System

Abstract

To provide a system for enabling an enterprise or a person in charge of marketing to quickly and efficiently formulate and optimize a data-driven marketing strategy.SOLUTION: Means for a user to input a purpose or a target of a marketing strategy via a terminal, means for a server to specify a keyword or a parameter in order to collect related data from an Internet resource, means for the server to collect the related data from the Internet resource, means for the server to preprocess the collected data and convert the data into a format suitable for analysis, and means for the server to analyze the preprocessed data, A system comprising: means for extracting metrics related to a user's strategy; means for a server to generate personalized insights and recommendations for the user based on the analysis; means for the server to display the insights and recommendations in a real-time data dashboard; means for the user to access the dashboard via a terminal to review and modify the strategy; and means for the user to re-enter the modified strategy.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] Formulating a marketing strategy requires the selection, collection, and analysis of a wide range of data, and requires specialized knowledge, as well as a large amount of time and effort. Traditional methods rely on humans to handle these tasks, so efficient alternatives are needed. Additionally, there is a lack of tools for updating data in real time and quickly reviewing strategies. Therefore, there is a need for a system that allows companies and marketers to quickly and efficiently formulate and optimize data-driven marketing strategies. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system including: means for a user to input the objectives and goals of a marketing strategy via a terminal; means for a server to identify keywords and parameters for collecting relevant data from Internet resources; means for the server to collect relevant data from Internet resources; means for the server to preprocess the collected data and convert it into a format suitable for analysis; means for the server to analyze the preprocessed data and extract metrics relevant to the user's strategy; means for the server to generate personalized insights and suggestions for the user based on the analysis results; means for the server to display the insights and suggestions on a real-time data dashboard; means for the user to access the dashboard via a terminal to review and modify the strategy; and means for the user to re-input the modified strategy.

[0006] A "terminal" is a device used by a user to input and confirm data, and includes personal computers, tablets, smartphones, etc.

[0007] "Server" means a computer system that collects, pre-processes, analyzes, and generates insights from data and operates in response to user input.

[0008] "Internet resources" refers to data and information sources found on the Internet, including social media, websites, news articles, industry reports, etc.

[0009] "Keywords and parameters" refer to the conditions and search terms specified by the server for data collection, in order to extract important elements related to the user's strategy.

[0010] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis, removing noise data, and cleaning the data.

[0011] "Metrics" refer to specific numerical values ​​or data points extracted from the analysis results that help users evaluate and improve their strategies.

[0012] "Personalized insights and recommendations" are specific advice and strategies tailored to your specific needs and goals, based on your input and collected data.

[0013] A "data dashboard" is an interface that visually displays the latest data and analysis results in real time, allowing users to easily grasp the information and review their strategies as appropriate. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram 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

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

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

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

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

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

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

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

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

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

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

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

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

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

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

[0035] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is designed to help companies and marketers efficiently and quickly develop and optimize their marketing strategies. This paper explains the program processing of this system in natural language and provides examples.

[0036] User inputs marketing strategy

[0037] The user uses the terminal to input the purpose and goal of the marketing strategy. For example, the user might input, "We want to strengthen the online promotion of new product A."

[0038] The server prepares to collect data

[0039] The server analyzes the user's input and identifies keywords and parameters for collecting the necessary data. For example, it might list keywords such as "New Product A," "Online Promotion," and "Competitors."

[0040] The server collects the data

[0041] The server collects relevant data from internet resources (social media, websites, news articles, industry reports, etc.). For example, it uses the Twitter API to collect tweets about "New Product A." It then stores the tweet's posting time, number of likes and retweets, and post content in a database.

[0042] The server preprocesses the data

[0043] The server cleans the collected data and converts it into a format suitable for analysis, for example, filtering out noise data and tokenizing text data.

[0044] The server analyzes the data

[0045] The server analyzes the preprocessed data and extracts metrics relevant to the user's strategy (such as engagement rate, trends, and customer sentiment analysis). It uses natural language processing (NLP) and machine learning models to gain insights. For example, it analyzes collected tweet text data with an NLP model to classify customer sentiment (positive, negative, or neutral).

[0046] The server generates personalized insights

[0047] The server then uses the results of the data analysis to create personalized insights and suggestions for users, such as "Promotions for new product A are particularly effective on weekday evenings."

[0048] The server updates the data dashboard

[0049] The server then displays these insights and recommendations in a real-time data dashboard, which visually displays the latest indicators and trending information, making it easy for users to understand the information.

[0050] Users reassess their strategies

[0051] Users access the dashboard via their devices to view new data and insights, which can then be used to develop new marketing strategies and adjust them as needed, for example, by scheduling promotions on weekday evenings.

[0052] User re-enters strategy

[0053] The user then re-enters the revised strategy into the terminal, which starts the cycle again, continuously optimizing based on the latest data.

[0054] This concludes the natural language explanation of the AIEMI system's program processing. This system frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize marketing strategies. The inclusion of specific operational examples makes it easier for users to understand how to use the system and its effectiveness.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The user inputs the objectives and goals of the marketing strategy via the terminal. The user enters a specific marketing goal, for example, "I want to strengthen the online promotion of new product A," into the input form on the terminal.

[0058] Step 2:

[0059] The server receives user input and identifies keywords and parameters for collecting the required data. The server lists keywords such as "New Product A," "Online Promotion," and "Competitors."

[0060] Step 3:

[0061] The server collects relevant data from internet resources, such as tweets, blog posts, news articles, and industry reports, using social media APIs and web scraping techniques.

[0062] Step 4:

[0063] The server pre-processes the collected data, cleaning it, for example, by removing duplicates and removing emojis and special characters from social media posts.

[0064] Step 5:

[0065] The server analyzes the pre-processed data, uses natural language processing (NLP) to tokenize the text data and perform sentiment analysis, and uses machine learning models to calculate engagement rates and trend metrics.

[0066] Step 6:

[0067] The server generates personalized insights and suggestions based on the analysis results, for example, suggesting that "it would be effective to promote new product A in the evening on weekdays."

[0068] Step 7:

[0069] The server displays insights and recommendations in a real-time data dashboard, which displays the latest metrics and analytics in the form of graphs and charts.

[0070] Step 8:

[0071] Users access the dashboard via their devices to view new data and insights, and use the information in the dashboard to review and revise their marketing strategies.

[0072] Step 9:

[0073] The user inputs the revised strategy into the terminal again, and the revised strategy is sent to the server, where data is collected and analyzed again, providing a continuous optimization process.

[0074] Example 1

[0075] 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."

[0076] Traditionally, developing and optimizing marketing strategies has required a lot of time and effort, and collecting and analyzing relevant data has often been done manually, resulting in inefficiencies and limited insights, making it difficult for companies and marketers to make fast and effective decisions.

[0077] 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.

[0078] In this invention, the server includes: a means for a user to input the purpose and goals of a marketing strategy via a terminal; a means for the server to analyze the user's input data and identify necessary keywords and parameters; a means for the server to collect relevant data from Internet resources; a means for the server to preprocess the collected data and convert it into a format suitable for analysis; a means for the server to analyze the preprocessed data and extract indicators related to the user's strategy; a means for the server to generate personalized insights and suggestions for the user based on the analysis results; a means for the server to display the insights and suggestions on a real-time data dashboard; a means for a user to access the dashboard via a terminal to review and revise the strategy; and a means for the user to re-input the revised strategy. This frees companies and marketers from the burden of extensive data analysis, enabling them to quickly and efficiently formulate and optimize marketing strategies.

[0079] "User" refers to the end-user who inputs information and receives results to develop and optimize marketing strategies through this system.

[0080] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that a user uses to access the system and enter information.

[0081] "Server" refers to the central computer system that analyzes user input data and performs data collection, pre-processing, analysis, and display of results.

[0082] "Marketing strategy" refers to the plans and policies developed to optimize the promotion and sale of products and services.

[0083] "Objectives and goals" refer to the specific results and indicators you want to achieve through your marketing strategy.

[0084] "Analyzing input data" refers to the process of processing the text or information entered by the user and extracting the necessary keywords and parameters.

[0085] "Keywords and parameters" refer to key words and numbers used to indicate specific targets in data collection and analysis.

[0086] "Internet resources" refers to online sources of information such as social media, websites, news articles, and industry reports.

[0087] "Harvesting data" refers to the process of obtaining relevant information from Internet resources.

[0088] "Preprocessing" refers to the preparation of collected data to convert it into a format suitable for analysis.

[0089] "Analysis" refers to the process of using pre-processed data to extract specific metrics and trends and gain insights.

[0090] "Metrics" refers to specific numerical values ​​or indicators of analytical results obtained from data (e.g., engagement rate, trends, sentiment analysis).

[0091] "Insights" refers to knowledge and suggestions useful for marketing strategies obtained from data analysis.

[0092] A "data dashboard" refers to a user interface that visually displays real-time analysis results and indicators.

[0093] A "revised strategy" refers to a marketing strategy that has been reviewed and re-formulated based on analysis results and insights.

[0094] "NLP (Natural Language Processing)" refers to artificial intelligence technology for analyzing, understanding, and generating human language.

[0095] "Machine learning" refers to algorithms that use large amounts of data to train models to improve their accuracy at specific tasks.

[0096] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is a system that allows companies and marketers to efficiently and quickly build and optimize their marketing strategies. The system starts when the user inputs the purpose and goals of the marketing strategy via a terminal, and the server collects, preprocesses, analyzes, and displays the results of the data.

[0097] First, the user inputs the objectives and goals of the marketing strategy through the terminal. For example, they might input, "We want to strengthen the online promotion of new product A." This input can be done using a GUI (Graphical User Interface) such as a text input field.

[0098] The server then analyzes the user's input. It uses text analysis algorithms to identify the required keywords and parameters. Natural language processing libraries such as Python's NLTK or SpaCy can be used here. For example, keywords such as "New Product A," "Online Promotion," and "Competitor" can be extracted.

[0099] The server then scans Internet resources and collects relevant data. This process can be performed using the Twitter API or other web scraping tools (such as Beautiful Soup or Selenium). For example, the server uses the Twitter API to collect tweets about "New Product A." Data such as the posting time, number of likes and retweets, and post content are then stored in a database.

[0100] The collected data is preprocessed by the server. NLP techniques are used to remove noise and tokenize the text data. For example, spam and duplicate posts on social media are deleted, and the remaining text data is split into words. Preprocessing also includes format conversion, such as standardizing the encoding method.

[0101] The preprocessed data is then analyzed in detail by the server to extract important metrics. The server uses natural language processing (NLP) and machine learning (ML) models to obtain metrics relevant to marketing strategies (such as engagement rates, trends, and customer sentiment analysis). In a specific example, the collected tweet text data is analyzed using an NLP model (such as BERT or GPT) to classify customer sentiment (positive, negative, or neutral).

[0102] The server then generates personalized insights and suggestions for users based on the analysis results, such as "Promoting new product A is particularly effective on weekday evenings." At this stage, machine learning models can be used to analyze past data and trends to suggest optimal strategies.

[0103] Finally, the server displays these insights and recommendations in a real-time data dashboard, visually displaying the latest indicators and trend information, making it easy for users to understand the information.Specific technologies that can be used include data visualization libraries such as React and D3.js.

[0104] Users can access the dashboard through their device and view new data and insights. Using this information, they can develop new marketing strategies and modify them as needed, such as scheduling promotions for weekday evenings. The modified strategies are then entered back into the device, and the cycle begins again.

[0105] Example prompt sentence:

[0106] "We want to strengthen online promotion for new product A and increase engagement rates by 20% within one month."

[0107] This system will free companies and marketers from the burden of extensive data analysis, enabling them to quickly and efficiently formulate and optimize marketing strategies.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1: User Marketing Strategy Input

[0110] The user uses the terminal to input the objectives and goals of the marketing strategy.

[0111] Input: The user types in the text field, "I want to strengthen the online promotion of new product A."

[0112] Operation: Information entered through the terminal's GUI (Graphical User Interface) is sent to the server.

[0113] Output: Marketing strategy objectives and goals text sent to the server.

[0114] Step 2: Parse the input data by the server

[0115] The server analyzes the user's input data and identifies any required keywords or parameters.

[0116] Input: Marketing strategy text ("We want to strengthen online promotion for new product A").

[0117] How it works: The server uses natural language processing (NLP) libraries such as Python's NLTK or SpaCy to extract important keywords and parameters from the input text.

[0118] Output: A list of keywords such as "New Product A", "Online Promotion", "Competitor", etc.

[0119] Step 3: Data collection by the server

[0120] The server collects relevant data from Internet resources.

[0121] Input: Keyword list ("New Product A", "Online Promotion", "Competitor").

[0122] How it works: The server uses web scraping tools such as Twitter API, Beautiful Soup, or Selenium to collect relevant data from internet resources (social media, websites, news articles, etc.). For example, the server uses Twitter API to collect tweets about "New Product A."

[0123] Output: Tweet data (posting time, number of likes and retweets, post content).

[0124] Step 4: Preprocessing the data on the server

[0125] The server cleans the collected data and converts it into a format suitable for analysis.

[0126] Input: Collected tweet data.

[0127] How it works: The server uses NLP techniques to remove noise data, eliminate duplicate data, tokenize text data, and unify encoding methods.

[0128] Output: Preprocessed and clean text data.

[0129] Step 5: Parse the data on the server

[0130] The server analyzes the pre-processed data and extracts metrics related to the user's strategy.

[0131] Input: Preprocessed clean text data.

[0132] How it works: The server uses NLP models (e.g., BERT or GPT) or machine learning models to extract metrics such as customer sentiment analysis (positive, negative, neutral), engagement rates, and trends from the text data.

[0133] Output: Sentiment analysis results, engagement rate, and trend information.

[0134] Step 6: Server generates personalized insights

[0135] The server generates personalized insights and suggestions for users based on the results of the data analysis.

[0136] Inputs: Sentiment analysis results, engagement rates, and trend information.

[0137] How it works: The server uses machine learning models to analyze historical data and trends to generate optimal marketing offers for users.

[0138] Output: Personalized marketing suggestions (e.g., "Promoting new product A is particularly effective on weekday evenings").

[0139] Step 7: Server Updates Data Dashboard

[0140] The server updates a real-time data dashboard, making it easy for users to understand the information.

[0141] Input: Personalized marketing suggestions, latest metrics and trend information.

[0142] How it works: The server uses data visualization libraries such as React and D3.js to display the latest metrics and trending information in graphs and charts.

[0143] Output: An updated data dashboard.

[0144] Step 8: User review of strategy

[0145] Users access the dashboard through their devices to see new data and insights.

[0146] Input: Updated data dashboard.

[0147] How it works: Users review dashboard metrics and recommendations to refine their marketing strategy.

[0148] Output: A revised marketing strategy.

[0149] Step 9: User re-enters strategy

[0150] The user inputs the revised strategy into the terminal again.

[0151] Enter: a revised marketing strategy.

[0152] Operation: A correction strategy entered through the terminal GUI is sent to the server.

[0153] Output: The modified marketing strategy sent to the server.

[0154] (Application example 1)

[0155] 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."

[0156] In modern advertising campaigns, advertisers and marketers need to develop effective strategies based on massive amounts of data. However, collecting, organizing, and analyzing data requires a significant amount of time and effort. Another challenge is the difficulty of optimizing advertising in real time based on customer sentiment and activity times. Furthermore, it is difficult to predict engagement rates and generate appropriate prompts using past data. Therefore, there is a strong demand for a system that can efficiently optimize advertising campaigns.

[0157] 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.

[0158] In this invention, the server includes means for sentiment analyzing collected data and notifying users of an average sentiment score and peak activity time, means for analyzing the effectiveness of advertising campaigns in real time and proposing optimal advertising strategies, means for collecting social media data and classifying customer sentiment using natural language processing and visualizing it in real time, means for building a predictive model of engagement rates based on past data and showing users the effectiveness of promotions on specific days and times, and means for generating prompt sentences for users using a generative AI model based on the collected data. This automates the process from data collection to analysis and strategy proposals, making it possible to optimize advertising campaigns in real time.

[0159] "Marketing strategy objectives and goals" refer to the specific results and targets that users want to achieve through their marketing activities.

[0160] "Internet resources" refers to information sources found on the internet, such as websites, social media, news articles, and industry reports.

[0161] "Relevant Data" means information or data that is relevant to the objectives and goals of the Marketing Strategy.

[0162] "Keywords and parameters" refer to important words and numerical settings identified for data collection and analysis.

[0163] "Data preprocessing" refers to the process of converting collected data into a format suitable for analysis, including removing noise data and tokenizing text data.

[0164] "Analysis" refers to the process of deriving marketing metrics and insights from collected and pre-processed data.

[0165] "Metrics" refer to quantitative data points used to measure the effectiveness and trends of marketing activities.

[0166] "Personalized insights and recommendations" means analysis results and action recommendations that are customized to fit a specific user's strategy and objectives.

[0167] A "real-time data dashboard" refers to an interface that visually displays the latest data and analysis results.

[0168] "Sentiment analysis" refers to the process of classifying and evaluating emotions (positive, negative, neutral) from the content of text data.

[0169] The "average emotion score" indicates the average value of the user's overall emotion calculated based on the collected data.

[0170] "Peak activity time" refers to the time period during which a particular subject is most active.

[0171] "Analysis of the effectiveness of advertising campaigns" means analysis to evaluate the efficiency and impact of ongoing advertising campaigns and to use the results to inform future measures.

[0172] "Engagement rate" means a rate that indicates the degree of response or involvement that a user shows with content.

[0173] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to automatically generate the data and information needed for a specific task.

[0174] A "prompt" refers to a sentence of instructions or suggestions that a generative AI model provides to a user.

[0175] The "AI-Enhanced Marketing Insights (AIEMI) System" of the present invention is a comprehensive system for analyzing the effectiveness of advertising campaigns in real time and proposing optimal advertising strategies. This system includes the following elements:

[0176] Hardware and Software Configuration

[0177] Hardware: smartphones, servers, databases

[0178] Software: Python, Twitter API, Pandas, Matplotlib, TextBlob, natural language processing (NLP) techniques, generative AI models (e.g., OpenAI's GPT-3)

[0179] Specific operation of the system

[0180] 1. Marketing Strategy Input:

[0181] Users input the objectives and goals of their marketing strategy from their device (smartphone or PC). For example, they might input, "I want to strengthen the online promotion of new product A."

[0182] 2. Data Collection:

[0183] The server analyzes the user's input and identifies keywords and parameters for the required data collection. It then collects relevant data from internet resources (social media, websites, news articles, etc.). Specifically, it uses the Twitter API to retrieve tweets related to the specified keywords.

[0184] 3. Data Preprocessing:

[0185] The server cleans the collected data and converts it into a format suitable for analysis, removing noise data and tokenizing text data.

[0186] 4. Data Analysis:

[0187] The server analyzes the preprocessed data and extracts metrics related to the user's strategy. It uses NLP and machine learning models to classify customer sentiment (positive, negative, neutral) and calculate a sentiment score. At the same time, it analyzes tweet posting times to identify peak activity times.

[0188] 5. Generating insights and recommendations:

[0189] The server generates personalized insights and suggestions for the user based on the analysis results, such as informing them that online promotions for new product A are particularly effective on weekday evenings. Furthermore, it uses a generative AI model to generate appropriate prompts.

[0190] 6. Update the data dashboard:

[0191] The server then displays these insights and recommendations in a real-time data dashboard, which visually displays the latest metrics and trending information.

[0192] 7. User Strategy Review:

[0193] Users can access the dashboard via their devices, review new data and insights, and then review and adjust their strategies as needed.

[0194] 8. Re-enter strategy:

[0195] The user continues the optimization cycle by re-entering the revised strategy into the terminal.

[0196] Examples and prompts

[0197] For example, if a user inputs, "Collect tweets about the online promotion of new product A and suggest the optimal advertising strategy. Analyze the sentiment score and activity time period from the tweets and notify me of the most effective advertising times," the system will collect and analyze related tweets and then generate the following prompt:

[0198] Example prompt sentence:

[0199] Collect tweets related to the online promotion of new product A and propose the optimal advertising strategy. Analyze the sentiment score and activity time from the tweets and inform effective advertising times.

[0200] Keywords: New Product A, Online Promotion

[0201] Output: Mean emotion score, peak activity time, histogram

[0202] The above is a specific embodiment for carrying out the present invention. This system frees advertisers and marketers from the burden of complex data analysis, enabling them to quickly and efficiently optimize their advertising campaigns.

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] The user inputs the objectives and goals of the marketing strategy via a terminal. For example, the user may input a goal such as "I want to strengthen the online promotion of new product A." The input goal becomes the starting point of the system.

[0206] input:

[0207] Marketing strategy objectives and goals (e.g., "We want to strengthen online promotions for new product A")

[0208] output:

[0209] Data including strategic objectives and goals

[0210] Step 2:

[0211] The server analyzes the user's input and identifies keywords and parameters for data collection, for example, listing important keywords such as "New Product A," "Online Promotion," and "Competitors."

[0212] input:

[0213] Strategic Objectives and Targets Data

[0214] output:

[0215] Keywords and parameters for data collection (e.g., "New Product A," "Online Promotion")

[0216] Step 3:

[0217] The server collects relevant data from Internet resources, using Twitter APIs and other methods to retrieve tweets and other relevant information related to the identified keywords, and stores the tweet posting time, number of likes and retweets, and post content in a database.

[0218] input:

[0219] Keywords and parameters (e.g., "New Product A," "Online Promotion")

[0220] output:

[0221] Related data (e.g. tweet data)

[0222] Step 4:

[0223] The server preprocesses the collected data and converts it into a format suitable for analysis, specifically removing noise data and tokenizing text data, which makes the data clean and suitable for analysis.

[0224] input:

[0225] Related data (e.g. tweet data)

[0226] output:

[0227] Pre-processed, clean data

[0228] Step 5:

[0229] The server analyzes the pre-processed data and extracts metrics related to the user's strategy. It uses NLP and machine learning models to classify customer sentiment (positive, negative, neutral) and calculate a sentiment score. It also analyzes tweet posting times to identify peak activity times.

[0230] input:

[0231] Pre-processed, clean data

[0232] output:

[0233] Analysis results (e.g., emotion scores, peak activity times)

[0234] Step 6:

[0235] Based on the analysis results, the server generates personalized insights and suggestions for the user, such as "Online promotions for new product A are particularly effective on weekday evenings." It also uses a generative AI model to generate appropriate prompts.

[0236] input:

[0237] Analysis results (e.g., emotion scores, peak activity times)

[0238] output:

[0239] Personalized insights and recommendations (e.g., "Online promotions for new product A are particularly effective on weekday evenings")

[0240] Prompt statement (e.g., "We suggest setting promotion times for weekday evenings.")

[0241] Step 7:

[0242] The server displays these insights and recommendations in a real-time data dashboard, which visually displays the analysis results and makes them easy for users to understand.

[0243] input:

[0244] Personalized insights and recommendations (e.g., "Online promotions for new product A are particularly effective on weekday evenings")

[0245] output:

[0246] Real-time data dashboard

[0247] Step 8:

[0248] Users can access the dashboard through their devices to view new data and insights, and use this information to develop new marketing strategies and adjust them as needed.

[0249] input:

[0250] Real-time data dashboard

[0251] output:

[0252] User strategy adjustments

[0253] Step 9:

[0254] The user then re-enters the revised strategy into the terminal, and the system continues optimizing the strategy based on the latest data.

[0255] input:

[0256] Revised strategy (e.g., promotion time changed to weekday evenings)

[0257] output:

[0258] New Strategic Data

[0259] By following these steps, advertisers and marketers can effectively optimize their advertising campaigns and efficiently achieve their goals.

[0260] 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.

[0261] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is designed to help companies and marketers efficiently and quickly build and optimize their marketing strategies, and by combining it with an emotion engine, it achieves even greater personalization. The program processing of this system is explained in natural language, with concrete examples.

[0262] User inputs marketing strategy

[0263] The user uses a device to input the objectives and goals of the marketing strategy. For example, they might input, "We want to strengthen the online promotion of new product A." This input is then analyzed by the emotion engine.

[0264] The server prepares to collect data

[0265] The server analyzes the user's input and identifies keywords and parameters for collecting the necessary data. For example, it might list keywords such as "New Product A," "Online Promotion," and "Competitors."

[0266] The server collects the data

[0267] The server collects relevant data from internet resources (social media, websites, news articles, industry reports, etc.). For example, it uses the Twitter API to collect tweets about "New Product A." It then stores the tweet's posting time, number of likes and retweets, and post content in a database.

[0268] The server preprocesses the data

[0269] The server cleans the collected data and converts it into a format suitable for analysis, for example, filtering out noise data and tokenizing text data.

[0270] The server analyzes the data

[0271] The server analyzes the preprocessed data and extracts metrics relevant to the user's strategy (such as engagement rate, trends, and customer sentiment analysis). It uses natural language processing (NLP) and machine learning models to gain insights. For example, it analyzes collected tweet text data with an NLP model to classify customer sentiment (positive, negative, or neutral).

[0272] The server generates personalized insights

[0273] The server then uses the results of the data analysis to create personalized insights and suggestions for users, such as "Promotions for new product A are particularly effective on weekday evenings."

[0274] The server utilizes the emotion engine

[0275] The server's emotion engine recognizes the user's emotions in real time based on their input and browsing history. This generates personalized insights and suggestions that reflect the user's current emotional state. For example, if the user feels impatient or anxious, the system will suggest time management and resource optimization to alleviate that feeling.

[0276] The server updates the data dashboard

[0277] The server displays these insights and recommendations in a real-time data dashboard, which displays the latest metrics and analysis results in graphs and charts for easy user comprehension.

[0278] Users reassess their strategies

[0279] Users can access the dashboard via their devices to view new data and insights, and use the information in the dashboard to revise and adjust their marketing strategies, for example by scheduling promotions on weekday evenings.

[0280] User re-enters strategy

[0281] The user then re-enters the revised strategy into the terminal, which starts the cycle again, continuously optimizing based on the latest data.

[0282] The above is a natural language explanation of the program processing of the AIEMI system, which combines an emotion engine. This system frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize marketing strategies. The emotion engine provides personalized insights and suggestions that incorporate the user's emotions, resulting in greater accuracy and effectiveness.

[0283] The processing flow will be explained below.

[0284] Step 1:

[0285] The user inputs the objectives and goals of the marketing strategy via the terminal. The user enters a specific marketing goal, for example, "I want to strengthen the online promotion of new product A," into the input form on the terminal.

[0286] Step 2:

[0287] The server receives the user's input, analyzes it with an emotion engine, and recognizes the user's emotional state. For example, it classifies the user as feeling "impatient" based on the input.

[0288] Step 3:

[0289] Based on the user's input, the server identifies keywords and parameters (e.g., "New Product A," "Online Promotion," "Competitors") for collecting the required data.

[0290] Step 4:

[0291] The server collects relevant data from internet resources, such as tweets, blog posts, news articles, and industry reports, using social media APIs and web scraping techniques. For example, the server uses the Twitter API to collect tweets about "New Product A."

[0292] Step 5:

[0293] The server preprocesses the collected data, specifically removing noise data, tokenizing text data, and filtering out unnecessary information.

[0294] Step 6:

[0295] The server analyzes the preprocessed data. It uses natural language processing (NLP) to perform semantic analysis and sentiment analysis of the text. For example, it classifies the sentiment of collected tweets into "positive," "negative," and "neutral" sentiments.

[0296] Step 7:

[0297] The server generates personalized insights and suggestions for users based on the results of data analysis, such as "Promotions for new product A are particularly effective on weekday evenings."

[0298] Step 8:

[0299] The server generates insights and recommendations that are displayed in a real-time data dashboard that also displays the user's emotional state, for example, "The user is feeling anxious."

[0300] Step 9:

[0301] Users can access the dashboard via their devices to view the latest data and insights, and can use the information in the dashboard to revise their marketing strategies, for example by changing promotion times to weekday evenings.

[0302] Step 10:

[0303] The user inputs the revised strategy into the terminal again. The user's emotional state is analyzed again by the emotion engine, and the cycle begins again. The server repeats data collection and analysis based on this new strategy.

[0304] This allows the system to continually optimize personalized marketing strategies that reflect the user's emotional state.

[0305] Example 2

[0306] 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."

[0307] Traditional marketing strategy development and optimization involves time-consuming and labor-intensive large-scale data analysis, which takes a long time to produce results. Furthermore, personalized proposals are often lacking, making it difficult to develop marketing strategies that take into account the detailed emotions and circumstances of each customer. This makes it difficult for companies and marketers to quickly and efficiently develop optimal strategies.

[0308] 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.

[0309] In this invention, the server includes means for the user to input the objectives and goals of the marketing strategy via the terminal, means for identifying keywords and parameters for collecting relevant data from internet resources, and means for pre-processing and converting the collected data into a format suitable for analysis, thereby enabling the generation of personalized insights and recommendations for the user.

[0310] "User" refers to the individual or organization that operates the system and inputs or modifies marketing strategies.

[0311] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that a user uses to perform operations such as input and display.

[0312] "Server" refers to a central computer system that analyzes input data, performs related processing, and provides the results to users.

[0313] A "marketing strategy" refers to the strategic direction or plan of action that a company or organization plans to bring a product or service to market and increase sales and awareness.

[0314] "Keywords" refer to important words or phrases that represent a particular theme or topic used during data collection and analysis.

[0315] "Parameter" refers to a specific condition or setting used during data collection and analysis.

[0316] "Internet resources" refers to information sources found on the internet, such as social media, websites, news articles, and industry reports.

[0317] "Data preprocessing" refers to operations such as removing noise data and tokenizing data to prepare the data in a format suitable for analysis.

[0318] "Analysis" refers to the process of applying statistical methods and algorithms to collected data to derive useful metrics and insights.

[0319] "Personalized insights" refers to customized information and recommendations based on a user's specific needs and emotional state.

[0320] A "data dashboard" refers to an interface that visually displays analytical results and insights, allowing users to easily understand the information.

[0321] "Natural language processing (NLP)" refers to the technology that enables computers to understand and analyze human language.

[0322] "Customer sentiment" refers to the emotional state a customer has about a product or service, whether positive, negative, or neutral.

[0323] "Engagement rate" refers to an indicator that shows the degree of interest and involvement that customers show in a product or service.

[0324] The AI-Enhanced Marketing Insights (AIEMI) system of the present invention allows companies and marketers to efficiently and quickly build and optimize their marketing strategies. This system achieves further personalization by combining an emotion engine. The following describes an embodiment of the present invention.

[0325] 1. User Interface

[0326] The user uses the device to input the objectives and goals of the marketing strategy. This input is analyzed by the emotion engine and sent to the server. Specifically, this involves the user entering "I would like to strengthen the online promotion of new product A" into the input form and clicking the "Submit" button.

[0327] 2. Data collection from internet resources

[0328] The server receives user input and identifies keywords and parameters for collecting the required data. Based on these keywords, the server collects relevant data from Internet resources. For example, it uses the Twitter API to collect tweets about "New Product A."

[0329] As a concrete example, the following prompt sentence is input to the generative AI model:

[0330] "Collect the latest tweets about new product A and perform sentiment analysis to classify them as positive, negative, or neutral."

[0331] 3. Data Preprocessing

[0332] The server cleans the collected data and converts it into a format suitable for analysis. At this stage, noise data is removed, text data is tokenized, and missing values ​​are filled in. The collected tweets are analyzed using an NLP model to classify customer sentiment (positive, negative, neutral).

[0333] 4. Data Analysis

[0334] The server analyzes the preprocessed data. Using machine learning models and natural language processing (NLP) techniques, it calculates metrics such as engagement rates, trends, and customer sentiment analysis. For example, the analysis results can provide insights such as, "Promoting new product A is particularly effective in the evenings on weekdays."

[0335] 5. Generating personalized insights

[0336] The server uses the results of the data analysis to create personalized insights and suggestions for users. These insights and suggestions reflect the user's current emotional state. The emotion engine analyzes the user's input and browsing history in real time to provide personalized suggestions. For example, if the user feels impatient or anxious, it will suggest time management and resource optimization to alleviate that feeling.

[0337] 6. Update the data dashboard

[0338] The server displays these insights and recommendations in a real-time data dashboard, which displays the latest metrics and analysis results in graphs and charts for easy user comprehension.

[0339] 7. Review and re-enter your strategy

[0340] Users access the dashboard via their device to view new data and insights, allowing them to review and revise their marketing strategy, for example by scheduling a promotion for weekday evenings. They then re-enter the revised strategy into their device, and the cycle begins again, continually optimizing based on the latest data.

[0341] In this way, the present invention allows for the rapid and efficient development and optimization of marketing strategies, with even greater accuracy and effectiveness achieved through the use of an emotion engine.

[0342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0343] Step 1:

[0344] The user inputs the objectives and goals of the marketing strategy via the terminal.

[0345] Specific operation: The user enters "I would like to strengthen the online promotion of new product A" into the input form on the device and clicks the "Submit" button.

[0346] Input: The purpose or goal of your marketing strategy (e.g., "We want to strengthen online promotion for new product A").

[0347] Output: The entered data is sent to the server.

[0348] Step 2:

[0349] The server parses the user's input and identifies keywords and parameters for collecting the required data.

[0350] Specific operation: The server analyzes the received data using a natural language processing (NLP) engine and extracts key keywords (e.g., "New Product A," "Online Promotion").

[0351] Input: The marketing strategy entered by the user.

[0352] Output: Identified keywords and parameters.

[0353] Step 3:

[0354] The server collects relevant data from Internet resources.

[0355] Specific operation: The server uses the Twitter API to collect tweets about "New Product A." The collected tweets are stored in a database.

[0356] Input: The keywords or parameters specified.

[0357] Output: Collected tweet data (posting time, number of likes and retweets, post content, etc.).

[0358] Step 4:

[0359] The server preprocesses the collected data and converts it into a format suitable for analysis.

[0360] What it does: The server runs data cleaning scripts to filter out noise data, tokenize text data, and also impute missing values.

[0361] Input: Collected tweet data.

[0362] Output: Cleaned and tokenized text data.

[0363] Step 5:

[0364] The server analyzes the pre-processed data and extracts metrics related to the user's strategy.

[0365] What it does: The server applies NLP models to classify the sentiment of tweets (positive, negative, neutral) and calculate engagement rates and trends.

[0366] Input: Preprocessed text data.

[0367] Output: Sentiment classification results and metrics such as engagement rate and trend.

[0368] Step 6:

[0369] The server generates personalized insights and suggestions for users based on the results of the data analysis.

[0370] Specific operation: The server generates insights using the user profile and analysis results, and compiles them in the form of a report. For example, it makes a suggestion such as, "Promoting new product A is particularly effective in the evenings on weekdays."

[0371] Inputs: Sentiment classification results, engagement rates, trend metrics, and user profiles.

[0372] Output: Personalized insights and recommendations.

[0373] Step 7:

[0374] The server uses an emotion engine to recognize the user's emotions in real time based on the user's input and browsing history.

[0375] What it does: The emotion engine assesses the user's current emotional state and generates personalized insights and suggestions based on that. For example, if the user feels anxious or impatient, it will suggest time management and resource optimization to alleviate that.

[0376] Input: User input, browsing history.

[0377] Output: Personalized insights based on emotional state.

[0378] Step 8:

[0379] The server displays these insights and recommendations in a real-time data dashboard.

[0380] What it does: Runs the data dashboard update script and displays the new data in graphs and charts.

[0381] Input: Insights and suggestions.

[0382] Output: An updated data dashboard.

[0383] Step 9:

[0384] Users access the dashboard via their devices to see new data and insights.

[0385] Specific actions: The user views the information on the dashboard and confirms and modifies the marketing strategy, for example, setting the promotion time to weekday evenings.

[0386] Input: Updated data dashboard.

[0387] Output: A revised marketing strategy.

[0388] Step 10:

[0389] The user inputs the revised strategy into the terminal again.

[0390] What happens: The user enters a new strategy and clicks the "Submit" button, which starts the cycle again.

[0391] Enter: a revised marketing strategy.

[0392] Output: The new marketing strategy sent to the server.

[0393] (Application example 2)

[0394] 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."

[0395] Conventional marketing analysis systems have faced challenges due to the heavy burden of data collection and analysis, making it difficult to rapidly optimize marketing strategies. Furthermore, they have been unable to fully grasp users' emotions and behavioral history in real time and optimize personalized advertising based on that information, making it difficult to maximize advertising effectiveness. There is a need for a system that can solve these problems and support the formulation of more efficient and effective marketing strategies.

[0396] 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.

[0397] In this invention, the server includes means for a user to input the purpose and goals of a marketing strategy via a terminal, means for the server to identify keywords and parameters for collecting related data from Internet resources, means for recognizing the emotional state of the user using an emotion engine and generating personalized proposals taking that into consideration, and means for optimizing advertisements in real time based on the collected emotion data and behavioral history. This streamlines the process from building to optimizing a marketing strategy, and enables real-time advertisement optimization based on the user's emotions and behavioral history.

[0398] "User" refers to a person who uses the system to develop and optimize a marketing strategy.

[0399] "Terminal" refers to an information processing device such as a computer, smartphone, or tablet that allows a user to access the system.

[0400] A "marketing strategy" refers to a series of measures or action plans designed to promote a product or service.

[0401] "Internet resources" refers to information and data publicly available on the Internet, such as websites, social media, news articles, and industry reports.

[0402] "Server" refers to the computer system that runs the entire system, including storing collected data, analyzing it, and generating personalized insights.

[0403] "Keywords or parameters" refers to a set of significant words or values ​​identified for data collection or analysis.

[0404] "Data preprocessing" refers to a series of processes that remove noise from collected data and convert it into a form suitable for analysis.

[0405] "Personalized insights" refers to personalized information and recommendations provided based on a user's specific circumstances and needs.

[0406] An "emotion engine" refers to algorithms or software that recognize emotions based on user input and behavioral history and generate personalized suggestions.

[0407] "Real-time ad optimization" refers to the process of analyzing user emotions and behavioral history data in real time, and selecting and displaying the most appropriate advertisements based on the results.

[0408] A "data dashboard" refers to an interface for visually displaying analytical results and insights.

[0409] The invention begins when a user inputs the objectives and goals of their marketing strategy via a device. Based on this input, a server collects relevant data from internet resources. The server identifies keywords and parameters and uses them to gather data from resources such as websites, social media, news articles, and industry reports.

[0410] The server preprocesses the collected data and converts it into a form suitable for analysis. Preprocessing includes removing noise data and tokenizing text data. The server then analyzes the preprocessed data and extracts indicators related to the user's strategy. This involves using natural language processing (NLP) techniques and machine learning models to analyze customer sentiment and evaluate engagement rates.

[0411] Based on the analysis results, the server generates personalized insights and suggestions, suggesting specific areas for improvement in marketing strategies and promotions. Using an emotion engine, the system can recognize the user's emotional state in real time, enabling highly personalized suggestions. For example, if the user is feeling anxious, the system will display advice to alleviate that anxiety.

[0412] Furthermore, based on the emotion engine and historical behavioral data, the server optimizes ads in real time, selecting and displaying the most effective ads for users.These insights and suggestions are displayed in real time on the data dashboard, which users can access at any time.

[0413] For example, if the user ID is "12345," the server retrieves emotion data from the Emotion API and reads behavioral history from the database. The most appropriate advertisement is then selected based on the collected text data. This entire process is carried out in real time, making it possible to build an efficient and effective marketing strategy.

[0414] Examples of prompts for a generative AI model might include:

[0415] Create a program that recommends optimal ads for user ID 12345 based on their current emotional state and behavioral history. Use the following script to retrieve emotional data from the Emotion API and implement a function that optimizes ads based on that data and behavioral history.

[0416] This invention frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize their marketing strategies. Furthermore, the emotion engine provides personalized insights and suggestions that incorporate user emotions, resulting in even greater accuracy and effectiveness.

[0417] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0418] Step 1:

[0419] The user inputs the objectives and goals of the marketing strategy via the terminal.

[0420] Input: Marketing strategy objectives and goals (e.g., "We want to strengthen online promotions for our new products")

[0421] Output: The entered marketing strategy objectives and goals are sent to the server as text data.

[0422] Operation: When a user enters a strategic goal into the input form on the terminal and presses the submit button, the data is sent to the server.

[0423] Step 2:

[0424] The server analyzes the input purpose or goal and identifies keywords and parameters.

[0425] Input: User-entered marketing strategy objectives and goals

[0426] Output: Identified keywords or parameters (e.g. "new product", "online promotion", "competitor")

[0427] How it works: The server uses natural language processing (NLP) techniques to extract important keywords and parameters from the input text.

[0428] Step 3:

[0429] The server collects relevant data from Internet resources.

[0430] Input: Identified keywords or parameters

[0431] Output: Collected internet resource data (e.g., social media posts, news articles, website information)

[0432] How it works: The server collects data based on the identified keywords using social media APIs and web scraping techniques.

[0433] Step 4:

[0434] The server preprocesses the collected data and converts it into a format suitable for analysis.

[0435] Input: Collected internet resource data

[0436] Output: Preprocessed data (denoised and tokenized text data)

[0437] Operation: The server performs preprocessing to remove noise data and tokenize text data.

[0438] Step 5:

[0439] The server analyzes the pre-processed data and extracts indicators relevant to the user's strategy.

[0440] Input: Preprocessed data

[0441] Output: Extracted metrics (e.g., engagement rates, trends, customer sentiment analysis results)

[0442] How it works: The server uses natural language processing (NLP) and machine learning models to analyze the data and extract the necessary metrics.

[0443] Step 6:

[0444] The server uses the analysis results to generate personalized insights and suggestions for users.

[0445] Input: extracted metrics, user input

[0446] Output: Personalized insights and recommendations (e.g., "New product promotions are most effective on weekday evenings")

[0447] How it works: The server applies algorithms based on extracted metrics and user input to generate insights and recommendations.

[0448] Step 7:

[0449] The server utilizes an emotion engine to recognize the user's emotional state and take it into account to generate personalized suggestions.

[0450] Input: User's emotional data, behavioral history

[0451] Output: Personalized suggestions based on the user's emotions (e.g., time management suggestions to reduce impatience and anxiety)

[0452] How it works: The server uses the Emotion API to obtain the user's emotional data, analyzes it, and reflects it in the suggestions.

[0453] Step 8:

[0454] Advertisements are optimized in real time based on the emotional data and behavioral history collected by the server.

[0455] Input: Emotion data, behavioral history

[0456] Output: Optimized ad (e.g. "Ad 1")

[0457] How it works: The server uses machine learning models to analyze emotional data and behavioral history to select the most appropriate advertisement.

[0458] Step 9:

[0459] Server-generated insights and recommendations are displayed in a real-time data dashboard.

[0460] Input: Personalized insights and suggestions

[0461] Output: Information displayed on a data dashboard (e.g., analysis results in the form of graphs and charts)

[0462] How it works: The server takes the generated data and puts it into a data dashboard for visual display.

[0463] Step 10:

[0464] Users access the dashboard via their devices to review and revise their strategies.

[0465] Input: Information displayed in the data dashboard

[0466] Output: Revised marketing strategy

[0467] How it works: Users consider and input new strategies based on the information displayed in the data dashboard.

[0468] Step 11:

[0469] The user re-enters the revised strategy.

[0470] Input: Revised marketing strategy

[0471] Output: The re-entered marketing strategy is sent to the server as text data.

[0472] Operation: When the user inputs the newly set strategic goal into the terminal and presses the send button, the data is sent to the server and analyzed again.

[0473] 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.

[0474] 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.

[0475] 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.

[0476] [Second embodiment]

[0477] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0478] 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.

[0479] 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).

[0480] 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.

[0481] 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.

[0482] 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).

[0483] 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. 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.

[0484] 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.

[0485] 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.

[0486] 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.

[0487] 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.

[0488] 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."

[0489] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is designed to help companies and marketers efficiently and quickly develop and optimize their marketing strategies. The program processing of this system is explained in natural language, with concrete examples.

[0490] User inputs marketing strategy

[0491] The user uses the terminal to input the purpose and goal of the marketing strategy. For example, the user might input, "We want to strengthen the online promotion of new product A."

[0492] The server prepares to collect data

[0493] The server analyzes the user's input and identifies keywords and parameters for collecting the necessary data. For example, it might list keywords such as "New Product A," "Online Promotion," and "Competitors."

[0494] The server collects the data

[0495] The server collects relevant data from internet resources (social media, websites, news articles, industry reports, etc.). For example, it uses the Twitter API to collect tweets about "New Product A." It then stores the tweet's posting time, number of likes and retweets, and post content in a database.

[0496] The server preprocesses the data

[0497] The server cleans the collected data and converts it into a format suitable for analysis, for example, filtering out noise data and tokenizing text data.

[0498] The server analyzes the data

[0499] The server analyzes the preprocessed data and extracts metrics relevant to the user's strategy (such as engagement rate, trends, and customer sentiment analysis). It uses natural language processing (NLP) and machine learning models to gain insights. For example, it analyzes collected tweet text data with an NLP model to classify customer sentiment (positive, negative, or neutral).

[0500] The server generates personalized insights

[0501] The server then uses the results of the data analysis to create personalized insights and suggestions for users, such as "Promotions for new product A are particularly effective on weekday evenings."

[0502] The server updates the data dashboard

[0503] The server then displays these insights and recommendations in a real-time data dashboard, which visually displays the latest indicators and trending information, making it easy for users to understand the information.

[0504] Users reassess their strategies

[0505] Users access the dashboard via their devices to view new data and insights, which can then be used to develop new marketing strategies and adjust them as needed, for example, by scheduling promotions on weekday evenings.

[0506] User re-enters strategy

[0507] The user then re-enters the revised strategy into the terminal, which starts the cycle again, continuously optimizing based on the latest data.

[0508] This concludes the natural language explanation of the AIEMI system's program processing. This system frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize marketing strategies. The inclusion of specific operational examples makes it easier for users to understand how to use the system and its effectiveness.

[0509] The processing flow will be explained below.

[0510] Step 1:

[0511] The user inputs the objectives and goals of the marketing strategy via the terminal. The user enters a specific marketing goal, for example, "I want to strengthen the online promotion of new product A," into the input form on the terminal.

[0512] Step 2:

[0513] The server receives user input and identifies keywords and parameters for collecting the required data. The server lists keywords such as "New Product A," "Online Promotion," and "Competitors."

[0514] Step 3:

[0515] The server collects relevant data from internet resources, such as tweets, blog posts, news articles, and industry reports, using social media APIs and web scraping techniques.

[0516] Step 4:

[0517] The server pre-processes the collected data, cleaning it, for example, by removing duplicates and removing emojis and special characters from social media posts.

[0518] Step 5:

[0519] The server analyzes the pre-processed data, uses natural language processing (NLP) to tokenize the text data and perform sentiment analysis, and uses machine learning models to calculate engagement rates and trend metrics.

[0520] Step 6:

[0521] The server generates personalized insights and suggestions based on the analysis results, for example, suggesting that "it would be effective to promote new product A in the evening on weekdays."

[0522] Step 7:

[0523] The server displays insights and recommendations in a real-time data dashboard, which displays the latest metrics and analytics in the form of graphs and charts.

[0524] Step 8:

[0525] Users access the dashboard via their devices to view new data and insights, and use the information in the dashboard to review and revise their marketing strategies.

[0526] Step 9:

[0527] The user inputs the revised strategy into the terminal again, and the revised strategy is sent to the server, where data is collected and analyzed again, providing a continuous optimization process.

[0528] Example 1

[0529] 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."

[0530] Traditionally, developing and optimizing marketing strategies has required a lot of time and effort, and collecting and analyzing relevant data has often been done manually, resulting in inefficiencies and limited insights, making it difficult for companies and marketers to make fast and effective decisions.

[0531] 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.

[0532] In this invention, the server includes: a means for a user to input the purpose and goals of a marketing strategy via a terminal; a means for the server to analyze the user's input data and identify necessary keywords and parameters; a means for the server to collect relevant data from Internet resources; a means for the server to preprocess the collected data and convert it into a format suitable for analysis; a means for the server to analyze the preprocessed data and extract indicators related to the user's strategy; a means for the server to generate personalized insights and suggestions for the user based on the analysis results; a means for the server to display the insights and suggestions on a real-time data dashboard; a means for a user to access the dashboard via a terminal to review and revise the strategy; and a means for the user to re-input the revised strategy. This frees companies and marketers from the burden of extensive data analysis, enabling them to quickly and efficiently formulate and optimize marketing strategies.

[0533] "User" refers to the end-user who inputs information and receives results to develop and optimize marketing strategies through this system.

[0534] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that a user uses to access the system and enter information.

[0535] "Server" refers to the central computer system that analyzes user input data and performs data collection, pre-processing, analysis, and display of results.

[0536] "Marketing strategy" refers to the plans and policies developed to optimize the promotion and sale of products and services.

[0537] "Objectives and goals" refer to the specific results and indicators you want to achieve through your marketing strategy.

[0538] "Analyzing input data" refers to the process of processing the text or information entered by the user and extracting the necessary keywords and parameters.

[0539] "Keywords and parameters" refer to key words and numbers used to indicate specific targets in data collection and analysis.

[0540] "Internet resources" refers to online sources of information such as social media, websites, news articles, and industry reports.

[0541] "Harvesting data" refers to the process of obtaining relevant information from Internet resources.

[0542] "Preprocessing" refers to the preparation of collected data to convert it into a format suitable for analysis.

[0543] "Analysis" refers to the process of using pre-processed data to extract specific metrics and trends and gain insights.

[0544] "Metrics" refers to specific numerical values ​​or indicators of analytical results obtained from data (e.g., engagement rate, trends, sentiment analysis).

[0545] "Insights" refers to knowledge and suggestions useful for marketing strategies obtained from data analysis.

[0546] A "data dashboard" refers to a user interface that visually displays real-time analysis results and indicators.

[0547] A "revised strategy" refers to a marketing strategy that has been reviewed and re-formulated based on analysis results and insights.

[0548] "NLP (Natural Language Processing)" refers to artificial intelligence technology for analyzing, understanding, and generating human language.

[0549] "Machine learning" refers to algorithms that use large amounts of data to train models to improve their accuracy at specific tasks.

[0550] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is a system that allows companies and marketers to efficiently and quickly build and optimize their marketing strategies. The system starts when the user inputs the purpose and goals of the marketing strategy via a terminal, and the server collects, preprocesses, analyzes, and displays the results of the data.

[0551] First, the user inputs the objectives and goals of the marketing strategy through the terminal. For example, they might input, "We want to strengthen the online promotion of new product A." This input can be done using a GUI (Graphical User Interface) such as a text input field.

[0552] The server then analyzes the user's input. It uses text analysis algorithms to identify the required keywords and parameters. Natural language processing libraries such as Python's NLTK or SpaCy can be used here. For example, keywords such as "New Product A," "Online Promotion," and "Competitor" can be extracted.

[0553] The server then scans Internet resources and collects relevant data. This process can be performed using the Twitter API or other web scraping tools (such as Beautiful Soup or Selenium). For example, the server uses the Twitter API to collect tweets about "New Product A." Data such as the posting time, number of likes and retweets, and post content are then stored in a database.

[0554] The collected data is preprocessed by the server. NLP techniques are used to remove noise and tokenize the text data. For example, spam and duplicate posts on social media are deleted, and the remaining text data is split into words. Preprocessing also includes format conversion, such as standardizing the encoding method.

[0555] The preprocessed data is then analyzed in detail by the server to extract important metrics. The server uses natural language processing (NLP) and machine learning (ML) models to obtain metrics relevant to marketing strategies (such as engagement rates, trends, and customer sentiment analysis). In a specific example, the collected tweet text data is analyzed using an NLP model (such as BERT or GPT) to classify customer sentiment (positive, negative, or neutral).

[0556] The server then generates personalized insights and suggestions for users based on the analysis results, such as "Promoting new product A is particularly effective on weekday evenings." At this stage, machine learning models can be used to analyze past data and trends to suggest optimal strategies.

[0557] Finally, the server displays these insights and recommendations in a real-time data dashboard, visually displaying the latest indicators and trend information, making it easy for users to understand the information.Specific technologies that can be used include data visualization libraries such as React and D3.js.

[0558] Users can access the dashboard through their device and view new data and insights. Using this information, they can develop new marketing strategies and modify them as needed, such as scheduling promotions for weekday evenings. The modified strategies are then entered back into the device, and the cycle begins again.

[0559] Example prompt sentence:

[0560] "We want to strengthen online promotion for new product A and increase engagement rates by 20% within one month."

[0561] This system will free companies and marketers from the burden of extensive data analysis, enabling them to quickly and efficiently formulate and optimize marketing strategies.

[0562] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0563] Step 1: User Marketing Strategy Input

[0564] The user uses the terminal to input the objectives and goals of the marketing strategy.

[0565] Input: The user types in the text field, "I want to strengthen the online promotion of new product A."

[0566] Operation: Information entered through the terminal's GUI (Graphical User Interface) is sent to the server.

[0567] Output: Marketing strategy objectives and goals text sent to the server.

[0568] Step 2: Parse the input data by the server

[0569] The server analyzes the user's input data and identifies any required keywords or parameters.

[0570] Input: Marketing strategy text ("We want to strengthen online promotion for new product A").

[0571] How it works: The server uses natural language processing (NLP) libraries such as Python's NLTK or SpaCy to extract important keywords and parameters from the input text.

[0572] Output: A list of keywords such as "New Product A", "Online Promotion", "Competitor", etc.

[0573] Step 3: Data collection by the server

[0574] The server collects relevant data from Internet resources.

[0575] Input: Keyword list ("New Product A", "Online Promotion", "Competitor").

[0576] How it works: The server uses web scraping tools such as Twitter API, Beautiful Soup, or Selenium to collect relevant data from internet resources (social media, websites, news articles, etc.). For example, the server uses Twitter API to collect tweets about "New Product A."

[0577] Output: Tweet data (posting time, number of likes and retweets, post content).

[0578] Step 4: Preprocessing the data on the server

[0579] The server cleans the collected data and converts it into a format suitable for analysis.

[0580] Input: Collected tweet data.

[0581] How it works: The server uses NLP techniques to remove noise data, eliminate duplicate data, tokenize text data, and unify encoding methods.

[0582] Output: Preprocessed and clean text data.

[0583] Step 5: Parse the data on the server

[0584] The server analyzes the pre-processed data and extracts metrics related to the user's strategy.

[0585] Input: Preprocessed clean text data.

[0586] How it works: The server uses NLP models (e.g., BERT or GPT) or machine learning models to extract metrics such as customer sentiment analysis (positive, negative, neutral), engagement rates, and trends from the text data.

[0587] Output: Sentiment analysis results, engagement rate, and trend information.

[0588] Step 6: Server generates personalized insights

[0589] The server generates personalized insights and suggestions for users based on the results of the data analysis.

[0590] Inputs: Sentiment analysis results, engagement rates, and trend information.

[0591] How it works: The server uses machine learning models to analyze historical data and trends to generate optimal marketing offers for users.

[0592] Output: Personalized marketing suggestions (e.g., "Promoting new product A is particularly effective on weekday evenings").

[0593] Step 7: Server Updates Data Dashboard

[0594] The server updates a real-time data dashboard, making it easy for users to understand the information.

[0595] Input: Personalized marketing suggestions, latest metrics and trend information.

[0596] How it works: The server uses data visualization libraries such as React and D3.js to display the latest metrics and trending information in graphs and charts.

[0597] Output: An updated data dashboard.

[0598] Step 8: User review of strategy

[0599] Users access the dashboard through their devices to see new data and insights.

[0600] Input: Updated data dashboard.

[0601] How it works: Users review dashboard metrics and recommendations to refine their marketing strategy.

[0602] Output: A revised marketing strategy.

[0603] Step 9: User re-enters strategy

[0604] The user inputs the revised strategy into the terminal again.

[0605] Enter: a revised marketing strategy.

[0606] Operation: A correction strategy entered through the terminal GUI is sent to the server.

[0607] Output: The modified marketing strategy sent to the server.

[0608] (Application example 1)

[0609] 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."

[0610] In modern advertising campaigns, advertisers and marketers need to develop effective strategies based on massive amounts of data. However, collecting, organizing, and analyzing data requires a significant amount of time and effort. Another challenge is the difficulty of optimizing advertising in real time based on customer sentiment and activity times. Furthermore, it is difficult to predict engagement rates and generate appropriate prompts using past data. Therefore, there is a strong demand for a system that can efficiently optimize advertising campaigns.

[0611] 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.

[0612] In this invention, the server includes means for sentiment analyzing collected data and notifying users of an average sentiment score and peak activity time, means for analyzing the effectiveness of advertising campaigns in real time and proposing optimal advertising strategies, means for collecting social media data and classifying customer sentiment using natural language processing and visualizing it in real time, means for building a predictive model of engagement rates based on past data and showing users the effectiveness of promotions on specific days and times, and means for generating prompt sentences for users using a generative AI model based on the collected data. This automates the process from data collection to analysis and strategy proposals, making it possible to optimize advertising campaigns in real time.

[0613] "Marketing strategy objectives and goals" refer to the specific results and targets that users want to achieve through their marketing activities.

[0614] "Internet resources" refers to information sources found on the internet, such as websites, social media, news articles, and industry reports.

[0615] "Relevant Data" means information or data that is relevant to the objectives and goals of the Marketing Strategy.

[0616] "Keywords and parameters" refer to important words and numerical settings identified for data collection and analysis.

[0617] "Data preprocessing" refers to the process of converting collected data into a format suitable for analysis, including removing noise data and tokenizing text data.

[0618] "Analysis" refers to the process of deriving marketing metrics and insights from collected and pre-processed data.

[0619] "Metrics" refer to quantitative data points used to measure the effectiveness and trends of marketing activities.

[0620] "Personalized insights and recommendations" means analysis results and action recommendations that are customized to fit a specific user's strategy and objectives.

[0621] A "real-time data dashboard" refers to an interface that visually displays the latest data and analysis results.

[0622] "Sentiment analysis" refers to the process of classifying and evaluating emotions (positive, negative, neutral) from the content of text data.

[0623] The "average emotion score" indicates the average value of the user's overall emotion calculated based on the collected data.

[0624] "Peak activity time" refers to the time period during which a particular subject is most active.

[0625] "Analysis of the effectiveness of advertising campaigns" means analysis to evaluate the efficiency and impact of ongoing advertising campaigns and to use the results to inform future measures.

[0626] "Engagement rate" means a rate that indicates the degree of response or involvement that a user shows with content.

[0627] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to automatically generate the data and information needed for a specific task.

[0628] A "prompt" refers to a sentence of instructions or suggestions that a generative AI model provides to a user.

[0629] The "AI-Enhanced Marketing Insights (AIEMI) System" of the present invention is a comprehensive system for analyzing the effectiveness of advertising campaigns in real time and proposing optimal advertising strategies. This system includes the following elements:

[0630] Hardware and Software Configuration

[0631] Hardware: smartphones, servers, databases

[0632] Software: Python, Twitter API, Pandas, Matplotlib, TextBlob, Natural Language Processing (NLP) techniques, generative AI models (e.g., OpenAI's GPT-3)

[0633] Specific operation of the system

[0634] 1. Marketing Strategy Input:

[0635] Users input the objectives and goals of their marketing strategy from their device (smartphone or PC). For example, they might input, "I want to strengthen the online promotion of new product A."

[0636] 2. Data Collection:

[0637] The server analyzes the user's input and identifies keywords and parameters for the required data collection. It then collects relevant data from internet resources (social media, websites, news articles, etc.). Specifically, it uses the Twitter API to retrieve tweets related to the specified keywords.

[0638] 3. Data Preprocessing:

[0639] The server cleans the collected data and converts it into a format suitable for analysis, removing noise data and tokenizing text data.

[0640] 4. Data Analysis:

[0641] The server analyzes the preprocessed data and extracts metrics related to the user's strategy. It uses NLP and machine learning models to classify customer sentiment (positive, negative, neutral) and calculate a sentiment score. At the same time, it analyzes tweet posting times to identify peak activity times.

[0642] 5. Generating insights and recommendations:

[0643] The server generates personalized insights and suggestions for the user based on the analysis results, such as informing them that online promotions for new product A are particularly effective on weekday evenings. Furthermore, it uses a generative AI model to generate appropriate prompts.

[0644] 6. Update the data dashboard:

[0645] The server then displays these insights and recommendations in a real-time data dashboard, which visually displays the latest metrics and trending information.

[0646] 7. User Strategy Review:

[0647] Users can access the dashboard via their devices, review new data and insights, and then review and adjust their strategies as needed.

[0648] 8. Re-enter strategy:

[0649] The user continues the optimization cycle by re-entering the revised strategy into the terminal.

[0650] Examples and prompts

[0651] For example, if a user inputs, "Collect tweets about the online promotion of new product A and suggest the optimal advertising strategy. Analyze the sentiment score and activity time period from the tweets and notify me of the most effective advertising times," the system will collect and analyze related tweets and then generate the following prompt:

[0652] Example prompt sentence:

[0653] Collect tweets related to the online promotion of new product A and propose the optimal advertising strategy. Analyze the sentiment score and activity time from the tweets and inform effective advertising times.

[0654] Keywords: New Product A, Online Promotion

[0655] Output: Mean emotion score, peak activity time, histogram

[0656] The above is a specific embodiment for carrying out the present invention. This system frees advertisers and marketers from the burden of complex data analysis, enabling them to quickly and efficiently optimize their advertising campaigns.

[0657] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0658] Step 1:

[0659] The user inputs the objectives and goals of the marketing strategy via a terminal. For example, the user may input a goal such as "I want to strengthen the online promotion of new product A." The input goal becomes the starting point of the system.

[0660] input:

[0661] Marketing strategy objectives and goals (e.g., "We want to strengthen online promotions for new product A")

[0662] output:

[0663] Data including strategic objectives and goals

[0664] Step 2:

[0665] The server analyzes the user's input and identifies keywords and parameters for data collection, for example, listing important keywords such as "New Product A," "Online Promotion," and "Competitors."

[0666] input:

[0667] Strategic Objectives and Targets Data

[0668] output:

[0669] Keywords and parameters for data collection (e.g., "New Product A," "Online Promotion")

[0670] Step 3:

[0671] The server collects relevant data from Internet resources, using Twitter APIs and other methods to retrieve tweets and other relevant information related to the identified keywords, and stores the tweet posting time, number of likes and retweets, and post content in a database.

[0672] input:

[0673] Keywords and parameters (e.g., "New Product A," "Online Promotion")

[0674] output:

[0675] Related data (e.g. tweet data)

[0676] Step 4:

[0677] The server preprocesses the collected data and converts it into a format suitable for analysis, specifically removing noise data and tokenizing text data, which makes the data clean and suitable for analysis.

[0678] input:

[0679] Related data (e.g. tweet data)

[0680] output:

[0681] Pre-processed, clean data

[0682] Step 5:

[0683] The server analyzes the pre-processed data and extracts metrics related to the user's strategy. It uses NLP and machine learning models to classify customer sentiment (positive, negative, neutral) and calculate a sentiment score. It also analyzes tweet posting times to identify peak activity times.

[0684] input:

[0685] Pre-processed, clean data

[0686] output:

[0687] Analysis results (e.g., emotion scores, peak activity times)

[0688] Step 6:

[0689] Based on the analysis results, the server generates personalized insights and suggestions for the user, such as "Online promotions for new product A are particularly effective on weekday evenings." It also uses a generative AI model to generate appropriate prompts.

[0690] input:

[0691] Analysis results (e.g., emotion scores, peak activity times)

[0692] output:

[0693] Personalized insights and recommendations (e.g., "Online promotions for new product A are particularly effective on weekday evenings")

[0694] Prompt statement (e.g., "We suggest setting promotion times for weekday evenings.")

[0695] Step 7:

[0696] The server displays these insights and recommendations in a real-time data dashboard, which visually displays the analysis results and makes them easy for users to understand.

[0697] input:

[0698] Personalized insights and recommendations (e.g., "Online promotions for new product A are particularly effective on weekday evenings")

[0699] output:

[0700] Real-time data dashboard

[0701] Step 8:

[0702] Users can access the dashboard through their devices to view new data and insights, and use this information to develop new marketing strategies and adjust them as needed.

[0703] input:

[0704] Real-time data dashboard

[0705] output:

[0706] User strategy adjustments

[0707] Step 9:

[0708] The user then re-enters the revised strategy into the terminal, and the system continues optimizing the strategy based on the latest data.

[0709] input:

[0710] Revised strategy (e.g., promotion time changed to weekday evenings)

[0711] output:

[0712] New Strategic Data

[0713] By following these steps, advertisers and marketers can effectively optimize their advertising campaigns and efficiently achieve their goals.

[0714] 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.

[0715] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is designed to help companies and marketers efficiently and quickly build and optimize their marketing strategies, and by combining it with an emotion engine, it achieves even greater personalization. The program processing of this system is explained in natural language, with concrete examples.

[0716] User inputs marketing strategy

[0717] The user uses a device to input the objectives and goals of the marketing strategy. For example, they might input, "We want to strengthen the online promotion of new product A." This input is then analyzed by the emotion engine.

[0718] The server prepares to collect data

[0719] The server analyzes the user's input and identifies keywords and parameters for collecting the necessary data. For example, it might list keywords such as "New Product A," "Online Promotion," and "Competitors."

[0720] The server collects the data

[0721] The server collects relevant data from internet resources (social media, websites, news articles, industry reports, etc.). For example, it uses the Twitter API to collect tweets about "New Product A." It then stores the tweet's posting time, number of likes and retweets, and post content in a database.

[0722] The server preprocesses the data

[0723] The server cleans the collected data and converts it into a format suitable for analysis, for example, filtering out noise data and tokenizing text data.

[0724] The server analyzes the data

[0725] The server analyzes the preprocessed data and extracts metrics relevant to the user's strategy (such as engagement rate, trends, and customer sentiment analysis). It uses natural language processing (NLP) and machine learning models to gain insights. For example, it analyzes collected tweet text data with an NLP model to classify customer sentiment (positive, negative, or neutral).

[0726] The server generates personalized insights

[0727] The server then uses the results of the data analysis to create personalized insights and suggestions for users, such as "Promotions for new product A are particularly effective on weekday evenings."

[0728] The server utilizes the emotion engine

[0729] The server's emotion engine recognizes the user's emotions in real time based on their input and browsing history. This generates personalized insights and suggestions that reflect the user's current emotional state. For example, if the user feels impatient or anxious, the system will suggest time management and resource optimization to alleviate that feeling.

[0730] The server updates the data dashboard

[0731] The server displays these insights and recommendations in a real-time data dashboard, which displays the latest metrics and analysis results in graphs and charts for easy user comprehension.

[0732] Users reassess their strategies

[0733] Users can access the dashboard via their devices to view new data and insights, and use the information in the dashboard to revise and adjust their marketing strategies, for example by scheduling promotions on weekday evenings.

[0734] User re-enters strategy

[0735] The user then re-enters the revised strategy into the terminal, which starts the cycle again, continuously optimizing based on the latest data.

[0736] The above is a natural language explanation of the program processing of the AIEMI system, which combines an emotion engine. This system frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize marketing strategies. The emotion engine provides personalized insights and suggestions that incorporate the user's emotions, resulting in greater accuracy and effectiveness.

[0737] The processing flow will be explained below.

[0738] Step 1:

[0739] The user inputs the objectives and goals of the marketing strategy via the terminal. The user enters a specific marketing goal, for example, "I want to strengthen the online promotion of new product A," into the input form on the terminal.

[0740] Step 2:

[0741] The server receives the user's input, analyzes it with an emotion engine, and recognizes the user's emotional state. For example, it classifies the user as feeling "impatient" based on the input.

[0742] Step 3:

[0743] Based on the user's input, the server identifies keywords and parameters (e.g., "New Product A," "Online Promotion," "Competitors") for collecting the required data.

[0744] Step 4:

[0745] The server collects relevant data from internet resources, such as tweets, blog posts, news articles, and industry reports, using social media APIs and web scraping techniques. For example, the server uses the Twitter API to collect tweets about "New Product A."

[0746] Step 5:

[0747] The server preprocesses the collected data, specifically removing noise data, tokenizing text data, and filtering out unnecessary information.

[0748] Step 6:

[0749] The server analyzes the preprocessed data. It uses natural language processing (NLP) to perform semantic analysis and sentiment analysis of the text. For example, it classifies the sentiment of collected tweets into "positive," "negative," and "neutral" sentiments.

[0750] Step 7:

[0751] The server generates personalized insights and suggestions for users based on the results of data analysis, such as "Promotions for new product A are particularly effective on weekday evenings."

[0752] Step 8:

[0753] The server generates insights and recommendations that are displayed in a real-time data dashboard that also displays the user's emotional state, for example, "The user is feeling anxious."

[0754] Step 9:

[0755] Users can access the dashboard via their devices to view the latest data and insights, and can use the information in the dashboard to revise their marketing strategies, for example by changing promotion times to weekday evenings.

[0756] Step 10:

[0757] The user inputs the revised strategy into the terminal again. The user's emotional state is analyzed again by the emotion engine, and the cycle begins again. The server repeats data collection and analysis based on this new strategy.

[0758] This allows the system to continually optimize personalized marketing strategies that reflect the user's emotional state.

[0759] Example 2

[0760] 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."

[0761] Traditional marketing strategy development and optimization involves time-consuming and labor-intensive large-scale data analysis, which takes a long time to produce results. Furthermore, personalized proposals are often lacking, making it difficult to develop marketing strategies that take into account the detailed emotions and circumstances of each customer. This makes it difficult for companies and marketers to quickly and efficiently develop optimal strategies.

[0762] 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.

[0763] In this invention, the server includes means for the user to input the objectives and goals of the marketing strategy via the terminal, means for identifying keywords and parameters for collecting relevant data from internet resources, and means for pre-processing and converting the collected data into a format suitable for analysis, thereby enabling the generation of personalized insights and recommendations for the user.

[0764] "User" refers to the individual or organization that operates the system and inputs or modifies marketing strategies.

[0765] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that a user uses to perform operations such as input and display.

[0766] "Server" refers to a central computer system that analyzes input data, performs related processing, and provides the results to users.

[0767] A "marketing strategy" refers to the strategic direction or plan of action that a company or organization plans to bring a product or service to market and increase sales and awareness.

[0768] "Keywords" refer to important words or phrases that represent a particular theme or topic used during data collection and analysis.

[0769] "Parameter" refers to a specific condition or setting used during data collection and analysis.

[0770] "Internet resources" refers to information sources found on the internet, such as social media, websites, news articles, and industry reports.

[0771] "Data preprocessing" refers to operations such as removing noise data and tokenizing data to prepare the data in a format suitable for analysis.

[0772] "Analysis" refers to the process of applying statistical methods and algorithms to collected data to derive useful metrics and insights.

[0773] "Personalized insights" refers to customized information and recommendations based on a user's specific needs and emotional state.

[0774] A "data dashboard" refers to an interface that visually displays analytical results and insights, allowing users to easily understand the information.

[0775] "Natural language processing (NLP)" refers to the technology that enables computers to understand and analyze human language.

[0776] "Customer sentiment" refers to the emotional state a customer has about a product or service, whether positive, negative, or neutral.

[0777] "Engagement rate" refers to an indicator that shows the degree of interest and involvement that customers show in a product or service.

[0778] The AI-Enhanced Marketing Insights (AIEMI) system of the present invention allows companies and marketers to efficiently and quickly build and optimize their marketing strategies. This system achieves further personalization by combining an emotion engine. The following describes an embodiment of the present invention.

[0779] 1. User Interface

[0780] The user uses the device to input the objectives and goals of the marketing strategy. This input is analyzed by the emotion engine and sent to the server. Specifically, this involves the user entering "I would like to strengthen the online promotion of new product A" into the input form and clicking the "Submit" button.

[0781] 2. Data collection from internet resources

[0782] The server receives user input and identifies keywords and parameters for collecting the required data. Based on these keywords, the server collects relevant data from Internet resources. For example, it uses the Twitter API to collect tweets about "New Product A."

[0783] As a concrete example, the following prompt sentence is input to the generative AI model:

[0784] "Collect the latest tweets about new product A and perform sentiment analysis to classify them as positive, negative, or neutral."

[0785] 3. Data Preprocessing

[0786] The server cleans the collected data and converts it into a format suitable for analysis. At this stage, noise data is removed, text data is tokenized, and missing values ​​are filled in. The collected tweets are analyzed using an NLP model to classify customer sentiment (positive, negative, neutral).

[0787] 4. Data Analysis

[0788] The server analyzes the preprocessed data. Using machine learning models and natural language processing (NLP) techniques, it calculates metrics such as engagement rates, trends, and customer sentiment analysis. For example, the analysis results can provide insights such as, "Promoting new product A is particularly effective in the evenings on weekdays."

[0789] 5. Generating personalized insights

[0790] The server uses the results of the data analysis to create personalized insights and suggestions for users. These insights and suggestions reflect the user's current emotional state. The emotion engine analyzes the user's input and browsing history in real time to provide personalized suggestions. For example, if the user feels impatient or anxious, it will suggest time management and resource optimization to alleviate that feeling.

[0791] 6. Update the data dashboard

[0792] The server displays these insights and recommendations in a real-time data dashboard, which displays the latest metrics and analysis results in graphs and charts for easy user comprehension.

[0793] 7. Review and re-enter your strategy

[0794] Users access the dashboard via their device to view new data and insights, allowing them to review and revise their marketing strategy, for example by scheduling a promotion for weekday evenings. They then re-enter the revised strategy into their device, and the cycle begins again, continually optimizing based on the latest data.

[0795] In this way, the present invention allows for the rapid and efficient development and optimization of marketing strategies, with even greater accuracy and effectiveness achieved through the use of an emotion engine.

[0796] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0797] Step 1:

[0798] The user inputs the objectives and goals of the marketing strategy via the terminal.

[0799] Specific operation: The user enters "I would like to strengthen the online promotion of new product A" into the input form on the device and clicks the "Submit" button.

[0800] Input: The purpose or goal of your marketing strategy (e.g., "We want to strengthen online promotion for new product A").

[0801] Output: The entered data is sent to the server.

[0802] Step 2:

[0803] The server parses the user's input and identifies keywords and parameters for collecting the required data.

[0804] Specific operation: The server analyzes the received data using a natural language processing (NLP) engine and extracts key keywords (e.g., "New Product A," "Online Promotion").

[0805] Input: The marketing strategy entered by the user.

[0806] Output: Identified keywords and parameters.

[0807] Step 3:

[0808] The server collects relevant data from Internet resources.

[0809] Specific operation: The server uses the Twitter API to collect tweets about "New Product A." The collected tweets are stored in a database.

[0810] Input: The keywords or parameters specified.

[0811] Output: Collected tweet data (posting time, number of likes and retweets, post content, etc.).

[0812] Step 4:

[0813] The server preprocesses the collected data and converts it into a format suitable for analysis.

[0814] What it does: The server runs data cleaning scripts to filter out noise data, tokenize text data, and also impute missing values.

[0815] Input: Collected tweet data.

[0816] Output: Cleaned and tokenized text data.

[0817] Step 5:

[0818] The server analyzes the pre-processed data and extracts metrics related to the user's strategy.

[0819] What it does: The server applies NLP models to classify the sentiment of tweets (positive, negative, neutral) and calculate engagement rates and trends.

[0820] Input: Preprocessed text data.

[0821] Output: Sentiment classification results and metrics such as engagement rate and trend.

[0822] Step 6:

[0823] The server generates personalized insights and suggestions for users based on the results of the data analysis.

[0824] Specific operation: The server generates insights using the user profile and analysis results, and compiles them in the form of a report. For example, it makes a suggestion such as, "Promoting new product A is particularly effective in the evenings on weekdays."

[0825] Inputs: Sentiment classification results, engagement rates, trend metrics, and user profiles.

[0826] Output: Personalized insights and recommendations.

[0827] Step 7:

[0828] The server uses an emotion engine to recognize the user's emotions in real time based on the user's input and browsing history.

[0829] What it does: The emotion engine assesses the user's current emotional state and generates personalized insights and suggestions based on that. For example, if the user feels anxious or impatient, it will suggest time management and resource optimization to alleviate that.

[0830] Input: User input, browsing history.

[0831] Output: Personalized insights based on emotional state.

[0832] Step 8:

[0833] The server displays these insights and recommendations in a real-time data dashboard.

[0834] What it does: Runs the data dashboard update script and displays the new data in graphs and charts.

[0835] Input: Insights and suggestions.

[0836] Output: An updated data dashboard.

[0837] Step 9:

[0838] Users access the dashboard via their devices to see new data and insights.

[0839] Specific actions: The user views the information on the dashboard and confirms and modifies the marketing strategy, for example, setting the promotion time to weekday evenings.

[0840] Input: Updated data dashboard.

[0841] Output: A revised marketing strategy.

[0842] Step 10:

[0843] The user inputs the revised strategy into the terminal again.

[0844] What happens: The user enters a new strategy and clicks the "Submit" button, which starts the cycle again.

[0845] Enter: a revised marketing strategy.

[0846] Output: The new marketing strategy sent to the server.

[0847] (Application example 2)

[0848] 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."

[0849] Conventional marketing analysis systems have faced challenges due to the heavy burden of data collection and analysis, making it difficult to rapidly optimize marketing strategies. Furthermore, they have been unable to fully grasp users' emotions and behavioral history in real time and optimize personalized advertising based on that information, making it difficult to maximize advertising effectiveness. There is a need for a system that can solve these problems and support the formulation of more efficient and effective marketing strategies.

[0850] 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.

[0851] In this invention, the server includes means for a user to input the purpose and goals of a marketing strategy via a terminal, means for the server to identify keywords and parameters for collecting related data from Internet resources, means for recognizing the emotional state of the user using an emotion engine and generating personalized proposals taking that into consideration, and means for optimizing advertisements in real time based on the collected emotion data and behavioral history. This streamlines the process from building to optimizing a marketing strategy, and enables real-time advertisement optimization based on the user's emotions and behavioral history.

[0852] "User" refers to a person who uses the system to develop and optimize a marketing strategy.

[0853] "Terminal" refers to an information processing device such as a computer, smartphone, or tablet that allows a user to access the system.

[0854] A "marketing strategy" refers to a series of measures or action plans designed to promote a product or service.

[0855] "Internet resources" refers to information and data publicly available on the Internet, such as websites, social media, news articles, and industry reports.

[0856] "Server" refers to the computer system that runs the entire system, including storing collected data, analyzing it, and generating personalized insights.

[0857] "Keywords or parameters" refers to a set of significant words or values ​​identified for data collection or analysis.

[0858] "Data preprocessing" refers to a series of processes that remove noise from collected data and convert it into a form suitable for analysis.

[0859] "Personalized insights" refers to personalized information and recommendations provided based on a user's specific circumstances and needs.

[0860] An "emotion engine" refers to algorithms or software that recognize emotions based on user input and behavioral history and generate personalized suggestions.

[0861] "Real-time ad optimization" refers to the process of analyzing user emotions and behavioral history data in real time, and selecting and displaying the most appropriate advertisements based on the results.

[0862] A "data dashboard" refers to an interface for visually displaying analytical results and insights.

[0863] The invention begins when a user inputs the objectives and goals of their marketing strategy via a device. Based on this input, a server collects relevant data from internet resources. The server identifies keywords and parameters and uses them to gather data from resources such as websites, social media, news articles, and industry reports.

[0864] The server preprocesses the collected data and converts it into a form suitable for analysis. Preprocessing includes removing noise data and tokenizing text data. The server then analyzes the preprocessed data and extracts indicators related to the user's strategy. This involves using natural language processing (NLP) techniques and machine learning models to analyze customer sentiment and evaluate engagement rates.

[0865] Based on the analysis results, the server generates personalized insights and suggestions, suggesting specific areas for improvement in marketing strategies and promotions. Using an emotion engine, the system can recognize the user's emotional state in real time, enabling highly personalized suggestions. For example, if the user is feeling anxious, the system will display advice to alleviate that anxiety.

[0866] Furthermore, based on the emotion engine and historical behavioral data, the server optimizes ads in real time, selecting and displaying the most effective ads for users.These insights and suggestions are displayed in real time on the data dashboard, which users can access at any time.

[0867] For example, if the user ID is "12345," the server retrieves emotion data from the Emotion API and reads behavioral history from the database. The most appropriate advertisement is then selected based on the collected text data. This entire process is carried out in real time, making it possible to build an efficient and effective marketing strategy.

[0868] Examples of prompts for a generative AI model might include:

[0869] Create a program that recommends optimal ads for user ID 12345 based on their current emotional state and behavioral history. Use the following script to retrieve emotional data from the Emotion API and implement a function that optimizes ads based on that data and behavioral history.

[0870] This invention frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize their marketing strategies. Furthermore, the emotion engine provides personalized insights and suggestions that incorporate user emotions, resulting in even greater accuracy and effectiveness.

[0871] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0872] Step 1:

[0873] The user inputs the objectives and goals of the marketing strategy via the terminal.

[0874] Input: Marketing strategy objectives and goals (e.g., "We want to strengthen online promotions for our new products")

[0875] Output: The entered marketing strategy objectives and goals are sent to the server as text data.

[0876] Operation: When a user enters a strategic goal into the input form on the terminal and presses the submit button, the data is sent to the server.

[0877] Step 2:

[0878] The server analyzes the input purpose or goal and identifies keywords and parameters.

[0879] Input: User-entered marketing strategy objectives and goals

[0880] Output: Identified keywords or parameters (e.g. "new product", "online promotion", "competitor")

[0881] How it works: The server uses natural language processing (NLP) techniques to extract important keywords and parameters from the input text.

[0882] Step 3:

[0883] The server collects relevant data from Internet resources.

[0884] Input: Identified keywords or parameters

[0885] Output: Collected internet resource data (e.g., social media posts, news articles, website information)

[0886] How it works: The server collects data based on the identified keywords using social media APIs and web scraping techniques.

[0887] Step 4:

[0888] The server preprocesses the collected data and converts it into a format suitable for analysis.

[0889] Input: Collected internet resource data

[0890] Output: Preprocessed data (denoised and tokenized text data)

[0891] Operation: The server performs preprocessing to remove noise data and tokenize text data.

[0892] Step 5:

[0893] The server analyzes the pre-processed data and extracts indicators relevant to the user's strategy.

[0894] Input: Preprocessed data

[0895] Output: Extracted metrics (e.g., engagement rates, trends, customer sentiment analysis results)

[0896] How it works: The server uses natural language processing (NLP) and machine learning models to analyze the data and extract the necessary metrics.

[0897] Step 6:

[0898] The server uses the analysis results to generate personalized insights and suggestions for users.

[0899] Input: extracted metrics, user input

[0900] Output: Personalized insights and recommendations (e.g., "New product promotions are most effective on weekday evenings")

[0901] How it works: The server applies algorithms based on extracted metrics and user input to generate insights and recommendations.

[0902] Step 7:

[0903] The server utilizes an emotion engine to recognize the user's emotional state and take it into account to generate personalized suggestions.

[0904] Input: User's emotional data, behavioral history

[0905] Output: Personalized suggestions based on the user's emotions (e.g., time management suggestions to reduce impatience and anxiety)

[0906] How it works: The server uses the Emotion API to obtain the user's emotional data, analyzes it, and reflects it in the suggestions.

[0907] Step 8:

[0908] Advertisements are optimized in real time based on the emotional data and behavioral history collected by the server.

[0909] Input: Emotion data, behavioral history

[0910] Output: Optimized ad (e.g. "Ad 1")

[0911] How it works: The server uses machine learning models to analyze emotional data and behavioral history to select the most appropriate advertisement.

[0912] Step 9:

[0913] Server-generated insights and recommendations are displayed in a real-time data dashboard.

[0914] Input: Personalized insights and suggestions

[0915] Output: Information displayed on a data dashboard (e.g., analysis results in the form of graphs and charts)

[0916] How it works: The server takes the generated data and puts it into a data dashboard for visual display.

[0917] Step 10:

[0918] Users access the dashboard via their devices to review and revise their strategies.

[0919] Input: Information displayed in the data dashboard

[0920] Output: Revised marketing strategy

[0921] How it works: Users consider and input new strategies based on the information displayed in the data dashboard.

[0922] Step 11:

[0923] The user re-enters the revised strategy.

[0924] Input: Revised marketing strategy

[0925] Output: The re-entered marketing strategy is sent to the server as text data.

[0926] Operation: When the user inputs the newly set strategic goal into the terminal and presses the send button, the data is sent to the server and analyzed again.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] [Third embodiment]

[0931] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0932] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0933] 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).

[0934] 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.

[0935] 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.

[0936] 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).

[0937] 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. 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.

[0938] 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.

[0939] 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.

[0940] 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.

[0941] 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.

[0942] 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."

[0943] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is designed to help companies and marketers efficiently and quickly develop and optimize their marketing strategies. This paper explains the program processing of this system in natural language and provides examples.

[0944] User inputs marketing strategy

[0945] The user uses the terminal to input the purpose and goal of the marketing strategy. For example, the user might input, "We want to strengthen the online promotion of new product A."

[0946] The server prepares to collect data

[0947] The server analyzes the user's input and identifies keywords and parameters for collecting the necessary data. For example, it might list keywords such as "New Product A," "Online Promotion," and "Competitors."

[0948] The server collects the data

[0949] The server collects relevant data from internet resources (social media, websites, news articles, industry reports, etc.). For example, it uses the Twitter API to collect tweets about "New Product A." It then stores the tweet's posting time, number of likes and retweets, and post content in a database.

[0950] The server preprocesses the data

[0951] The server cleans the collected data and converts it into a format suitable for analysis, for example, filtering out noise data and tokenizing text data.

[0952] The server analyzes the data

[0953] The server analyzes the preprocessed data and extracts metrics relevant to the user's strategy (such as engagement rate, trends, and customer sentiment analysis). It uses natural language processing (NLP) and machine learning models to gain insights. For example, it analyzes collected tweet text data with an NLP model to classify customer sentiment (positive, negative, or neutral).

[0954] The server generates personalized insights

[0955] The server then uses the results of the data analysis to create personalized insights and suggestions for users, such as "Promotions for new product A are particularly effective on weekday evenings."

[0956] The server updates the data dashboard

[0957] The server then displays these insights and recommendations in a real-time data dashboard, which visually displays the latest indicators and trending information, making it easy for users to understand the information.

[0958] Users reassess their strategies

[0959] Users access the dashboard via their devices to view new data and insights, which can then be used to develop new marketing strategies and adjust them as needed, for example, by scheduling promotions on weekday evenings.

[0960] User re-enters strategy

[0961] The user then re-enters the revised strategy into the terminal, which starts the cycle again, continuously optimizing based on the latest data.

[0962] This concludes the natural language explanation of the AIEMI system's program processing. This system frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize marketing strategies. The inclusion of specific operational examples makes it easier for users to understand how to use the system and its effectiveness.

[0963] The processing flow will be explained below.

[0964] Step 1:

[0965] The user inputs the objectives and goals of the marketing strategy via the terminal. The user enters a specific marketing goal, for example, "I want to strengthen the online promotion of new product A," into the input form on the terminal.

[0966] Step 2:

[0967] The server receives user input and identifies keywords and parameters for collecting the required data. The server lists keywords such as "New Product A," "Online Promotion," and "Competitors."

[0968] Step 3:

[0969] The server collects relevant data from internet resources, such as tweets, blog posts, news articles, and industry reports, using social media APIs and web scraping techniques.

[0970] Step 4:

[0971] The server pre-processes the collected data, cleaning it, for example, by removing duplicates and removing emojis and special characters from social media posts.

[0972] Step 5:

[0973] The server analyzes the pre-processed data, uses natural language processing (NLP) to tokenize the text data and perform sentiment analysis, and uses machine learning models to calculate engagement rates and trend metrics.

[0974] Step 6:

[0975] The server generates personalized insights and suggestions based on the analysis results, for example, suggesting that "it would be effective to promote new product A in the evening on weekdays."

[0976] Step 7:

[0977] The server displays insights and recommendations in a real-time data dashboard, which displays the latest metrics and analytics in the form of graphs and charts.

[0978] Step 8:

[0979] Users access the dashboard via their devices to view new data and insights, and use the information in the dashboard to review and revise their marketing strategies.

[0980] Step 9:

[0981] The user inputs the revised strategy into the terminal again, and the revised strategy is sent to the server, where data is collected and analyzed again, providing a continuous optimization process.

[0982] Example 1

[0983] 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."

[0984] Traditionally, developing and optimizing marketing strategies has required a lot of time and effort, and collecting and analyzing relevant data has often been done manually, resulting in inefficiencies and limited insights, making it difficult for companies and marketers to make fast and effective decisions.

[0985] 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.

[0986] In this invention, the server includes: a means for a user to input the purpose and goals of a marketing strategy via a terminal; a means for the server to analyze the user's input data and identify necessary keywords and parameters; a means for the server to collect relevant data from Internet resources; a means for the server to preprocess the collected data and convert it into a format suitable for analysis; a means for the server to analyze the preprocessed data and extract indicators related to the user's strategy; a means for the server to generate personalized insights and suggestions for the user based on the analysis results; a means for the server to display the insights and suggestions on a real-time data dashboard; a means for a user to access the dashboard via a terminal to review and revise the strategy; and a means for the user to re-input the revised strategy. This frees companies and marketers from the burden of extensive data analysis, enabling them to quickly and efficiently formulate and optimize marketing strategies.

[0987] "User" refers to the end-user who inputs information and receives results to develop and optimize marketing strategies through this system.

[0988] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that a user uses to access the system and enter information.

[0989] "Server" refers to the central computer system that analyzes user input data and performs data collection, pre-processing, analysis, and display of results.

[0990] "Marketing strategy" refers to the plans and policies developed to optimize the promotion and sale of products and services.

[0991] "Objectives and goals" refer to the specific results and indicators you want to achieve through your marketing strategy.

[0992] "Analyzing input data" refers to the process of processing the text or information entered by the user and extracting the necessary keywords and parameters.

[0993] "Keywords and parameters" refer to key words and numbers used to indicate specific targets in data collection and analysis.

[0994] "Internet resources" refers to online sources of information such as social media, websites, news articles, and industry reports.

[0995] "Harvesting data" refers to the process of obtaining relevant information from Internet resources.

[0996] "Preprocessing" refers to the preparation of collected data to convert it into a format suitable for analysis.

[0997] "Analysis" refers to the process of using pre-processed data to extract specific metrics and trends and gain insights.

[0998] "Metrics" refers to specific numerical values ​​or indicators of analytical results obtained from data (e.g., engagement rate, trends, sentiment analysis).

[0999] "Insights" refers to knowledge and suggestions useful for marketing strategies obtained from data analysis.

[1000] A "data dashboard" refers to a user interface that visually displays real-time analysis results and indicators.

[1001] A "revised strategy" refers to a marketing strategy that has been reviewed and re-formulated based on analysis results and insights.

[1002] "NLP (Natural Language Processing)" refers to artificial intelligence technology for analyzing, understanding, and generating human language.

[1003] "Machine learning" refers to algorithms that use large amounts of data to train models to improve their accuracy at specific tasks.

[1004] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is a system that allows companies and marketers to efficiently and quickly build and optimize their marketing strategies. The system starts when the user inputs the purpose and goals of the marketing strategy via a terminal, and the server collects, preprocesses, analyzes, and displays the results of the data.

[1005] First, the user inputs the objectives and goals of the marketing strategy through the terminal. For example, they might input, "We want to strengthen the online promotion of new product A." This input can be done using a GUI (Graphical User Interface) such as a text input field.

[1006] The server then analyzes the user's input. It uses text analysis algorithms to identify the required keywords and parameters. Natural language processing libraries such as Python's NLTK or SpaCy can be used here. For example, keywords such as "New Product A," "Online Promotion," and "Competitor" can be extracted.

[1007] The server then scans Internet resources and collects relevant data. This process can be performed using the Twitter API or other web scraping tools (such as Beautiful Soup or Selenium). For example, the server uses the Twitter API to collect tweets about "New Product A." Data such as the posting time, number of likes and retweets, and post content are then stored in a database.

[1008] The collected data is preprocessed by the server. NLP techniques are used to remove noise and tokenize the text data. For example, spam and duplicate posts on social media are deleted, and the remaining text data is split into words. Preprocessing also includes format conversion, such as standardizing the encoding method.

[1009] The preprocessed data is then analyzed in detail by the server to extract important metrics. The server uses natural language processing (NLP) and machine learning (ML) models to obtain metrics relevant to marketing strategies (such as engagement rates, trends, and customer sentiment analysis). In a specific example, the collected tweet text data is analyzed using an NLP model (such as BERT or GPT) to classify customer sentiment (positive, negative, or neutral).

[1010] The server then generates personalized insights and suggestions for users based on the analysis results, such as "Promoting new product A is particularly effective on weekday evenings." At this stage, machine learning models can be used to analyze past data and trends to suggest optimal strategies.

[1011] Finally, the server displays these insights and recommendations in a real-time data dashboard, visually displaying the latest indicators and trend information, making it easy for users to understand the information.Specific technologies that can be used include data visualization libraries such as React and D3.js.

[1012] Users can access the dashboard through their device and view new data and insights. Using this information, they can develop new marketing strategies and modify them as needed, such as scheduling promotions for weekday evenings. The modified strategies are then entered back into the device, and the cycle begins again.

[1013] Example prompt sentence:

[1014] "We want to strengthen online promotion for new product A and increase engagement rates by 20% within one month."

[1015] This system will free companies and marketers from the burden of extensive data analysis, enabling them to quickly and efficiently formulate and optimize marketing strategies.

[1016] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1017] Step 1: User Marketing Strategy Input

[1018] The user uses the terminal to input the objectives and goals of the marketing strategy.

[1019] Input: The user types in the text field, "I want to strengthen the online promotion of new product A."

[1020] Operation: Information entered through the terminal's GUI (Graphical User Interface) is sent to the server.

[1021] Output: Marketing strategy objectives and goals text sent to the server.

[1022] Step 2: Parse the input data by the server

[1023] The server analyzes the user's input data and identifies any required keywords or parameters.

[1024] Input: Marketing strategy text ("We want to strengthen online promotion for new product A").

[1025] How it works: The server uses natural language processing (NLP) libraries such as Python's NLTK or SpaCy to extract important keywords and parameters from the input text.

[1026] Output: A list of keywords such as "New Product A", "Online Promotion", "Competitor", etc.

[1027] Step 3: Data collection by the server

[1028] The server collects relevant data from Internet resources.

[1029] Input: Keyword list ("New Product A", "Online Promotion", "Competitor").

[1030] How it works: The server uses web scraping tools such as Twitter API, Beautiful Soup, or Selenium to collect relevant data from internet resources (social media, websites, news articles, etc.). For example, the server uses Twitter API to collect tweets about "New Product A."

[1031] Output: Tweet data (posting time, number of likes and retweets, post content).

[1032] Step 4: Preprocessing the data on the server

[1033] The server cleans the collected data and converts it into a format suitable for analysis.

[1034] Input: Collected tweet data.

[1035] How it works: The server uses NLP techniques to remove noise data, eliminate duplicate data, tokenize text data, and unify encoding methods.

[1036] Output: Preprocessed and clean text data.

[1037] Step 5: Parse the data on the server

[1038] The server analyzes the pre-processed data and extracts metrics related to the user's strategy.

[1039] Input: Preprocessed clean text data.

[1040] How it works: The server uses NLP models (e.g., BERT or GPT) or machine learning models to extract metrics such as customer sentiment analysis (positive, negative, neutral), engagement rates, and trends from the text data.

[1041] Output: Sentiment analysis results, engagement rate, and trend information.

[1042] Step 6: Server generates personalized insights

[1043] The server generates personalized insights and suggestions for users based on the results of the data analysis.

[1044] Inputs: Sentiment analysis results, engagement rates, and trend information.

[1045] How it works: The server uses machine learning models to analyze historical data and trends to generate optimal marketing offers for users.

[1046] Output: Personalized marketing suggestions (e.g., "Promoting new product A is particularly effective on weekday evenings").

[1047] Step 7: Server Updates Data Dashboard

[1048] The server updates a real-time data dashboard, making it easy for users to understand the information.

[1049] Input: Personalized marketing suggestions, latest metrics and trend information.

[1050] How it works: The server uses data visualization libraries such as React and D3.js to display the latest metrics and trending information in graphs and charts.

[1051] Output: An updated data dashboard.

[1052] Step 8: User review of strategy

[1053] Users access the dashboard through their devices to see new data and insights.

[1054] Input: Updated data dashboard.

[1055] How it works: Users review dashboard metrics and recommendations to refine their marketing strategy.

[1056] Output: A revised marketing strategy.

[1057] Step 9: User re-enters strategy

[1058] The user inputs the revised strategy into the terminal again.

[1059] Enter: a revised marketing strategy.

[1060] Operation: A correction strategy entered through the terminal GUI is sent to the server.

[1061] Output: The modified marketing strategy sent to the server.

[1062] (Application example 1)

[1063] 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."

[1064] In modern advertising campaigns, advertisers and marketers need to develop effective strategies based on massive amounts of data. However, collecting, organizing, and analyzing data requires a significant amount of time and effort. Another challenge is the difficulty of optimizing advertising in real time based on customer sentiment and activity times. Furthermore, it is difficult to predict engagement rates and generate appropriate prompts using past data. Therefore, there is a strong demand for a system that can efficiently optimize advertising campaigns.

[1065] 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.

[1066] In this invention, the server includes means for sentiment analyzing collected data and notifying users of an average sentiment score and peak activity time, means for analyzing the effectiveness of advertising campaigns in real time and proposing optimal advertising strategies, means for collecting social media data and classifying customer sentiment using natural language processing and visualizing it in real time, means for building a predictive model of engagement rates based on past data and showing users the effectiveness of promotions on specific days and times, and means for generating prompt sentences for users using a generative AI model based on the collected data. This automates the process from data collection to analysis and strategy proposals, making it possible to optimize advertising campaigns in real time.

[1067] "Marketing strategy objectives and goals" refer to the specific results and targets that users want to achieve through their marketing activities.

[1068] "Internet resources" refers to information sources found on the internet, such as websites, social media, news articles, and industry reports.

[1069] "Relevant Data" means information or data that is relevant to the objectives and goals of the Marketing Strategy.

[1070] "Keywords and parameters" refer to important words and numerical settings identified for data collection and analysis.

[1071] "Data preprocessing" refers to the process of converting collected data into a format suitable for analysis, including removing noise data and tokenizing text data.

[1072] "Analysis" refers to the process of deriving marketing metrics and insights from collected and pre-processed data.

[1073] "Metrics" refer to quantitative data points used to measure the effectiveness and trends of marketing activities.

[1074] "Personalized insights and recommendations" means analysis results and action recommendations that are customized to fit a specific user's strategy and objectives.

[1075] A "real-time data dashboard" refers to an interface that visually displays the latest data and analysis results.

[1076] "Sentiment analysis" refers to the process of classifying and evaluating emotions (positive, negative, neutral) from the content of text data.

[1077] The "average emotion score" indicates the average value of the user's overall emotion calculated based on the collected data.

[1078] "Peak activity time" refers to the time period during which a particular subject is most active.

[1079] "Analysis of the effectiveness of advertising campaigns" means analysis to evaluate the efficiency and impact of ongoing advertising campaigns and to use the results to inform future measures.

[1080] "Engagement rate" means a rate that indicates the degree of response or involvement that a user shows with content.

[1081] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to automatically generate the data and information needed for a specific task.

[1082] A "prompt" refers to a sentence of instructions or suggestions that a generative AI model provides to a user.

[1083] The "AI-Enhanced Marketing Insights (AIEMI) System" of the present invention is a comprehensive system for analyzing the effectiveness of advertising campaigns in real time and proposing optimal advertising strategies. This system includes the following elements:

[1084] Hardware and Software Configuration

[1085] Hardware: smartphones, servers, databases

[1086] Software: Python, Twitter API, Pandas, Matplotlib, TextBlob, Natural Language Processing (NLP) techniques, generative AI models (e.g., OpenAI's GPT-3)

[1087] Specific operation of the system

[1088] 1. Marketing Strategy Input:

[1089] Users input the objectives and goals of their marketing strategy from their device (smartphone or PC). For example, they might input, "I want to strengthen the online promotion of new product A."

[1090] 2. Data Collection:

[1091] The server analyzes the user's input and identifies keywords and parameters for the required data collection. It then collects relevant data from internet resources (social media, websites, news articles, etc.). Specifically, it uses the Twitter API to retrieve tweets related to the specified keywords.

[1092] 3. Data Preprocessing:

[1093] The server cleans the collected data and converts it into a format suitable for analysis, removing noise data and tokenizing text data.

[1094] 4. Data Analysis:

[1095] The server analyzes the preprocessed data and extracts metrics related to the user's strategy. It uses NLP and machine learning models to classify customer sentiment (positive, negative, neutral) and calculate a sentiment score. At the same time, it analyzes tweet posting times to identify peak activity times.

[1096] 5. Generating insights and recommendations:

[1097] The server generates personalized insights and suggestions for the user based on the analysis results, such as informing them that online promotions for new product A are particularly effective on weekday evenings. Furthermore, it uses a generative AI model to generate appropriate prompts.

[1098] 6. Update the data dashboard:

[1099] The server then displays these insights and recommendations in a real-time data dashboard, which visually displays the latest metrics and trending information.

[1100] 7. User Strategy Review:

[1101] Users can access the dashboard via their devices, review new data and insights, and then review and adjust their strategies as needed.

[1102] 8. Re-enter strategy:

[1103] The user continues the optimization cycle by re-entering the revised strategy into the terminal.

[1104] Examples and prompts

[1105] For example, if a user inputs, "Collect tweets about the online promotion of new product A and suggest the optimal advertising strategy. Analyze the sentiment score and activity time period from the tweets and notify me of the most effective advertising times," the system will collect and analyze related tweets and then generate the following prompt:

[1106] Example prompt sentence:

[1107] Collect tweets related to the online promotion of new product A and propose the optimal advertising strategy. Analyze the sentiment score and activity time from the tweets and inform effective advertising times.

[1108] Keywords: New Product A, Online Promotion

[1109] Output: Mean emotion score, peak activity time, histogram

[1110] The above is a specific embodiment for carrying out the present invention. This system frees advertisers and marketers from the burden of complex data analysis, enabling them to quickly and efficiently optimize their advertising campaigns.

[1111] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1112] Step 1:

[1113] The user inputs the objectives and goals of the marketing strategy via a terminal. For example, the user may input a goal such as "I want to strengthen the online promotion of new product A." The input goal becomes the starting point of the system.

[1114] input:

[1115] Marketing strategy objectives and goals (e.g., "We want to strengthen online promotions for new product A")

[1116] output:

[1117] Data including strategic objectives and goals

[1118] Step 2:

[1119] The server analyzes the user's input and identifies keywords and parameters for data collection, for example, listing important keywords such as "New Product A," "Online Promotion," and "Competitors."

[1120] input:

[1121] Strategic Objectives and Targets Data

[1122] output:

[1123] Keywords and parameters for data collection (e.g., "New Product A," "Online Promotion")

[1124] Step 3:

[1125] The server collects relevant data from Internet resources, using Twitter APIs and other methods to retrieve tweets and other relevant information related to the identified keywords, and stores the tweet posting time, number of likes and retweets, and post content in a database.

[1126] input:

[1127] Keywords and parameters (e.g., "New Product A," "Online Promotion")

[1128] output:

[1129] Related data (e.g. tweet data)

[1130] Step 4:

[1131] The server preprocesses the collected data and converts it into a format suitable for analysis, specifically removing noise data and tokenizing text data, which makes the data clean and suitable for analysis.

[1132] input:

[1133] Related data (e.g. tweet data)

[1134] output:

[1135] Pre-processed, clean data

[1136] Step 5:

[1137] The server analyzes the pre-processed data and extracts metrics related to the user's strategy. It uses NLP and machine learning models to classify customer sentiment (positive, negative, neutral) and calculate a sentiment score. It also analyzes tweet posting times to identify peak activity times.

[1138] input:

[1139] Pre-processed, clean data

[1140] output:

[1141] Analysis results (e.g., emotion scores, peak activity times)

[1142] Step 6:

[1143] Based on the analysis results, the server generates personalized insights and suggestions for the user, such as "Online promotions for new product A are particularly effective on weekday evenings." It also uses a generative AI model to generate appropriate prompts.

[1144] input:

[1145] Analysis results (e.g., emotion scores, peak activity times)

[1146] output:

[1147] Personalized insights and recommendations (e.g., "Online promotions for new product A are particularly effective on weekday evenings")

[1148] Prompt statement (e.g., "We suggest setting promotion times for weekday evenings.")

[1149] Step 7:

[1150] The server displays these insights and recommendations in a real-time data dashboard, which visually displays the analysis results and makes them easy for users to understand.

[1151] input:

[1152] Personalized insights and recommendations (e.g., "Online promotions for new product A are particularly effective on weekday evenings")

[1153] output:

[1154] Real-time data dashboard

[1155] Step 8:

[1156] Users can access the dashboard through their devices to view new data and insights, and use this information to develop new marketing strategies and adjust them as needed.

[1157] input:

[1158] Real-time data dashboard

[1159] output:

[1160] User strategy adjustments

[1161] Step 9:

[1162] The user then re-enters the revised strategy into the terminal, and the system continues optimizing the strategy based on the latest data.

[1163] input:

[1164] Revised strategy (e.g., promotion time changed to weekday evenings)

[1165] output:

[1166] New Strategic Data

[1167] By following these steps, advertisers and marketers can effectively optimize their advertising campaigns and efficiently achieve their goals.

[1168] 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.

[1169] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is designed to help companies and marketers efficiently and quickly build and optimize their marketing strategies, and by combining it with an emotion engine, it achieves even greater personalization. The program processing of this system is explained in natural language, with concrete examples.

[1170] User inputs marketing strategy

[1171] The user uses a device to input the objectives and goals of the marketing strategy. For example, they might input, "We want to strengthen the online promotion of new product A." This input is then analyzed by the emotion engine.

[1172] The server prepares to collect data

[1173] The server analyzes the user's input and identifies keywords and parameters for collecting the necessary data. For example, it might list keywords such as "New Product A," "Online Promotion," and "Competitors."

[1174] The server collects the data

[1175] The server collects relevant data from internet resources (social media, websites, news articles, industry reports, etc.). For example, it uses the Twitter API to collect tweets about "New Product A." It then stores the tweet's posting time, number of likes and retweets, and post content in a database.

[1176] The server preprocesses the data

[1177] The server cleans the collected data and converts it into a format suitable for analysis, for example, filtering out noise data and tokenizing text data.

[1178] The server analyzes the data

[1179] The server analyzes the preprocessed data and extracts metrics relevant to the user's strategy (such as engagement rate, trends, and customer sentiment analysis). It uses natural language processing (NLP) and machine learning models to gain insights. For example, it analyzes collected tweet text data with an NLP model to classify customer sentiment (positive, negative, or neutral).

[1180] The server generates personalized insights

[1181] The server then uses the results of the data analysis to create personalized insights and suggestions for users, such as "Promotions for new product A are particularly effective on weekday evenings."

[1182] The server utilizes the emotion engine

[1183] The server's emotion engine recognizes the user's emotions in real time based on their input and browsing history. This generates personalized insights and suggestions that reflect the user's current emotional state. For example, if the user feels impatient or anxious, the system will suggest time management and resource optimization to alleviate that feeling.

[1184] The server updates the data dashboard

[1185] The server displays these insights and recommendations in a real-time data dashboard, which displays the latest metrics and analysis results in graphs and charts for easy user comprehension.

[1186] Users reassess their strategies

[1187] Users can access the dashboard via their devices to view new data and insights, and use the information in the dashboard to revise and adjust their marketing strategies, for example by scheduling promotions on weekday evenings.

[1188] User re-enters strategy

[1189] The user then re-enters the revised strategy into the terminal, which starts the cycle again, continuously optimizing based on the latest data.

[1190] The above is a natural language explanation of the program processing of the AIEMI system, which combines an emotion engine. This system frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize marketing strategies. The emotion engine provides personalized insights and suggestions that incorporate the user's emotions, resulting in greater accuracy and effectiveness.

[1191] The processing flow will be explained below.

[1192] Step 1:

[1193] The user inputs the objectives and goals of the marketing strategy via the terminal. The user enters a specific marketing goal, for example, "I want to strengthen the online promotion of new product A," into the input form on the terminal.

[1194] Step 2:

[1195] The server receives the user's input, analyzes it with an emotion engine, and recognizes the user's emotional state. For example, it classifies the user as feeling "impatient" based on the input.

[1196] Step 3:

[1197] Based on the user's input, the server identifies keywords and parameters (e.g., "New Product A," "Online Promotion," "Competitors") for collecting the required data.

[1198] Step 4:

[1199] The server collects relevant data from internet resources, such as tweets, blog posts, news articles, and industry reports, using social media APIs and web scraping techniques. For example, the server uses the Twitter API to collect tweets about "New Product A."

[1200] Step 5:

[1201] The server preprocesses the collected data, specifically removing noise data, tokenizing text data, and filtering out unnecessary information.

[1202] Step 6:

[1203] The server analyzes the preprocessed data. It uses natural language processing (NLP) to perform semantic analysis and sentiment analysis of the text. For example, it classifies the sentiment of collected tweets into "positive," "negative," and "neutral" sentiments.

[1204] Step 7:

[1205] The server generates personalized insights and suggestions for users based on the results of data analysis, such as "Promotions for new product A are particularly effective on weekday evenings."

[1206] Step 8:

[1207] The server generates insights and recommendations that are displayed in a real-time data dashboard that also displays the user's emotional state, for example, "The user is feeling anxious."

[1208] Step 9:

[1209] Users can access the dashboard via their devices to view the latest data and insights, and can use the information in the dashboard to revise their marketing strategies, for example by changing promotion times to weekday evenings.

[1210] Step 10:

[1211] The user inputs the revised strategy into the terminal again. The user's emotional state is analyzed again by the emotion engine, and the cycle begins again. The server repeats data collection and analysis based on this new strategy.

[1212] This allows the system to continually optimize personalized marketing strategies that reflect the user's emotional state.

[1213] Example 2

[1214] 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."

[1215] Traditional marketing strategy development and optimization involves time-consuming and labor-intensive large-scale data analysis, which takes a long time to produce results. Furthermore, personalized proposals are often lacking, making it difficult to develop marketing strategies that take into account the detailed emotions and circumstances of each customer. This makes it difficult for companies and marketers to quickly and efficiently develop optimal strategies.

[1216] 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.

[1217] In this invention, the server includes means for the user to input the objectives and goals of the marketing strategy via the terminal, means for identifying keywords and parameters for collecting relevant data from internet resources, and means for pre-processing and converting the collected data into a format suitable for analysis, thereby enabling the generation of personalized insights and recommendations for the user.

[1218] "User" refers to the individual or organization that operates the system and inputs or modifies marketing strategies.

[1219] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that a user uses to perform operations such as input and display.

[1220] "Server" refers to a central computer system that analyzes input data, performs related processing, and provides the results to users.

[1221] A "marketing strategy" refers to the strategic direction or plan of action that a company or organization plans to bring a product or service to market and increase sales and awareness.

[1222] "Keywords" refer to important words or phrases that represent a particular theme or topic used during data collection and analysis.

[1223] "Parameter" refers to a specific condition or setting used during data collection and analysis.

[1224] "Internet resources" refers to information sources found on the internet, such as social media, websites, news articles, and industry reports.

[1225] "Data preprocessing" refers to operations such as removing noise data and tokenizing data to prepare the data in a format suitable for analysis.

[1226] "Analysis" refers to the process of applying statistical methods and algorithms to collected data to derive useful metrics and insights.

[1227] "Personalized insights" refers to customized information and recommendations based on a user's specific needs and emotional state.

[1228] A "data dashboard" refers to an interface that visually displays analytical results and insights, allowing users to easily understand the information.

[1229] "Natural language processing (NLP)" refers to the technology that enables computers to understand and analyze human language.

[1230] "Customer sentiment" refers to the emotional state a customer has about a product or service, whether positive, negative, or neutral.

[1231] "Engagement rate" refers to an indicator that shows the degree of interest and involvement that customers show in a product or service.

[1232] The AI-Enhanced Marketing Insights (AIEMI) system of the present invention allows companies and marketers to efficiently and quickly build and optimize their marketing strategies. This system achieves further personalization by combining an emotion engine. The following describes an embodiment of the present invention.

[1233] 1. User Interface

[1234] The user uses the device to input the objectives and goals of the marketing strategy. This input is analyzed by the emotion engine and sent to the server. Specifically, this involves the user entering "I would like to strengthen the online promotion of new product A" into the input form and clicking the "Submit" button.

[1235] 2. Data collection from internet resources

[1236] The server receives user input and identifies keywords and parameters for collecting the required data. Based on these keywords, the server collects relevant data from Internet resources. For example, it uses the Twitter API to collect tweets about "New Product A."

[1237] As a concrete example, the following prompt sentence is input to the generative AI model:

[1238] "Collect the latest tweets about new product A and perform sentiment analysis to classify them as positive, negative, or neutral."

[1239] 3. Data Preprocessing

[1240] The server cleans the collected data and converts it into a format suitable for analysis. At this stage, noise data is removed, text data is tokenized, and missing values ​​are filled in. The collected tweets are analyzed using an NLP model to classify customer sentiment (positive, negative, neutral).

[1241] 4. Data Analysis

[1242] The server analyzes the preprocessed data. Using machine learning models and natural language processing (NLP) techniques, it calculates metrics such as engagement rates, trends, and customer sentiment analysis. For example, the analysis results can provide insights such as, "Promoting new product A is particularly effective in the evenings on weekdays."

[1243] 5. Generating personalized insights

[1244] The server uses the results of the data analysis to create personalized insights and suggestions for users. These insights and suggestions reflect the user's current emotional state. The emotion engine analyzes the user's input and browsing history in real time to provide personalized suggestions. For example, if the user feels impatient or anxious, it will suggest time management and resource optimization to alleviate that feeling.

[1245] 6. Update the data dashboard

[1246] The server displays these insights and recommendations in a real-time data dashboard, which displays the latest metrics and analysis results in graphs and charts for easy user comprehension.

[1247] 7. Review and re-enter your strategy

[1248] Users access the dashboard via their device to view new data and insights, allowing them to review and revise their marketing strategy, for example by scheduling a promotion for weekday evenings. They then re-enter the revised strategy into their device, and the cycle begins again, continually optimizing based on the latest data.

[1249] In this way, the present invention allows for the rapid and efficient development and optimization of marketing strategies, with even greater accuracy and effectiveness achieved through the use of an emotion engine.

[1250] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1251] Step 1:

[1252] The user inputs the objectives and goals of the marketing strategy via the terminal.

[1253] Specific operation: The user enters "I would like to strengthen the online promotion of new product A" into the input form on the device and clicks the "Submit" button.

[1254] Input: The purpose or goal of your marketing strategy (e.g., "We want to strengthen online promotion for new product A").

[1255] Output: The entered data is sent to the server.

[1256] Step 2:

[1257] The server parses the user's input and identifies keywords and parameters for collecting the required data.

[1258] Specific operation: The server analyzes the received data using a natural language processing (NLP) engine and extracts key keywords (e.g., "New Product A," "Online Promotion").

[1259] Input: The marketing strategy entered by the user.

[1260] Output: Identified keywords and parameters.

[1261] Step 3:

[1262] The server collects relevant data from Internet resources.

[1263] Specific operation: The server uses the Twitter API to collect tweets about "New Product A." The collected tweets are stored in a database.

[1264] Input: The keywords or parameters specified.

[1265] Output: Collected tweet data (posting time, number of likes and retweets, post content, etc.).

[1266] Step 4:

[1267] The server preprocesses the collected data and converts it into a format suitable for analysis.

[1268] What it does: The server runs data cleaning scripts to filter out noise data, tokenize text data, and also impute missing values.

[1269] Input: Collected tweet data.

[1270] Output: Cleaned and tokenized text data.

[1271] Step 5:

[1272] The server analyzes the pre-processed data and extracts metrics related to the user's strategy.

[1273] What it does: The server applies NLP models to classify the sentiment of tweets (positive, negative, neutral) and calculate engagement rates and trends.

[1274] Input: Preprocessed text data.

[1275] Output: Sentiment classification results and metrics such as engagement rate and trend.

[1276] Step 6:

[1277] The server generates personalized insights and suggestions for users based on the results of the data analysis.

[1278] Specific operation: The server generates insights using the user profile and analysis results, and compiles them in the form of a report. For example, it makes a suggestion such as, "Promoting new product A is particularly effective in the evenings on weekdays."

[1279] Inputs: Sentiment classification results, engagement rates, trend metrics, and user profiles.

[1280] Output: Personalized insights and recommendations.

[1281] Step 7:

[1282] The server uses an emotion engine to recognize the user's emotions in real time based on the user's input and browsing history.

[1283] What it does: The emotion engine assesses the user's current emotional state and generates personalized insights and suggestions based on that. For example, if the user feels anxious or impatient, it will suggest time management and resource optimization to alleviate that.

[1284] Input: User input, browsing history.

[1285] Output: Personalized insights based on emotional state.

[1286] Step 8:

[1287] The server displays these insights and recommendations in a real-time data dashboard.

[1288] What it does: Runs the data dashboard update script and displays the new data in graphs and charts.

[1289] Input: Insights and suggestions.

[1290] Output: An updated data dashboard.

[1291] Step 9:

[1292] Users access the dashboard via their devices to see new data and insights.

[1293] Specific actions: The user views the information on the dashboard and confirms and modifies the marketing strategy, for example, setting the promotion time to weekday evenings.

[1294] Input: Updated data dashboard.

[1295] Output: A revised marketing strategy.

[1296] Step 10:

[1297] The user inputs the revised strategy into the terminal again.

[1298] What happens: The user enters a new strategy and clicks the "Submit" button, which starts the cycle again.

[1299] Enter: a revised marketing strategy.

[1300] Output: The new marketing strategy sent to the server.

[1301] (Application example 2)

[1302] 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."

[1303] Conventional marketing analysis systems have faced challenges due to the heavy burden of data collection and analysis, making it difficult to rapidly optimize marketing strategies. Furthermore, they have been unable to fully grasp users' emotions and behavioral history in real time and optimize personalized advertising based on that information, making it difficult to maximize advertising effectiveness. There is a need for a system that can solve these problems and support the formulation of more efficient and effective marketing strategies.

[1304] 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.

[1305] In this invention, the server includes means for a user to input the purpose and goals of a marketing strategy via a terminal, means for the server to identify keywords and parameters for collecting related data from Internet resources, means for recognizing the emotional state of the user using an emotion engine and generating personalized proposals taking that into consideration, and means for optimizing advertisements in real time based on the collected emotion data and behavioral history. This streamlines the process from building to optimizing a marketing strategy, and enables real-time advertisement optimization based on the user's emotions and behavioral history.

[1306] "User" refers to a person who uses the system to develop and optimize a marketing strategy.

[1307] "Terminal" refers to an information processing device such as a computer, smartphone, or tablet that allows a user to access the system.

[1308] A "marketing strategy" refers to a series of measures or action plans designed to promote a product or service.

[1309] "Internet resources" refers to information and data publicly available on the Internet, such as websites, social media, news articles, and industry reports.

[1310] "Server" refers to the computer system that runs the entire system, including storing collected data, analyzing it, and generating personalized insights.

[1311] "Keywords or parameters" refers to a set of significant words or values ​​identified for data collection or analysis.

[1312] "Data preprocessing" refers to a series of processes that remove noise from collected data and convert it into a form suitable for analysis.

[1313] "Personalized insights" refers to personalized information and recommendations provided based on a user's specific circumstances and needs.

[1314] An "emotion engine" refers to algorithms or software that recognize emotions based on user input and behavioral history and generate personalized suggestions.

[1315] "Real-time ad optimization" refers to the process of analyzing user emotions and behavioral history data in real time, and selecting and displaying the most appropriate advertisements based on the results.

[1316] A "data dashboard" refers to an interface for visually displaying analytical results and insights.

[1317] The invention begins when a user inputs the objectives and goals of their marketing strategy via a device. Based on this input, a server collects relevant data from internet resources. The server identifies keywords and parameters and uses them to gather data from resources such as websites, social media, news articles, and industry reports.

[1318] The server preprocesses the collected data and converts it into a form suitable for analysis. Preprocessing includes removing noise data and tokenizing text data. The server then analyzes the preprocessed data and extracts indicators related to the user's strategy. This involves using natural language processing (NLP) techniques and machine learning models to analyze customer sentiment and evaluate engagement rates.

[1319] Based on the analysis results, the server generates personalized insights and suggestions, suggesting specific areas for improvement in marketing strategies and promotions. Using an emotion engine, the system can recognize the user's emotional state in real time, enabling highly personalized suggestions. For example, if the user is feeling anxious, the system will display advice to alleviate that anxiety.

[1320] Furthermore, based on the emotion engine and historical behavioral data, the server optimizes ads in real time, selecting and displaying the most effective ads for users.These insights and suggestions are displayed in real time on the data dashboard, which users can access at any time.

[1321] For example, if the user ID is "12345," the server retrieves emotion data from the Emotion API and reads behavioral history from the database. The most appropriate advertisement is then selected based on the collected text data. This entire process is carried out in real time, making it possible to build an efficient and effective marketing strategy.

[1322] Examples of prompts for a generative AI model might include:

[1323] Create a program that recommends optimal ads for user ID 12345 based on their current emotional state and behavioral history. Use the following script to retrieve emotional data from the Emotion API and implement a function that optimizes ads based on that data and behavioral history.

[1324] This invention frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize their marketing strategies. Furthermore, the emotion engine provides personalized insights and suggestions that incorporate user emotions, resulting in even greater accuracy and effectiveness.

[1325] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1326] Step 1:

[1327] The user inputs the objectives and goals of the marketing strategy via the terminal.

[1328] Input: Marketing strategy objectives and goals (e.g., "We want to strengthen online promotions for our new products")

[1329] Output: The entered marketing strategy objectives and goals are sent to the server as text data.

[1330] Operation: When a user enters a strategic goal into the input form on the terminal and presses the submit button, the data is sent to the server.

[1331] Step 2:

[1332] The server analyzes the input purpose or goal and identifies keywords and parameters.

[1333] Input: User-entered marketing strategy objectives and goals

[1334] Output: Identified keywords or parameters (e.g. "new product", "online promotion", "competitor")

[1335] How it works: The server uses natural language processing (NLP) techniques to extract important keywords and parameters from the input text.

[1336] Step 3:

[1337] The server collects relevant data from Internet resources.

[1338] Input: Identified keywords or parameters

[1339] Output: Collected internet resource data (e.g., social media posts, news articles, website information)

[1340] How it works: The server collects data based on the identified keywords using social media APIs and web scraping techniques.

[1341] Step 4:

[1342] The server preprocesses the collected data and converts it into a format suitable for analysis.

[1343] Input: Collected internet resource data

[1344] Output: Preprocessed data (denoised and tokenized text data)

[1345] Operation: The server performs preprocessing to remove noise data and tokenize text data.

[1346] Step 5:

[1347] The server analyzes the pre-processed data and extracts indicators relevant to the user's strategy.

[1348] Input: Preprocessed data

[1349] Output: Extracted metrics (e.g., engagement rates, trends, customer sentiment analysis results)

[1350] How it works: The server uses natural language processing (NLP) and machine learning models to analyze the data and extract the necessary metrics.

[1351] Step 6:

[1352] The server uses the analysis results to generate personalized insights and suggestions for users.

[1353] Input: extracted metrics, user input

[1354] Output: Personalized insights and recommendations (e.g., "New product promotions are most effective on weekday evenings")

[1355] How it works: The server applies algorithms based on extracted metrics and user input to generate insights and recommendations.

[1356] Step 7:

[1357] The server utilizes an emotion engine to recognize the user's emotional state and take it into account to generate personalized suggestions.

[1358] Input: User's emotional data, behavioral history

[1359] Output: Personalized suggestions based on the user's emotions (e.g., time management suggestions to reduce impatience and anxiety)

[1360] How it works: The server uses the Emotion API to obtain the user's emotional data, analyzes it, and reflects it in the suggestions.

[1361] Step 8:

[1362] Advertisements are optimized in real time based on the emotional data and behavioral history collected by the server.

[1363] Input: Emotion data, behavioral history

[1364] Output: Optimized ad (e.g. "Ad 1")

[1365] How it works: The server uses machine learning models to analyze emotional data and behavioral history to select the most appropriate advertisement.

[1366] Step 9:

[1367] Server-generated insights and recommendations are displayed in a real-time data dashboard.

[1368] Input: Personalized insights and suggestions

[1369] Output: Information displayed on a data dashboard (e.g., analysis results in the form of graphs and charts)

[1370] How it works: The server takes the generated data and puts it into a data dashboard for visual display.

[1371] Step 10:

[1372] Users access the dashboard via their devices to review and revise their strategies.

[1373] Input: Information displayed in the data dashboard

[1374] Output: Revised marketing strategy

[1375] How it works: Users consider and input new strategies based on the information displayed in the data dashboard.

[1376] Step 11:

[1377] The user re-enters the revised strategy.

[1378] Input: Revised marketing strategy

[1379] Output: The re-entered marketing strategy is sent to the server as text data.

[1380] Operation: When the user inputs the newly set strategic goal into the terminal and presses the send button, the data is sent to the server and analyzed again.

[1381] 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.

[1382] 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.

[1383] 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.

[1384] [Fourth embodiment]

[1385] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1386] 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.

[1387] 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).

[1388] 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.

[1389] 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.

[1390] 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).

[1391] 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. 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.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] 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."

[1398] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is designed to help companies and marketers efficiently and quickly develop and optimize their marketing strategies. This paper explains the program processing of this system in natural language and provides examples.

[1399] User inputs marketing strategy

[1400] The user uses the terminal to input the purpose and goal of the marketing strategy. For example, the user might input, "We want to strengthen the online promotion of new product A."

[1401] The server prepares to collect data

[1402] The server analyzes the user's input and identifies keywords and parameters for collecting the necessary data. For example, it might list keywords such as "New Product A," "Online Promotion," and "Competitors."

[1403] The server collects the data

[1404] The server collects relevant data from internet resources (social media, websites, news articles, industry reports, etc.). For example, it uses the Twitter API to collect tweets about "New Product A." It then stores the tweet's posting time, number of likes and retweets, and post content in a database.

[1405] The server preprocesses the data

[1406] The server cleans the collected data and converts it into a format suitable for analysis, for example, filtering out noise data and tokenizing text data.

[1407] The server analyzes the data

[1408] The server analyzes the preprocessed data and extracts metrics relevant to the user's strategy (such as engagement rate, trends, and customer sentiment analysis). It uses natural language processing (NLP) and machine learning models to gain insights. For example, it analyzes collected tweet text data with an NLP model to classify customer sentiment (positive, negative, or neutral).

[1409] The server generates personalized insights

[1410] The server then uses the results of the data analysis to create personalized insights and suggestions for users, such as "Promotions for new product A are particularly effective on weekday evenings."

[1411] The server updates the data dashboard

[1412] The server then displays these insights and recommendations in a real-time data dashboard, which visually displays the latest indicators and trending information, making it easy for users to understand the information.

[1413] Users reassess their strategies

[1414] Users access the dashboard via their devices to view new data and insights, which can then be used to develop new marketing strategies and adjust them as needed, for example, by scheduling promotions on weekday evenings.

[1415] User re-enters strategy

[1416] The user then re-enters the revised strategy into the terminal, which starts the cycle again, continuously optimizing based on the latest data.

[1417] This concludes the natural language explanation of the AIEMI system's program processing. This system frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize marketing strategies. The inclusion of specific operational examples makes it easier for users to understand how to use the system and its effectiveness.

[1418] The processing flow will be explained below.

[1419] Step 1:

[1420] The user inputs the objectives and goals of the marketing strategy via the terminal. The user enters a specific marketing goal, for example, "I want to strengthen the online promotion of new product A," into the input form on the terminal.

[1421] Step 2:

[1422] The server receives user input and identifies keywords and parameters for collecting the required data. The server lists keywords such as "New Product A," "Online Promotion," and "Competitors."

[1423] Step 3:

[1424] The server collects relevant data from internet resources, such as tweets, blog posts, news articles, and industry reports, using social media APIs and web scraping techniques.

[1425] Step 4:

[1426] The server pre-processes the collected data, cleaning it, for example, by removing duplicates and removing emojis and special characters from social media posts.

[1427] Step 5:

[1428] The server analyzes the pre-processed data, uses natural language processing (NLP) to tokenize the text data and perform sentiment analysis, and uses machine learning models to calculate engagement rates and trend metrics.

[1429] Step 6:

[1430] The server generates personalized insights and suggestions based on the analysis results, for example, suggesting that "it would be effective to promote new product A in the evening on weekdays."

[1431] Step 7:

[1432] The server displays insights and recommendations in a real-time data dashboard, which displays the latest metrics and analytics in the form of graphs and charts.

[1433] Step 8:

[1434] Users access the dashboard via their devices to view new data and insights, and use the information in the dashboard to review and revise their marketing strategies.

[1435] Step 9:

[1436] The user inputs the revised strategy into the terminal again, and the revised strategy is sent to the server, where data is collected and analyzed again, providing a continuous optimization process.

[1437] Example 1

[1438] 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."

[1439] Traditionally, developing and optimizing marketing strategies has required a lot of time and effort, and collecting and analyzing relevant data has often been done manually, resulting in inefficiencies and limited insights, making it difficult for companies and marketers to make fast and effective decisions.

[1440] 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.

[1441] In this invention, the server includes: a means for a user to input the purpose and goals of a marketing strategy via a terminal; a means for the server to analyze the user's input data and identify necessary keywords and parameters; a means for the server to collect relevant data from Internet resources; a means for the server to preprocess the collected data and convert it into a format suitable for analysis; a means for the server to analyze the preprocessed data and extract indicators related to the user's strategy; a means for the server to generate personalized insights and suggestions for the user based on the analysis results; a means for the server to display the insights and suggestions on a real-time data dashboard; a means for a user to access the dashboard via a terminal to review and revise the strategy; and a means for the user to re-input the revised strategy. This frees companies and marketers from the burden of extensive data analysis, enabling them to quickly and efficiently formulate and optimize marketing strategies.

[1442] "User" refers to the end-user who inputs information and receives results to develop and optimize marketing strategies through this system.

[1443] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that a user uses to access the system and enter information.

[1444] "Server" refers to the central computer system that analyzes user input data and performs data collection, pre-processing, analysis, and display of results.

[1445] "Marketing strategy" refers to the plans and policies developed to optimize the promotion and sale of products and services.

[1446] "Objectives and goals" refer to the specific results and indicators you want to achieve through your marketing strategy.

[1447] "Analyzing input data" refers to the process of processing the text or information entered by the user and extracting the necessary keywords and parameters.

[1448] "Keywords and parameters" refer to key words and numbers used to indicate specific targets in data collection and analysis.

[1449] "Internet resources" refers to online sources of information such as social media, websites, news articles, and industry reports.

[1450] "Harvesting data" refers to the process of obtaining relevant information from Internet resources.

[1451] "Preprocessing" refers to the preparation of collected data to convert it into a format suitable for analysis.

[1452] "Analysis" refers to the process of using pre-processed data to extract specific metrics and trends and gain insights.

[1453] "Metrics" refers to specific numerical values ​​or indicators of analytical results obtained from data (e.g., engagement rate, trends, sentiment analysis).

[1454] "Insights" refers to knowledge and suggestions useful for marketing strategies obtained from data analysis.

[1455] A "data dashboard" refers to a user interface that visually displays real-time analysis results and indicators.

[1456] A "revised strategy" refers to a marketing strategy that has been reviewed and re-formulated based on analysis results and insights.

[1457] "NLP (Natural Language Processing)" refers to artificial intelligence technology for analyzing, understanding, and generating human language.

[1458] "Machine learning" refers to algorithms that use large amounts of data to train models to improve their accuracy at specific tasks.

[1459] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is a system that allows companies and marketers to efficiently and quickly build and optimize their marketing strategies. The system starts when the user inputs the purpose and goals of the marketing strategy via a terminal, and the server collects, preprocesses, analyzes, and displays the results of the data.

[1460] First, the user inputs the objectives and goals of the marketing strategy through the terminal. For example, they might input, "We want to strengthen the online promotion of new product A." This input can be done using a GUI (Graphical User Interface) such as a text input field.

[1461] The server then analyzes the user's input. It uses text analysis algorithms to identify the required keywords and parameters. Natural language processing libraries such as Python's NLTK or SpaCy can be used here. For example, keywords such as "New Product A," "Online Promotion," and "Competitor" can be extracted.

[1462] The server then scans Internet resources and collects relevant data. This process can be performed using the Twitter API or other web scraping tools (such as Beautiful Soup or Selenium). For example, the server uses the Twitter API to collect tweets about "New Product A." Data such as the posting time, number of likes and retweets, and post content are then stored in a database.

[1463] The collected data is preprocessed by the server. NLP techniques are used to remove noise and tokenize the text data. For example, spam and duplicate posts on social media are deleted, and the remaining text data is split into words. Preprocessing also includes format conversion, such as standardizing the encoding method.

[1464] The preprocessed data is then analyzed in detail by the server to extract important metrics. The server uses natural language processing (NLP) and machine learning (ML) models to obtain metrics relevant to marketing strategies (such as engagement rates, trends, and customer sentiment analysis). In a specific example, the collected tweet text data is analyzed using an NLP model (such as BERT or GPT) to classify customer sentiment (positive, negative, or neutral).

[1465] The server then generates personalized insights and suggestions for users based on the analysis results, such as "Promoting new product A is particularly effective on weekday evenings." At this stage, machine learning models can be used to analyze past data and trends to suggest optimal strategies.

[1466] Finally, the server displays these insights and recommendations in a real-time data dashboard, visually displaying the latest indicators and trend information, making it easy for users to understand the information.Specific technologies that can be used include data visualization libraries such as React and D3.js.

[1467] Users can access the dashboard through their device and view new data and insights. Using this information, they can develop new marketing strategies and modify them as needed, such as scheduling promotions for weekday evenings. The modified strategies are then entered back into the device, and the cycle begins again.

[1468] Example prompt sentence:

[1469] "We want to strengthen online promotion for new product A and increase engagement rates by 20% within one month."

[1470] This system will free companies and marketers from the burden of extensive data analysis, enabling them to quickly and efficiently formulate and optimize marketing strategies.

[1471] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1472] Step 1: User Marketing Strategy Input

[1473] The user uses the terminal to input the objectives and goals of the marketing strategy.

[1474] Input: The user types in the text field, "I want to strengthen the online promotion of new product A."

[1475] Operation: Information entered through the terminal's GUI (Graphical User Interface) is sent to the server.

[1476] Output: Marketing strategy objectives and goals text sent to the server.

[1477] Step 2: Parse the input data by the server

[1478] The server analyzes the user's input data and identifies any required keywords or parameters.

[1479] Input: Marketing strategy text ("We want to strengthen online promotion for new product A").

[1480] How it works: The server uses natural language processing (NLP) libraries such as Python's NLTK or SpaCy to extract important keywords and parameters from the input text.

[1481] Output: A list of keywords such as "New Product A", "Online Promotion", "Competitor", etc.

[1482] Step 3: Data collection by the server

[1483] The server collects relevant data from Internet resources.

[1484] Input: Keyword list ("New Product A", "Online Promotion", "Competitor").

[1485] How it works: The server uses web scraping tools such as Twitter API, Beautiful Soup, or Selenium to collect relevant data from internet resources (social media, websites, news articles, etc.). For example, the server uses Twitter API to collect tweets about "New Product A."

[1486] Output: Tweet data (posting time, number of likes and retweets, post content).

[1487] Step 4: Preprocessing the data on the server

[1488] The server cleans the collected data and converts it into a format suitable for analysis.

[1489] Input: Collected tweet data.

[1490] How it works: The server uses NLP techniques to remove noise data, eliminate duplicate data, tokenize text data, and unify encoding methods.

[1491] Output: Preprocessed and clean text data.

[1492] Step 5: Parse the data on the server

[1493] The server analyzes the pre-processed data and extracts metrics related to the user's strategy.

[1494] Input: Preprocessed clean text data.

[1495] How it works: The server uses NLP models (e.g., BERT or GPT) or machine learning models to extract metrics such as customer sentiment analysis (positive, negative, neutral), engagement rates, and trends from the text data.

[1496] Output: Sentiment analysis results, engagement rate, and trend information.

[1497] Step 6: Server generates personalized insights

[1498] The server generates personalized insights and suggestions for users based on the results of the data analysis.

[1499] Inputs: Sentiment analysis results, engagement rates, and trend information.

[1500] How it works: The server uses machine learning models to analyze historical data and trends to generate optimal marketing offers for users.

[1501] Output: Personalized marketing suggestions (e.g., "Promoting new product A is particularly effective on weekday evenings").

[1502] Step 7: Server Updates Data Dashboard

[1503] The server updates a real-time data dashboard, making it easy for users to understand the information.

[1504] Input: Personalized marketing suggestions, latest metrics and trend information.

[1505] How it works: The server uses data visualization libraries such as React and D3.js to display the latest metrics and trending information in graphs and charts.

[1506] Output: An updated data dashboard.

[1507] Step 8: User review of strategy

[1508] Users access the dashboard through their devices to see new data and insights.

[1509] Input: Updated data dashboard.

[1510] How it works: Users review dashboard metrics and recommendations to refine their marketing strategy.

[1511] Output: A revised marketing strategy.

[1512] Step 9: User re-enters strategy

[1513] The user inputs the revised strategy into the terminal again.

[1514] Enter: a revised marketing strategy.

[1515] Operation: A correction strategy entered through the terminal GUI is sent to the server.

[1516] Output: The modified marketing strategy sent to the server.

[1517] (Application example 1)

[1518] 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."

[1519] In modern advertising campaigns, advertisers and marketers need to develop effective strategies based on massive amounts of data. However, collecting, organizing, and analyzing data requires a significant amount of time and effort. Another challenge is the difficulty of optimizing advertising in real time based on customer sentiment and activity times. Furthermore, it is difficult to predict engagement rates and generate appropriate prompts using past data. Therefore, there is a strong demand for a system that can efficiently optimize advertising campaigns.

[1520] 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.

[1521] In this invention, the server includes means for sentiment analyzing collected data and notifying users of an average sentiment score and peak activity time, means for analyzing the effectiveness of advertising campaigns in real time and proposing optimal advertising strategies, means for collecting social media data and classifying customer sentiment using natural language processing and visualizing it in real time, means for building a predictive model of engagement rates based on past data and showing users the effectiveness of promotions on specific days and times, and means for generating prompt sentences for users using a generative AI model based on the collected data. This automates the process from data collection to analysis and strategy proposals, making it possible to optimize advertising campaigns in real time.

[1522] "Marketing strategy objectives and goals" refer to the specific results and targets that users want to achieve through their marketing activities.

[1523] "Internet resources" refers to information sources found on the internet, such as websites, social media, news articles, and industry reports.

[1524] "Relevant Data" means information or data that is relevant to the objectives and goals of the Marketing Strategy.

[1525] "Keywords and parameters" refer to important words and numerical settings identified for data collection and analysis.

[1526] "Data preprocessing" refers to the process of converting collected data into a format suitable for analysis, including removing noise data and tokenizing text data.

[1527] "Analysis" refers to the process of deriving marketing metrics and insights from collected and pre-processed data.

[1528] "Metrics" refer to quantitative data points used to measure the effectiveness and trends of marketing activities.

[1529] "Personalized insights and recommendations" means analysis results and action recommendations that are customized to fit a specific user's strategy and objectives.

[1530] A "real-time data dashboard" refers to an interface that visually displays the latest data and analysis results.

[1531] "Sentiment analysis" refers to the process of classifying and evaluating emotions (positive, negative, neutral) from the content of text data.

[1532] The "average emotion score" indicates the average value of the user's overall emotion calculated based on the collected data.

[1533] "Peak activity time" refers to the time period during which a particular subject is most active.

[1534] "Analysis of the effectiveness of advertising campaigns" means analysis to evaluate the efficiency and impact of ongoing advertising campaigns and to use the results to inform future measures.

[1535] "Engagement rate" means a rate that indicates the degree of response or involvement that a user shows with content.

[1536] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to automatically generate the data and information needed for a specific task.

[1537] A "prompt" refers to a sentence of instructions or suggestions that a generative AI model provides to a user.

[1538] The "AI-Enhanced Marketing Insights (AIEMI) System" of the present invention is a comprehensive system for analyzing the effectiveness of advertising campaigns in real time and proposing optimal advertising strategies. This system includes the following elements:

[1539] Hardware and Software Configuration

[1540] Hardware: smartphones, servers, databases

[1541] Software: Python, Twitter API, Pandas, Matplotlib, TextBlob, Natural Language Processing (NLP) techniques, generative AI models (e.g., OpenAI's GPT-3)

[1542] Specific operation of the system

[1543] 1. Marketing Strategy Input:

[1544] Users input the objectives and goals of their marketing strategy from their device (smartphone or PC). For example, they might input, "I want to strengthen the online promotion of new product A."

[1545] 2. Data Collection:

[1546] The server analyzes the user's input and identifies keywords and parameters for the required data collection. It then collects relevant data from internet resources (social media, websites, news articles, etc.). Specifically, it uses the Twitter API to retrieve tweets related to the specified keywords.

[1547] 3. Data Preprocessing:

[1548] The server cleans the collected data and converts it into a format suitable for analysis, removing noise data and tokenizing text data.

[1549] 4. Data Analysis:

[1550] The server analyzes the preprocessed data and extracts metrics related to the user's strategy. It uses NLP and machine learning models to classify customer sentiment (positive, negative, neutral) and calculate a sentiment score. At the same time, it analyzes tweet posting times to identify peak activity times.

[1551] 5. Generating insights and recommendations:

[1552] The server generates personalized insights and suggestions for the user based on the analysis results, such as informing them that online promotions for new product A are particularly effective on weekday evenings. Furthermore, it uses a generative AI model to generate appropriate prompts.

[1553] 6. Update the data dashboard:

[1554] The server then displays these insights and recommendations in a real-time data dashboard, which visually displays the latest metrics and trending information.

[1555] 7. User Strategy Review:

[1556] Users can access the dashboard via their devices, review new data and insights, and then review and adjust their strategies as needed.

[1557] 8. Re-enter strategy:

[1558] The user continues the optimization cycle by re-entering the revised strategy into the terminal.

[1559] Examples and prompts

[1560] For example, if a user inputs, "Collect tweets about the online promotion of new product A and suggest the optimal advertising strategy. Analyze the sentiment score and activity time period from the tweets and notify me of the most effective advertising times," the system will collect and analyze related tweets and then generate the following prompt:

[1561] Example prompt sentence:

[1562] Collect tweets related to the online promotion of new product A and propose the optimal advertising strategy. Analyze the sentiment score and activity time from the tweets and inform effective advertising times.

[1563] Keywords: New Product A, Online Promotion

[1564] Output: Mean emotion score, peak activity time, histogram

[1565] The above is a specific embodiment for carrying out the present invention. This system frees advertisers and marketers from the burden of complex data analysis, enabling them to quickly and efficiently optimize their advertising campaigns.

[1566] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1567] Step 1:

[1568] The user inputs the objectives and goals of the marketing strategy via a terminal. For example, the user may input a goal such as "I want to strengthen the online promotion of new product A." The input goal becomes the starting point of the system.

[1569] input:

[1570] Marketing strategy objectives and goals (e.g., "We want to strengthen online promotions for new product A")

[1571] output:

[1572] Data including strategic objectives and goals

[1573] Step 2:

[1574] The server analyzes the user's input and identifies keywords and parameters for data collection, for example, listing important keywords such as "New Product A," "Online Promotion," and "Competitors."

[1575] input:

[1576] Strategic Objectives and Targets Data

[1577] output:

[1578] Keywords and parameters for data collection (e.g., "New Product A," "Online Promotion")

[1579] Step 3:

[1580] The server collects relevant data from Internet resources, using Twitter APIs and other methods to retrieve tweets and other relevant information related to the identified keywords, and stores the tweet posting time, number of likes and retweets, and post content in a database.

[1581] input:

[1582] Keywords and parameters (e.g., "New Product A," "Online Promotion")

[1583] output:

[1584] Related data (e.g. tweet data)

[1585] Step 4:

[1586] The server preprocesses the collected data and converts it into a format suitable for analysis, specifically removing noise data and tokenizing text data, which makes the data clean and suitable for analysis.

[1587] input:

[1588] Related data (e.g. tweet data)

[1589] output:

[1590] Pre-processed, clean data

[1591] Step 5:

[1592] The server analyzes the pre-processed data and extracts metrics related to the user's strategy. It uses NLP and machine learning models to classify customer sentiment (positive, negative, neutral) and calculate a sentiment score. It also analyzes tweet posting times to identify peak activity times.

[1593] input:

[1594] Pre-processed, clean data

[1595] output:

[1596] Analysis results (e.g., emotion scores, peak activity times)

[1597] Step 6:

[1598] Based on the analysis results, the server generates personalized insights and suggestions for the user, such as "Online promotions for new product A are particularly effective on weekday evenings." It also uses a generative AI model to generate appropriate prompts.

[1599] input:

[1600] Analysis results (e.g., emotion scores, peak activity times)

[1601] output:

[1602] Personalized insights and recommendations (e.g., "Online promotions for new product A are particularly effective on weekday evenings")

[1603] Prompt statement (e.g., "We suggest setting promotion times for weekday evenings.")

[1604] Step 7:

[1605] The server displays these insights and recommendations in a real-time data dashboard, which visually displays the analysis results and makes them easy for users to understand.

[1606] input:

[1607] Personalized insights and recommendations (e.g., "Online promotions for new product A are particularly effective on weekday evenings")

[1608] output:

[1609] Real-time data dashboard

[1610] Step 8:

[1611] Users can access the dashboard through their devices to view new data and insights, and use this information to develop new marketing strategies and adjust them as needed.

[1612] input:

[1613] Real-time data dashboard

[1614] output:

[1615] User strategy adjustments

[1616] Step 9:

[1617] The user then re-enters the revised strategy into the terminal, and the system continues optimizing the strategy based on the latest data.

[1618] input:

[1619] Revised strategy (e.g., promotion time changed to weekday evenings)

[1620] output:

[1621] New Strategic Data

[1622] By following these steps, advertisers and marketers can effectively optimize their advertising campaigns and efficiently achieve their goals.

[1623] 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.

[1624] The AI-Enhanced Marketing Insights (AIEMI) system of this invention is designed to help companies and marketers efficiently and quickly build and optimize their marketing strategies, and by combining it with an emotion engine, it achieves even greater personalization. The program processing of this system is explained in natural language, with concrete examples.

[1625] User inputs marketing strategy

[1626] The user uses a device to input the objectives and goals of the marketing strategy. For example, they might input, "We want to strengthen the online promotion of new product A." This input is then analyzed by the emotion engine.

[1627] The server prepares to collect data

[1628] The server analyzes the user's input and identifies keywords and parameters for collecting the necessary data. For example, it might list keywords such as "New Product A," "Online Promotion," and "Competitors."

[1629] The server collects the data

[1630] The server collects relevant data from internet resources (social media, websites, news articles, industry reports, etc.). For example, it uses the Twitter API to collect tweets about "New Product A." It then stores the tweet's posting time, number of likes and retweets, and post content in a database.

[1631] The server preprocesses the data

[1632] The server cleans the collected data and converts it into a format suitable for analysis, for example, filtering out noise data and tokenizing text data.

[1633] The server analyzes the data

[1634] The server analyzes the preprocessed data and extracts metrics relevant to the user's strategy (such as engagement rate, trends, and customer sentiment analysis). It uses natural language processing (NLP) and machine learning models to gain insights. For example, it analyzes collected tweet text data with an NLP model to classify customer sentiment (positive, negative, or neutral).

[1635] The server generates personalized insights

[1636] The server then uses the results of the data analysis to create personalized insights and suggestions for users, such as "Promotions for new product A are particularly effective on weekday evenings."

[1637] The server utilizes the emotion engine

[1638] The server's emotion engine recognizes the user's emotions in real time based on their input and browsing history. This generates personalized insights and suggestions that reflect the user's current emotional state. For example, if the user feels impatient or anxious, the system will suggest time management and resource optimization to alleviate that feeling.

[1639] The server updates the data dashboard

[1640] The server displays these insights and recommendations in a real-time data dashboard, which displays the latest metrics and analysis results in graphs and charts for easy user comprehension.

[1641] Users reassess their strategies

[1642] Users can access the dashboard via their devices to view new data and insights, and use the information in the dashboard to revise and adjust their marketing strategies, for example by scheduling promotions on weekday evenings.

[1643] User re-enters strategy

[1644] The user then re-enters the revised strategy into the terminal, which starts the cycle again, continuously optimizing based on the latest data.

[1645] The above is a natural language explanation of the program processing of the AIEMI system, which combines an emotion engine. This system frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize marketing strategies. The emotion engine provides personalized insights and suggestions that incorporate the user's emotions, resulting in greater accuracy and effectiveness.

[1646] The processing flow will be explained below.

[1647] Step 1:

[1648] The user inputs the objectives and goals of the marketing strategy via the terminal. The user enters a specific marketing goal, for example, "I want to strengthen the online promotion of new product A," into the input form on the terminal.

[1649] Step 2:

[1650] The server receives the user's input, analyzes it with an emotion engine, and recognizes the user's emotional state. For example, it classifies the user as feeling "impatient" based on the input.

[1651] Step 3:

[1652] Based on the user's input, the server identifies keywords and parameters (e.g., "New Product A," "Online Promotion," "Competitors") for collecting the required data.

[1653] Step 4:

[1654] The server collects relevant data from internet resources, such as tweets, blog posts, news articles, and industry reports, using social media APIs and web scraping techniques. For example, the server uses the Twitter API to collect tweets about "New Product A."

[1655] Step 5:

[1656] The server preprocesses the collected data, specifically removing noise data, tokenizing text data, and filtering out unnecessary information.

[1657] Step 6:

[1658] The server analyzes the preprocessed data. It uses natural language processing (NLP) to perform semantic analysis and sentiment analysis of the text. For example, it classifies the sentiment of collected tweets into "positive," "negative," and "neutral" sentiments.

[1659] Step 7:

[1660] The server generates personalized insights and suggestions for users based on the results of data analysis, such as "Promotions for new product A are particularly effective on weekday evenings."

[1661] Step 8:

[1662] The server generates insights and recommendations that are displayed in a real-time data dashboard that also displays the user's emotional state, for example, "The user is feeling anxious."

[1663] Step 9:

[1664] Users can access the dashboard via their devices to view the latest data and insights, and can use the information in the dashboard to revise their marketing strategies, for example by changing promotion times to weekday evenings.

[1665] Step 10:

[1666] The user inputs the revised strategy into the terminal again. The user's emotional state is analyzed again by the emotion engine, and the cycle begins again. The server repeats data collection and analysis based on this new strategy.

[1667] This allows the system to continually optimize personalized marketing strategies that reflect the user's emotional state.

[1668] Example 2

[1669] 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."

[1670] Traditional marketing strategy development and optimization involves time-consuming and labor-intensive large-scale data analysis, which takes a long time to produce results. Furthermore, personalized proposals are often lacking, making it difficult to develop marketing strategies that take into account the detailed emotions and circumstances of each customer. This makes it difficult for companies and marketers to quickly and efficiently develop optimal strategies.

[1671] 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.

[1672] In this invention, the server includes means for the user to input the objectives and goals of the marketing strategy via the terminal, means for identifying keywords and parameters for collecting relevant data from internet resources, and means for pre-processing and converting the collected data into a format suitable for analysis, thereby enabling the generation of personalized insights and recommendations for the user.

[1673] "User" refers to the individual or organization that operates the system and inputs or modifies marketing strategies.

[1674] "Terminal" refers to an electronic device such as a computer, smartphone, or tablet that a user uses to perform operations such as input and display.

[1675] "Server" refers to a central computer system that analyzes input data, performs related processing, and provides the results to users.

[1676] A "marketing strategy" refers to the strategic direction or plan of action that a company or organization plans to bring a product or service to market and increase sales and awareness.

[1677] "Keywords" refer to important words or phrases that represent a particular theme or topic used during data collection and analysis.

[1678] "Parameter" refers to a specific condition or setting used during data collection and analysis.

[1679] "Internet resources" refers to information sources found on the internet, such as social media, websites, news articles, and industry reports.

[1680] "Data preprocessing" refers to operations such as removing noise data and tokenizing data to prepare the data in a format suitable for analysis.

[1681] "Analysis" refers to the process of applying statistical methods and algorithms to collected data to derive useful metrics and insights.

[1682] "Personalized insights" refers to customized information and recommendations based on a user's specific needs and emotional state.

[1683] A "data dashboard" refers to an interface that visually displays analytical results and insights, allowing users to easily understand the information.

[1684] "Natural language processing (NLP)" refers to the technology that enables computers to understand and analyze human language.

[1685] "Customer sentiment" refers to the emotional state a customer has about a product or service, whether positive, negative, or neutral.

[1686] "Engagement rate" refers to an indicator that shows the degree of interest and involvement that customers show in a product or service.

[1687] The AI-Enhanced Marketing Insights (AIEMI) system of the present invention allows companies and marketers to efficiently and quickly build and optimize their marketing strategies. This system achieves further personalization by combining an emotion engine. The following describes an embodiment of the present invention.

[1688] 1. User Interface

[1689] The user uses the device to input the objectives and goals of the marketing strategy. This input is analyzed by the emotion engine and sent to the server. Specifically, this involves the user entering "I would like to strengthen the online promotion of new product A" into the input form and clicking the "Submit" button.

[1690] 2. Data collection from internet resources

[1691] The server receives user input and identifies keywords and parameters for collecting the required data. Based on these keywords, the server collects relevant data from Internet resources. For example, it uses the Twitter API to collect tweets about "New Product A."

[1692] As a concrete example, the following prompt sentence is input to the generative AI model:

[1693] "Collect the latest tweets about new product A and perform sentiment analysis to classify them as positive, negative, or neutral."

[1694] 3. Data Preprocessing

[1695] The server cleans the collected data and converts it into a format suitable for analysis. At this stage, noise data is removed, text data is tokenized, and missing values ​​are filled in. The collected tweets are analyzed using an NLP model to classify customer sentiment (positive, negative, neutral).

[1696] 4. Data Analysis

[1697] The server analyzes the preprocessed data. Using machine learning models and natural language processing (NLP) techniques, it calculates metrics such as engagement rates, trends, and customer sentiment analysis. For example, the analysis results can provide insights such as, "Promoting new product A is particularly effective in the evenings on weekdays."

[1698] 5. Generating personalized insights

[1699] The server uses the results of the data analysis to create personalized insights and suggestions for users. These insights and suggestions reflect the user's current emotional state. The emotion engine analyzes the user's input and browsing history in real time to provide personalized suggestions. For example, if the user feels impatient or anxious, it will suggest time management and resource optimization to alleviate that feeling.

[1700] 6. Update the data dashboard

[1701] The server displays these insights and recommendations in a real-time data dashboard, which displays the latest metrics and analysis results in graphs and charts for easy user comprehension.

[1702] 7. Review and re-enter your strategy

[1703] Users access the dashboard via their device to view new data and insights, allowing them to review and revise their marketing strategy, for example by scheduling a promotion for weekday evenings. They then re-enter the revised strategy into their device, and the cycle begins again, continually optimizing based on the latest data.

[1704] In this way, the present invention allows for the rapid and efficient development and optimization of marketing strategies, with even greater accuracy and effectiveness achieved through the use of an emotion engine.

[1705] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1706] Step 1:

[1707] The user inputs the objectives and goals of the marketing strategy via the terminal.

[1708] Specific operation: The user enters "I would like to strengthen the online promotion of new product A" into the input form on the device and clicks the "Submit" button.

[1709] Input: The purpose or goal of your marketing strategy (e.g., "We want to strengthen online promotion for new product A").

[1710] Output: The entered data is sent to the server.

[1711] Step 2:

[1712] The server parses the user's input and identifies keywords and parameters for collecting the required data.

[1713] Specific operation: The server analyzes the received data using a natural language processing (NLP) engine and extracts key keywords (e.g., "New Product A," "Online Promotion").

[1714] Input: The marketing strategy entered by the user.

[1715] Output: Identified keywords and parameters.

[1716] Step 3:

[1717] The server collects relevant data from Internet resources.

[1718] Specific operation: The server uses the Twitter API to collect tweets about "New Product A." The collected tweets are stored in a database.

[1719] Input: The keywords or parameters specified.

[1720] Output: Collected tweet data (posting time, number of likes and retweets, post content, etc.).

[1721] Step 4:

[1722] The server preprocesses the collected data and converts it into a format suitable for analysis.

[1723] What it does: The server runs data cleaning scripts to filter out noise data, tokenize text data, and also impute missing values.

[1724] Input: Collected tweet data.

[1725] Output: Cleaned and tokenized text data.

[1726] Step 5:

[1727] The server analyzes the pre-processed data and extracts metrics related to the user's strategy.

[1728] What it does: The server applies NLP models to classify the sentiment of tweets (positive, negative, neutral) and calculate engagement rates and trends.

[1729] Input: Preprocessed text data.

[1730] Output: Sentiment classification results and metrics such as engagement rate and trend.

[1731] Step 6:

[1732] The server generates personalized insights and suggestions for users based on the results of the data analysis.

[1733] Specific operation: The server generates insights using the user profile and analysis results, and compiles them in the form of a report. For example, it makes a suggestion such as, "Promoting new product A is particularly effective in the evenings on weekdays."

[1734] Inputs: Sentiment classification results, engagement rates, trend metrics, and user profiles.

[1735] Output: Personalized insights and recommendations.

[1736] Step 7:

[1737] The server uses an emotion engine to recognize the user's emotions in real time based on the user's input and browsing history.

[1738] What it does: The emotion engine assesses the user's current emotional state and generates personalized insights and suggestions based on that. For example, if the user feels anxious or impatient, it will suggest time management and resource optimization to alleviate that.

[1739] Input: User input, browsing history.

[1740] Output: Personalized insights based on emotional state.

[1741] Step 8:

[1742] The server displays these insights and recommendations in a real-time data dashboard.

[1743] What it does: Runs the data dashboard update script and displays the new data in graphs and charts.

[1744] Input: Insights and suggestions.

[1745] Output: An updated data dashboard.

[1746] Step 9:

[1747] Users access the dashboard via their devices to see new data and insights.

[1748] Specific actions: The user views the information on the dashboard and confirms and modifies the marketing strategy, for example, setting the promotion time to weekday evenings.

[1749] Input: Updated data dashboard.

[1750] Output: A revised marketing strategy.

[1751] Step 10:

[1752] The user inputs the revised strategy into the terminal again.

[1753] What happens: The user enters a new strategy and clicks the "Submit" button, which starts the cycle again.

[1754] Enter: a revised marketing strategy.

[1755] Output: The new marketing strategy sent to the server.

[1756] (Application example 2)

[1757] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1758] Conventional marketing analysis systems have faced challenges due to the heavy burden of data collection and analysis, making it difficult to rapidly optimize marketing strategies. Furthermore, they have been unable to fully grasp users' emotions and behavioral history in real time and optimize personalized advertising based on that information, making it difficult to maximize advertising effectiveness. There is a need for a system that can solve these problems and support the formulation of more efficient and effective marketing strategies.

[1759] 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.

[1760] In this invention, the server includes means for a user to input the purpose and goals of a marketing strategy via a terminal, means for the server to identify keywords and parameters for collecting related data from Internet resources, means for recognizing the emotional state of the user using an emotion engine and generating personalized proposals taking that into consideration, and means for optimizing advertisements in real time based on the collected emotion data and behavioral history. This streamlines the process from building to optimizing a marketing strategy, and enables real-time advertisement optimization based on the user's emotions and behavioral history.

[1761] "User" refers to a person who uses the system to develop and optimize a marketing strategy.

[1762] "Terminal" refers to an information processing device such as a computer, smartphone, or tablet that allows a user to access the system.

[1763] A "marketing strategy" refers to a series of measures or action plans designed to promote a product or service.

[1764] "Internet resources" refers to information and data publicly available on the Internet, such as websites, social media, news articles, and industry reports.

[1765] "Server" refers to the computer system that runs the entire system, including storing collected data, analyzing it, and generating personalized insights.

[1766] "Keywords or parameters" refers to a set of significant words or values ​​identified for data collection or analysis.

[1767] "Data preprocessing" refers to a series of processes that remove noise from collected data and convert it into a form suitable for analysis.

[1768] "Personalized insights" refers to personalized information and recommendations provided based on a user's specific circumstances and needs.

[1769] An "emotion engine" refers to algorithms or software that recognize emotions based on user input and behavioral history and generate personalized suggestions.

[1770] "Real-time ad optimization" refers to the process of analyzing user emotions and behavioral history data in real time, and selecting and displaying the most appropriate advertisements based on the results.

[1771] A "data dashboard" refers to an interface for visually displaying analytical results and insights.

[1772] The invention begins when a user inputs the objectives and goals of their marketing strategy via a device. Based on this input, a server collects relevant data from internet resources. The server identifies keywords and parameters and uses them to gather data from resources such as websites, social media, news articles, and industry reports.

[1773] The server preprocesses the collected data and converts it into a form suitable for analysis. Preprocessing includes removing noise data and tokenizing text data. The server then analyzes the preprocessed data and extracts indicators related to the user's strategy. This involves using natural language processing (NLP) techniques and machine learning models to analyze customer sentiment and evaluate engagement rates.

[1774] Based on the analysis results, the server generates personalized insights and suggestions, suggesting specific areas for improvement in marketing strategies and promotions. Using an emotion engine, the system can recognize the user's emotional state in real time, enabling highly personalized suggestions. For example, if the user is feeling anxious, the system will display advice to alleviate that anxiety.

[1775] Furthermore, based on the emotion engine and historical behavioral data, the server optimizes ads in real time, selecting and displaying the most effective ads for users.These insights and suggestions are displayed in real time on the data dashboard, which users can access at any time.

[1776] For example, if the user ID is "12345," the server retrieves emotion data from the Emotion API and reads behavioral history from the database. The most appropriate advertisement is then selected based on the collected text data. This entire process is carried out in real time, making it possible to build an efficient and effective marketing strategy.

[1777] Examples of prompts for a generative AI model might include:

[1778] Create a program that recommends optimal ads for user ID 12345 based on their current emotional state and behavioral history. Use the following script to retrieve emotional data from the Emotion API and implement a function that optimizes ads based on that data and behavioral history.

[1779] This invention frees companies and marketers from the burden of analyzing a wide range of data, enabling them to quickly and efficiently formulate and optimize their marketing strategies. Furthermore, the emotion engine provides personalized insights and suggestions that incorporate user emotions, resulting in even greater accuracy and effectiveness.

[1780] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1781] Step 1:

[1782] The user inputs the objectives and goals of the marketing strategy via the terminal.

[1783] Input: Marketing strategy objectives and goals (e.g., "We want to strengthen online promotions for our new products")

[1784] Output: The entered marketing strategy objectives and goals are sent to the server as text data.

[1785] Operation: When a user enters a strategic goal into the input form on the terminal and presses the submit button, the data is sent to the server.

[1786] Step 2:

[1787] The server analyzes the input purpose or goal and identifies keywords and parameters.

[1788] Input: User-entered marketing strategy objectives and goals

[1789] Output: Identified keywords or parameters (e.g. "new product", "online promotion", "competitor")

[1790] How it works: The server uses natural language processing (NLP) techniques to extract important keywords and parameters from the input text.

[1791] Step 3:

[1792] The server collects relevant data from Internet resources.

[1793] Input: Identified keywords or parameters

[1794] Output: Collected internet resource data (e.g., social media posts, news articles, website information)

[1795] How it works: The server collects data based on the identified keywords using social media APIs and web scraping techniques.

[1796] Step 4:

[1797] The server preprocesses the collected data and converts it into a format suitable for analysis.

[1798] Input: Collected internet resource data

[1799] Output: Preprocessed data (denoised and tokenized text data)

[1800] Operation: The server performs preprocessing to remove noise data and tokenize text data.

[1801] Step 5:

[1802] The server analyzes the pre-processed data and extracts indicators relevant to the user's strategy.

[1803] Input: Preprocessed data

[1804] Output: Extracted metrics (e.g., engagement rates, trends, customer sentiment analysis results)

[1805] How it works: The server uses natural language processing (NLP) and machine learning models to analyze the data and extract the necessary metrics.

[1806] Step 6:

[1807] The server uses the analysis results to generate personalized insights and suggestions for users.

[1808] Input: extracted metrics, user input

[1809] Output: Personalized insights and recommendations (e.g., "New product promotions are most effective on weekday evenings")

[1810] How it works: The server applies algorithms based on extracted metrics and user input to generate insights and recommendations.

[1811] Step 7:

[1812] The server utilizes an emotion engine to recognize the user's emotional state and take it into account to generate personalized suggestions.

[1813] Input: User's emotional data, behavioral history

[1814] Output: Personalized suggestions based on the user's emotions (e.g., time management suggestions to reduce impatience and anxiety)

[1815] How it works: The server uses the Emotion API to obtain the user's emotional data, analyzes it, and reflects it in the suggestions.

[1816] Step 8:

[1817] Advertisements are optimized in real time based on the emotional data and behavioral history collected by the server.

[1818] Input: Emotion data, behavioral history

[1819] Output: Optimized ad (e.g. "Ad 1")

[1820] How it works: The server uses machine learning models to analyze emotional data and behavioral history to select the most appropriate advertisement.

[1821] Step 9:

[1822] Server-generated insights and recommendations are displayed in a real-time data dashboard.

[1823] Input: Personalized insights and suggestions

[1824] Output: Information displayed on a data dashboard (e.g., analysis results in the form of graphs and charts)

[1825] How it works: The server takes the generated data and puts it into a data dashboard for visual display.

[1826] Step 10:

[1827] Users access the dashboard via their devices to review and revise their strategies.

[1828] Input: Information displayed in the data dashboard

[1829] Output: Revised marketing strategy

[1830] How it works: Users consider and input new strategies based on the information displayed in the data dashboard.

[1831] Step 11:

[1832] The user re-enters the revised strategy.

[1833] Input: Revised marketing strategy

[1834] Output: The re-entered marketing strategy is sent to the server as text data.

[1835] Operation: When the user inputs the newly set strategic goal into the terminal and presses the send button, the data is sent to the server and analyzed again.

[1836] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1837] 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.

[1838] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1839] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1840] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1841] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1842] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1843] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1844] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1845] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1846] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1847] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1848] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1849] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1850] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1851] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1852] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1853] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1854] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1855] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1856] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1857] The following is further disclosed regarding the above embodiment.

[1858] (Claim 1)

[1859] A means for users to input the objectives and goals of their marketing strategy via a terminal;

[1860] a means by which the server identifies keywords or parameters for collecting relevant data from the Internet resource;

[1861] means for the server to collect relevant data from Internet resources;

[1862] A means for the server to preprocess the collected data and convert it into a format suitable for analysis;

[1863] means for the server to analyze the pre-processed data and extract indicators related to the user's strategy;

[1864] a means for the server to generate personalized insights and recommendations for the user based on the analysis results;

[1865] A means for the server to display the above insights and recommendations in a real-time data dashboard; and

[1866] A means for users to access the dashboard via their devices and review and revise their strategies;

[1867] The system includes a means for the user to re-enter modified strategies.

[1868] (Claim 2)

[1869] 10. The system of claim 1, wherein the server comprises means for collecting social media data and classifying customer sentiment using natural language processing.

[1870] (Claim 3)

[1871] 2. The system according to claim 1, wherein the server is provided with a means for constructing a predictive model of engagement rate based on past data and showing users the effectiveness of promotions on specific days and times.

[1872] "Example 1"

[1873] (Claim 1)

[1874] A means for users to input the objectives and goals of their marketing strategy via a terminal;

[1875] A means for the server to analyze the user's input data and identify necessary keywords and parameters;

[1876] means for the server to collect relevant data from Internet resources;

[1877] A means for the server to preprocess the collected data and convert it into a format suitable for analysis;

[1878] means for the server to analyze the pre-processed data and extract indicators related to the user's strategy;

[1879] A means for the server to generate personalized insights and recommendations for the user based on the analysis results; and

[1880] A means for the server to display the above insights and recommendations in a real-time data dashboard; and

[1881] A means for users to access the dashboard via their devices and review and revise their strategies;

[1882] The system includes a means for the user to re-enter modified strategies.

[1883] (Claim 2)

[1884] 10. The system of claim 1, wherein the server comprises means for collecting social media data and classifying customer sentiment using natural language processing.

[1885] (Claim 3)

[1886] 2. The system according to claim 1, wherein the server is provided with a means for constructing a predictive model of engagement rate based on past data and showing users the effectiveness of promotions on specific days and times.

[1887] "Application Example 1"

[1888] (Claim 1)

[1889] A means for users to input the objectives and goals of their marketing strategy via a terminal;

[1890] a means by which the server identifies keywords or parameters for collecting relevant data from the Internet resource;

[1891] means for the server to collect relevant data from Internet resources;

[1892] A means for the server to preprocess the collected data and convert it into a format suitable for analysis;

[1893] means for the server to analyze the pre-processed data and extract indicators related to the user's strategy;

[1894] a means for the server to generate personalized insights and recommendations for the user based on the analysis results;

[1895] A means for the server to display the above insights and recommendations in a real-time data dashboard; and

[1896] A means for users to access the dashboard via their devices and review and revise their strategies;

[1897] a means for the user to re-enter a modified strategy;

[1898] means for performing sentiment analysis on the collected data and notifying the user of an average sentiment score and peak activity time;

[1899] A system that includes a means for analyzing the effectiveness of advertising campaigns in real time and proposing optimal advertising strategies.

[1900] (Claim 2)

[1901] 10. The system of claim 1, wherein the server comprises means for collecting social media data, classifying customer sentiment using natural language processing, and visualizing it in real time.

[1902] (Claim 3)

[1903] The system of claim 1, wherein the server is provided with a means for constructing a predictive model of engagement rate based on past data and showing users the effectiveness of promotions on specific days and times, and a means for generating prompt sentences for users using a generative AI model based on collected data.

[1904] "Example 2: Combining Emotion Engines"

[1905] (Claim 1)

[1906] A means for users to input the objectives and goals of their marketing strategy via a terminal;

[1907] a means by which the server identifies keywords or parameters for collecting relevant data from the Internet resource;

[1908] means for the server to collect relevant data from Internet resources;

[1909] A means for the server to preprocess the collected data and convert it into a format suitable for analysis;

[1910] means for the server to analyze the pre-processed data and extract indicators related to the user's strategy;

[1911] a means for the server to generate personalized insights and recommendations for the user based on the analysis results;

[1912] A means for the server to recognize emotions based on user input and browsing history and generate personalized insights and suggestions;

[1913] A means for the server to display the above insights and recommendations in a real-time data dashboard; and

[1914] A means for users to access the dashboard via their devices and review and revise their strategies;

[1915] The system includes a means for the user to re-enter modified strategies.

[1916] (Claim 2)

[1917] 10. The system of claim 1, wherein the server comprises means for collecting social media data and classifying customer sentiment using natural language processing.

[1918] (Claim 3)

[1919] 2. The system according to claim 1, wherein the server is provided with a means for constructing a predictive model of engagement rate based on past data and showing users the effectiveness of promotions on specific days and times.

[1920] "Application example 2 when combining emotion engines"

[1921] (Claim 1)

[1922] A means for users to input the objectives and goals of their marketing strategy via a terminal;

[1923] a means by which the server identifies keywords or parameters for collecting relevant data from the Internet resource;

[1924] means for the server to collect relevant data from Internet resources;

[1925] A means for the server to preprocess the collected data and convert it into a format suitable for analysis;

[1926] means for the server to analyze the pre-processed data and extract indicators related to the user's strategy;

[1927] a means for the server to generate personalized insights and recommendations for the user based on the analysis results;

[1928] A means for the server to display the above insights and recommendations in a real-time data dashboard; and

[1929] A means for users to access the dashboard via their devices and review and revise their strategies;

[1930] a means for the user to re-enter a modified strategy;

[1931] a means for utilizing an emotion engine to recognize a user's emotional state and take it into account to generate personalized suggestions;

[1932] A system that includes a means for optimizing advertising in real time based on collected emotional data and behavioral history.

[1933] (Claim 2)

[1934] 10. The system of claim 1, wherein the server comprises means for collecting social media data and classifying customer sentiment using natural language processing.

[1935] (Claim 3)

[1936] The system of claim 1, wherein the server is provided with a means for constructing a predictive model of engagement rate based on past data, showing users the effectiveness of promotions on specific days and times, and a means for selecting advertisements in real time taking into account user emotional data. [Explanation of symbols]

[1937] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to input the objectives and goals of their marketing strategy via a terminal; a means by which the server identifies keywords or parameters for collecting relevant data from the Internet resource; means for the server to collect relevant data from Internet resources; A means for the server to preprocess the collected data and convert it into a format suitable for analysis; means for the server to analyze the pre-processed data and extract indicators related to the user's strategy; a means for the server to generate personalized insights and recommendations for the user based on the analysis results; A means for the server to display the above insights and recommendations in a real-time data dashboard; and A means for users to access the dashboard via their devices and review and revise their strategies; The system includes a means for the user to re-enter modified strategies.

2. 10. The system of claim 1, wherein the server comprises means for collecting social media data and classifying customer sentiment using natural language processing.

3. 2. The system according to claim 1, wherein the server comprises means for constructing a predictive model of engagement rate based on past data and for showing the user the effectiveness of promotions on specific days and times.

Images