions and develop countermeasures that took these emotions into account, the accuracy of customer churn prevention measures and customer acquisition strategies was low. To address these issues, technology that can analyze emotions and reflect them in marketing is required.

[0556] 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.

[0557] In this invention, the server includes means for analyzing emotions, means for personalizing a marketing strategy based on the emotion analysis results, means for generating advertising copy using a generation AI, means for generating brand visuals using an image generation AI, means for personalizing the generated advertising copy and visuals based on the emotion analysis results, and means for personalizing countermeasures based on the emotion analysis results. This makes it possible to create effective marketing strategies that reflect user emotions, generate personalized advertising copy and visuals, and develop countermeasures.

[0558] "Market trend data" is data that shows the overall trends and tendencies of the market.

[0559] "Customer behavior data" refers to data that indicates customer behavior, such as customer purchase history and website browsing history.

[0560] "Competitive information" is information about competitors' companies and products.

[0561] "Means for analyzing emotions" refers to means for analyzing text, audio, images, etc. to identify a user's emotional state.

[0562] "Means for personalizing marketing strategies based on the results of sentiment analysis" refers to means for creating marketing strategies optimized for individual users using the results of sentiment analysis.

[0563] "Methods for generating advertising copy using generative AI" refers to methods for automatically creating advertising copy using artificial intelligence.

[0564] "Method for generating brand visuals using image generation AI" refers to a method for automatically creating visual elements of a brand using artificial intelligence.

[0565] "Means for integrating advertising copy and brand visuals" refers to means for combining the generated advertising copy and brand visuals into a single advertisement.

[0566] "Means for personalizing advertising copy and visuals generated based on the results of sentiment analysis" refers to a means for creating advertising copy and visuals that are most suitable for individual users based on the results of sentiment analysis.

[0567] "Analytical methods for predicting customer acquisition and churn" are methods that analyze customer data and predict whether new customers will be acquired or whether they will churn.

[0568] "Means for analyzing reasons for customer churn" refers to a method for analyzing data to identify the reasons why customers churn.

[0569] The "means for generating countermeasures" is a means for automatically creating appropriate countermeasures based on the reasons for dropout.

[0570] "Means for personalizing countermeasures" refers to creating countermeasures that are optimal for individual users based on the results of sentiment analysis.

[0571] The system of this invention streamlines marketing operations and enables the generation of personalized marketing strategies, advertising copy, brand visuals, and countermeasures based on user emotions. The specific configuration of the system and its processing procedures are described below.

[0572] First, the server acquires market trend data, customer behavior data, and competitive information, cleansing and integrating them. Next, the integrated data is input into a generative AI model and analyzed based on a marketing framework. Based on the analysis results, a marketing strategy is formulated and provided to users in the form of a report, utilizing sentiment analysis methods. The results of the sentiment analysis are used to personalize the marketing strategy.

[0573] The system has the ability to generate ad copy using generative AI, and also includes the ability to generate brand visuals using image generation AI based on the generated ad copy. Furthermore, the system personalizes the generated ad copy and visuals based on the results of sentiment analysis and provides them to users.

[0574] For example, suppose a user inputs the concept "environmentally friendly product" and their emotion at the time is "excitement." The server confirms this emotion using an emotion analysis engine and inputs it into the generative AI model. Based on this information, the generative AI model generates advertising copy such as "One choice to nurture the future" along with energetic, natural visuals, and presents them to the user.

[0575] Sentiment analysis is performed by analyzing text, audio, and image data, and the emotion engine used is the Emotion Engine API. The generative AI model is applied using the Generation AI API. This processing enables the creation of effective marketing strategies and advertisements that reflect user emotions.

[0576] Examples of specific prompts include:

[0577] "Excitement, eco-friendly products"

[0578] This allows companies to implement personalized marketing strategies that take user emotions into account, increasing the appeal of advertising and improving the effectiveness of customer acquisition and retention.

[0579] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0580] Step 1:

[0581] The server obtains market trend data, customer behavior data, and competitive information.

[0582] Inputs: Market trend data from websites and APIs, customer behavior data from a company's CRM system and partner data providers, competitive intelligence obtained through web crawlers and other means.

[0583] Output: Raw market trend data, customer behavior data, competitive intelligence.

[0584] Specific operation: Collect necessary data from multiple data sources and import it into the server.

[0585] Step 2:

[0586] The server cleanses the retrieved data.

[0587] Inputs: Raw market trend data, customer behavior data, competitive intelligence.

[0588] Output: A cleansed and tidy dataset.

[0589] Specific Actions: Deduplicate, format, and correct inaccurate data.

[0590] Step 3:

[0591] The server integrates multiple data sets and performs analysis.

[0592] Input: The cleansed dataset.

[0593] Output: Data for input into a generative AI model.

[0594] Specific actions: Classify and aggregate data and analyze it in line with marketing frameworks (3C, STP, 4P, etc.).

[0595] Step 4:

[0596] The server formulates a marketing strategy based on the generated analysis results.

[0597] Input: Data for input to a generative AI model.

[0598] Output: Proposed marketing strategy.

[0599] Specific operation: Input data into the generative AI model and create a specific marketing strategy based on the analysis results.

[0600] Step 5:

[0601] The server analyzes the user's emotion data using an emotion analysis means.

[0602] Input: User input text, voice, or image data.

[0603] Output: The user's emotional state.

[0604] What it does: It uses the Emotion Engine API to analyze text, audio, and image data to identify the user's emotional state.

[0605] Step 6:

[0606] The server personalizes the marketing strategy based on the sentiment analysis results.

[0607] Input: Marketing strategy ideas, user emotional state.

[0608] Output: Personalized marketing strategies.

[0609] Specific operation: Reflecting the results of sentiment analysis, we create marketing strategies optimized for individual users.

[0610] Step 7:

[0611] The server generates the ad copy using a generation AI.

[0612] Input: Concepts, keywords, and the user's emotional state.

[0613] Output: Ad copy.

[0614] Specific operation: Input the prompt text into the generative AI model (Generation AI API) to automatically generate ad copy.

[0615] An example of a specific prompt: "Excitement, eco-friendly products."

[0616] Step 8:

[0617] The server uses image generation AI to generate brand visuals based on the generated advertising copy.

[0618] Input: ad copy, user's emotional state.

[0619] Output: Brand visuals.

[0620] What it does: Uses image generation AI to create branded visuals that perfectly complement ad copy.

[0621] Step 9:

[0622] The server integrates the generated advertising copy with the brand visuals and provides them to the user.

[0623] Input: ad copy, brand visuals.

[0624] Output: Integrated advertising content.

[0625] Specific operation: The generated ad copy and visuals are compiled into one ad content and provided to the user.

[0626] Step 10:

[0627] The server cleanses customer data, analyzes reasons for customer abandonment, and generates countermeasures.

[0628] Input: Customer behavior data, emotional state.

[0629] Output: Personalized countermeasures.

[0630] Specific operations: Organize customer data, identify reasons for abandonment based on sentiment analysis results, and automatically generate appropriate countermeasures.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] [Second embodiment]

[0635] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0636] 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.

[0637] 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).

[0638] 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.

[0639] 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.

[0640] 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).

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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."

[0647] This invention is a system for streamlining and optimizing corporate marketing activities, and mainly realizes the functions of data collection, data analysis, strategy planning, creative generation, and customer forecasting. This system is mainly composed of a server and user terminals, and implements multiple functions including generation AI.

[0648] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0649] Users collect data through their devices to create marketing strategies. The server first obtains market trend data. This includes data collected from websites and APIs. Next, the server collects customer behavior data. This data is obtained from the company's CRM system and affiliated data providers. Competitive information is also obtained by the server using methods such as web crawlers. This data is then cleansed and integrated into a single, well-organized data set by the server.

[0650] The server then inputs the data into a generative AI model and performs analysis in accordance with marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy for the user and delivers it to the user's device in the form of a report.

[0651] Specific examples

[0652] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior.The user can use this information to find the appropriate target market and determine positioning.

[0653] Brand visuals + copy creation

[0654] The user inputs the campaign concept and keywords through the device. The server provides the input information to the generation AI, which automatically generates the ad copy. At the same time, the server also uses the image generation AI to generate brand visuals. The generated text and visuals are integrated on the server and provided to the user.

[0655] Specific examples

[0656] When a user inputs the concept of "environmentally friendly products" for a new campaign, the server generates the copy "One choice to nurture the future" along with a natural-looking visual that matches it, and delivers it to the user's device. The user then uses this to develop an advertisement.

[0657] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0658] The server collects and cleans customer data from the company's customer database. It then uses a predictive model to predict customer acquisition and churn. Based on the prediction results, the server analyzes the causes of churn and generates appropriate countermeasures. The generated countermeasures are delivered to the user's device in report format.

[0659] Specific examples

[0660] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The causes are identified as price competition and the emergence of new competitors. The server generates a report recommending countermeasures such as "implementing price promotions" or "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[0661] This system allows companies to efficiently in-house their marketing operations, reducing costs and accumulating marketing know-how.

[0662] The processing flow will be explained below.

[0663] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0664] Step 1: Data collection

[0665] 1. Obtaining market trend data

[0666] The server retrieves data about market trends through websites and APIs.

[0667] 2. Collecting customer behavior data

[0668] The server collects customer behavior data from the company's CRM system and affiliated data providers.

[0669] 3. Obtaining Competitive Information

[0670] The server uses web crawlers to gather information about competitors, including news, blogs, and social media data.

[0671] Step 2: Data cleansing

[0672] 1. Data normalization

[0673] The server inspects the collected data and corrects noise and missing values.

[0674] 2. Data integration

[0675] The server aggregates data from different sources into a single, coherent data set.

[0676] Step 3: Data analysis

[0677] 1. Entering data

[0678] The server inputs the prepared data into the generation AI.

[0679] 2. Applying a Marketing Framework

[0680] The server uses generated AI to perform analysis based on marketing frameworks such as 3C, STP, and 4P.

[0681] Step 4: Strategic planning

[0682] 1. Generating strategic proposals

[0683] The server generates marketing strategy proposals based on the analysis results.

[0684] 2. Report creation

[0685] The server prepares a report summarizing strategic proposals.

[0686] Step 5: Delivering results

[0687] 1. Report Distribution

[0688] The server delivers the generated report to the user's terminal.

[0689] 2. Confirm and implement the strategy

[0690] Users can check the reports on their devices and plan and implement specific marketing strategies.

[0691] Brand visuals + copy creation

[0692] Step 1: User Input

[0693] 1. Concept input

[0694] The user enters the campaign concept and keywords into the input form on the device.

[0695] Step 2: Generate a copy

[0696] 1. Concept Processing

[0697] The server analyzes the concepts and keywords entered.

[0698] 2. Generative AI copy creation

[0699] The server generates the ad copy using generation AI.

[0700] Step 3: Generate the visuals

[0701] 1. Use of image generation AI

[0702] The server creates brand visuals based on the copy using image generation AI.

[0703] Step 4: Creative Integration

[0704] 1. Integrate copy and visuals

[0705] The server integrates the generated ad copy with the brand visuals.

[0706] Step 5: Delivering results

[0707] 1. Creative Delivery

[0708] The server delivers the integrated creative to the user's device.

[0709] 2. Final confirmation and adoption

[0710] The user reviews the creative on their device and selects it as the final ad.

[0711] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0712] Step 1: Data collection and cleansing

[0713] 1. Collection of Customer Data

[0714] A server collects customer data from a company's customer database.

[0715] 2. Data cleansing

[0716] The server cleanses the collected data and puts it in a form suitable for analysis.

[0717] Step 2: Predictive analytics

[0718] 1. Data model input

[0719] The server inputs the cleansed data into a predictive model.

[0720] 2. Customer acquisition and churn prediction

[0721] The server uses predictive models to analyze the likelihood of customer acquisition or churn.

[0722] Step 3: Analyze causes and develop countermeasures

[0723] 1. Analysis of dropout factors

[0724] Based on the prediction results, the server analyzes the factors that cause customers to leave.

[0725] 2. Generating countermeasures

[0726] The server generates specific countermeasures based on the analysis results.

[0727] Step 4: Create and deliver the report

[0728] 1. Report creation

[0729] The server creates a report summarizing the cause analysis and proposed countermeasures.

[0730] 2. Report distribution

[0731] The server delivers the generated report to the user's terminal.

[0732] 3. Implementing measures

[0733] The user checks the report on the device and takes specific measures.

[0734] With this detailed processing flow, the system of the present invention can automate and streamline marketing operations, and solve many of the problems that companies face.

[0735] Example 1

[0736] 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."

[0737] In conventional marketing systems, each process, such as data collection, cleansing, analysis, and strategy planning, is performed piecemeal, preventing overall efficiency and optimization. Furthermore, it is often difficult to link individual data analysis tools and ad copy generation tools, resulting in a lack of consistency in marketing activities. The present invention aims to provide a system that comprehensively solves these issues and streamlines and optimizes the entire marketing process.

[0738] 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.

[0739] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple data, means for inputting data into a generative AI model and performing analysis based on a marketing framework, means for formulating a marketing strategy based on the generated analysis results, and means for providing the generated marketing strategy to a user in the form of a report. This makes it possible to consistently and efficiently carry out the marketing process from data collection to analysis, strategy formulation, and report creation.

[0740] "Market trend data" refers to data that shows market trends and demand, competitor trends, consumer preferences, etc. It includes dynamic information collected from websites and APIs and obtained from a variety of sources.

[0741] "Customer behavior data" refers to data that shows how customers behave. This includes data collected internally by a company, such as purchase history, browsing history, and CRM system information, as well as data provided by partner data providers.

[0742] "Competitive information" refers to data that shows competitors' activities, strategies, product information, etc. It includes information collected by crawling websites using methods such as web crawlers.

[0743] "Data cleansing" is the process of correcting or removing inaccurate, missing, or redundant portions of collected data, thereby improving the quality of the data set used for subsequent analysis.

[0744] A "generative AI model" is an AI model that uses artificial intelligence technology to analyze data and perform specific tasks, such as analyzing data based on a marketing framework or generating advertising copy.

[0745] A "marketing framework" refers to the basic frameworks and methods for formulating marketing strategies such as 3C, STP, and 4P. These frameworks provide an important analytical perspective in building a marketing strategy.

[0746] "Ad copy" refers to sentences and phrases that effectively communicate an advertisement or campaign. It is automatically generated using a generative AI model based on input concepts and keywords.

[0747] "Image generation AI" is an artificial intelligence technology that automatically generates visuals (images and designs) based on a specified concept or theme. This allows for the rapid and consistent generation of visuals for branding and advertising.

[0748] The "report format" is a document format that summarizes analysis results, strategic proposals, countermeasures, etc. in an easy-to-understand format. Charts and text are organized so that users can easily grasp the content.

[0749] A "predictive model" is a mathematical model that uses data to forecast future trends and outcomes. It is used to predict things like customer acquisition and churn.

[0750] Strategic planning is the process of devising and formulating the most effective marketing strategy based on collected and analyzed data, which determines the specific approach to achieving a company's goals.

[0751] This invention is a system for streamlining and optimizing corporate marketing activities, and realizes the functions of data collection, data analysis, strategy planning, creative generation, and customer prediction. This system is mainly composed of a server and user terminals, and implements multiple functions including generative AI models.

[0752] Hardware and software used

[0753] Hardware: Servers, user terminals, database servers, web crawlers

[0754] Software: Generative AI models, image generation AI, CRM systems, API integration tools, data cleansing tools, predictive models

[0755] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0756] To help users develop marketing strategies through their devices, the server collects market trend data, customer behavior data, and competitive information. Market trend data is primarily obtained from websites and APIs. Customer behavior data is collected from the company's CRM system and affiliated data providers, while competitive information is obtained from websites using web crawlers.

[0757] The collected data is cleansed by the server and compiled into an integrated dataset. This integrated dataset is input into a generative AI model, which performs analysis based on marketing frameworks such as 3C, STP, and 4P. A marketing strategy is developed based on the generated analysis results and provided to the user's device in report format.

[0758] Specific examples

[0759] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior.The user can use this information to find the appropriate target market and determine positioning.

[0760] Brand visuals + copy creation

[0761] The user inputs the campaign concept and keywords via their device. The server provides this input information to a generative AI model, which automatically generates advertising copy. At the same time, image generation AI is used to generate brand visuals. The generated advertising copy and brand visuals are integrated on the server and provided to the user's device.

[0762] Specific examples

[0763] When a user inputs the concept of "environmentally friendly products" for a new campaign, the server generates the copy "One choice to nurture the future" along with natural-looking visuals that match it, and delivers them to the user's device. The user then uses this to develop an advertisement. "An example of a prompt for the generative AI model is, 'Please generate advertising copy for an environmentally friendly product campaign.'"

[0764] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0765] The server collects and cleans customer data from the company's customer database. It then uses a predictive model to predict customer acquisition and churn, and analyzes the causes of churn based on the prediction results. Finally, it generates appropriate countermeasures and provides them to the user's device in the form of a report.

[0766] Specific examples

[0767] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The causes are identified as price competition and the emergence of new competitors. The server generates a report recommending countermeasures such as "implementing price promotions" or "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[0768] This system allows companies to efficiently in-house their marketing operations, reducing costs and accumulating marketing know-how.

[0769] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0770] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0771] Step 1: Data collection request

[0772] The user issues a data collection request from a terminal, specifying the data type (market trends, customer behavior, competitive information) required for formulating a marketing strategy.

[0773] Input: Data collection request details (data type, etc.)

[0774] Output: Data collection instructions to the server

[0775] Step 2: Collect market trend data

[0776] The server sends requests to designated websites or APIs to retrieve market trend data, which is then stored in a database.

[0777] Input: Website or API URL, query parameters

[0778] Output: Raw data (market trend information)

[0779] Specific behavior: The server sends an HTTP request to an API endpoint, receives the response, and stores it in a database.

[0780] Step 3: Collect customer behavior data

[0781] The server collects customer behavior data from the company's CRM system and partner data providers, retrieves the data via API, and stores it in a local database.

[0782] Input: API endpoint, authentication information

[0783] Output: Raw data (customer behavior information)

[0784] What happens: The server executes the API call and writes the returned data to a local database.

[0785] Step 4: Gather competitive intelligence

[0786] The server launches a web crawler to collect data from the websites of the specified competitors, which is then stored in a database.

[0787] Input: Competitor URL list

[0788] Output: Raw data (competitive information)

[0789] What it does: The server runs a web crawler and parses the HTML data to extract useful information.

[0790] Step 5: Data cleansing

[0791] The server cleanses the collected data and corrects or removes inaccuracies, missing parts, or duplicates.

[0792] Input: Raw datasets (market trends, customer behavior, competitive intelligence)

[0793] Output: Cleansed dataset

[0794] What it does: The server uses data cleansing tools to improve data consistency and accuracy.

[0795] Step 6: Data Integration

[0796] The server combines the cleansed data from multiple data sources into a single integrated data set.

[0797] Input: Cleansed dataset

[0798] Output: Unified dataset

[0799] Specific operation: The server performs a database join operation to generate a consolidated dataset.

[0800] Step 7: Data analysis

[0801] The server inputs the integrated data set into a generative AI model and performs analysis based on marketing frameworks such as 3C, STP, and 4P.

[0802] Input: Unified dataset

[0803] Output: Analysis results

[0804] Specific operations: The server runs the generative AI model and performs marketing analysis.

[0805] Step 8: Strategic Planning and Reporting

[0806] The server develops a marketing strategy based on the analysis results, compiles the results in report format, and delivers them to the user's device.

[0807] Input: Analysis results

[0808] Output: Marketing Strategy Report

[0809] What it does: The server uses a reporting tool to document the analysis results in a format that is easy to visualize.

[0810] Brand visuals + copy creation

[0811] Step 1: Concept entry

[0812] The user inputs the campaign concept and keywords into the system via a terminal.

[0813] Input: Campaign concept, keywords

[0814] Output: Input information to the server

[0815] Step 2: Input to the generative AI model

[0816] The server feeds input concepts and keywords into a generative AI model to generate ad copy, while also using image-generating AI to generate brand visuals.

[0817] Input: Campaign concept, keywords

[0818] Output: Advertising copy, brand visuals

[0819] Specific operation: The server passes the prompt sentence to the generative AI model and executes the generative AI model and image generation AI.

[0820] Step 3: Integrate copy and visuals

[0821] The server integrates the generated advertising copy with the brand visuals and provides them to the user's terminal.

[0822] Input: Ad copy, brand visuals

[0823] Output: Integrated marketing materials

[0824] Specific operation: The server combines the copy and visuals into a single file or document and sends it to the user's terminal.

[0825] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0826] Step 1: Collect and cleanse customer data

[0827] The server collects and cleans customer data from the company's customer database.

[0828] Input: Customer database

[0829] Output: Cleansed customer data

[0830] Specific operation: The server extracts data from the database, corrects outliers, and completes the data.

[0831] Step 2: Run the predictive model

[0832] The server inputs the cleansed customer data into a predictive model to predict customer acquisition and churn.

[0833] Input: Cleansed customer data

[0834] Output: Prediction results

[0835] What happens: The server applies the predictive model to predict customer behavior.

[0836] Step 3: Factor analysis

[0837] The server analyzes the reasons for customer abandonment based on the prediction results.

[0838] Input: Prediction result

[0839] Output: Factor analysis results

[0840] Specific actions: The server uses data analysis tools to identify the reasons for abandonment.

[0841] Step 4: Generate countermeasures

[0842] The server generates appropriate countermeasures based on the results of analyzing the reasons for dropout.

[0843] Input: Factor analysis results

[0844] Output: Countermeasures

[0845] Specific operation: The server uses the generative AI model to create countermeasures.

[0846] Step 5: Reporting

[0847] The server compiles the generated countermeasures into a report and provides it to the user's terminal.

[0848] Input: Countermeasures

[0849] Output: Countermeasures report

[0850] What happens: The server uses a reporting tool to document the proposed action and send it to the user.

[0851] (Application example 1)

[0852] 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."

[0853] Conventional marketing systems often require a huge amount of time and resources for data collection, analysis, and marketing strategy planning. Especially for advertising campaigns, specialized knowledge and skills are required to quickly create effective advertising copy and visuals. Furthermore, it is difficult to analyze market trends and obtain competitive information in real time, making it difficult to accurately predict customer behavior and quickly take countermeasures based on that information. To solve these problems, a multifunctional marketing support system is needed.

[0854] 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.

[0855] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple pieces of data, means for generating advertising copy using a generation AI, means for generating brand visuals using an image generation AI, and means for integrating the generated advertising copy and brand visuals and providing them to users. This makes it possible to grasp market trends, customer behavior, and competitive information in real time, and to quickly create and deploy effective advertising campaigns.

[0856] "Market trend data" is data that shows market trends and consumer behavior patterns.

[0857] "Customer behavior data" is data that records the actions of customers when they make purchases, browse, make inquiries, etc.

[0858] "Competitive information" is data about competing companies and products in the same market.

[0859] "Data cleansing" is the process of removing noise, redundancies, and errors from collected data and preparing it for use.

[0860] "Data integration" is the process of combining multiple data sets into a single, coherent data set.

[0861] "Generative AI" is artificial intelligence that automatically generates text, visuals, etc. using natural language processing models, etc.

[0862] "Ad copy" is a short, persuasive sentence or catchphrase used in an advertisement.

[0863] "Image generation AI" is an artificial intelligence that automatically generates images based on a specified concept.

[0864] "Brand visuals" are images and designs that visually express the brand's values ​​and messages.

[0865] "Real-time prediction" is a technology that instantly predicts future results based on current data.

[0866] "Report creation means" is a function that provides analysis results and strategy proposals to users in document format.

[0867] To realize this application example, cooperation between the server, terminals, and users is essential. The system of the present invention is composed of the following main means.

[0868] First, the server acquires market trend data. This data is acquired using tools that collect information from websites and APIs. Next, the server collects customer behavior data. This data is derived from the company's CRM system and partner data providers. Finally, the server uses a web crawler to acquire competitive information. This data is then cleansed on the server and compiled into a single, integrated dataset.

[0869] The integrated data set is analyzed and a generative AI is used to create a marketing strategy. Specifically, based on the concepts and keywords entered by the user, the generative AI generates advertising copy and the image generation AI generates brand visuals. For example, if a user enters the concept "environmentally friendly products," the server sends the following prompt to the generative AI: "Please create advertising copy based on the following concept: environmentally friendly products."

[0870] The generated advertising copy and brand visuals are integrated by the server and provided to the user's device. Based on this, the user can develop an effective advertising campaign. The server also analyzes market trends, competitive information, and customer behavior data in real time to predict the effectiveness of the advertising campaign. The results are fed back to the user in real time, allowing them to adjust their strategy as needed.

[0871] Regarding the hardware and software used, the server is a computer with high-performance data processing and AI models. Also, a Python program uses generative AI (e.g., GPT-3) and image generation AI (e.g., DALL-E). An application is installed on the user's device to receive and display the generated results.

[0872] This system makes it possible to grasp market trends and competitive information in real time, and quickly create and deploy effective advertising campaigns. Specifically, consider the case where a user inputs the concept of "environmentally friendly products." The server sends a prompt message saying, "Please create an advertising copy based on the following concept: environmentally friendly products," and generates the advertising copy "One choice to nurture the future" along with natural visuals that match it. This allows users to effectively deploy high-quality advertising campaigns.

[0873] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0874] Step 1:

[0875] The server obtains market trend data. Specifically, the server collects information about market trends from designated websites or APIs and stores it in a database. The input is market trend information from websites or APIs, and the output is organized market trend data.

[0876] Step 2:

[0877] The server collects customer behavior data. It retrieves the data from the company's CRM system or partner data providers, cleanses it, and integrates it into a database. The input is customer behavior data retrieved from the company's CRM system or data providers, and the output is cleansed customer behavior data.

[0878] Step 3:

[0879] The server obtains competitive information using a web crawler. This involves collecting competitor websites and public information and converting it into an analyzable format. The input is competitor information collected by the web crawler, and the output is formatted competitive information.

[0880] Step 4:

[0881] The server cleanses the acquired market trend data, customer behavior data, and competitive information to create an integrated dataset. The input is the various data obtained in the previous step, and the output is the integrated, cleansed dataset.

[0882] Step 5:

[0883] The server inputs the integrated dataset into the generative AI model for analysis, including analysis based on marketing frameworks such as 3C, STP, and 4P. The input is the integrated dataset, and the output is the analysis result of the generated marketing strategy.

[0884] Step 6:

[0885] The server uses a generation AI to generate advertising copy based on the concepts and keywords entered by the user. For example, if a user enters the concept "environmentally friendly products," the server sends the prompt "Please create advertising copy based on the following concept: environmentally friendly products" to the generation AI. The input is the user's concept or keywords, and the output is the generated advertising copy.

[0886] Step 7:

[0887] The server generates brand visuals using image generation AI based on the generated advertising copy. For example, it sends a prompt statement, "Please create an advertising visual based on an environmentally friendly product," to the image generation AI. The input is the generated advertising copy, and the output is the generated brand visual.

[0888] Step 8:

[0889] The server integrates the generated advertising copy and brand visuals and provides them to the user. The input is the generated advertising copy and brand visuals, and the output is the integrated advertising campaign materials, which the user can use to develop their advertising campaign.

[0890] Step 9:

[0891] The server analyzes market trends, customer behavior data, and competitive information in real time to predict the effectiveness of advertising campaigns. The inputs are market trend data, customer behavior data, and competitive information collected in real time, and the output is the predicted results of the advertising campaign.

[0892] Step 10:

[0893] The server feeds back the real-time prediction results to the user's device and modifies the strategy as necessary. The input is the real-time prediction results, and the output is a modified marketing strategy.

[0894] Through the above steps, the system of the present invention is able to grasp market trends and competitive information in real time, and quickly create and develop effective advertising campaigns.

[0895] 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.

[0896] This invention is a system for streamlining and optimizing corporate marketing operations, and in particular, by combining an emotion engine, it is possible to understand user emotions and generate marketing strategies and creatives more effectively. This system is mainly composed of a server, terminals, generation AI, and an emotion engine.

[0897] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0898] Users collect data through their devices to create marketing strategies. The server first obtains market trend data. This includes data collected from websites and APIs. Next, the server collects customer behavior data. This data is obtained from the company's CRM system and affiliated data providers. Competitive information is also obtained by the server using methods such as web crawlers. This data is then cleansed and integrated into a single, well-organized data set by the server.

[0899] The server then inputs the data into a generative AI model and performs analysis in accordance with marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy for the user and delivers it to the user's device in report format. Furthermore, by combining it with an emotion engine, it becomes possible to provide personalized strategies that take into account the user's emotional data.

[0900] Specific examples

[0901] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior. Based on user input, the emotion engine analyzes the user's level of excitement and interest, and suggests more appropriate target markets and positioning.

[0902] Brand visuals + copy creation

[0903] The user inputs the campaign concept and keywords via their device. The emotion engine analyzes the user's input and understands their emotional state at the time. The server provides this to the generation AI, which automatically generates advertising copy. At the same time, the server also uses image generation AI to generate brand visuals. The generated text and visuals are integrated on the server and provided to the user.

[0904] Specific examples

[0905] When a user inputs the concept "environmentally friendly products" for a new campaign, the emotion engine recognizes the user's emotion as "excitement." Based on this, the server generates the copy "One choice to nurture the future" along with energetic, natural visuals, which are then delivered to the user's device. The user then uses this to develop an advertisement.

[0906] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0907] The server collects and cleans customer data from a company's customer database. It then uses a predictive model to predict customer acquisition and churn. Based on the prediction results, the server analyzes the causes of churn and generates appropriate countermeasures. The generated countermeasures are delivered in report format to the user's device. Furthermore, by combining it with an emotion engine, it becomes possible to provide countermeasures that take user emotions into account.

[0908] Specific examples

[0909] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The emotion engine analyzes the users' feelings of "anxiety" and "dissatisfaction" and identifies price competition and the emergence of new competitors as the causes. The server generates a report recommending countermeasures such as "implementing price promotions" and "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[0910] This system allows companies to efficiently in-house their marketing operations, and by taking user emotions into account, they can implement even more effective marketing strategies.

[0911] The processing flow will be explained below.

[0912] Market trends / customer behavior / competitive analysis + marketing strategy planning

[0913] Step 1: Data collection

[0914] 1. Obtaining market trend data

[0915] The server retrieves data about market trends through the API, including economic indicators and consumer behavior.

[0916] 2. Collecting customer behavior data

[0917] The server collects customer purchase history and website visit records from the company's CRM system.

[0918] 3. Obtaining Competitive Information

[0919] The server uses a web crawler to collect public information (news, social media posts, etc.) about competitors.

[0920] Step 2: Data cleansing

[0921] 1. Data normalization

[0922] The server cleanses the collected data and corrects inconsistencies and missing values, for example, removing duplicate data and imputing missing values.

[0923] 2. Data integration

[0924] The server consolidates market trend data, customer behavior data, and competitive intelligence, and organizes it into a format suitable for analysis.

[0925] Step 3: Data analysis

[0926] 1. Entering data

[0927] The server inputs the cleansed data into the generation AI.

[0928] 2. Applying a Marketing Framework

[0929] The server uses generated AI to perform analysis based on marketing frameworks such as 3C, STP, and 4P.

[0930] Step 4: Integrating Emotional Data

[0931] 1. Entering emotions

[0932] The user inputs emotion data from the device, and the system recognizes the user's emotion by analyzing the voice and text input.

[0933] 2. Applying the Emotion Engine

[0934] The server uses an emotion engine to analyze the user's emotions and integrates the emotion data into the analysis results.

[0935] Step 5: Strategic planning

[0936] 1. Generating strategic proposals

[0937] The server generates an individually personalized marketing strategy based on the analysis results and sentiment data.

[0938] 2. Report creation

[0939] The server prepares a report summarizing strategic proposals.

[0940] Step 6: Delivering results

[0941] 1. Report Distribution

[0942] The server delivers the generated report to the user's terminal.

[0943] 2. Confirm and implement the strategy

[0944] Users can check the reports on their devices and plan and implement specific marketing strategies.

[0945] Brand visuals + copy creation

[0946] Step 1: User Input

[0947] 1. Concept input

[0948] The user enters the campaign concept and keywords into the input form on the device.

[0949] Step 2: Analyze the emotion data

[0950] 1. Emotion Analysis

[0951] The server uses an emotion engine to analyze emotions from concepts and keywords entered by the user.

[0952] Step 3: Generate a copy

[0953] 1. Concept Processing

[0954] The server provides concepts and keywords along with emotional data to the generation AI.

[0955] 2. Generative AI copy creation

[0956] The server generates the ad copy using generation AI.

[0957] Step 4: Generate the visuals

[0958] 1. Use of image generation AI

[0959] The server uses image generation AI to create brand visuals based on copy and emotional data.

[0960] Step 5: Creative Integration

[0961] 1. Integrate copy and visuals

[0962] The server integrates the generated ad copy with the brand visuals.

[0963] Step 6: Delivering results

[0964] 1. Creative Delivery

[0965] The server delivers the integrated creative to the user's device.

[0966] 2. Final confirmation and adoption

[0967] The user reviews the creative on their device and selects it as the final ad.

[0968] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[0969] Step 1: Data collection and cleansing

[0970] 1. Collection of Customer Data

[0971] A server collects customer data from a company's customer database.

[0972] 2. Data cleansing

[0973] The server cleanses the collected data and corrects inconsistencies and missing values.

[0974] Step 2: Run the predictive model

[0975] 1. Data model input

[0976] The server inputs the cleansed data into a predictive model.

[0977] 2. Customer acquisition and churn prediction

[0978] The server uses predictive models to analyze the likelihood of customer acquisition or churn.

[0979] Step 3: Integrating Emotional Data

[0980] 1. Entering emotions

[0981] The user inputs emotion data into the device. The emotion engine analyzes the voice and text input and recognizes the emotion.

[0982] 2. Application of Emotion Data

[0983] The server integrates the emotion data into the prediction results.

[0984] Step 4: Analyze causes and develop countermeasures

[0985] 1. Analysis of dropout factors

[0986] The server analyzes the factors behind customer abandonment based on the prediction results and emotional data.

[0987] 2. Generating countermeasures

[0988] The server generates specific countermeasures based on the analysis results.

[0989] Step 5: Create and deliver the report

[0990] 1. Report creation

[0991] The server creates a report summarizing the cause analysis and proposed countermeasures.

[0992] 2. Report distribution

[0993] The server delivers the generated report to the user's terminal.

[0994] 3. Implementing measures

[0995] The user checks the report on the device and takes specific measures.

[0996] This detailed processing flow enables the system of the present invention to automate and streamline marketing operations, and to solve many of the problems that companies face. In addition, by combining it with an emotion engine, it is possible to implement more effective marketing strategies that take user emotions into account.

[0997] Example 2

[0998] 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."

[0999] To respond to complex and diverse marketing environments, modern companies need to collect large amounts of data and analyze that data to develop effective marketing strategies. However, manually collecting, cleansing, and analyzing massive amounts of data requires time and effort, and the accuracy of the analysis often depends on human subjectivity, making it difficult to develop optimal marketing strategies. Furthermore, conventional marketing analysis methods have difficulty taking user emotions into account, and they have not been able to provide personalized strategies sufficiently. Therefore, there is a need for a system that can efficiently collect and analyze data and automatically generate marketing strategies that take user emotions into account.

[1000] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1001] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple pieces of data, means for analyzing data based on a marketing framework using a generative AI model, means for analyzing user emotion data using an emotion engine, means for formulating a marketing strategy based on the generated analysis results, and means for providing the generated marketing strategy to the user in report form. This enables efficient and accurate collection and analysis of data, and realizes automatic generation of a marketing strategy that takes user emotions into consideration.

[1002] "Market trend data" is information that indicates market trends and consumer behavior patterns, obtained from internet data sources and APIs.

[1003] "Customer behavior data" is information that shows how a company's customers behave, collected from CRM systems and affiliated data providers.

[1004] "Competitive information" refers to information about competitors' activities, products, and services, and is obtained using web crawlers.

[1005] "Data cleansing" is the process of removing missing values ​​and outliers from collected data to improve the quality of the data.

[1006] "Data integration" is the process of combining multiple data sets into a single, coherent data set.

[1007] A "generative AI model" is an artificial intelligence model that performs marketing analysis and text generation based on large amounts of data.

[1008] An "emotion engine" is software that analyzes a user's emotional state based on their input and behavior.

[1009] A "marketing framework" is an analytical tool used to plan marketing strategies, and includes 3C, STP, 4P, etc.

[1010] A "marketing strategy" is a strategy that a company should implement based on market trends, customer behavior, and competitive information.

[1011] A "report format" is a document format designed to communicate analysis results and strategies to users in an easy-to-understand manner.

[1012] "Ad Copy" means text used in a marketing campaign that is generated by a generative AI model.

[1013] "Brand visuals" are visual elements used in advertising and marketing campaigns that are generated by image generation AI.

[1014] A "predictive model" is an algorithm that predicts future customer behavior based on past data.

[1015] "Countermeasures" are specific countermeasures to problems such as customer defection, and are generated based on the analysis results.

[1016] This invention is a system for streamlining and optimizing corporate marketing operations, and in particular, by combining an emotion engine, it is possible to understand user emotions and generate marketing strategies and creatives more effectively. This system is mainly composed of a server, terminals, a generative AI model, and an emotion engine.

[1017] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1018] When a user issues a market research command from their device, the server executes the following steps: First, the server uses the Python requests library to retrieve market trend data from an external API. Next, the server uses an SQL query to collect customer behavior data from the company's CRM system. The server also uses BeautifulSoup to retrieve competitive information using a web crawler and collect that information.

[1019] The server cleanses the collected data using the pandas library and compiles it into a single integrated dataset. The cleansed dataset is then input into a generative AI model (using, for example, TensorFlow or PyTorch) and analyzed based on marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy and generates a PDF report using, for example, the PDFKit library.

[1020] Furthermore, the emotion engine analyzes the user's emotional data and personalizes marketing strategies. The report generated in this way is delivered from the server to the user's device, and the user can use it to decide on marketing measures.

[1021] Specific examples

[1022] When a user issues a command from a terminal saying, "Start market research for a new product," the server collects and analyzes market trends, customer behavior, and competitive information. For example, the user might enter the following prompt:

[1023] I'd like to create a marketing strategy for a new product. Can you provide me with an analysis of competitor trends and customer purchasing behavior?

[1024] Brand visuals + copy creation

[1025] When a user inputs a campaign concept or keywords through their device, the emotion engine analyzes the user's emotional state. Based on this emotional information, the server generates advertising copy using a generative AI model (e.g., GPT-3). The server then generates brand visuals using an image generation AI (e.g., DALL-E).

[1026] The generated advertising copy and brand visuals are integrated on the server and delivered to the user's device, where the user can use it to create content for their marketing campaign.

[1027] Specific examples

[1028] When a user enters "eco-friendly products" as their "new campaign concept," the emotion engine analyzes the user's emotion as "excitement." Based on this, the generative AI model generates the following ad copy:

[1029] One choice to nurture the future

[1030] In parallel, image generation AI generates energetic and natural visuals, which are then delivered to the user's device.

[1031] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1032] The server collects data from a company's customer database and cleans it using the pandas library. The server then predicts customer acquisition and churn using a machine learning model from Scikit-learn. Based on the prediction results, the server analyzes the reasons for churn and generates specific countermeasures.

[1033] The emotion engine analyzes the user's emotional data and personalizes countermeasures. The countermeasures are generated in report format and sent from the server to the user's device. The user then implements marketing measures based on this report.

[1034] Specific examples

[1035] The server analyzes customer data and discovers that purchases are declining in a particular segment. The emotion engine analyzes user "anxiety" and "dissatisfaction" and identifies price competition and the emergence of new competitors as the causes. Based on this information, the server generates specific countermeasures such as:

[1036] Implementing price promotions and strengthening loyalty programs

[1037] These proposed solutions are provided to the user in the form of a report.

[1038] As described above, the system of the present invention achieves efficient and accurate collection and analysis of data, and automatically generates marketing strategies and creatives that take user emotions into consideration.

[1039] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1040] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1041] Step 1:

[1042] The user issues market research instructions from the terminal.

[1043] Input: The user types "Start market research for new product" into the terminal and presses the "Collect data" button.

[1044] Output: Market research instructions are sent to the server.

[1045] Step 2:

[1046] The server retrieves market trend data.

[1047] Input: Receive market research instructions.

[1048] Data processing / calculation: The server uses the requests library to retrieve market trend data from external APIs.

[1049] What happens: The server sends a request to a specific API endpoint and receives market trend data in JSON format.

[1050] Output: Obtained market trend data.

[1051] Step 3:

[1052] The server collects customer behavior data.

[1053] Input: Access the CRM system using an SQL query.

[1054] Data processing / calculation: Extract customer behavior data and format it using the pandas library.

[1055] Specific operation: Extract the necessary customer behavior data from the SQL database and convert it into a data frame.

[1056] Output: Collected customer behavior data.

[1057] Step 4:

[1058] The server retrieves the conflict information.

[1059] Input: Scraping instructions using a web crawler.

[1060] Data processing / calculation: Use the BeautifulSoup library to crawl competitors' websites and extract data.

[1061] What it does: The server accesses the web page of each competitor and runs a script to extract the required information.

[1062] Output: The obtained competitive intelligence data.

[1063] Step 5:

[1064] The server performs data cleansing and integration.

[1065] Inputs: Captured market trend data, customer behavior data, and competitive intelligence data.

[1066] Data processing / calculation: Use the pandas library to fill in missing values ​​and remove outliers to create a single integrated dataset.

[1067] Specific actions: Run scripts to impute missing values, remove outliers, merge necessary fields, etc.

[1068] Output: A cleansed, consolidated dataset.

[1069] Step 6:

[1070] The server analyzes the data using the generative AI model.

[1071] Input: The cleansed consolidated dataset.

[1072] Data processing / computation: Use generative AI models (e.g., PyTorch, TensorFlow) to perform analysis based on marketing frameworks.

[1073] How it works: The integrated dataset is fed into a generative AI model to obtain results based on frameworks such as 3C, STP, and 4P.

[1074] Output: Analysis results.

[1075] Step 7:

[1076] The server creates marketing strategies and generates reports.

[1077] Input: Analysis results.

[1078] Data processing / calculation: Use the PDFKit library to visualize the analysis results and create detailed PDF reports.

[1079] What it does: Generate graphs and charts from the analysis results and convert them to PDF format.

[1080] Output: PDF report.

[1081] Step 8:

[1082] The server uses an emotion engine to personalize the marketing strategy.

[1083] Input: PDF report and user sentiment data.

[1084] Data processing / calculation: The emotion engine analyzes the user's past inputs and reactions to customize the report content.

[1085] What it does: Perform real-time analysis using the sentiment engine and adjust some of the reports.

[1086] Output: Personalized PDF report.

[1087] Step 9:

[1088] The server delivers the report to the user.

[1089] Input: A personalized PDF report.

[1090] Output: The report is delivered to the user's device.

[1091] Brand visuals + copy creation

[1092] Step 1:

[1093] The user enters the campaign concept and keywords into the terminal.

[1094] Input: Campaign concept or keywords (e.g. "eco-friendly products").

[1095] Output: The input concepts or keywords.

[1096] Step 2:

[1097] An emotion engine analyzes the user's emotional state.

[1098] Input: The concept or keyword entered.

[1099] Data processing / calculation: The emotion engine analyzes the user's emotions.

[1100] Specific behavior: Analyzes emotional state (e.g., "excited") in real time based on user input.

[1101] Output: Parsed emotion data.

[1102] Step 3:

[1103] The server generates the ad copy using a generative AI model.

[1104] Input: Sentiment data and concepts, keywords.

[1105] Data processing / computation: Using generative AI models (e.g., GPT-3) to generate ad copy based on sentiment data.

[1106] What it does: Concepts and keywords are input as prompts into the generation AI, which then generates ad copy.

[1107] Output: The generated ad copy.

[1108] Step 4:

[1109] The server generates brand visuals using image generation AI.

[1110] Input: ad copy and sentiment data.

[1111] Data processing / calculation: Use image generation AI (e.g., DALL-E) to generate brand visuals based on emotional data.

[1112] What it does: Ad copy is fed into an image generation AI as a prompt to generate a visual.

[1113] Output: Generated brand visuals.

[1114] Step 5:

[1115] The server integrates the generated ad copy with the brand visuals.

[1116] Input: Generated ad copy and brand visuals.

[1117] Data processing / calculation: Integrate copy and visuals into one file in HTML format.

[1118] What it does: Runs a script that embeds ad copy and brand visuals into an HTML template.

[1119] Output: Integrated marketing content.

[1120] Step 6:

[1121] The server provides the aggregated content to the user.

[1122] Input: Integrated marketing content.

[1123] Output: The content is delivered to the user's device.

[1124] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1125] Step 1:

[1126] The server collects and cleanses customer data.

[1127] Input: Instructions to gather customer data from a company database using an SQL query.

[1128] Data processing / calculation: Cleanse the data using the pandas library.

[1129] Specific behavior: Extract data from SQL database and handle missing values ​​and outliers.

[1130] Output: Cleansed customer data.

[1131] Step 2:

[1132] The server uses a predictive model to predict customer acquisition and churn.

[1133] Input: Cleansed customer data.

[1134] Data processing / calculation: Predictions are made using Scikit-learn machine learning models.

[1135] Specific operation: The cleansed data is input into a predictive model to generate acquisition and churn predictions.

[1136] Output: Prediction results.

[1137] Step 3:

[1138] The server analyzes the reasons for dropout based on the prediction results.

[1139] Input: Prediction results.

[1140] Data processing / calculation: Identify reasons for dropout using analytical methods such as Feature Importance.

[1141] Specific operation: Analyze important variables of the model to identify customer abandonment factors from the prediction results.

[1142] Output: Dropout factors.

[1143] Step 4:

[1144] The server generates specific countermeasures.

[1145] Input: Churn factors.

[1146] Data processing / calculation: Consider quantitative and qualitative data to generate countermeasures.

[1147] Specific actions: Based on the reasons for abandonment, we propose countermeasures such as price promotions and strengthening loyalty programs.

[1148] Output: Proposed solution.

[1149] Step 5:

[1150] Use an emotion engine to personalize countermeasures.

[1151] Input: Countermeasure proposal and user sentiment data.

[1152] Data processing / calculation: The emotion engine analyzes the user's emotional data and customizes countermeasures.

[1153] Specific actions: Adjust some of the proposed countermeasures based on the user's past reactions and emotional data.

[1154] Output: Personalized countermeasures.

[1155] Step 6:

[1156] The server generates the report and delivers it to the user.

[1157] Input: personalized countermeasures.

[1158] Data processing / calculation: Use libraries such as PDFKit to create a report of proposed countermeasures.

[1159] Specific operation: A report in PDF format is generated based on the proposed countermeasures and delivered to the user's device.

[1160] Output: A personalized action report.

[1161] The above is the specific processing flow of this system.

[1162] (Application example 2)

[1163] 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."

[1164] Conventional marketing systems developed marketing strategies and generated advertising copy and brand visuals based on market trend data, customer behavior data, and competitive intelligence. However, they were unable to generate personalized strategies and advertisements that took user emotions into account. As a result, marketing effectiveness was insufficient, resulting in a decrease in appeal to target customers. Furthermore, because they were unable to analyze customer emotions and develop countermeasures that took these emotions into account, the accuracy of customer churn prevention measures and customer acquisition strategies was low. To address these issues, technology that can analyze emotions and reflect them in marketing is required.

[1165] 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.

[1166] In this invention, the server includes means for analyzing emotions, means for personalizing a marketing strategy based on the emotion analysis results, means for generating advertising copy using a generation AI, means for generating brand visuals using an image generation AI, means for personalizing the generated advertising copy and visuals based on the emotion analysis results, and means for personalizing countermeasures based on the emotion analysis results. This makes it possible to create effective marketing strategies that reflect user emotions, generate personalized advertising copy and visuals, and develop countermeasures.

[1167] "Market trend data" is data that shows the overall trends and tendencies of the market.

[1168] "Customer behavior data" refers to data that indicates customer behavior, such as customer purchase history and website browsing history.

[1169] "Competitive information" is information about competitors' companies and products.

[1170] "Means for analyzing emotions" refers to means for analyzing text, audio, images, etc. to identify a user's emotional state.

[1171] "Means for personalizing marketing strategies based on the results of sentiment analysis" refers to means for creating marketing strategies optimized for individual users using the results of sentiment analysis.

[1172] "Methods for generating advertising copy using generative AI" refers to methods for automatically creating advertising copy using artificial intelligence.

[1173] "Method for generating brand visuals using image generation AI" refers to a method for automatically creating visual elements of a brand using artificial intelligence.

[1174] "Means for integrating advertising copy and brand visuals" refers to means for combining the generated advertising copy and brand visuals into a single advertisement.

[1175] "Means for personalizing advertising copy and visuals generated based on the results of sentiment analysis" refers to a means for creating advertising copy and visuals that are most suitable for individual users based on the results of sentiment analysis.

[1176] "Analytical methods for predicting customer acquisition and churn" are methods that analyze customer data and predict whether new customers will be acquired or whether they will churn.

[1177] "Means for analyzing reasons for customer churn" refers to a method for analyzing data to identify the reasons why customers churn.

[1178] The "means for generating countermeasures" is a means for automatically creating appropriate countermeasures based on the reasons for dropout.

[1179] "Means for personalizing countermeasures" refers to creating countermeasures that are optimal for individual users based on the results of sentiment analysis.

[1180] The system of this invention streamlines marketing operations and enables the generation of personalized marketing strategies, advertising copy, brand visuals, and countermeasures based on user emotions. The specific configuration of the system and its processing procedures are described below.

[1181] First, the server acquires market trend data, customer behavior data, and competitive information, cleansing and integrating them. Next, the integrated data is input into a generative AI model and analyzed based on a marketing framework. Based on the analysis results, a marketing strategy is formulated and provided to users in the form of a report, utilizing sentiment analysis methods. The results of the sentiment analysis are used to personalize the marketing strategy.

[1182] The system has the ability to generate ad copy using generative AI, and also includes the ability to generate brand visuals using image generation AI based on the generated ad copy. Furthermore, the system personalizes the generated ad copy and visuals based on the results of sentiment analysis and provides them to users.

[1183] For example, suppose a user inputs the concept "environmentally friendly product" and their emotion at the time is "excitement." The server confirms this emotion using an emotion analysis engine and inputs it into the generative AI model. Based on this information, the generative AI model generates advertising copy such as "One choice to nurture the future" along with energetic, natural visuals, and presents them to the user.

[1184] Sentiment analysis is performed by analyzing text, audio, and image data, and the emotion engine used is the Emotion Engine API. The generative AI model is applied using the Generation AI API. This processing enables the creation of effective marketing strategies and advertisements that reflect user emotions.

[1185] Examples of specific prompts include:

[1186] "Excitement, eco-friendly products"

[1187] This allows companies to implement personalized marketing strategies that take user emotions into account, increasing the appeal of advertising and improving the effectiveness of customer acquisition and retention.

[1188] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1189] Step 1:

[1190] The server obtains market trend data, customer behavior data, and competitive information.

[1191] Inputs: Market trend data from websites and APIs, customer behavior data from a company's CRM system and partner data providers, competitive intelligence obtained through web crawlers and other means.

[1192] Output: Raw market trend data, customer behavior data, competitive intelligence.

[1193] Specific operation: Collect necessary data from multiple data sources and import it into the server.

[1194] Step 2:

[1195] The server cleanses the retrieved data.

[1196] Inputs: Raw market trend data, customer behavior data, competitive intelligence.

[1197] Output: A cleansed and tidy dataset.

[1198] Specific Actions: Deduplicate, format, and correct inaccurate data.

[1199] Step 3:

[1200] The server integrates multiple data sets and performs analysis.

[1201] Input: The cleansed dataset.

[1202] Output: Data for input into a generative AI model.

[1203] Specific actions: Classify and aggregate data and analyze it in line with marketing frameworks (3C, STP, 4P, etc.).

[1204] Step 4:

[1205] The server formulates a marketing strategy based on the generated analysis results.

[1206] Input: Data for input to a generative AI model.

[1207] Output: Proposed marketing strategy.

[1208] Specific operation: Input data into the generative AI model and create a specific marketing strategy based on the analysis results.

[1209] Step 5:

[1210] The server analyzes the user's emotion data using an emotion analysis means.

[1211] Input: User input text, voice, or image data.

[1212] Output: The user's emotional state.

[1213] What it does: It uses the Emotion Engine API to analyze text, audio, and image data to identify the user's emotional state.

[1214] Step 6:

[1215] The server personalizes the marketing strategy based on the sentiment analysis results.

[1216] Input: Marketing strategy ideas, user emotional state.

[1217] Output: Personalized marketing strategies.

[1218] Specific operation: Reflecting the results of sentiment analysis, we create marketing strategies optimized for individual users.

[1219] Step 7:

[1220] The server generates the ad copy using a generation AI.

[1221] Input: Concepts, keywords, and the user's emotional state.

[1222] Output: Ad copy.

[1223] Specific operation: Input the prompt text into the generative AI model (Generation AI API) to automatically generate ad copy.

[1224] An example of a specific prompt: "Excitement, eco-friendly products."

[1225] Step 8:

[1226] The server uses image generation AI to generate brand visuals based on the generated advertising copy.

[1227] Input: ad copy, user's emotional state.

[1228] Output: Brand visuals.

[1229] What it does: Uses image generation AI to create branded visuals that perfectly complement ad copy.

[1230] Step 9:

[1231] The server integrates the generated advertising copy with the brand visuals and provides them to the user.

[1232] Input: ad copy, brand visuals.

[1233] Output: Integrated advertising content.

[1234] Specific operation: The generated ad copy and visuals are compiled into one ad content and provided to the user.

[1235] Step 10:

[1236] The server cleanses customer data, analyzes reasons for customer abandonment, and generates countermeasures.

[1237] Input: Customer behavior data, emotional state.

[1238] Output: Personalized countermeasures.

[1239] Specific operations: Organize customer data, identify reasons for abandonment based on sentiment analysis results, and automatically generate appropriate countermeasures.

[1240] 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.

[1241] 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.

[1242] 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.

[1243] [Third embodiment]

[1244] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1245] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1246] 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).

[1247] 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.

[1248] 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.

[1249] 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).

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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."

[1256] This invention is a system for streamlining and optimizing corporate marketing activities, and mainly realizes the functions of data collection, data analysis, strategy planning, creative generation, and customer forecasting. This system is mainly composed of a server and user terminals, and implements multiple functions including generation AI.

[1257] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1258] Users collect data through their devices to create marketing strategies. The server first obtains market trend data. This includes data collected from websites and APIs. Next, the server collects customer behavior data. This data is obtained from the company's CRM system and affiliated data providers. Competitive information is also obtained by the server using methods such as web crawlers. This data is then cleansed and integrated into a single, well-organized data set by the server.

[1259] The server then inputs the data into a generative AI model and performs analysis in accordance with marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy for the user and delivers it to the user's device in the form of a report.

[1260] Specific examples

[1261] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior.The user can use this information to find the appropriate target market and determine positioning.

[1262] Brand visuals + copy creation

[1263] The user inputs the campaign concept and keywords through the device. The server provides the input information to the generation AI, which automatically generates the ad copy. At the same time, the server also uses the image generation AI to generate brand visuals. The generated text and visuals are integrated on the server and provided to the user.

[1264] Specific examples

[1265] When a user inputs the concept of "environmentally friendly products" for a new campaign, the server generates the copy "One choice to nurture the future" along with a natural-looking visual that matches it, and delivers it to the user's device. The user then uses this to develop an advertisement.

[1266] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1267] The server collects and cleans customer data from the company's customer database. It then uses a predictive model to predict customer acquisition and churn. Based on the prediction results, the server analyzes the causes of churn and generates appropriate countermeasures. The generated countermeasures are delivered to the user's device in report format.

[1268] Specific examples

[1269] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The causes are identified as price competition and the emergence of new competitors. The server generates a report recommending countermeasures such as "implementing price promotions" or "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[1270] This system allows companies to efficiently in-house their marketing operations, reducing costs and accumulating marketing know-how.

[1271] The processing flow will be explained below.

[1272] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1273] Step 1: Data collection

[1274] 1. Obtaining market trend data

[1275] The server retrieves data about market trends through websites and APIs.

[1276] 2. Collecting customer behavior data

[1277] The server collects customer behavior data from the company's CRM system and affiliated data providers.

[1278] 3. Obtaining Competitive Information

[1279] The server uses web crawlers to gather information about competitors, including news, blogs, and social media data.

[1280] Step 2: Data cleansing

[1281] 1. Data normalization

[1282] The server inspects the collected data and corrects noise and missing values.

[1283] 2. Data integration

[1284] The server aggregates data from different sources into a single, coherent data set.

[1285] Step 3: Data analysis

[1286] 1. Entering data

[1287] The server inputs the prepared data into the generation AI.

[1288] 2. Applying a Marketing Framework

[1289] The server uses generated AI to perform analysis based on marketing frameworks such as 3C, STP, and 4P.

[1290] Step 4: Strategic planning

[1291] 1. Generating strategic proposals

[1292] The server generates marketing strategy proposals based on the analysis results.

[1293] 2. Report creation

[1294] The server prepares a report summarizing strategic proposals.

[1295] Step 5: Delivering results

[1296] 1. Report Distribution

[1297] The server delivers the generated report to the user's terminal.

[1298] 2. Confirm and implement the strategy

[1299] Users can check the reports on their devices and plan and implement specific marketing strategies.

[1300] Brand visuals + copy creation

[1301] Step 1: User Input

[1302] 1. Concept input

[1303] The user enters the campaign concept and keywords into the input form on the device.

[1304] Step 2: Generate a copy

[1305] 1. Concept Processing

[1306] The server analyzes the concepts and keywords entered.

[1307] 2. Generative AI copy creation

[1308] The server generates the ad copy using generation AI.

[1309] Step 3: Generate the visuals

[1310] 1. Use of image generation AI

[1311] The server creates brand visuals based on the copy using image generation AI.

[1312] Step 4: Creative Integration

[1313] 1. Integrate copy and visuals

[1314] The server integrates the generated ad copy with the brand visuals.

[1315] Step 5: Delivering results

[1316] 1. Creative Delivery

[1317] The server delivers the integrated creative to the user's device.

[1318] 2. Final confirmation and adoption

[1319] The user reviews the creative on their device and selects it as the final ad.

[1320] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1321] Step 1: Data collection and cleansing

[1322] 1. Collection of Customer Data

[1323] A server collects customer data from a company's customer database.

[1324] 2. Data cleansing

[1325] The server cleanses the collected data and puts it in a form suitable for analysis.

[1326] Step 2: Predictive analytics

[1327] 1. Data model input

[1328] The server inputs the cleansed data into a predictive model.

[1329] 2. Customer acquisition and churn prediction

[1330] The server uses predictive models to analyze the likelihood of customer acquisition or churn.

[1331] Step 3: Analyze causes and develop countermeasures

[1332] 1. Analysis of dropout factors

[1333] Based on the prediction results, the server analyzes the factors that cause customers to leave.

[1334] 2. Generating countermeasures

[1335] The server generates specific countermeasures based on the analysis results.

[1336] Step 4: Create and deliver the report

[1337] 1. Report creation

[1338] The server creates a report summarizing the cause analysis and proposed countermeasures.

[1339] 2. Report distribution

[1340] The server delivers the generated report to the user's terminal.

[1341] 3. Implementing measures

[1342] The user checks the report on the device and takes specific measures.

[1343] With this detailed processing flow, the system of the present invention can automate and streamline marketing operations, and solve many of the problems that companies face.

[1344] Example 1

[1345] 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."

[1346] In conventional marketing systems, each process, such as data collection, cleansing, analysis, and strategy planning, is performed piecemeal, preventing overall efficiency and optimization. Furthermore, it is often difficult to link individual data analysis tools and ad copy generation tools, resulting in a lack of consistency in marketing activities. The present invention aims to provide a system that comprehensively solves these issues and streamlines and optimizes the entire marketing process.

[1347] 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.

[1348] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple data, means for inputting data into a generative AI model and performing analysis based on a marketing framework, means for formulating a marketing strategy based on the generated analysis results, and means for providing the generated marketing strategy to a user in the form of a report. This makes it possible to consistently and efficiently carry out the marketing process from data collection to analysis, strategy formulation, and report creation.

[1349] "Market trend data" refers to data that shows market trends and demand, competitor trends, consumer preferences, etc. It includes dynamic information collected from websites and APIs and obtained from a variety of sources.

[1350] "Customer behavior data" refers to data that shows how customers behave. This includes data collected internally by a company, such as purchase history, browsing history, and CRM system information, as well as data provided by partner data providers.

[1351] "Competitive information" refers to data that shows competitors' activities, strategies, product information, etc. It includes information collected by crawling websites using methods such as web crawlers.

[1352] "Data cleansing" is the process of correcting or removing inaccurate, missing, or redundant portions of collected data, thereby improving the quality of the data set used for subsequent analysis.

[1353] A "generative AI model" is an AI model that uses artificial intelligence technology to analyze data and perform specific tasks, such as analyzing data based on a marketing framework or generating advertising copy.

[1354] A "marketing framework" refers to the basic frameworks and methods for formulating marketing strategies such as 3C, STP, and 4P. These frameworks provide an important analytical perspective in building a marketing strategy.

[1355] "Ad copy" refers to sentences and phrases that effectively communicate an advertisement or campaign. It is automatically generated using a generative AI model based on input concepts and keywords.

[1356] "Image generation AI" is an artificial intelligence technology that automatically generates visuals (images and designs) based on a specified concept or theme. This allows for the rapid and consistent generation of visuals for branding and advertising.

[1357] The "report format" is a document format that summarizes analysis results, strategic proposals, countermeasures, etc. in an easy-to-understand format. Charts and text are organized so that users can easily grasp the content.

[1358] A "predictive model" is a mathematical model that uses data to forecast future trends and outcomes. It is used to predict things like customer acquisition and churn.

[1359] Strategic planning is the process of devising and formulating the most effective marketing strategy based on collected and analyzed data, which determines the specific approach to achieving a company's goals.

[1360] This invention is a system for streamlining and optimizing corporate marketing activities, and realizes the functions of data collection, data analysis, strategy planning, creative generation, and customer prediction. This system is mainly composed of a server and user terminals, and implements multiple functions including generative AI models.

[1361] Hardware and software used

[1362] Hardware: Servers, user terminals, database servers, web crawlers

[1363] Software: Generative AI models, image generation AI, CRM systems, API integration tools, data cleansing tools, predictive models

[1364] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1365] To help users develop marketing strategies through their devices, the server collects market trend data, customer behavior data, and competitive information. Market trend data is primarily obtained from websites and APIs. Customer behavior data is collected from the company's CRM system and affiliated data providers, while competitive information is obtained from websites using web crawlers.

[1366] The collected data is cleansed by the server and compiled into an integrated dataset. This integrated dataset is input into a generative AI model, which performs analysis based on marketing frameworks such as 3C, STP, and 4P. A marketing strategy is developed based on the generated analysis results and provided to the user's device in report format.

[1367] Specific examples

[1368] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior.The user can use this information to find the appropriate target market and determine positioning.

[1369] Brand visuals + copy creation

[1370] The user inputs the campaign concept and keywords via their device. The server provides this input information to a generative AI model, which automatically generates advertising copy. At the same time, image generation AI is used to generate brand visuals. The generated advertising copy and brand visuals are integrated on the server and provided to the user's device.

[1371] Specific examples

[1372] When a user inputs the concept of "environmentally friendly products" for a new campaign, the server generates the copy "One choice to nurture the future" along with natural-looking visuals that match it, and delivers them to the user's device. The user then uses this to develop an advertisement. "An example of a prompt for the generative AI model is, 'Please generate advertising copy for an environmentally friendly product campaign.'"

[1373] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1374] The server collects and cleans customer data from the company's customer database. It then uses a predictive model to predict customer acquisition and churn, and analyzes the causes of churn based on the prediction results. Finally, it generates appropriate countermeasures and provides them to the user's device in the form of a report.

[1375] Specific examples

[1376] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The causes are identified as price competition and the emergence of new competitors. The server generates a report recommending countermeasures such as "implementing price promotions" or "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[1377] This system allows companies to efficiently in-house their marketing operations, reducing costs and accumulating marketing know-how.

[1378] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1379] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1380] Step 1: Data collection request

[1381] The user issues a data collection request from a terminal, specifying the data type (market trends, customer behavior, competitive information) required for formulating a marketing strategy.

[1382] Input: Data collection request details (data type, etc.)

[1383] Output: Data collection instructions to the server

[1384] Step 2: Collect market trend data

[1385] The server sends requests to designated websites or APIs to retrieve market trend data, which is then stored in a database.

[1386] Input: Website or API URL, query parameters

[1387] Output: Raw data (market trend information)

[1388] Specific behavior: The server sends an HTTP request to an API endpoint, receives the response, and stores it in a database.

[1389] Step 3: Collect customer behavior data

[1390] The server collects customer behavior data from the company's CRM system and partner data providers, retrieves the data via API, and stores it in a local database.

[1391] Input: API endpoint, authentication information

[1392] Output: Raw data (customer behavior information)

[1393] What happens: The server executes the API call and writes the returned data to a local database.

[1394] Step 4: Gather competitive intelligence

[1395] The server launches a web crawler to collect data from the websites of the specified competitors, which is then stored in a database.

[1396] Input: Competitor URL list

[1397] Output: Raw data (competitive information)

[1398] What it does: The server runs a web crawler and parses the HTML data to extract useful information.

[1399] Step 5: Data cleansing

[1400] The server cleanses the collected data and corrects or removes inaccuracies, missing parts, or duplicates.

[1401] Input: Raw datasets (market trends, customer behavior, competitive intelligence)

[1402] Output: Cleansed dataset

[1403] What it does: The server uses data cleansing tools to improve data consistency and accuracy.

[1404] Step 6: Data Integration

[1405] The server combines the cleansed data from multiple data sources into a single integrated data set.

[1406] Input: Cleansed dataset

[1407] Output: Unified dataset

[1408] Specific operation: The server performs a database join operation to generate a consolidated dataset.

[1409] Step 7: Data analysis

[1410] The server inputs the integrated data set into a generative AI model and performs analysis based on marketing frameworks such as 3C, STP, and 4P.

[1411] Input: Unified dataset

[1412] Output: Analysis results

[1413] Specific operations: The server runs the generative AI model and performs marketing analysis.

[1414] Step 8: Strategic Planning and Reporting

[1415] The server develops a marketing strategy based on the analysis results, compiles the results in report format, and delivers them to the user's device.

[1416] Input: Analysis results

[1417] Output: Marketing Strategy Report

[1418] What it does: The server uses a reporting tool to document the analysis results in a format that is easy to visualize.

[1419] Brand visuals + copy creation

[1420] Step 1: Concept entry

[1421] The user inputs the campaign concept and keywords into the system via a terminal.

[1422] Input: Campaign concept, keywords

[1423] Output: Input information to the server

[1424] Step 2: Input to the generative AI model

[1425] The server feeds input concepts and keywords into a generative AI model to generate ad copy, while also using image-generating AI to generate brand visuals.

[1426] Input: Campaign concept, keywords

[1427] Output: Advertising copy, brand visuals

[1428] Specific operation: The server passes the prompt sentence to the generative AI model and executes the generative AI model and image generation AI.

[1429] Step 3: Integrate copy and visuals

[1430] The server integrates the generated advertising copy with the brand visuals and provides them to the user's terminal.

[1431] Input: Ad copy, brand visuals

[1432] Output: Integrated marketing materials

[1433] Specific operation: The server combines the copy and visuals into a single file or document and sends it to the user's terminal.

[1434] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1435] Step 1: Collect and cleanse customer data

[1436] The server collects and cleans customer data from the company's customer database.

[1437] Input: Customer database

[1438] Output: Cleansed customer data

[1439] Specific operation: The server extracts data from the database, corrects outliers, and completes the data.

[1440] Step 2: Run the predictive model

[1441] The server inputs the cleansed customer data into a predictive model to predict customer acquisition and churn.

[1442] Input: Cleansed customer data

[1443] Output: Prediction results

[1444] What happens: The server applies the predictive model to predict customer behavior.

[1445] Step 3: Factor analysis

[1446] The server analyzes the reasons for customer abandonment based on the prediction results.

[1447] Input: Prediction result

[1448] Output: Factor analysis results

[1449] Specific actions: The server uses data analysis tools to identify the reasons for abandonment.

[1450] Step 4: Generate countermeasures

[1451] The server generates appropriate countermeasures based on the results of analyzing the reasons for dropout.

[1452] Input: Factor analysis results

[1453] Output: Countermeasures

[1454] Specific operation: The server uses the generative AI model to create countermeasures.

[1455] Step 5: Reporting

[1456] The server compiles the generated countermeasures into a report and provides it to the user's terminal.

[1457] Input: Countermeasures

[1458] Output: Countermeasures report

[1459] What happens: The server uses a reporting tool to document the proposed action and send it to the user.

[1460] (Application example 1)

[1461] 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."

[1462] Conventional marketing systems often require a huge amount of time and resources for data collection, analysis, and marketing strategy planning. Especially for advertising campaigns, specialized knowledge and skills are required to quickly create effective advertising copy and visuals. Furthermore, it is difficult to analyze market trends and obtain competitive information in real time, making it difficult to accurately predict customer behavior and quickly take countermeasures based on that information. To solve these problems, a multifunctional marketing support system is needed.

[1463] 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.

[1464] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple pieces of data, means for generating advertising copy using a generation AI, means for generating brand visuals using an image generation AI, and means for integrating the generated advertising copy and brand visuals and providing them to users. This makes it possible to grasp market trends, customer behavior, and competitive information in real time, and to quickly create and deploy effective advertising campaigns.

[1465] "Market trend data" is data that shows market trends and consumer behavior patterns.

[1466] "Customer behavior data" is data that records the actions of customers when they make purchases, browse, make inquiries, etc.

[1467] "Competitive information" is data about competing companies and products in the same market.

[1468] "Data cleansing" is the process of removing noise, redundancies, and errors from collected data and preparing it for use.

[1469] "Data integration" is the process of combining multiple data sets into a single, coherent data set.

[1470] "Generative AI" is artificial intelligence that automatically generates text, visuals, etc. using natural language processing models, etc.

[1471] "Ad copy" is a short, persuasive sentence or catchphrase used in an advertisement.

[1472] "Image generation AI" is an artificial intelligence that automatically generates images based on a specified concept.

[1473] "Brand visuals" are images and designs that visually express the brand's values ​​and messages.

[1474] "Real-time prediction" is a technology that instantly predicts future results based on current data.

[1475] "Report creation means" is a function that provides analysis results and strategy proposals to users in document format.

[1476] To realize this application example, cooperation between the server, terminals, and users is essential. The system of the present invention is composed of the following main means.

[1477] First, the server acquires market trend data. This data is acquired using tools that collect information from websites and APIs. Next, the server collects customer behavior data. This data is derived from the company's CRM system and partner data providers. Finally, the server uses a web crawler to acquire competitive information. This data is then cleansed on the server and compiled into a single, integrated dataset.

[1478] The integrated data set is analyzed and a generative AI is used to create a marketing strategy. Specifically, based on the concepts and keywords entered by the user, the generative AI generates advertising copy and the image generation AI generates brand visuals. For example, if a user enters the concept "environmentally friendly products," the server sends the following prompt to the generative AI: "Please create advertising copy based on the following concept: environmentally friendly products."

[1479] The generated advertising copy and brand visuals are integrated by the server and provided to the user's device. Based on this, the user can develop an effective advertising campaign. The server also analyzes market trends, competitive information, and customer behavior data in real time to predict the effectiveness of the advertising campaign. The results are fed back to the user in real time, allowing them to adjust their strategy as needed.

[1480] Regarding the hardware and software used, the server is a computer with high-performance data processing and AI models. Also, a Python program uses generative AI (e.g., GPT-3) and image generation AI (e.g., DALL-E). An application is installed on the user's device to receive and display the generated results.

[1481] This system makes it possible to grasp market trends and competitive information in real time, and quickly create and deploy effective advertising campaigns. Specifically, consider the case where a user inputs the concept of "environmentally friendly products." The server sends a prompt message saying, "Please create an advertising copy based on the following concept: environmentally friendly products," and generates the advertising copy "One choice to nurture the future" along with natural visuals that match it. This allows users to effectively deploy high-quality advertising campaigns.

[1482] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1483] Step 1:

[1484] The server obtains market trend data. Specifically, the server collects information about market trends from designated websites or APIs and stores it in a database. The input is market trend information from websites or APIs, and the output is organized market trend data.

[1485] Step 2:

[1486] The server collects customer behavior data. It retrieves the data from the company's CRM system or partner data providers, cleanses it, and integrates it into a database. The input is customer behavior data retrieved from the company's CRM system or data providers, and the output is cleansed customer behavior data.

[1487] Step 3:

[1488] The server obtains competitive information using a web crawler. This involves collecting competitor websites and public information and converting it into an analyzable format. The input is competitor information collected by the web crawler, and the output is formatted competitive information.

[1489] Step 4:

[1490] The server cleanses the acquired market trend data, customer behavior data, and competitive information to create an integrated dataset. The input is the various data obtained in the previous step, and the output is the integrated, cleansed dataset.

[1491] Step 5:

[1492] The server inputs the integrated dataset into the generative AI model for analysis, including analysis based on marketing frameworks such as 3C, STP, and 4P. The input is the integrated dataset, and the output is the analysis result of the generated marketing strategy.

[1493] Step 6:

[1494] The server uses a generation AI to generate advertising copy based on the concepts and keywords entered by the user. For example, if a user enters the concept "environmentally friendly products," the server sends the prompt "Please create advertising copy based on the following concept: environmentally friendly products" to the generation AI. The input is the user's concept or keywords, and the output is the generated advertising copy.

[1495] Step 7:

[1496] The server generates brand visuals using image generation AI based on the generated advertising copy. For example, it sends a prompt statement, "Please create an advertising visual based on an environmentally friendly product," to the image generation AI. The input is the generated advertising copy, and the output is the generated brand visual.

[1497] Step 8:

[1498] The server integrates the generated advertising copy and brand visuals and provides them to the user. The input is the generated advertising copy and brand visuals, and the output is the integrated advertising campaign materials, which the user can use to develop their advertising campaign.

[1499] Step 9:

[1500] The server analyzes market trends, customer behavior data, and competitive information in real time to predict the effectiveness of advertising campaigns. The inputs are market trend data, customer behavior data, and competitive information collected in real time, and the output is the predicted results of the advertising campaign.

[1501] Step 10:

[1502] The server feeds back the real-time prediction results to the user's device and modifies the strategy as necessary. The input is the real-time prediction results, and the output is a modified marketing strategy.

[1503] Through the above steps, the system of the present invention is able to grasp market trends and competitive information in real time, and quickly create and develop effective advertising campaigns.

[1504] 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.

[1505] This invention is a system for streamlining and optimizing corporate marketing operations, and in particular, by combining an emotion engine, it is possible to understand user emotions and generate marketing strategies and creatives more effectively. This system is mainly composed of a server, terminals, generation AI, and an emotion engine.

[1506] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1507] Users collect data through their devices to create marketing strategies. The server first obtains market trend data. This includes data collected from websites and APIs. Next, the server collects customer behavior data. This data is obtained from the company's CRM system and affiliated data providers. Competitive information is also obtained by the server using methods such as web crawlers. This data is then cleansed and integrated into a single, well-organized data set by the server.

[1508] The server then inputs the data into a generative AI model and performs analysis in accordance with marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy for the user and delivers it to the user's device in report format. Furthermore, by combining it with an emotion engine, it becomes possible to provide personalized strategies that take into account the user's emotional data.

[1509] Specific examples

[1510] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior. Based on user input, the emotion engine analyzes the user's level of excitement and interest, and suggests more appropriate target markets and positioning.

[1511] Brand visuals + copy creation

[1512] The user inputs the campaign concept and keywords via their device. The emotion engine analyzes the user's input and understands their emotional state at the time. The server provides this to the generation AI, which automatically generates advertising copy. At the same time, the server also uses image generation AI to generate brand visuals. The generated text and visuals are integrated on the server and provided to the user.

[1513] Specific examples

[1514] When a user inputs the concept "environmentally friendly products" for a new campaign, the emotion engine recognizes the user's emotion as "excitement." Based on this, the server generates the copy "One choice to nurture the future" along with energetic, natural visuals, which are then delivered to the user's device. The user then uses this to develop an advertisement.

[1515] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1516] The server collects and cleans customer data from a company's customer database. It then uses a predictive model to predict customer acquisition and churn. Based on the prediction results, the server analyzes the causes of churn and generates appropriate countermeasures. The generated countermeasures are delivered in report format to the user's device. Furthermore, by combining it with an emotion engine, it becomes possible to provide countermeasures that take user emotions into account.

[1517] Specific examples

[1518] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The emotion engine analyzes the users' feelings of "anxiety" and "dissatisfaction" and identifies price competition and the emergence of new competitors as the causes. The server generates a report recommending countermeasures such as "implementing price promotions" and "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[1519] This system allows companies to efficiently in-house their marketing operations, and by taking user emotions into account, they can implement even more effective marketing strategies.

[1520] The processing flow will be explained below.

[1521] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1522] Step 1: Data collection

[1523] 1. Obtaining market trend data

[1524] The server retrieves data about market trends through the API, including economic indicators and consumer behavior.

[1525] 2. Collecting customer behavior data

[1526] The server collects customer purchase history and website visit records from the company's CRM system.

[1527] 3. Obtaining Competitive Information

[1528] The server uses a web crawler to collect public information (news, social media posts, etc.) about competitors.

[1529] Step 2: Data cleansing

[1530] 1. Data normalization

[1531] The server cleanses the collected data and corrects inconsistencies and missing values, for example, removing duplicate data and imputing missing values.

[1532] 2. Data integration

[1533] The server consolidates market trend data, customer behavior data, and competitive intelligence, and organizes it into a format suitable for analysis.

[1534] Step 3: Data analysis

[1535] 1. Entering data

[1536] The server inputs the cleansed data into the generation AI.

[1537] 2. Applying a Marketing Framework

[1538] The server uses generated AI to perform analysis based on marketing frameworks such as 3C, STP, and 4P.

[1539] Step 4: Integrating Emotional Data

[1540] 1. Entering emotions

[1541] The user inputs emotion data from the device, and the system recognizes the user's emotion by analyzing the voice and text input.

[1542] 2. Applying the Emotion Engine

[1543] The server uses an emotion engine to analyze the user's emotions and integrates the emotion data into the analysis results.

[1544] Step 5: Strategic planning

[1545] 1. Generating strategic proposals

[1546] The server generates an individually personalized marketing strategy based on the analysis results and sentiment data.

[1547] 2. Report creation

[1548] The server prepares a report summarizing strategic proposals.

[1549] Step 6: Delivering results

[1550] 1. Report Distribution

[1551] The server delivers the generated report to the user's terminal.

[1552] 2. Confirm and implement the strategy

[1553] Users can check the reports on their devices and plan and implement specific marketing strategies.

[1554] Brand visuals + copy creation

[1555] Step 1: User Input

[1556] 1. Concept input

[1557] The user enters the campaign concept and keywords into the input form on the device.

[1558] Step 2: Analyze the emotion data

[1559] 1. Emotion Analysis

[1560] The server uses an emotion engine to analyze emotions from concepts and keywords entered by the user.

[1561] Step 3: Generate a copy

[1562] 1. Concept Processing

[1563] The server provides concepts and keywords along with emotional data to the generation AI.

[1564] 2. Generative AI copy creation

[1565] The server generates the ad copy using generation AI.

[1566] Step 4: Generate the visuals

[1567] 1. Use of image generation AI

[1568] The server uses image generation AI to create brand visuals based on copy and emotional data.

[1569] Step 5: Creative Integration

[1570] 1. Integrate copy and visuals

[1571] The server integrates the generated ad copy with the brand visuals.

[1572] Step 6: Delivering results

[1573] 1. Creative Delivery

[1574] The server delivers the integrated creative to the user's device.

[1575] 2. Final confirmation and adoption

[1576] The user reviews the creative on their device and selects it as the final ad.

[1577] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1578] Step 1: Data collection and cleansing

[1579] 1. Collection of Customer Data

[1580] A server collects customer data from a company's customer database.

[1581] 2. Data cleansing

[1582] The server cleanses the collected data and corrects inconsistencies and missing values.

[1583] Step 2: Run the predictive model

[1584] 1. Data model input

[1585] The server inputs the cleansed data into a predictive model.

[1586] 2. Customer acquisition and churn prediction

[1587] The server uses predictive models to analyze the likelihood of customer acquisition or churn.

[1588] Step 3: Integrating Emotional Data

[1589] 1. Entering emotions

[1590] The user inputs emotion data into the device. The emotion engine analyzes the voice and text input and recognizes the emotion.

[1591] 2. Application of Emotion Data

[1592] The server integrates the emotion data into the prediction results.

[1593] Step 4: Analyze causes and develop countermeasures

[1594] 1. Analysis of dropout factors

[1595] The server analyzes the factors behind customer abandonment based on the prediction results and emotional data.

[1596] 2. Generating countermeasures

[1597] The server generates specific countermeasures based on the analysis results.

[1598] Step 5: Create and deliver the report

[1599] 1. Report creation

[1600] The server creates a report summarizing the cause analysis and proposed countermeasures.

[1601] 2. Report distribution

[1602] The server delivers the generated report to the user's terminal.

[1603] 3. Implementing measures

[1604] The user checks the report on the device and takes specific measures.

[1605] This detailed processing flow enables the system of the present invention to automate and streamline marketing operations, and to solve many of the problems that companies face. In addition, by combining it with an emotion engine, it is possible to implement more effective marketing strategies that take user emotions into account.

[1606] Example 2

[1607] 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."

[1608] To respond to complex and diverse marketing environments, modern companies need to collect large amounts of data and analyze that data to develop effective marketing strategies. However, manually collecting, cleansing, and analyzing massive amounts of data requires time and effort, and the accuracy of the analysis often depends on human subjectivity, making it difficult to develop optimal marketing strategies. Furthermore, conventional marketing analysis methods have difficulty taking user emotions into account, and they have not been able to provide personalized strategies sufficiently. Therefore, there is a need for a system that can efficiently collect and analyze data and automatically generate marketing strategies that take user emotions into account.

[1609] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1610] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple pieces of data, means for analyzing data based on a marketing framework using a generative AI model, means for analyzing user emotion data using an emotion engine, means for formulating a marketing strategy based on the generated analysis results, and means for providing the generated marketing strategy to the user in report form. This enables efficient and accurate collection and analysis of data, and realizes automatic generation of a marketing strategy that takes user emotions into consideration.

[1611] "Market trend data" is information that indicates market trends and consumer behavior patterns, obtained from internet data sources and APIs.

[1612] "Customer behavior data" is information that shows how a company's customers behave, collected from CRM systems and affiliated data providers.

[1613] "Competitive information" refers to information about competitors' activities, products, and services, and is obtained using web crawlers.

[1614] "Data cleansing" is the process of removing missing values ​​and outliers from collected data to improve the quality of the data.

[1615] "Data integration" is the process of combining multiple data sets into a single, coherent data set.

[1616] A "generative AI model" is an artificial intelligence model that performs marketing analysis and text generation based on large amounts of data.

[1617] An "emotion engine" is software that analyzes a user's emotional state based on their input and behavior.

[1618] A "marketing framework" is an analytical tool used to plan marketing strategies, and includes 3C, STP, 4P, etc.

[1619] A "marketing strategy" is a strategy that a company should implement based on market trends, customer behavior, and competitive information.

[1620] A "report format" is a document format designed to communicate analysis results and strategies to users in an easy-to-understand manner.

[1621] "Ad Copy" means text used in a marketing campaign that is generated by a generative AI model.

[1622] "Brand visuals" are visual elements used in advertising and marketing campaigns that are generated by image generation AI.

[1623] A "predictive model" is an algorithm that predicts future customer behavior based on past data.

[1624] "Countermeasures" are specific countermeasures to problems such as customer defection, and are generated based on the analysis results.

[1625] This invention is a system for streamlining and optimizing corporate marketing operations, and in particular, by combining an emotion engine, it is possible to understand user emotions and generate marketing strategies and creatives more effectively. This system is mainly composed of a server, terminals, a generative AI model, and an emotion engine.

[1626] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1627] When a user issues a market research command from their device, the server executes the following steps: First, the server uses the Python requests library to retrieve market trend data from an external API. Next, the server uses an SQL query to collect customer behavior data from the company's CRM system. The server also uses BeautifulSoup to retrieve competitive information using a web crawler and collect that information.

[1628] The server cleanses the collected data using the pandas library and compiles it into a single integrated dataset. The cleansed dataset is then input into a generative AI model (using, for example, TensorFlow or PyTorch) and analyzed based on marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy and generates a PDF report using, for example, the PDFKit library.

[1629] Furthermore, the emotion engine analyzes the user's emotional data and personalizes marketing strategies. The report generated in this way is delivered from the server to the user's device, and the user can use it to decide on marketing measures.

[1630] Specific examples

[1631] When a user issues a command from a terminal saying, "Start market research for a new product," the server collects and analyzes market trends, customer behavior, and competitive information. For example, the user might enter the following prompt:

[1632] I'd like to create a marketing strategy for a new product. Can you provide me with an analysis of competitor trends and customer purchasing behavior?

[1633] Brand visuals + copy creation

[1634] When a user inputs a campaign concept or keywords through their device, the emotion engine analyzes the user's emotional state. Based on this emotional information, the server generates advertising copy using a generative AI model (e.g., GPT-3). The server then generates brand visuals using an image generation AI (e.g., DALL-E).

[1635] The generated advertising copy and brand visuals are integrated on the server and delivered to the user's device, where the user can use it to create content for their marketing campaign.

[1636] Specific examples

[1637] When a user enters "eco-friendly products" as their "new campaign concept," the emotion engine analyzes the user's emotion as "excitement." Based on this, the generative AI model generates the following ad copy:

[1638] One choice to nurture the future

[1639] In parallel, image generation AI generates energetic and natural visuals, which are then delivered to the user's device.

[1640] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1641] The server collects data from a company's customer database and cleans it using the pandas library. The server then predicts customer acquisition and churn using a machine learning model from Scikit-learn. Based on the prediction results, the server analyzes the reasons for churn and generates specific countermeasures.

[1642] The emotion engine analyzes the user's emotional data and personalizes countermeasures. The countermeasures are generated in report format and sent from the server to the user's device. The user then implements marketing measures based on this report.

[1643] Specific examples

[1644] The server analyzes customer data and discovers that purchases are declining in a particular segment. The emotion engine analyzes user "anxiety" and "dissatisfaction" and identifies price competition and the emergence of new competitors as the causes. Based on this information, the server generates specific countermeasures such as:

[1645] Implementing price promotions and strengthening loyalty programs

[1646] These proposed solutions are provided to the user in the form of a report.

[1647] As described above, the system of the present invention achieves efficient and accurate collection and analysis of data, and automatically generates marketing strategies and creatives that take user emotions into consideration.

[1648] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1649] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1650] Step 1:

[1651] The user issues market research instructions from the terminal.

[1652] Input: The user types "Start market research for new product" into the terminal and presses the "Collect data" button.

[1653] Output: Market research instructions are sent to the server.

[1654] Step 2:

[1655] The server retrieves market trend data.

[1656] Input: Receive market research instructions.

[1657] Data processing / calculation: The server uses the requests library to retrieve market trend data from external APIs.

[1658] What happens: The server sends a request to a specific API endpoint and receives market trend data in JSON format.

[1659] Output: Obtained market trend data.

[1660] Step 3:

[1661] The server collects customer behavior data.

[1662] Input: Access the CRM system using an SQL query.

[1663] Data processing / calculation: Extract customer behavior data and format it using the pandas library.

[1664] Specific operation: Extract the necessary customer behavior data from the SQL database and convert it into a data frame.

[1665] Output: Collected customer behavior data.

[1666] Step 4:

[1667] The server retrieves the conflict information.

[1668] Input: Scraping instructions using a web crawler.

[1669] Data processing / calculation: Use the BeautifulSoup library to crawl competitors' websites and extract data.

[1670] What it does: The server accesses the web page of each competitor and runs a script to extract the required information.

[1671] Output: The obtained competitive intelligence data.

[1672] Step 5:

[1673] The server performs data cleansing and integration.

[1674] Inputs: Captured market trend data, customer behavior data, and competitive intelligence data.

[1675] Data processing / calculation: Use the pandas library to fill in missing values ​​and remove outliers to create a single integrated dataset.

[1676] Specific actions: Run scripts to impute missing values, remove outliers, merge necessary fields, etc.

[1677] Output: A cleansed, consolidated dataset.

[1678] Step 6:

[1679] The server analyzes the data using the generative AI model.

[1680] Input: The cleansed consolidated dataset.

[1681] Data processing / computation: Use generative AI models (e.g., PyTorch, TensorFlow) to perform analysis based on marketing frameworks.

[1682] How it works: The integrated dataset is fed into a generative AI model to obtain results based on frameworks such as 3C, STP, and 4P.

[1683] Output: Analysis results.

[1684] Step 7:

[1685] The server creates marketing strategies and generates reports.

[1686] Input: Analysis results.

[1687] Data processing / calculation: Use the PDFKit library to visualize the analysis results and create detailed PDF reports.

[1688] What it does: Generate graphs and charts from the analysis results and convert them to PDF format.

[1689] Output: PDF report.

[1690] Step 8:

[1691] The server uses an emotion engine to personalize the marketing strategy.

[1692] Input: PDF report and user sentiment data.

[1693] Data processing / calculation: The emotion engine analyzes the user's past inputs and reactions to customize the report content.

[1694] What it does: Perform real-time analysis using the sentiment engine and adjust some of the reports.

[1695] Output: Personalized PDF report.

[1696] Step 9:

[1697] The server delivers the report to the user.

[1698] Input: A personalized PDF report.

[1699] Output: The report is delivered to the user's device.

[1700] Brand visuals + copy creation

[1701] Step 1:

[1702] The user enters the campaign concept and keywords into the terminal.

[1703] Input: Campaign concept or keywords (e.g. "eco-friendly products").

[1704] Output: The input concepts or keywords.

[1705] Step 2:

[1706] An emotion engine analyzes the user's emotional state.

[1707] Input: The concept or keyword entered.

[1708] Data processing / calculation: The emotion engine analyzes the user's emotions.

[1709] Specific behavior: Analyzes emotional state (e.g., "excited") in real time based on user input.

[1710] Output: Parsed emotion data.

[1711] Step 3:

[1712] The server generates the ad copy using a generative AI model.

[1713] Input: Sentiment data and concepts, keywords.

[1714] Data processing / computation: Using generative AI models (e.g., GPT-3) to generate ad copy based on sentiment data.

[1715] What it does: Concepts and keywords are input as prompts into the generation AI, which then generates ad copy.

[1716] Output: The generated ad copy.

[1717] Step 4:

[1718] The server generates brand visuals using image generation AI.

[1719] Input: ad copy and sentiment data.

[1720] Data processing / calculation: Use image generation AI (e.g., DALL-E) to generate brand visuals based on emotional data.

[1721] What it does: Ad copy is fed into an image generation AI as a prompt to generate a visual.

[1722] Output: Generated brand visuals.

[1723] Step 5:

[1724] The server integrates the generated ad copy with the brand visuals.

[1725] Input: Generated ad copy and brand visuals.

[1726] Data processing / calculation: Integrate copy and visuals into one file in HTML format.

[1727] What it does: Runs a script that embeds ad copy and brand visuals into an HTML template.

[1728] Output: Integrated marketing content.

[1729] Step 6:

[1730] The server provides the aggregated content to the user.

[1731] Input: Integrated marketing content.

[1732] Output: The content is delivered to the user's device.

[1733] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1734] Step 1:

[1735] The server collects and cleanses customer data.

[1736] Input: Instructions to gather customer data from a company database using an SQL query.

[1737] Data processing / calculation: Cleanse the data using the pandas library.

[1738] Specific behavior: Extract data from SQL database and handle missing values ​​and outliers.

[1739] Output: Cleansed customer data.

[1740] Step 2:

[1741] The server uses a predictive model to predict customer acquisition and churn.

[1742] Input: Cleansed customer data.

[1743] Data processing / calculation: Predictions are made using Scikit-learn machine learning models.

[1744] Specific operation: The cleansed data is input into a predictive model to generate acquisition and churn predictions.

[1745] Output: Prediction results.

[1746] Step 3:

[1747] The server analyzes the reasons for dropout based on the prediction results.

[1748] Input: Prediction results.

[1749] Data processing / calculation: Identify reasons for dropout using analytical methods such as Feature Importance.

[1750] Specific operation: Analyze important variables of the model to identify customer abandonment factors from the prediction results.

[1751] Output: Dropout factors.

[1752] Step 4:

[1753] The server generates specific countermeasures.

[1754] Input: Churn factors.

[1755] Data processing / calculation: Consider quantitative and qualitative data to generate countermeasures.

[1756] Specific actions: Based on the reasons for abandonment, we propose countermeasures such as price promotions and strengthening loyalty programs.

[1757] Output: Proposed solution.

[1758] Step 5:

[1759] Use an emotion engine to personalize countermeasures.

[1760] Input: Countermeasure proposal and user sentiment data.

[1761] Data processing / calculation: The emotion engine analyzes the user's emotional data and customizes countermeasures.

[1762] Specific actions: Adjust some of the proposed countermeasures based on the user's past reactions and emotional data.

[1763] Output: Personalized countermeasures.

[1764] Step 6:

[1765] The server generates the report and delivers it to the user.

[1766] Input: personalized countermeasures.

[1767] Data processing / calculation: Use libraries such as PDFKit to create a report of proposed countermeasures.

[1768] Specific operation: A report in PDF format is generated based on the proposed countermeasures and delivered to the user's device.

[1769] Output: A personalized action report.

[1770] The above is the specific processing flow of this system.

[1771] (Application example 2)

[1772] 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."

[1773] Conventional marketing systems developed marketing strategies and generated advertising copy and brand visuals based on market trend data, customer behavior data, and competitive intelligence. However, they were unable to generate personalized strategies and advertisements that took user emotions into account. As a result, marketing effectiveness was insufficient, resulting in a decrease in appeal to target customers. Furthermore, because they were unable to analyze customer emotions and develop countermeasures that took these emotions into account, the accuracy of customer churn prevention measures and customer acquisition strategies was low. To address these issues, technology that can analyze emotions and reflect them in marketing is required.

[1774] 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.

[1775] In this invention, the server includes means for analyzing emotions, means for personalizing a marketing strategy based on the emotion analysis results, means for generating advertising copy using a generation AI, means for generating brand visuals using an image generation AI, means for personalizing the generated advertising copy and visuals based on the emotion analysis results, and means for personalizing countermeasures based on the emotion analysis results. This makes it possible to create effective marketing strategies that reflect user emotions, generate personalized advertising copy and visuals, and develop countermeasures.

[1776] "Market trend data" is data that shows the overall trends and tendencies of the market.

[1777] "Customer behavior data" refers to data that indicates customer behavior, such as customer purchase history and website browsing history.

[1778] "Competitive information" is information about competitors' companies and products.

[1779] "Means for analyzing emotions" refers to means for analyzing text, audio, images, etc. to identify a user's emotional state.

[1780] "Means for personalizing marketing strategies based on the results of sentiment analysis" refers to means for creating marketing strategies optimized for individual users using the results of sentiment analysis.

[1781] "Methods for generating advertising copy using generative AI" refers to methods for automatically creating advertising copy using artificial intelligence.

[1782] "Method for generating brand visuals using image generation AI" refers to a method for automatically creating visual elements of a brand using artificial intelligence.

[1783] "Means for integrating advertising copy and brand visuals" refers to means for combining the generated advertising copy and brand visuals into a single advertisement.

[1784] "Means for personalizing advertising copy and visuals generated based on the results of sentiment analysis" refers to a means for creating advertising copy and visuals that are most suitable for individual users based on the results of sentiment analysis.

[1785] "Analytical methods for predicting customer acquisition and churn" are methods that analyze customer data and predict whether new customers will be acquired or whether they will churn.

[1786] "Means for analyzing reasons for customer churn" refers to a method for analyzing data to identify the reasons why customers churn.

[1787] The "means for generating countermeasures" is a means for automatically creating appropriate countermeasures based on the reasons for dropout.

[1788] "Means for personalizing countermeasures" refers to creating countermeasures that are optimal for individual users based on the results of sentiment analysis.

[1789] The system of this invention streamlines marketing operations and enables the generation of personalized marketing strategies, advertising copy, brand visuals, and countermeasures based on user emotions. The specific configuration of the system and its processing procedures are described below.

[1790] First, the server acquires market trend data, customer behavior data, and competitive information, cleansing and integrating them. Next, the integrated data is input into a generative AI model and analyzed based on a marketing framework. Based on the analysis results, a marketing strategy is formulated and provided to users in the form of a report, utilizing sentiment analysis methods. The results of the sentiment analysis are used to personalize the marketing strategy.

[1791] The system has the ability to generate ad copy using generative AI, and also includes the ability to generate brand visuals using image generation AI based on the generated ad copy. Furthermore, the system personalizes the generated ad copy and visuals based on the results of sentiment analysis and provides them to users.

[1792] For example, suppose a user inputs the concept "environmentally friendly product" and their emotion at the time is "excitement." The server confirms this emotion using an emotion analysis engine and inputs it into the generative AI model. Based on this information, the generative AI model generates advertising copy such as "One choice to nurture the future" along with energetic, natural visuals, and presents them to the user.

[1793] Sentiment analysis is performed by analyzing text, audio, and image data, and the emotion engine used is the Emotion Engine API. The generative AI model is applied using the Generation AI API. This processing enables the creation of effective marketing strategies and advertisements that reflect user emotions.

[1794] Examples of specific prompts include:

[1795] "Excitement, eco-friendly products"

[1796] This allows companies to implement personalized marketing strategies that take user emotions into account, increasing the appeal of advertising and improving the effectiveness of customer acquisition and retention.

[1797] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1798] Step 1:

[1799] The server obtains market trend data, customer behavior data, and competitive information.

[1800] Inputs: Market trend data from websites and APIs, customer behavior data from a company's CRM system and partner data providers, competitive intelligence obtained through web crawlers and other means.

[1801] Output: Raw market trend data, customer behavior data, competitive intelligence.

[1802] Specific operation: Collect necessary data from multiple data sources and import it into the server.

[1803] Step 2:

[1804] The server cleanses the retrieved data.

[1805] Inputs: Raw market trend data, customer behavior data, competitive intelligence.

[1806] Output: A cleansed and tidy dataset.

[1807] Specific Actions: Deduplicate, format, and correct inaccurate data.

[1808] Step 3:

[1809] The server integrates multiple data sets and performs analysis.

[1810] Input: The cleansed dataset.

[1811] Output: Data for input into a generative AI model.

[1812] Specific actions: Classify and aggregate data and analyze it in line with marketing frameworks (3C, STP, 4P, etc.).

[1813] Step 4:

[1814] The server formulates a marketing strategy based on the generated analysis results.

[1815] Input: Data for input to a generative AI model.

[1816] Output: Proposed marketing strategy.

[1817] Specific operation: Input data into the generative AI model and create a specific marketing strategy based on the analysis results.

[1818] Step 5:

[1819] The server analyzes the user's emotion data using an emotion analysis means.

[1820] Input: User input text, voice, or image data.

[1821] Output: The user's emotional state.

[1822] What it does: It uses the Emotion Engine API to analyze text, audio, and image data to identify the user's emotional state.

[1823] Step 6:

[1824] The server personalizes the marketing strategy based on the sentiment analysis results.

[1825] Input: Marketing strategy ideas, user emotional state.

[1826] Output: Personalized marketing strategies.

[1827] Specific operation: Reflecting the results of sentiment analysis, we create marketing strategies optimized for individual users.

[1828] Step 7:

[1829] The server generates the ad copy using a generation AI.

[1830] Input: Concepts, keywords, and the user's emotional state.

[1831] Output: Ad copy.

[1832] Specific operation: Input the prompt text into the generative AI model (Generation AI API) to automatically generate ad copy.

[1833] An example of a specific prompt: "Excitement, eco-friendly products."

[1834] Step 8:

[1835] The server uses image generation AI to generate brand visuals based on the generated advertising copy.

[1836] Input: ad copy, user's emotional state.

[1837] Output: Brand visuals.

[1838] What it does: Uses image generation AI to create branded visuals that perfectly complement ad copy.

[1839] Step 9:

[1840] The server integrates the generated advertising copy with the brand visuals and provides them to the user.

[1841] Input: ad copy, brand visuals.

[1842] Output: Integrated advertising content.

[1843] Specific operation: The generated ad copy and visuals are compiled into one ad content and provided to the user.

[1844] Step 10:

[1845] The server cleanses customer data, analyzes reasons for customer abandonment, and generates countermeasures.

[1846] Input: Customer behavior data, emotional state.

[1847] Output: Personalized countermeasures.

[1848] Specific operations: Organize customer data, identify reasons for abandonment based on sentiment analysis results, and automatically generate appropriate countermeasures.

[1849] 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.

[1850] 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.

[1851] 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.

[1852] [Fourth embodiment]

[1853] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1854] 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.

[1855] 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).

[1856] 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.

[1857] 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.

[1858] 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).

[1859] 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.

[1860] 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.

[1861] 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.

[1862] 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.

[1863] 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.

[1864] 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.

[1865] 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."

[1866] This invention is a system for streamlining and optimizing corporate marketing activities, and mainly realizes the functions of data collection, data analysis, strategy planning, creative generation, and customer forecasting. This system is mainly composed of a server and user terminals, and implements multiple functions including generation AI.

[1867] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1868] Users collect data through their devices to create marketing strategies. The server first obtains market trend data. This includes data collected from websites and APIs. Next, the server collects customer behavior data. This data is obtained from the company's CRM system and affiliated data providers. Competitive information is also obtained by the server using methods such as web crawlers. This data is then cleansed and integrated into a single, well-organized data set by the server.

[1869] The server then inputs the data into a generative AI model and performs analysis in accordance with marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy for the user and delivers it to the user's device in the form of a report.

[1870] Specific examples

[1871] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior.The user can use this information to find the appropriate target market and determine positioning.

[1872] Brand visuals + copy creation

[1873] The user inputs the campaign concept and keywords through the device. The server provides the input information to the generation AI, which automatically generates the ad copy. At the same time, the server also uses the image generation AI to generate brand visuals. The generated text and visuals are integrated on the server and provided to the user.

[1874] Specific examples

[1875] When a user inputs the concept of "environmentally friendly products" for a new campaign, the server generates the copy "One choice to nurture the future" along with a natural-looking visual that matches it, and delivers it to the user's device. The user then uses this to develop an advertisement.

[1876] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1877] The server collects and cleans customer data from the company's customer database. It then uses a predictive model to predict customer acquisition and churn. Based on the prediction results, the server analyzes the causes of churn and generates appropriate countermeasures. The generated countermeasures are delivered to the user's device in report format.

[1878] Specific examples

[1879] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The causes are identified as price competition and the emergence of new competitors. The server generates a report recommending countermeasures such as "implementing price promotions" or "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[1880] This system allows companies to efficiently in-house their marketing operations, reducing costs and accumulating marketing know-how.

[1881] The processing flow will be explained below.

[1882] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1883] Step 1: Data collection

[1884] 1. Obtaining market trend data

[1885] The server retrieves data about market trends through websites and APIs.

[1886] 2. Collecting customer behavior data

[1887] The server collects customer behavior data from the company's CRM system and affiliated data providers.

[1888] 3. Obtaining Competitive Information

[1889] The server uses web crawlers to gather information about competitors, including news, blogs, and social media data.

[1890] Step 2: Data cleansing

[1891] 1. Data normalization

[1892] The server inspects the collected data and corrects noise and missing values.

[1893] 2. Data integration

[1894] The server aggregates data from different sources into a single, coherent data set.

[1895] Step 3: Data analysis

[1896] 1. Entering data

[1897] The server inputs the prepared data into the generation AI.

[1898] 2. Applying a Marketing Framework

[1899] The server uses generated AI to perform analysis based on marketing frameworks such as 3C, STP, and 4P.

[1900] Step 4: Strategic planning

[1901] 1. Generating strategic proposals

[1902] The server generates marketing strategy proposals based on the analysis results.

[1903] 2. Report creation

[1904] The server prepares a report summarizing strategic proposals.

[1905] Step 5: Delivering results

[1906] 1. Report Distribution

[1907] The server delivers the generated report to the user's terminal.

[1908] 2. Confirm and implement the strategy

[1909] Users can check the reports on their devices and plan and implement specific marketing strategies.

[1910] Brand visuals + copy creation

[1911] Step 1: User Input

[1912] 1. Concept input

[1913] The user enters the campaign concept and keywords into the input form on the device.

[1914] Step 2: Generate a copy

[1915] 1. Concept Processing

[1916] The server analyzes the concepts and keywords entered.

[1917] 2. Generative AI copy creation

[1918] The server generates the ad copy using generation AI.

[1919] Step 3: Generate the visuals

[1920] 1. Use of image generation AI

[1921] The server creates brand visuals based on the copy using image generation AI.

[1922] Step 4: Creative Integration

[1923] 1. Integrate copy and visuals

[1924] The server integrates the generated ad copy with the brand visuals.

[1925] Step 5: Delivering results

[1926] 1. Creative Delivery

[1927] The server delivers the integrated creative to the user's device.

[1928] 2. Final confirmation and adoption

[1929] The user reviews the creative on their device and selects it as the final ad.

[1930] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1931] Step 1: Data collection and cleansing

[1932] 1. Collection of Customer Data

[1933] A server collects customer data from a company's customer database.

[1934] 2. Data cleansing

[1935] The server cleanses the collected data and puts it in a form suitable for analysis.

[1936] Step 2: Predictive analytics

[1937] 1. Data model input

[1938] The server inputs the cleansed data into a predictive model.

[1939] 2. Customer acquisition and churn prediction

[1940] The server uses predictive models to analyze the likelihood of customer acquisition or churn.

[1941] Step 3: Analyze causes and develop countermeasures

[1942] 1. Analysis of dropout factors

[1943] Based on the prediction results, the server analyzes the factors that cause customers to leave.

[1944] 2. Generating countermeasures

[1945] The server generates specific countermeasures based on the analysis results.

[1946] Step 4: Create and deliver the report

[1947] 1. Report creation

[1948] The server creates a report summarizing the cause analysis and proposed countermeasures.

[1949] 2. Report distribution

[1950] The server delivers the generated report to the user's terminal.

[1951] 3. Implementing measures

[1952] The user checks the report on the device and takes specific measures.

[1953] With this detailed processing flow, the system of the present invention can automate and streamline marketing operations, and solve many of the problems that companies face.

[1954] Example 1

[1955] 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."

[1956] In conventional marketing systems, each process, such as data collection, cleansing, analysis, and strategy planning, is performed piecemeal, preventing overall efficiency and optimization. Furthermore, it is often difficult to link individual data analysis tools and ad copy generation tools, resulting in a lack of consistency in marketing activities. The present invention aims to provide a system that comprehensively solves these issues and streamlines and optimizes the entire marketing process.

[1957] 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.

[1958] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple data, means for inputting data into a generative AI model and performing analysis based on a marketing framework, means for formulating a marketing strategy based on the generated analysis results, and means for providing the generated marketing strategy to a user in the form of a report. This makes it possible to consistently and efficiently carry out the marketing process from data collection to analysis, strategy formulation, and report creation.

[1959] "Market trend data" refers to data that shows market trends and demand, competitor trends, consumer preferences, etc. It includes dynamic information collected from websites and APIs and obtained from a variety of sources.

[1960] "Customer behavior data" refers to data that shows how customers behave. This includes data collected internally by a company, such as purchase history, browsing history, and CRM system information, as well as data provided by partner data providers.

[1961] "Competitive information" refers to data that shows competitors' activities, strategies, product information, etc. It includes information collected by crawling websites using methods such as web crawlers.

[1962] "Data cleansing" is the process of correcting or removing inaccurate, missing, or redundant portions of collected data, thereby improving the quality of the data set used for subsequent analysis.

[1963] A "generative AI model" is an AI model that uses artificial intelligence technology to analyze data and perform specific tasks, such as analyzing data based on a marketing framework or generating advertising copy.

[1964] A "marketing framework" refers to the basic frameworks and methods for formulating marketing strategies such as 3C, STP, and 4P. These frameworks provide an important analytical perspective in building a marketing strategy.

[1965] "Ad copy" refers to sentences and phrases that effectively communicate an advertisement or campaign. It is automatically generated using a generative AI model based on input concepts and keywords.

[1966] "Image generation AI" is an artificial intelligence technology that automatically generates visuals (images and designs) based on a specified concept or theme. This allows for the rapid and consistent generation of visuals for branding and advertising.

[1967] The "report format" is a document format that summarizes analysis results, strategic proposals, countermeasures, etc. in an easy-to-understand format. Charts and text are organized so that users can easily grasp the content.

[1968] A "predictive model" is a mathematical model that uses data to forecast future trends and outcomes. It is used to predict things like customer acquisition and churn.

[1969] Strategic planning is the process of devising and formulating the most effective marketing strategy based on collected and analyzed data, which determines the specific approach to achieving a company's goals.

[1970] This invention is a system for streamlining and optimizing corporate marketing activities, and realizes the functions of data collection, data analysis, strategy planning, creative generation, and customer prediction. This system is mainly composed of a server and user terminals, and implements multiple functions including generative AI models.

[1971] Hardware and software used

[1972] Hardware: Servers, user terminals, database servers, web crawlers

[1973] Software: Generative AI models, image generation AI, CRM systems, API integration tools, data cleansing tools, predictive models

[1974] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1975] To help users develop marketing strategies through their devices, the server collects market trend data, customer behavior data, and competitive information. Market trend data is primarily obtained from websites and APIs. Customer behavior data is collected from the company's CRM system and affiliated data providers, while competitive information is obtained from websites using web crawlers.

[1976] The collected data is cleansed by the server and compiled into an integrated dataset. This integrated dataset is input into a generative AI model, which performs analysis based on marketing frameworks such as 3C, STP, and 4P. A marketing strategy is developed based on the generated analysis results and provided to the user's device in report format.

[1977] Specific examples

[1978] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior.The user can use this information to find the appropriate target market and determine positioning.

[1979] Brand visuals + copy creation

[1980] The user inputs the campaign concept and keywords via their device. The server provides this input information to a generative AI model, which automatically generates advertising copy. At the same time, image generation AI is used to generate brand visuals. The generated advertising copy and brand visuals are integrated on the server and provided to the user's device.

[1981] Specific examples

[1982] When a user inputs the concept of "environmentally friendly products" for a new campaign, the server generates the copy "One choice to nurture the future" along with natural-looking visuals that match it, and delivers them to the user's device. The user then uses this to develop an advertisement. "An example of a prompt for the generative AI model is, 'Please generate advertising copy for an environmentally friendly product campaign.'"

[1983] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[1984] The server collects and cleans customer data from the company's customer database. It then uses a predictive model to predict customer acquisition and churn, and analyzes the causes of churn based on the prediction results. Finally, it generates appropriate countermeasures and provides them to the user's device in the form of a report.

[1985] Specific examples

[1986] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The causes are identified as price competition and the emergence of new competitors. The server generates a report recommending countermeasures such as "implementing price promotions" or "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[1987] This system allows companies to efficiently in-house their marketing operations, reducing costs and accumulating marketing know-how.

[1988] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1989] Market trends / customer behavior / competitive analysis + marketing strategy planning

[1990] Step 1: Data collection request

[1991] The user issues a data collection request from a terminal, specifying the data type (market trends, customer behavior, competitive information) required for formulating a marketing strategy.

[1992] Input: Data collection request details (data type, etc.)

[1993] Output: Data collection instructions to the server

[1994] Step 2: Collect market trend data

[1995] The server sends requests to designated websites or APIs to retrieve market trend data, which is then stored in a database.

[1996] Input: Website or API URL, query parameters

[1997] Output: Raw data (market trend information)

[1998] Specific behavior: The server sends an HTTP request to an API endpoint, receives the response, and stores it in a database.

[1999] Step 3: Collect customer behavior data

[2000] The server collects customer behavior data from the company's CRM system and partner data providers, retrieves the data via API, and stores it in a local database.

[2001] Input: API endpoint, authentication information

[2002] Output: Raw data (customer behavior information)

[2003] What happens: The server executes the API call and writes the returned data to a local database.

[2004] Step 4: Gather competitive intelligence

[2005] The server launches a web crawler to collect data from the websites of the specified competitors, which is then stored in a database.

[2006] Input: Competitor URL list

[2007] Output: Raw data (competitive information)

[2008] What it does: The server runs a web crawler and parses the HTML data to extract useful information.

[2009] Step 5: Data cleansing

[2010] The server cleanses the collected data and corrects or removes inaccuracies, missing parts, or duplicates.

[2011] Input: Raw datasets (market trends, customer behavior, competitive intelligence)

[2012] Output: Cleansed dataset

[2013] What it does: The server uses data cleansing tools to improve data consistency and accuracy.

[2014] Step 6: Data Integration

[2015] The server combines the cleansed data from multiple data sources into a single integrated data set.

[2016] Input: Cleansed dataset

[2017] Output: Unified dataset

[2018] Specific operation: The server performs a database join operation to generate a consolidated dataset.

[2019] Step 7: Data analysis

[2020] The server inputs the integrated data set into a generative AI model and performs analysis based on marketing frameworks such as 3C, STP, and 4P.

[2021] Input: Unified dataset

[2022] Output: Analysis results

[2023] Specific operations: The server runs the generative AI model and performs marketing analysis.

[2024] Step 8: Strategic Planning and Reporting

[2025] The server develops a marketing strategy based on the analysis results, compiles the results in report format, and delivers them to the user's device.

[2026] Input: Analysis results

[2027] Output: Marketing Strategy Report

[2028] What it does: The server uses a reporting tool to document the analysis results in a format that is easy to visualize.

[2029] Brand visuals + copy creation

[2030] Step 1: Concept entry

[2031] The user inputs the campaign concept and keywords into the system via a terminal.

[2032] Input: Campaign concept, keywords

[2033] Output: Input information to the server

[2034] Step 2: Input to the generative AI model

[2035] The server feeds input concepts and keywords into a generative AI model to generate ad copy, while also using image-generating AI to generate brand visuals.

[2036] Input: Campaign concept, keywords

[2037] Output: Advertising copy, brand visuals

[2038] Specific operation: The server passes the prompt sentence to the generative AI model and executes the generative AI model and image generation AI.

[2039] Step 3: Integrate copy and visuals

[2040] The server integrates the generated advertising copy with the brand visuals and provides them to the user's terminal.

[2041] Input: Ad copy, brand visuals

[2042] Output: Integrated marketing materials

[2043] Specific operation: The server combines the copy and visuals into a single file or document and sends it to the user's terminal.

[2044] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[2045] Step 1: Collect and cleanse customer data

[2046] The server collects and cleans customer data from the company's customer database.

[2047] Input: Customer database

[2048] Output: Cleansed customer data

[2049] Specific operation: The server extracts data from the database, corrects outliers, and completes the data.

[2050] Step 2: Run the predictive model

[2051] The server inputs the cleansed customer data into a predictive model to predict customer acquisition and churn.

[2052] Input: Cleansed customer data

[2053] Output: Prediction results

[2054] What happens: The server applies the predictive model to predict customer behavior.

[2055] Step 3: Factor analysis

[2056] The server analyzes the reasons for customer abandonment based on the prediction results.

[2057] Input: Prediction result

[2058] Output: Factor analysis results

[2059] Specific actions: The server uses data analysis tools to identify the reasons for abandonment.

[2060] Step 4: Generate countermeasures

[2061] The server generates appropriate countermeasures based on the results of analyzing the reasons for dropout.

[2062] Input: Factor analysis results

[2063] Output: Countermeasures

[2064] Specific operation: The server uses the generative AI model to create countermeasures.

[2065] Step 5: Reporting

[2066] The server compiles the generated countermeasures into a report and provides it to the user's terminal.

[2067] Input: Countermeasures

[2068] Output: Countermeasures report

[2069] What happens: The server uses a reporting tool to document the proposed action and send it to the user.

[2070] (Application example 1)

[2071] 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."

[2072] Conventional marketing systems often require a huge amount of time and resources for data collection, analysis, and marketing strategy planning. Especially for advertising campaigns, specialized knowledge and skills are required to quickly create effective advertising copy and visuals. Furthermore, it is difficult to analyze market trends and obtain competitive information in real time, making it difficult to accurately predict customer behavior and quickly take countermeasures based on that information. To solve these problems, a multifunctional marketing support system is needed.

[2073] 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.

[2074] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple pieces of data, means for generating advertising copy using a generation AI, means for generating brand visuals using an image generation AI, and means for integrating the generated advertising copy and brand visuals and providing them to users. This makes it possible to grasp market trends, customer behavior, and competitive information in real time, and to quickly create and deploy effective advertising campaigns.

[2075] "Market trend data" is data that shows market trends and consumer behavior patterns.

[2076] "Customer behavior data" is data that records the actions of customers when they make purchases, browse, make inquiries, etc.

[2077] "Competitive information" is data about competing companies and products in the same market.

[2078] "Data cleansing" is the process of removing noise, redundancies, and errors from collected data and preparing it for use.

[2079] "Data integration" is the process of combining multiple data sets into a single, coherent data set.

[2080] "Generative AI" is artificial intelligence that automatically generates text, visuals, etc. using natural language processing models, etc.

[2081] "Ad copy" is a short, persuasive sentence or catchphrase used in an advertisement.

[2082] "Image generation AI" is an artificial intelligence that automatically generates images based on a specified concept.

[2083] "Brand visuals" are images and designs that visually express the brand's values ​​and messages.

[2084] "Real-time prediction" is a technology that instantly predicts future results based on current data.

[2085] "Report creation means" is a function that provides analysis results and strategy proposals to users in document format.

[2086] To realize this application example, cooperation between the server, terminals, and users is essential. The system of the present invention is composed of the following main means.

[2087] First, the server acquires market trend data. This data is acquired using tools that collect information from websites and APIs. Next, the server collects customer behavior data. This data is derived from the company's CRM system and partner data providers. Finally, the server uses a web crawler to acquire competitive information. This data is then cleansed on the server and compiled into a single, integrated dataset.

[2088] The integrated data set is analyzed and a generative AI is used to create a marketing strategy. Specifically, based on the concepts and keywords entered by the user, the generative AI generates advertising copy and the image generation AI generates brand visuals. For example, if a user enters the concept "environmentally friendly products," the server sends the following prompt to the generative AI: "Please create advertising copy based on the following concept: environmentally friendly products."

[2089] The generated advertising copy and brand visuals are integrated by the server and provided to the user's device. Based on this, the user can develop an effective advertising campaign. The server also analyzes market trends, competitive information, and customer behavior data in real time to predict the effectiveness of the advertising campaign. The results are fed back to the user in real time, allowing them to adjust their strategy as needed.

[2090] Regarding the hardware and software used, the server is a computer with high-performance data processing and AI models. Also, a Python program uses generative AI (e.g., GPT-3) and image generation AI (e.g., DALL-E). An application is installed on the user's device to receive and display the generated results.

[2091] This system makes it possible to grasp market trends and competitive information in real time, and quickly create and deploy effective advertising campaigns. Specifically, consider the case where a user inputs the concept of "environmentally friendly products." The server sends a prompt message saying, "Please create an advertising copy based on the following concept: environmentally friendly products," and generates the advertising copy "One choice to nurture the future" along with natural visuals that match it. This allows users to effectively deploy high-quality advertising campaigns.

[2092] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2093] Step 1:

[2094] The server obtains market trend data. Specifically, the server collects information about market trends from designated websites or APIs and stores it in a database. The input is market trend information from websites or APIs, and the output is organized market trend data.

[2095] Step 2:

[2096] The server collects customer behavior data. It retrieves the data from the company's CRM system or partner data providers, cleanses it, and integrates it into a database. The input is customer behavior data retrieved from the company's CRM system or data providers, and the output is cleansed customer behavior data.

[2097] Step 3:

[2098] The server obtains competitive information using a web crawler. This involves collecting competitor websites and public information and converting it into an analyzable format. The input is competitor information collected by the web crawler, and the output is formatted competitive information.

[2099] Step 4:

[2100] The server cleanses the acquired market trend data, customer behavior data, and competitive information to create an integrated dataset. The input is the various data obtained in the previous step, and the output is the integrated, cleansed dataset.

[2101] Step 5:

[2102] The server inputs the integrated dataset into the generative AI model for analysis, including analysis based on marketing frameworks such as 3C, STP, and 4P. The input is the integrated dataset, and the output is the analysis result of the generated marketing strategy.

[2103] Step 6:

[2104] The server uses a generation AI to generate advertising copy based on the concepts and keywords entered by the user. For example, if a user enters the concept "environmentally friendly products," the server sends the prompt "Please create advertising copy based on the following concept: environmentally friendly products" to the generation AI. The input is the user's concept or keywords, and the output is the generated advertising copy.

[2105] Step 7:

[2106] The server generates brand visuals using image generation AI based on the generated advertising copy. For example, it sends a prompt statement, "Please create an advertising visual based on an environmentally friendly product," to the image generation AI. The input is the generated advertising copy, and the output is the generated brand visual.

[2107] Step 8:

[2108] The server integrates the generated advertising copy and brand visuals and provides them to the user. The input is the generated advertising copy and brand visuals, and the output is the integrated advertising campaign materials, which the user can use to develop their advertising campaign.

[2109] Step 9:

[2110] The server analyzes market trends, customer behavior data, and competitive information in real time to predict the effectiveness of advertising campaigns. The inputs are market trend data, customer behavior data, and competitive information collected in real time, and the output is the predicted results of the advertising campaign.

[2111] Step 10:

[2112] The server feeds back the real-time prediction results to the user's device and modifies the strategy as necessary. The input is the real-time prediction results, and the output is a modified marketing strategy.

[2113] Through the above steps, the system of the present invention is able to grasp market trends and competitive information in real time, and quickly create and develop effective advertising campaigns.

[2114] 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.

[2115] This invention is a system for streamlining and optimizing corporate marketing operations, and in particular, by combining an emotion engine, it is possible to understand user emotions and generate marketing strategies and creatives more effectively. This system is mainly composed of a server, terminals, generation AI, and an emotion engine.

[2116] Market trends / customer behavior / competitive analysis + marketing strategy planning

[2117] Users collect data through their devices to create marketing strategies. The server first obtains market trend data. This includes data collected from websites and APIs. Next, the server collects customer behavior data. This data is obtained from the company's CRM system and affiliated data providers. Competitive information is also obtained by the server using methods such as web crawlers. This data is then cleansed and integrated into a single, well-organized data set by the server.

[2118] The server then inputs the data into a generative AI model and performs analysis in accordance with marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy for the user and delivers it to the user's device in report format. Furthermore, by combining it with an emotion engine, it becomes possible to provide personalized strategies that take into account the user's emotional data.

[2119] Specific examples

[2120] For example, when planning a marketing strategy for a new product, the server analyzes market data and provides analysis results on competitor trends and customer purchasing behavior. Based on user input, the emotion engine analyzes the user's level of excitement and interest, and suggests more appropriate target markets and positioning.

[2121] Brand visuals + copy creation

[2122] The user inputs the campaign concept and keywords via their device. The emotion engine analyzes the user's input and understands their emotional state at the time. The server provides this to the generation AI, which automatically generates advertising copy. At the same time, the server also uses image generation AI to generate brand visuals. The generated text and visuals are integrated on the server and provided to the user.

[2123] Specific examples

[2124] When a user inputs the concept "environmentally friendly products" for a new campaign, the emotion engine recognizes the user's emotion as "excitement." Based on this, the server generates the copy "One choice to nurture the future" along with energetic, natural visuals, which are then delivered to the user's device. The user then uses this to develop an advertisement.

[2125] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[2126] The server collects and cleans customer data from a company's customer database. It then uses a predictive model to predict customer acquisition and churn. Based on the prediction results, the server analyzes the causes of churn and generates appropriate countermeasures. The generated countermeasures are delivered in report format to the user's device. Furthermore, by combining it with an emotion engine, it becomes possible to provide countermeasures that take user emotions into account.

[2127] Specific examples

[2128] The server analyzes customer data and discovers that a specific segment of customers is reducing their purchases. The emotion engine analyzes the users' feelings of "anxiety" and "dissatisfaction" and identifies price competition and the emergence of new competitors as the causes. The server generates a report recommending countermeasures such as "implementing price promotions" and "strengthening loyalty programs" and provides it to the user. The user then implements specific marketing measures based on the countermeasures suggested.

[2129] This system allows companies to efficiently in-house their marketing operations, and by taking user emotions into account, they can implement even more effective marketing strategies.

[2130] The processing flow will be explained below.

[2131] Market trends / customer behavior / competitive analysis + marketing strategy planning

[2132] Step 1: Data collection

[2133] 1. Obtaining market trend data

[2134] The server retrieves data about market trends through the API, including economic indicators and consumer behavior.

[2135] 2. Collecting customer behavior data

[2136] The server collects customer purchase history and website visit records from the company's CRM system.

[2137] 3. Obtaining Competitive Information

[2138] The server uses a web crawler to collect public information (news, social media posts, etc.) about competitors.

[2139] Step 2: Data cleansing

[2140] 1. Data normalization

[2141] The server cleanses the collected data and corrects inconsistencies and missing values, for example, removing duplicate data and imputing missing values.

[2142] 2. Data integration

[2143] The server consolidates market trend data, customer behavior data, and competitive intelligence, and organizes it into a format suitable for analysis.

[2144] Step 3: Data analysis

[2145] 1. Entering data

[2146] The server inputs the cleansed data into the generation AI.

[2147] 2. Applying a Marketing Framework

[2148] The server uses generated AI to perform analysis based on marketing frameworks such as 3C, STP, and 4P.

[2149] Step 4: Integrating Emotional Data

[2150] 1. Entering emotions

[2151] The user inputs emotion data from the device, and the system recognizes the user's emotion by analyzing the voice and text input.

[2152] 2. Applying the Emotion Engine

[2153] The server uses an emotion engine to analyze the user's emotions and integrates the emotion data into the analysis results.

[2154] Step 5: Strategic planning

[2155] 1. Generating strategic proposals

[2156] The server generates an individually personalized marketing strategy based on the analysis results and sentiment data.

[2157] 2. Report creation

[2158] The server prepares a report summarizing strategic proposals.

[2159] Step 6: Delivering results

[2160] 1. Report Distribution

[2161] The server delivers the generated report to the user's terminal.

[2162] 2. Confirm and implement the strategy

[2163] Users can check the reports on their devices and plan and implement specific marketing strategies.

[2164] Brand visuals + copy creation

[2165] Step 1: User Input

[2166] 1. Concept input

[2167] The user enters the campaign concept and keywords into the input form on the device.

[2168] Step 2: Analyze the emotion data

[2169] 1. Emotion Analysis

[2170] The server uses an emotion engine to analyze emotions from concepts and keywords entered by the user.

[2171] Step 3: Generate a copy

[2172] 1. Concept Processing

[2173] The server provides concepts and keywords along with emotional data to the generation AI.

[2174] 2. Generative AI copy creation

[2175] The server generates the ad copy using generation AI.

[2176] Step 4: Generate the visuals

[2177] 1. Use of image generation AI

[2178] The server uses image generation AI to create brand visuals based on copy and emotional data.

[2179] Step 5: Creative Integration

[2180] 1. Integrate copy and visuals

[2181] The server integrates the generated ad copy with the brand visuals.

[2182] Step 6: Delivering results

[2183] 1. Creative Delivery

[2184] The server delivers the integrated creative to the user's device.

[2185] 2. Final confirmation and adoption

[2186] The user reviews the creative on their device and selects it as the final ad.

[2187] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[2188] Step 1: Data collection and cleansing

[2189] 1. Collection of Customer Data

[2190] A server collects customer data from a company's customer database.

[2191] 2. Data cleansing

[2192] The server cleanses the collected data and corrects inconsistencies and missing values.

[2193] Step 2: Run the predictive model

[2194] 1. Data model input

[2195] The server inputs the cleansed data into a predictive model.

[2196] 2. Customer acquisition and churn prediction

[2197] The server uses predictive models to analyze the likelihood of customer acquisition or churn.

[2198] Step 3: Integrating Emotional Data

[2199] 1. Entering emotions

[2200] The user inputs emotion data into the device. The emotion engine analyzes the voice and text input and recognizes the emotion.

[2201] 2. Application of Emotion Data

[2202] The server integrates the emotion data into the prediction results.

[2203] Step 4: Analyze causes and develop countermeasures

[2204] 1. Analysis of dropout factors

[2205] The server analyzes the factors behind customer abandonment based on the prediction results and emotional data.

[2206] 2. Generating countermeasures

[2207] The server generates specific countermeasures based on the analysis results.

[2208] Step 5: Create and deliver the report

[2209] 1. Report creation

[2210] The server creates a report summarizing the cause analysis and proposed countermeasures.

[2211] 2. Report distribution

[2212] The server delivers the generated report to the user's terminal.

[2213] 3. Implementing measures

[2214] The user checks the report on the device and takes specific measures.

[2215] This detailed processing flow enables the system of the present invention to automate and streamline marketing operations, and to solve many of the problems that companies face. In addition, by combining it with an emotion engine, it is possible to implement more effective marketing strategies that take user emotions into account.

[2216] Example 2

[2217] 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."

[2218] To respond to complex and diverse marketing environments, modern companies need to collect large amounts of data and analyze that data to develop effective marketing strategies. However, manually collecting, cleansing, and analyzing massive amounts of data requires time and effort, and the accuracy of the analysis often depends on human subjectivity, making it difficult to develop optimal marketing strategies. Furthermore, conventional marketing analysis methods have difficulty taking user emotions into account, and they have not been able to provide personalized strategies sufficiently. Therefore, there is a need for a system that can efficiently collect and analyze data and automatically generate marketing strategies that take user emotions into account.

[2219] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2220] In this invention, the server includes means for acquiring market trend data, means for collecting customer behavior data, means for acquiring competitive information, means for cleansing the acquired data, means for integrating and analyzing multiple pieces of data, means for analyzing data based on a marketing framework using a generative AI model, means for analyzing user emotion data using an emotion engine, means for formulating a marketing strategy based on the generated analysis results, and means for providing the generated marketing strategy to the user in report form. This enables efficient and accurate collection and analysis of data, and realizes automatic generation of a marketing strategy that takes user emotions into consideration.

[2221] "Market trend data" is information that indicates market trends and consumer behavior patterns, obtained from internet data sources and APIs.

[2222] "Customer behavior data" is information that shows how a company's customers behave, collected from CRM systems and affiliated data providers.

[2223] "Competitive information" refers to information about competitors' activities, products, and services, and is obtained using web crawlers.

[2224] "Data cleansing" is the process of removing missing values ​​and outliers from collected data to improve the quality of the data.

[2225] "Data integration" is the process of combining multiple data sets into a single, coherent data set.

[2226] A "generative AI model" is an artificial intelligence model that performs marketing analysis and text generation based on large amounts of data.

[2227] An "emotion engine" is software that analyzes a user's emotional state based on their input and behavior.

[2228] A "marketing framework" is an analytical tool used to plan marketing strategies, and includes 3C, STP, 4P, etc.

[2229] A "marketing strategy" is a strategy that a company should implement based on market trends, customer behavior, and competitive information.

[2230] A "report format" is a document format designed to communicate analysis results and strategies to users in an easy-to-understand manner.

[2231] "Ad Copy" means text used in a marketing campaign that is generated by a generative AI model.

[2232] "Brand visuals" are visual elements used in advertising and marketing campaigns that are generated by image generation AI.

[2233] A "predictive model" is an algorithm that predicts future customer behavior based on past data.

[2234] "Countermeasures" are specific countermeasures to problems such as customer defection, and are generated based on the analysis results.

[2235] This invention is a system for streamlining and optimizing corporate marketing operations, and in particular, by combining an emotion engine, it is possible to understand user emotions and generate marketing strategies and creatives more effectively. This system is mainly composed of a server, terminals, a generative AI model, and an emotion engine.

[2236] Market trends / customer behavior / competitive analysis + marketing strategy planning

[2237] When a user issues a market research command from their device, the server executes the following steps: First, the server uses the Python requests library to retrieve market trend data from an external API. Next, the server uses an SQL query to collect customer behavior data from the company's CRM system. The server also uses BeautifulSoup to retrieve competitive information using a web crawler and collect that information.

[2238] The server cleanses the collected data using the pandas library and compiles it into a single integrated dataset. The cleansed dataset is then input into a generative AI model (using, for example, TensorFlow or PyTorch) and analyzed based on marketing frameworks such as 3C, STP, and 4P. Based on the analysis results, the server creates a marketing strategy and generates a PDF report using, for example, the PDFKit library.

[2239] Furthermore, the emotion engine analyzes the user's emotional data and personalizes marketing strategies. The report generated in this way is delivered from the server to the user's device, and the user can use it to decide on marketing measures.

[2240] Specific examples

[2241] When a user issues a command from a terminal saying, "Start market research for a new product," the server collects and analyzes market trends, customer behavior, and competitive information. For example, the user might enter the following prompt:

[2242] I'd like to create a marketing strategy for a new product. Can you provide me with an analysis of competitor trends and customer purchasing behavior?

[2243] Brand visuals + copy creation

[2244] When a user inputs a campaign concept or keywords through their device, the emotion engine analyzes the user's emotional state. Based on this emotional information, the server generates advertising copy using a generative AI model (e.g., GPT-3). The server then generates brand visuals using an image generation AI (e.g., DALL-E).

[2245] The generated advertising copy and brand visuals are integrated on the server and delivered to the user's device, where the user can use it to create content for their marketing campaign.

[2246] Specific examples

[2247] When a user enters "eco-friendly products" as their "new campaign concept," the emotion engine analyzes the user's emotion as "excitement." Based on this, the generative AI model generates the following ad copy:

[2248] One choice to nurture the future

[2249] In parallel, image generation AI generates energetic and natural visuals, which are then delivered to the user's device.

[2250] Customer acquisition and churn prediction + factor analysis and countermeasure planning

[2251] The server collects data from a company's customer database and cleans it using the pandas library. The server then predicts customer acquisition and churn using a machine learning model from Scikit-learn. Based on the prediction results, the server analyzes the reasons for churn and generates specific countermeasures.

[2252] The emotion engine analyzes the user's emotional data and personalizes countermeasures. The countermeasures are generated in report format and sent from the server to the user's device. The user then implements marketing measures based on this report.

[2253] Specific examples

[2254] The server analyzes customer data and discovers that purchases are declining in a particular segment. The emotion engine analyzes user "anxiety" and "dissatisfaction" and identifies price competition and the emergence of new competitors as the causes. Based on this information, the server generates specific countermeasures such as:

[2255] Implementing price promotions and strengthening loyalty programs

[2256] These proposed solutions are provided to the user in the form of a report.

[2257] As described above, the system of the present invention achieves efficient and accurate collection and analysis of data, and automatically generates marketing strategies and creatives that take user emotions into consideration.

[2258] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2259] Market trends / customer behavior / competitive analysis + marketing strategy planning

[2260] Step 1:

[2261] The user issues market research instructions from the terminal.

[2262] Input: The user types "Start market research for new product" into the terminal and presses the "Collect data" button.

[2263] Output: Market research instructions are sent to the server.

[2264] Step 2:

[2265] The server retrieves market trend data.

[2266] Input: Receive market research instructions.

[2267] Data processing / calculation: The server uses the requests library to retrieve market trend data from external APIs.

[2268] What happens: The server sends a request to a specific API endpoint and receives market trend data in JSON format.

[2269] Output: Obtained market trend data.

[2270] Step 3:

[2271] The server collects customer behavior data.

[2272] Input: Access the CRM system using an SQL query.

[2273] Data processing / calculation: Extract customer behavior data and format it using the pandas library.

[2274] Specific operation: Extract the necessary customer behavior data from the SQL database and convert it into a data frame.

[2275] Output: Collected customer behavior data.

[2276] Step 4:

[2277] The server retrieves the conflict information.

[2278] Input: Scraping instructions using a web crawler.

[2279] Data processing / calculation: Use the BeautifulSoup library to crawl competitors' websites and extract data.

[2280] What it does: The server accesses the web page of each competitor and runs a script to extract the required information.

[2281] Output: The obtained competitive intelligence data.

[2282] Step 5:

[2283] The server performs data cleansing and integration.

[2284] Inputs: Captured market trend data, customer behavior data, and competitive intelligence data.

[2285] Data processing / calculation: Use the pandas library to fill in missing values ​​and remove outliers to create a single integrated dataset.

[2286] Specific actions: Run scripts to impute missing values, remove outliers, merge necessary fields, etc.

[2287] Output: A cleansed, consolidated dataset.

[2288] Step 6:

[2289] The server analyzes the data using the generative AI model.

[2290] Input: The cleansed consolidated dataset.

[2291] Data processing / computation: Use generative AI models (e.g., PyTorch, TensorFlow) to perform analysis based on marketing frameworks.

[2292] How it works: The integrated dataset is fed into a generative AI model to obtain results based on frameworks such as 3C, STP, and 4P.

[2293] Output: Analysis results.

[2294] Step 7:

[2295] The server creates marketing strategies and generates reports.

[2296] Input: Analysis results.

[2297] Data processing / calculation: Use the PDFKit library to visualize the analysis results and create detailed PDF reports.

[2298] What it does: Generate graphs and charts from the analysis results and convert them to PDF format.

[2299] Output: PDF report.

[2300] Step 8:

[2301] The server uses an emotion engine to personalize the marketing strategy.

[2302] Input: PDF report and user sentiment data.

[2303] Data processing / calculation: The emotion engine analyzes the user's past inputs and reactions to customize the report content.

[2304] What it does: Perform real-time analysis using the sentiment engine and adjust some of the reports.

[2305] Output: Personalized PDF report.

[2306] Step 9:

[2307] The server delivers the report to the user.

[2308] Input: A personalized PDF report.

[2309] Output: The report is delivered to the user's device.

[2310] Brand visuals + copy creation

[2311] Step 1:

[2312] The user enters the campaign concept and keywords into the terminal.

[2313] Input: Campaign concept or keywords (e.g. "eco-friendly products").

[2314] Output: The input concepts or keywords.

[2315] Step 2:

[2316] An emotion engine analyzes the user's emotional state.

[2317] Input: The concept or keyword entered.

[2318] Data processing / calculation: The emotion engine analyzes the user's emotions.

[2319] Specific behavior: Analyzes emotional state (e.g., "excited") in real time based on user input.

[2320] Output: Parsed emotion data.

[2321] Step 3:

[2322] The server generates the ad copy using a generative AI model.

[2323] Input: Sentiment data and concepts, keywords.

[2324] Data processing / computation: Using generative AI models (e.g., GPT-3) to generate ad copy based on sentiment data.

[2325] What it does: Concepts and keywords are input as prompts into the generation AI, which then gene...

Claims

1. a means of obtaining market trend data; a means of collecting customer behavior data; a means of obtaining competitive information; a means for cleansing the acquired data; A means of integrating and analyzing multiple data, A means for formulating a marketing strategy based on the generated analysis results; a means for providing the generated marketing strategy to a user in the form of a report; A system including:

2. A means to generate ad copy using generative AI based on input concepts and keywords; A means for generating brand visuals using image generation AI based on the generated advertising copy; A means for integrating the generated advertising copy with brand visuals and providing them to users; The system of claim 1 , comprising:

3. A means of collecting and cleansing customer data; Analytical methods for predicting customer acquisition and churn, A means for analyzing the reasons for withdrawal based on the prediction results; A means for generating countermeasures against dropout factors; a report creation means for providing the generated countermeasure plan to a user; The system of claim 1 , comprising:

Images