system

Abstract

We provide the system. [Solution] A device that collects consumer data and analyzes consumer intentions, emotions, and trends using natural language processing technology, A device that proposes optimal advertising transmission and budget management based on past advertising activity data, A device that monitors the actions of competing companies and predicts market changes, A device that generates customized messages for each customer, A device that analyzes purchasing trends based on sales history and provides personalized product recommendations, A device for evaluating the effectiveness of a marketing strategy and suggesting the next strategy, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern marketing activities, it is difficult to quickly and accurately grasp consumer behavior and formulate an optimal marketing strategy based on it. In particular, the increase and diversification of consumer data, the rapid changes in the trends of competing companies, and the uncertainty of the market have increased the difficulty. Also, it is not easy to perform effective personalization for individual customers. Therefore, there is a need to establish a system that enables real-time data analysis and strategy formulation.

Means for Solving the Problems

[0005] This invention provides a system that collects consumer data and analyzes consumer intentions, emotions, and trends using natural language processing technology. This enables optimization of advertising delivery and budget proposals based on past campaign data. Furthermore, by monitoring the activities of competitors and predicting market changes, rapid strategic changes become possible. In addition, by automatically generating personalized messages based on customer profiles, it enables effective marketing tailored to individual customers. In this way, this invention supports accurate marketing activities by evaluating the effectiveness of marketing measures in real time and suggesting the next strategy.

[0006] "Consumer data" refers to information obtained from consumers' purchasing behavior, online activities, and statements made on social media.

[0007] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0008] "Intention" is a concept that indicates the purpose or reason for a consumer to take a particular action.

[0009] "Emotion" refers to the emotional response that consumers have to a particular product or brand.

[0010] A "trend" refers to a common pattern or fashion that many consumers exhibit within a specific period of time.

[0011] "Ad delivery optimization" is the process of adjusting various elements to display ads most effectively and achieve the best results.

[0012] A "budget proposal" is a suggestion for how to allocate funds in the most effective way possible using limited resources.

[0013] "Competitor activity" refers to the strategies, activities, and changes in those of competing companies within the market.

[0014] "Market changes" refer to how consumer needs and expectations, technological advancements, and economic conditions change over time.

[0015] A "customer profile" is a collection of information about individual customers, including purchase history and behavioral patterns.

[0016] A "personalized message" is a message that is customized to the specific needs and interests of each individual customer.

[0017] "Marketing effectiveness" refers to the measurement of the results and impact achieved by a particular marketing activity.

[0018] "Presenting the next strategy" means indicating the next actions or measures to take based on the collected data. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0021] First, the terms used in the following description will be described.

[0022] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] As shown in Figure 1, the 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.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0033] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] This invention is a system designed to support marketing activities and primarily operates through a program running on a server. The server collects and analyzes diverse consumer data. Specifically, it acquires data in real time from social media and online stores and analyzes consumer intentions and emotions using natural language processing technology. Using these results, the server predicts trends and provides them to the user's device as visual information.

[0041] Furthermore, the server optimizes ad delivery and budget allocation based on past campaign data. This includes analyzing the success factors of similar campaigns and applying them to the current advertising strategy.

[0042] Regarding the activities of competing companies, the server collects data from specific sources, analyzes it, and predicts market changes. These analysis results can be viewed on the terminal to help improve marketing strategies.

[0043] To enable customized marketing for each customer, the server automatically generates personalized messages and offers based on each customer's profile. This allows users to attract customers more effectively.

[0044] Finally, after the marketing campaign is implemented, the server analyzes its effectiveness based on the data obtained and proposes the next strategy. Users receive this information in real time through their devices, allowing them to quickly take action in line with market trends.

[0045] As a concrete example, when a store launches a new product, the server analyzes data from similar past successful campaigns and suggests the optimal advertising media and target audience to the user's terminal. Based on the provided report, the user can quickly adjust the campaign content to maximize its effectiveness. This system dramatically improves the accuracy and speed of marketing strategies.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server collects real-time data through APIs from social media platforms and online stores. This data includes consumer posts, reviews, and purchase history.

[0049] Step 2:

[0050] The server uses natural language processing technology to analyze collected consumer data and extract consumer intentions, emotions, and trends. This analysis identifies each consumer's interests and concerns.

[0051] Step 3:

[0052] The server uses the analyzed data to compare it with past campaign data and proposes optimized ad delivery and budget allocation. It extracts the characteristics of successful campaigns and suggests similar strategies.

[0053] Step 4:

[0054] The server crawls the activities of competitors and updates models that predict market changes. It provides information to re-evaluate marketing strategies while taking into account changes in the competitive landscape.

[0055] Step 5:

[0056] The server generates personalized messages and offers based on customer profiles, enabling communication optimized for each individual customer.

[0057] Step 6:

[0058] The server analyzes the results of implemented marketing initiatives and measures their effectiveness. The analysis results are displayed visually on a dashboard.

[0059] Step 7:

[0060] Users can review reports generated by the server via their devices and decide on their next strategy. Based on the suggested improvements, users can quickly adjust their marketing measures.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Traditional marketing systems struggled to grasp individual intentions and emotions in detail, making it difficult to provide timely and appropriate information to target customers. Furthermore, they failed to fully utilize data from past sales promotion activities, making optimal advertising distribution and budget allocation challenging. Additionally, the lack of objective criteria for efficiently analyzing the trends of similar businesses and predicting market changes hindered the rapid improvement of business strategies.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] This invention includes a server that collects personal data from a digital platform and analyzes individuals' intentions, emotions, and trends using natural language processing technology; means for proposing optimal advertising implementation and budget allocation based on past sales promotion activity data; and means for monitoring the behavior of similar businesses and predicting changes in the business environment. This enables personalized information provision, improves the efficiency of advertising delivery strategies and budget allocation, and allows for rapid strategic adjustments in the market.

[0066] A "digital platform" is an internet-based environment for collecting consumer data online, including social media and online stores.

[0067] "Personal data" refers to information that indicates consumer behavior and trends, and includes data that identifies a specific individual, such as online purchase history and interaction data.

[0068] "Natural language processing technology" is an information processing technology that uses computers to analyze human language and understand its linguistic features, emotions, and intentions.

[0069] "Sales promotion activity data" refers to records related to advertising campaigns and marketing activities conducted in the past, and is data that can be used for measuring effectiveness and making improvements.

[0070] "Competitors of the same type" refers to competing companies that provide similar goods or services in the same industry or market.

[0071] "Customized information" refers to messages and offers that are appropriately tailored based on the individual consumer's needs and profile.

[0072] "Visual tools" are software or technologies used to visually present the results of an analysis, including charts and graphs.

[0073] Modes for carrying out the invention

[0074] This invention is an advanced system for optimizing marketing strategies, and its main components include a server, terminals, and users. Specific implementation methods are described below.

[0075] The server first collects data from others on digital platforms. This includes using Python scripts to retrieve data from social media APIs and online stores. The collected data is stored in JSON format and later used for analysis.

[0076] Next, the server analyzes the collected data using natural language processing technology. By using the Google® Cloud Natural Language API, it efficiently extracts individual intentions, emotions, and trends. Through this data analysis, the server reveals consumers' latent needs.

[0077] Data processing libraries such as Pandas and NumPy are used to analyze past sales promotion activity data. Based on this, the server proposes the optimal advertising strategy and budget allocation to the terminal. For example, it selects the optimal media based on the conversion rate of advertisements.

[0078] To analyze the activities of competitors, the server uses RSS readers and news APIs to collect and analyze data from similar businesses. This allows for accurate prediction of market fluctuations and the competitive landscape.

[0079] The server uses a generative AI model to generate customized messages. For example, by inputting "Create a special offer message for female customers in their 20s" as a prompt based on a specific consumer profile, a message tailored to the purpose will be generated.

[0080] Finally, the server displays the analysis results visually using a visual tool. By using visualization libraries such as Matplotlib and sending the generated charts and graphs to the terminal, users can utilize this information in real time and quickly adjust their marketing strategies.

[0081] This invention enables users to conduct more precise and effective marketing activities, thereby enhancing their competitive advantage in the market.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server collects personal data from digital platforms. Specifically, it uses a Python script to send requests to social networking service (SNS) APIs and retrieves consumer posting data in JSON format. The input is the SNS API endpoint, and the output is the retrieved JSON data. The server stores this data as a base database for analysis.

[0085] Step 2:

[0086] The server analyzes the collected data using natural language processing technology. It sends the data to the Google Cloud Natural Language API to analyze consumer intent and sentiment. The input is the JSON data collected in step 1, and the output is metadata of the analyzed intent and sentiment. This provides information about consumer interests and demand forecasting.

[0087] Step 3:

[0088] The server analyzes the optimal strategy using past sales promotion activity data. It uses Pandas to read past campaign records and NumPy to perform statistical analysis. The input is historical campaign data in CSV format, and the output is an optimal advertising plan and budget allocation proposal. The calculated data is sent to the terminal as a suggestion.

[0089] Step 4:

[0090] The server monitors the activities of competitors and predicts changes in the business environment. It collects and analyzes the latest competitive information from RSS feeds and news APIs. Input is information from RSS feeds and news APIs, and output is competitive trends and market fluctuation predictions. These prediction results are also sent to terminals, which users can use for strategic planning.

[0091] Step 5:

[0092] The server generates personalized messages using a generative AI model. Based on a specific customer profile, prompt sentences are input to the generative AI model. The input is a prompt sentence such as "Create a special offer message for female customers in their 20s," and the output is the generated message. This provides users with effective marketing messages.

[0093] Step 6:

[0094] The server visually represents the analysis results using a visual tool and sends them to the terminal. For example, it uses Matplotlib to convert the data into charts and graphs. The input is the analysis results from steps 2 to 5, and the output is the visualized data. The terminal displays this, allowing the user to utilize the information in real time.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] In marketing activities, there is a need to understand consumer behavior and competitor trends in real time and to propose the most suitable products and advertisements to individual consumers based on this data. However, there is a lack of methods to quickly and effectively analyze diverse consumer data and technologies to automatically propose personalized marketing strategies. Therefore, an efficient system is needed to increase consumer purchasing intent and maintain and improve competitiveness.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes means for collecting consumer data and analyzing consumer intentions, emotions, and trends using natural language processing technology; means for proposing optimal advertising transmission and budget management based on past advertising activity data; and means for monitoring the activities of competitors and predicting market changes. This enables effective product recommendations and optimized advertising delivery for individual consumers.

[0100] "Consumer data" refers to data that includes a variety of information used in marketing activities, such as consumer behavior, intentions, emotions, and purchase history.

[0101] "Natural language processing technology" is a technology that uses computers to understand and analyze human language, and is used for analyzing text data and understanding consumers' intentions and emotions.

[0102] "Advertising transmission" refers to the activity of notifying consumers of information about products and services, and is a means of delivering messages optimized based on consumers' interests.

[0103] "Budget management" is the process of optimizing the allocation of funds to advertising in marketing activities, with the aim of using resources efficiently.

[0104] "Competitor activity" refers to the activities and strategies of competitors within the same market. Understanding this information allows us to predict market changes and business opportunities.

[0105] "Product recommendation" is a technical method used to increase purchasing intent by presenting products and services that are most suitable for consumers based on their preferences.

[0106] "Ad delivery optimization" is the process in marketing activities to deliver advertisements to target consumers in the most effective way, with the aim of maximizing the effectiveness of the advertisements.

[0107] The system for realizing this invention is comprised of a combination of multiple advanced technologies. The server plays a central role in storing and analyzing diverse data collected from consumers. This data includes consumer purchase history, online behavior history, and social media reactions. This data is analyzed using natural language processing technology to extract consumer intentions, emotions, and trend information.

[0108] The server also references a database of past advertising activities and uses machine learning algorithms to suggest optimal advertising delivery strategies and budget management. Specifically, it has the ability to automatically generate effective product recommendations and promotional offers for each target consumer group. This function ensures that personalized advertisements are delivered to individual consumers.

[0109] On the device side, the resulting analytical information is provided to the user in a visual format. This includes intuitive data visualization through a dashboard and real-time suggestion notifications. Based on personalized information, users can quickly make marketing strategy decisions and evaluate and improve the effectiveness of each measure.

[0110] For example, if a consumer is found to have a tendency to purchase new electronic devices, the server will recommend the latest gadget models relevant to that consumer and offer special discounts. This system can improve the accuracy of product selection by using a generative AI model to set a prompt such as "Which product is best suited for this consumer?"

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server collects consumer behavior history, purchase history, and real-time data from social media. It receives data from various data sources as input and stores it in a database. During this process, data preprocessing, such as removing duplicate data and standardizing formats, is performed to maintain data integrity.

[0114] Step 2:

[0115] The server applies natural language processing techniques to the collected data to analyze consumer intent, sentiment, and trends. It receives text data as input and uses a natural language processing engine to obtain analysis results. Specifically, this includes text summarization and sentiment analysis.

[0116] Step 3:

[0117] The server analyzes past advertising data using machine learning algorithms to formulate the optimal advertising delivery strategy. It receives historical campaign data as input and trains a model to identify success factors. The output is the advertising delivery pattern most effective for the target consumer.

[0118] Step 4:

[0119] The server collects information on competitors' activities from time-series data and news feeds to predict market trends. It receives the latest industry data from various sources as input, analyzes it, and automatically generates reports to predict market changes.

[0120] Step 5:

[0121] The server creates personalized product suggestions and advertisements based on the consumer's profile. It receives analyzed consumer sentiment and purchase history as input, and uses a generative AI model to recommend products using the prompt "What product is best suited for this consumer?". The output is a personalized product offer for the user.

[0122] Step 6:

[0123] The terminal visually presents analysis results and product recommendations obtained from the server to the user. It receives analysis results from the server as input, visualizes the data on a user-friendly dashboard, and notifies the user in real time.

[0124] Step 7:

[0125] Users make quick decisions and adjust marketing strategies based on the information presented on their devices. As input, they refer to visual information and offers from their devices to gather material for developing their next marketing initiatives. The output is the planned marketing plan.

[0126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0127] This invention is a marketing support system that combines consumer data analysis with an emotion engine. The server collects consumer posts and reviews in real time through APIs of social media and online stores. This data is analyzed using natural language processing technology and an emotion engine to extract consumer intentions, emotions, and more detailed trend information. The emotion engine precisely recognizes emotional elements such as positive, negative, and neutral from consumer posts, and the server uses this to improve the accuracy of predicting consumer behavior.

[0128] These analysis results are compared with past campaign data, allowing for more effective suggestions regarding ad delivery and budget allocation. Users can receive suggested strategies from the server via their devices and flexibly adjust their marketing measures.

[0129] Furthermore, the server builds customer profiles through consumer purchase history and other data, and generates personalized messages and offers based on that information. These messages, incorporating the results of the emotion engine, accurately address customer expectations and circumstances, thereby improving customer engagement.

[0130] Furthermore, the system constantly monitors the actions of competitors and displays market trend reports on the device, including the results of competitive data analysis using an emotion engine. Users can utilize this to respond quickly to the competitive environment.

[0131] As a concrete example, a strategy is employed in which consumer comments on social media regarding a particular product are analyzed using an emotion engine, and advertisements are concentrated on the moment when positive emotions are at their peak. Such timely responses can maximize the effectiveness of marketing. In this way, the present invention realizes marketing support that accurately reflects consumer needs and emotions.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server collects real-time consumer posting data from social media platforms using APIs. This allows for the rapid acquisition of the latest consumer trends and opinions.

[0135] Step 2:

[0136] The server analyzes consumer posts collected using natural language processing technology to extract consumer intentions, interests, and behavioral patterns. The analysis results are then used for sentiment analysis in the next step.

[0137] Step 3:

[0138] The server applies a sentiment engine to the collected data, classifying the sentiment of each post into positive, negative, or neutral categories. This clarifies consumer sentiment trends.

[0139] Step 4:

[0140] The server integrates natural language processing and sentiment engine analysis results to gain a detailed understanding of consumer trends. It then displays the latest trend information as a dashboard on the user's device.

[0141] Step 5:

[0142] The server references past campaign data and leverages sentiment data to generate suggestions for optimizing ad delivery and budget allocation. This makes it possible to develop strategies that align with consumer emotions.

[0143] Step 6:

[0144] Users can view various suggestions displayed on the server's dashboard via their devices and adjust their marketing strategies accordingly. They can also make immediate modifications based on the server's suggestions as needed.

[0145] Step 7:

[0146] The server monitors the results of marketing initiatives and evaluates their effectiveness along with sentiment data. The evaluation results are analyzed for future initiatives and provided as feedback to the terminal.

[0147] Step 8:

[0148] Users utilize the evaluation results provided on their devices to make decisions regarding future strategies. Furthermore, users continuously gain insights based on sentiment data provided by the server, which helps them evolve their marketing strategies.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] In today's digital age, accurately analyzing consumer data and formulating more effective marketing strategies is crucial. However, traditional methods have struggled to efficiently collect data and conduct precise analyses of consumer emotions and behavior, making effective personalization difficult. Furthermore, quickly tracking competitors' activities and responding flexibly to market changes has also been a challenge.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0153] In this invention, the server includes means for collecting information and analyzing users' intentions, emotions, and behaviors using natural language processing technology; means for preprocessing data and classifying data using an emotion engine; and means for predicting user behavior and using machine learning models. This enables highly accurate analysis of consumer data, rapid formulation of marketing strategies, and flexible response to market changes.

[0154] "Consumer data" refers to all information generated by consumers on digital platforms, including purchase history, posts, and reviews.

[0155] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, making it possible to analyze text and classify emotions.

[0156] An "emotion engine" is a system that uses natural language processing to identify and classify emotions from a user's text data.

[0157] "Users" refers to individuals or groups who provide information through this system, and specifically to consumers who engage in purchasing behavior or online activities.

[0158] "Data preprocessing" refers to the process of removing noise and normalizing acquired data in order to convert it into an analyzable format.

[0159] A "machine learning model" is a collection of algorithms that learn patterns from data and use them for prediction and classification.

[0160] "Personalized notifications" refer to customized messages that provide specific information based on an individual user's profile and behavior.

[0161] A "competitive entity" refers to another legal entity that operates in the same market or industry and is in a competitive relationship with the other entity.

[0162] This invention is a system that utilizes an emotion engine in consumer data analysis to formulate effective marketing strategies. The system is primarily implemented using servers and terminals.

[0163] The server collects data via APIs from social media and online stores. This collected data is preprocessed using natural language processing libraries (e.g., spaCy, NLTK) and then analyzed by an emotion engine. The emotion engine uses BERT and other similar generative AI models to subdivide emotions into positive, negative, and neutral. This allows for a precise understanding of the emotions behind consumers' posts.

[0164] Based on the analysis results, the server uses machine learning models (e.g., Random Forest, XGBoost) to predict consumer behavior and generate optimal ad delivery and resource allocation strategies. The server also generates personalized notifications based on the user's purchase history and sends them to the device. These notifications include personalized content that reflects the individual consumer's profile and sentiment data.

[0165] Users can use interactive dashboards presented from the server via their devices to review and adjust the provided marketing strategies. The devices also display market trends and competitor data, enabling users to quickly develop strategies that adapt to constantly changing market conditions.

[0166] One concrete example involves analyzing consumer social media posts about a new product. The emotion engine analyzes these posts and concentrates ad delivery at times when positive emotions are heightened, maximizing marketing effectiveness. This implementation enables strategies that accurately capture consumer intentions and emotions.

[0167] Examples of prompts to input into a generative AI model are as follows:

[0168] "Please analyze consumer social media posts about the new product XX based on the following points: Clearly indicate changes in consumer intent and emotion, including sentiment classification (positive, negative, neutral) and trend analysis. Also, compare this data with past campaign data and create suggestions for the optimal timing of ad delivery."

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The server collects consumer posts and reviews via APIs from social media and online stores. API endpoints and authentication credentials are required as input. At this stage, the latest posted data from each platform is output. This operation enables real-time information retrieval.

[0172] Step 2:

[0173] The server preprocesses the collected data. Here, it takes the raw data collected as input and performs normalization and de-noise removal. This includes, for example, removing HTML tags and interpreting emojis. The preprocessed, clean text data is output. This process creates an analyzable dataset.

[0174] Step 3:

[0175] The server analyzes pre-processed data using an emotion engine. It receives clean, pre-processed data as input and uses a generative AI model (e.g., BERT) to classify its sentiment. The output is a sentiment label (positive, negative, neutral) for each post. This analysis allows for a highly accurate understanding of consumer sentiment.

[0176] Step 4:

[0177] The server predicts consumer behavior based on the analysis results. It uses sentiment-labeled data as input and performs prediction calculations using a machine learning model (e.g., Random Forest). The predicted consumer behavior and purchase intent are output. This prediction helps in developing appropriate strategies.

[0178] Step 5:

[0179] The server generates marketing strategies based on consumer behavior predictions and historical campaign data. It combines behavioral prediction data and historical data as input to propose the optimal ad delivery schedule and resource allocation. At this stage, it outputs guidelines for specific strategy formulation.

[0180] Step 6:

[0181] The terminal receives strategies generated by the server and presents them to the user. It receives strategy information sent from the server as input and displays it on the dashboard. As output, the user receives a real-time interface to view and adjust the strategies.

[0182] Step 7:

[0183] The server generates personalized notifications based on the consumer's purchase history. The input consists of purchase history and sentiment analysis data. Based on this, a message optimized for each individual user is automatically created and output as a notification. This step achieves consumer personalization.

[0184] Step 8:

[0185] The server analyzes market trends using information on competing companies and generates reports. The input information is data on the trends of competing companies. An emotion engine and market analysis tools are used for the analysis, resulting in a comprehensive market report. Users can view this report on their terminals and use it to inform their strategies.

[0186] (Application Example 2)

[0187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0188] Modern marketing requires accurately capturing the diverse intentions and emotions of consumers and effectively delivering advertisements in increasingly competitive markets. However, traditional methods have been unable to adequately analyze real-time changes in consumer emotions or the actions of competitors, posing challenges to the timely optimization of advertising campaigns. Therefore, a new system is needed to realize strategic marketing that takes consumer emotions into consideration.

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

[0190] In this invention, the server includes means for collecting consumer data and analyzing consumer intent, emotions, and trends using natural language processing technology; means for proposing optimal ad delivery and budget allocation based on past campaign data; and means for monitoring the activities of competitors and predicting market changes. This makes it possible to optimize advertising campaigns based on the emotional state of consumers.

[0191] "Consumer data" refers to a collection of information obtained from consumers' online activities, purchase history, and statements on social media.

[0192] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0193] "Consumer intent" refers to the purpose or motivation behind a consumer's actions or purchases.

[0194] "Emotions" refer to the positive, negative, or neutral feelings that consumers have towards a given situation or piece of information.

[0195] A "trend" is a temporary tendency or fashion that attracts the interest and attention of consumers.

[0196] "Advertising distribution" is the activity of presenting advertisements to a specific target audience and is part of a company's marketing strategy.

[0197] "Budget allocation" is a plan for distributing limited resources in the most optimal way, and is a method of financial management in advertising activities.

[0198] "Competitor activity" refers to the strategies and actions of other companies operating in the same market, and is a factor that influences the formulation of one's own company's strategy.

[0199] "Market changes" refer to major market movements such as fluctuations in consumer demand and changes in the competitive environment.

[0200] "Personalized messaging" refers to communication content that is tailored based on the individual consumer's preferences and behavioral history.

[0201] "Advertising campaign optimization" is the process of optimizing the content, timing, and targeting of advertisements in order to achieve marketing goals.

[0202] "Industry trends" refer to long-term changes or tendencies observed across a particular industry or sector.

[0203] The system that implements this application is built as an application that runs on a smartphone. The server collects consumer data in real time through APIs of social networking services and online stores. The collected data is analyzed using natural language processing technology and an emotion engine. This analysis uses natural language processing libraries such as NLTK and SpaCy, and an emotion analysis engine such as IBM Watson® Natural Language Understanding.

[0204] The server extracts consumer intent, emotions, and trends from the analysis results. Based on this, it proposes optimal ad delivery and budget allocation by comparing it with past campaign data. Furthermore, it monitors the activities of competitors and continuously updates industry trends. This information is sent to the user's device and helps optimize ad campaigns and generate personalized messages, especially based on the sentiment analysis results.

[0205] Users can review the provided suggestions and flexibly adjust advertising strategies through the terminal application. In this way, it is possible to achieve a timely marketing approach based on consumer emotions.

[0206] As a concrete example, during a summer sale, one beverage manufacturer analyzed consumer feedback on social media using the phrase "Refreshing Summer" and distributed limited-time coupon advertisements at the moment when positive sentiment surged. This method has been shown to improve marketing effectiveness.

[0207] An example of a prompt message is, "For this month's product campaign, perform sentiment analysis based on data obtained from social media and develop the optimal advertising strategy." This effectively supports decision-making by utilizing generative AI models.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server collects consumer data in real time using APIs from social media and online stores. This data includes consumer posts and reviews. The input is text data via API, and the output is raw data that can be analyzed.

[0211] Step 2:

[0212] The server uses natural language processing techniques to clean and structure the collected consumer data. It removes noise from the raw input data and performs part-of-speech analysis. The output is structured data suitable for sentiment analysis.

[0213] Step 3:

[0214] The server feeds naturally language-processed data into a sentiment analysis engine to identify consumer emotions (positive, negative, or neutral). The input is structured text data, and the output is each emotion label and its score.

[0215] Step 4:

[0216] The server generates an optimal ad delivery and budget allocation strategy by comparing sentiment analysis results with historical campaign data. Specifically, it analyzes sentiment fluctuations at each time point and suggests effective timing for ad investment. Inputs are sentiment labels and scores, and historical data, while output is strategy recommendation data.

[0217] Step 5:

[0218] The terminal receives strategic proposals from the server and presents them to the user in a dashboard format. The user can then adjust their advertising campaign based on this information. The input is strategic proposal data, and the output is visualized dashboard information.

[0219] Step 6:

[0220] Users adjust and execute advertising strategies via their devices. Specifically, they configure ad content and delivery timing based on the provided strategy and launch the actual campaign. Input is the user's instructions, and output is the updated campaign settings information.

[0221] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0222] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0223] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0227] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0228] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0229] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0230] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0231] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0232] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0233] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0234] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0235] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0236] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0237] This invention is a system designed to support marketing activities and primarily operates through a program running on a server. The server collects and analyzes diverse consumer data. Specifically, it acquires data in real time from social media and online stores and analyzes consumer intentions and emotions using natural language processing technology. Using these results, the server predicts trends and provides them to the user's device as visual information.

[0238] Furthermore, the server optimizes ad delivery and budget allocation based on past campaign data. This includes analyzing the success factors of similar campaigns and applying them to the current advertising strategy.

[0239] Regarding the activities of competing companies, the server collects data from specific sources, analyzes it, and predicts market changes. These analysis results can be viewed on the terminal to help improve marketing strategies.

[0240] To enable customized marketing for each customer, the server automatically generates personalized messages and offers based on each customer's profile. This allows users to attract customers more effectively.

[0241] Finally, after the marketing campaign is implemented, the server analyzes its effectiveness based on the data obtained and proposes the next strategy. Users receive this information in real time through their devices, allowing them to quickly take action in line with market trends.

[0242] As a concrete example, when a store launches a new product, the server analyzes data from similar past successful campaigns and suggests the optimal advertising media and target audience to the user's terminal. Based on the provided report, the user can quickly adjust the campaign content to maximize its effectiveness. This system dramatically improves the accuracy and speed of marketing strategies.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server collects real-time data through APIs from social media platforms and online stores. This data includes consumer posts, reviews, and purchase history.

[0246] Step 2:

[0247] The server uses natural language processing technology to analyze collected consumer data and extract consumer intentions, emotions, and trends. This analysis identifies each consumer's interests and concerns.

[0248] Step 3:

[0249] The server uses the analyzed data to compare it with past campaign data and proposes optimized ad delivery and budget allocation. It extracts the characteristics of successful campaigns and suggests similar strategies.

[0250] Step 4:

[0251] The server crawls the activities of competitors and updates models that predict market changes. It provides information to re-evaluate marketing strategies while taking into account changes in the competitive landscape.

[0252] Step 5:

[0253] The server generates personalized messages and offers based on customer profiles, enabling communication optimized for each individual customer.

[0254] Step 6:

[0255] The server analyzes the results of implemented marketing initiatives and measures their effectiveness. The analysis results are displayed visually on a dashboard.

[0256] Step 7:

[0257] Users can review reports generated by the server via their devices and decide on their next strategy. Based on the suggested improvements, users can quickly adjust their marketing measures.

[0258] (Example 1)

[0259] Next, we will describe Example 1. 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."

[0260] Traditional marketing systems struggled to grasp individual intentions and emotions in detail, making it difficult to provide timely and appropriate information to target customers. Furthermore, they failed to fully utilize data from past sales promotion activities, making optimal advertising distribution and budget allocation challenging. Additionally, the lack of objective criteria for efficiently analyzing the trends of similar businesses and predicting market changes hindered the rapid improvement of business strategies.

[0261] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0262] This invention includes a server that collects personal data from a digital platform and analyzes individuals' intentions, emotions, and trends using natural language processing technology; means for proposing optimal advertising implementation and budget allocation based on past sales promotion activity data; and means for monitoring the behavior of similar businesses and predicting changes in the business environment. This enables personalized information provision, improves the efficiency of advertising delivery strategies and budget allocation, and allows for rapid strategic adjustments in the market.

[0263] A "digital platform" is an internet-based environment for collecting consumer data online, including social media and online stores.

[0264] "Personal data" refers to information that indicates consumer behavior and trends, and includes data that identifies a specific individual, such as online purchase history and interaction data.

[0265] "Natural language processing technology" is an information processing technology that uses computers to analyze human language and understand its linguistic features, emotions, and intentions.

[0266] "Sales promotion activity data" refers to records related to advertising campaigns and marketing activities conducted in the past, and is data that can be used for measuring effectiveness and making improvements.

[0267] "Competitors of the same type" refers to competing companies that provide similar goods or services in the same industry or market.

[0268] "Customized information" refers to messages and offers that are appropriately tailored based on the individual consumer's needs and profile.

[0269] "Visual tools" are software or technologies used to visually present the results of an analysis, including charts and graphs.

[0270] Modes for carrying out the invention

[0271] This invention is an advanced system for optimizing marketing strategies, and its main components include a server, terminals, and users. Specific implementation methods are described below.

[0272] The server first collects data from others on digital platforms. This includes using Python scripts to retrieve data from social media APIs and online stores. The collected data is stored in JSON format and later used for analysis.

[0273] Next, the server analyzes the collected data using natural language processing technology. By using the Google Cloud Natural Language API, it efficiently extracts individual intentions, emotions, and trends. Through this data analysis, the server reveals consumers' latent needs.

[0274] Data processing libraries such as Pandas and NumPy are used to analyze past sales promotion activity data. Based on this, the server proposes the optimal advertising strategy and budget allocation to the terminal. For example, it selects the optimal media based on the conversion rate of advertisements.

[0275] To analyze the activities of competitors, the server uses RSS readers and news APIs to collect and analyze data from similar businesses. This allows for accurate prediction of market fluctuations and the competitive landscape.

[0276] The server uses a generative AI model to generate customized messages. For example, by inputting "Create a special offer message for female customers in their 20s" as a prompt based on a specific consumer profile, a message tailored to the purpose will be generated.

[0277] Finally, the server displays the analysis results visually using a visual tool. By using visualization libraries such as Matplotlib and sending the generated charts and graphs to the terminal, users can utilize this information in real time and quickly adjust their marketing strategies.

[0278] This invention enables users to conduct more precise and effective marketing activities, thereby enhancing their competitive advantage in the market.

[0279] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0280] Step 1:

[0281] The server collects personal data from digital platforms. Specifically, it uses a Python script to send requests to social networking service (SNS) APIs and retrieves consumer posting data in JSON format. The input is the SNS API endpoint, and the output is the retrieved JSON data. The server stores this data as a base database for analysis.

[0282] Step 2:

[0283] The server analyzes the collected data using natural language processing technology. It sends the data to the Google Cloud Natural Language API and performs operations to analyze the consumers' intentions and emotions. The input is the JSON data collected in Step 1, and the output is the metadata of the analyzed intentions and emotions. This enables obtaining information regarding consumers' interests and demand predictions.

[0284] Step 3:

[0285] The server analyzes the optimal strategy using past sales promotion activity data. It uses Pandas to read the past campaign records and performs statistical analysis with NumPy. The input is the past campaign data in CSV format, and the output is the optimal promotion implementation plan and budget allocation plan. The calculated data is sent to the terminal as a proposal.

[0286] Step 4:

[0287] The server monitors the trends of competing companies and predicts changes in the business environment. It collects the latest competitive information from RSS feeds and news APIs and performs analysis. The input is the information from RSS feeds and news APIs, and the output is the prediction of competitive trends and market changes. This prediction result is also sent to the terminal for the user to utilize in formulating strategies.

[0288] Step 5:

[0289] The server generates personalized messages using a generative AI model. Based on a specific customer profile, it inputs a prompt sentence into the generative AI model. The input is a prompt sentence such as "Please create a special offer message for female customers in their 20s", and the output is the generated message. Effective marketing messages are provided to the user.

[0290] Step 6:

[0291] The server visually represents the analysis results using a visual tool and sends them to the terminal. For example, it uses Matplotlib to convert the data into charts and graphs. The input is the analysis results from steps 2 to 5, and the output is the visualized data. The terminal displays this, allowing the user to utilize the information in real time.

[0292] (Application Example 1)

[0293] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0294] In marketing activities, there is a need to understand consumer behavior and competitor trends in real time and to propose the most suitable products and advertisements to individual consumers based on this data. However, there is a lack of methods to quickly and effectively analyze diverse consumer data and technologies to automatically propose personalized marketing strategies. Therefore, an efficient system is needed to increase consumer purchasing intent and maintain and improve competitiveness.

[0295] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0296] In this invention, the server includes means for collecting consumer data and analyzing consumer intentions, emotions, and trends using natural language processing technology; means for proposing optimal advertising transmission and budget management based on past advertising activity data; and means for monitoring the activities of competitors and predicting market changes. This enables effective product recommendations and optimized advertising delivery for individual consumers.

[0297] "Consumer data" refers to data that includes a variety of information used in marketing activities, such as consumer behavior, intentions, emotions, and purchase history.

[0298] "Natural language processing technology" is a technology that uses computers to understand and analyze human language, and is used for analyzing text data and understanding consumers' intentions and emotions.

[0299] "Advertising transmission" refers to the activity of notifying consumers of information about products and services, and is a means of delivering messages optimized based on consumers' interests.

[0300] "Budget management" is the process of optimizing the allocation of funds to advertising in marketing activities, with the aim of using resources efficiently.

[0301] "Competitor activity" refers to the activities and strategies of competitors within the same market. Understanding this information allows us to predict market changes and business opportunities.

[0302] "Product recommendation" is a technical method used to increase purchasing intent by presenting products and services that are most suitable for consumers based on their preferences.

[0303] "Ad delivery optimization" is the process in marketing activities to deliver advertisements to target consumers in the most effective way, with the aim of maximizing the effectiveness of the advertisements.

[0304] The system for realizing this invention is comprised of a combination of multiple advanced technologies. The server plays a central role in storing and analyzing diverse data collected from consumers. This data includes consumer purchase history, online behavior history, and social media reactions. This data is analyzed using natural language processing technology to extract consumer intentions, emotions, and trend information.

[0305] The server also refers to the database of past promotional activities and uses machine learning algorithms to propose optimal advertising distribution strategies and budget management. Specifically, it has a function to automatically generate effective product recommendations and sales promotion offers for each target consumer group. With this function, personalized advertisements are delivered to individual consumers.

[0306] On the terminal side, the resulting analysis information is provided to the user in a visual form. This includes intuitive data visualization through a dashboard and real-time recommendation notifications. Based on the individualized information, the user can make quick decisions on marketing strategies and evaluate and improve the effects of each measure.

[0307] As a specific example, if it is found that a certain consumer has a tendency to purchase new electronic devices, the server recommends the latest models of gadgets related to that consumer and proposes special discounts for them. In this system, by setting a prompt of "which product is most suitable for this consumer" using a generative AI model, the accuracy in product selection can be improved.

[0308] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0309] Step 1:

[0310] The server collects consumers' behavior history, purchase history, and real-time data from SNS. As input, it receives data from various data sources and stores it in the database. At this time, in order to maintain data consistency, data preprocessing such as duplicate data elimination and format unification is performed.

[0311] Step 2:

[0312] The server applies natural language processing techniques to the collected data to analyze consumer intent, sentiment, and trends. It receives text data as input and uses a natural language processing engine to obtain analysis results. Specifically, this includes text summarization and sentiment analysis.

[0313] Step 3:

[0314] The server analyzes past advertising data using machine learning algorithms to formulate the optimal advertising delivery strategy. It receives historical campaign data as input and trains a model to identify success factors. The output is the advertising delivery pattern most effective for the target consumer.

[0315] Step 4:

[0316] The server collects information on competitors' activities from time-series data and news feeds to predict market trends. It receives the latest industry data from various sources as input, analyzes it, and automatically generates reports to predict market changes.

[0317] Step 5:

[0318] The server creates personalized product suggestions and advertisements based on the consumer's profile. It receives analyzed consumer sentiment and purchase history as input, and uses a generative AI model to recommend products using the prompt "What product is best suited for this consumer?". The output is a personalized product offer for the user.

[0319] Step 6:

[0320] The terminal visually presents analysis results and product recommendations obtained from the server to the user. It receives analysis results from the server as input, visualizes the data on a user-friendly dashboard, and notifies the user in real time.

[0321] Step 7:

[0322] Users make quick decisions and adjust marketing strategies based on the information presented on their devices. As input, they refer to visual information and offers from their devices to gather material for developing their next marketing initiatives. The output is the planned marketing plan.

[0323] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0324] This invention is a marketing support system that combines consumer data analysis with an emotion engine. The server collects consumer posts and reviews in real time through APIs of social media and online stores. This data is analyzed using natural language processing technology and an emotion engine to extract consumer intentions, emotions, and more detailed trend information. The emotion engine precisely recognizes emotional elements such as positive, negative, and neutral from consumer posts, and the server uses this to improve the accuracy of predicting consumer behavior.

[0325] These analysis results are compared with past campaign data, allowing for more effective suggestions regarding ad delivery and budget allocation. Users can receive suggested strategies from the server via their devices and flexibly adjust their marketing measures.

[0326] Furthermore, the server builds customer profiles through consumer purchase history and other data, and generates personalized messages and offers based on that information. These messages, incorporating the results of the emotion engine, accurately address customer expectations and circumstances, thereby improving customer engagement.

[0327] Furthermore, the system constantly monitors the actions of competitors and displays market trend reports on the device, including the results of competitive data analysis using an emotion engine. Users can utilize this to respond quickly to the competitive environment.

[0328] As a concrete example, a strategy is employed in which consumer comments on social media regarding a particular product are analyzed using an emotion engine, and advertisements are concentrated on the moment when positive emotions are at their peak. Such timely responses can maximize the effectiveness of marketing. In this way, the present invention realizes marketing support that accurately reflects consumer needs and emotions.

[0329] The following describes the processing flow.

[0330] Step 1:

[0331] The server collects real-time consumer posting data from social media platforms using APIs. This allows for the rapid acquisition of the latest consumer trends and opinions.

[0332] Step 2:

[0333] The server analyzes consumer posts collected using natural language processing technology to extract consumer intentions, interests, and behavioral patterns. The analysis results are then used for sentiment analysis in the next step.

[0334] Step 3:

[0335] The server applies a sentiment engine to the collected data, classifying the sentiment of each post into positive, negative, or neutral categories. This clarifies consumer sentiment trends.

[0336] Step 4:

[0337] The server integrates natural language processing and sentiment engine analysis results to gain a detailed understanding of consumer trends. It then displays the latest trend information as a dashboard on the user's device.

[0338] Step 5:

[0339] The server references past campaign data and leverages sentiment data to generate suggestions for optimizing ad delivery and budget allocation. This makes it possible to develop strategies that align with consumer emotions.

[0340] Step 6:

[0341] Users can view various suggestions displayed on the server's dashboard via their devices and adjust their marketing strategies accordingly. They can also make immediate modifications based on the server's suggestions as needed.

[0342] Step 7:

[0343] The server monitors the results of marketing initiatives and evaluates their effectiveness along with sentiment data. The evaluation results are analyzed for future initiatives and provided as feedback to the terminal.

[0344] Step 8:

[0345] Users utilize the evaluation results provided on their devices to make decisions regarding future strategies. Furthermore, users continuously gain insights based on sentiment data provided by the server, which helps them evolve their marketing strategies.

[0346] (Example 2)

[0347] Next, we will describe Example 2. 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".

[0348] In today's digital age, accurately analyzing consumer data and formulating more effective marketing strategies is crucial. However, traditional methods have struggled to efficiently collect data and conduct precise analyses of consumer emotions and behavior, making effective personalization difficult. Furthermore, quickly tracking competitors' activities and responding flexibly to market changes has also been a challenge.

[0349] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0350] In this invention, the server includes means for collecting information and analyzing users' intentions, emotions, and behaviors using natural language processing technology; means for preprocessing data and classifying data using an emotion engine; and means for predicting user behavior and using machine learning models. This enables highly accurate analysis of consumer data, rapid formulation of marketing strategies, and flexible response to market changes.

[0351] "Consumer data" refers to all information generated by consumers on digital platforms, including purchase history, posts, and reviews.

[0352] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, making it possible to analyze text and classify emotions.

[0353] An "emotion engine" is a system that uses natural language processing to identify and classify emotions from a user's text data.

[0354] "Users" refers to individuals or groups who provide information through this system, and specifically to consumers who engage in purchasing behavior or online activities.

[0355] "Data preprocessing" refers to the process of removing noise and normalizing acquired data in order to convert it into an analyzable format.

[0356] A "machine learning model" is a collection of algorithms that learn patterns from data and use them for prediction and classification.

[0357] "Personalized notifications" refer to customized messages that provide specific information based on an individual user's profile and behavior.

[0358] A "competitive entity" refers to another legal entity that operates in the same market or industry and is in a competitive relationship with the other entity.

[0359] This invention is a system that utilizes an emotion engine in consumer data analysis to formulate effective marketing strategies. The system is primarily implemented using servers and terminals.

[0360] The server collects data via APIs from social media and online stores. This collected data is preprocessed using natural language processing libraries (e.g., spaCy, NLTK) and then analyzed by an emotion engine. The emotion engine uses BERT and other similar generative AI models to subdivide emotions into positive, negative, and neutral. This allows for a precise understanding of the emotions behind consumers' posts.

[0361] Based on the analysis results, the server uses machine learning models (e.g., Random Forest, XGBoost) to predict consumer behavior and generate optimal ad delivery and resource allocation strategies. The server also generates personalized notifications based on the user's purchase history and sends them to the device. These notifications include personalized content that reflects the individual consumer's profile and sentiment data.

[0362] Users can use interactive dashboards presented from the server via their devices to review and adjust the provided marketing strategies. The devices also display market trends and competitor data, enabling users to quickly develop strategies that adapt to constantly changing market conditions.

[0363] One concrete example involves analyzing consumer social media posts about a new product. The emotion engine analyzes these posts and concentrates ad delivery at times when positive emotions are heightened, maximizing marketing effectiveness. This implementation enables strategies that accurately capture consumer intentions and emotions.

[0364] Examples of prompts to input into a generative AI model are as follows:

[0365] "Please analyze consumer social media posts about the new product XX based on the following points: Clearly indicate changes in consumer intent and emotion, including sentiment classification (positive, negative, neutral) and trend analysis. Also, compare this data with past campaign data and create suggestions for the optimal timing of ad delivery."

[0366] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0367] Step 1:

[0368] The server collects consumer posts and reviews via APIs from social media and online stores. API endpoints and authentication credentials are required as input. At this stage, the latest posted data from each platform is output. This operation enables real-time information retrieval.

[0369] Step 2:

[0370] The server preprocesses the collected data. Here, it takes the raw data collected as input and performs normalization and de-noise removal. This includes, for example, removing HTML tags and interpreting emojis. The preprocessed, clean text data is output. This process creates an analyzable dataset.

[0371] Step 3:

[0372] The server analyzes pre-processed data using an emotion engine. It receives clean, pre-processed data as input and uses a generative AI model (e.g., BERT) to classify its sentiment. The output is a sentiment label (positive, negative, neutral) for each post. This analysis allows for a highly accurate understanding of consumer sentiment.

[0373] Step 4:

[0374] The server predicts consumer behavior based on the analysis results. It uses sentiment-labeled data as input and performs prediction calculations using a machine learning model (e.g., Random Forest). The predicted consumer behavior and purchase intent are output. This prediction helps in developing appropriate strategies.

[0375] Step 5:

[0376] The server generates marketing strategies based on consumer behavior predictions and historical campaign data. It combines behavioral prediction data and historical data as input to propose the optimal ad delivery schedule and resource allocation. At this stage, it outputs guidelines for specific strategy formulation.

[0377] Step 6:

[0378] The terminal receives strategies generated by the server and presents them to the user. It receives strategy information sent from the server as input and displays it on the dashboard. As output, the user receives a real-time interface to view and adjust the strategies.

[0379] Step 7:

[0380] The server generates personalized notifications based on the consumer's purchase history. The input consists of purchase history and sentiment analysis data. Based on this, a message optimized for each individual user is automatically created and output as a notification. This step achieves consumer personalization.

[0381] Step 8:

[0382] The server analyzes market trends using information on competing companies and generates reports. The input information is data on the trends of competing companies. An emotion engine and market analysis tools are used for the analysis, resulting in a comprehensive market report. Users can view this report on their terminals and use it to inform their strategies.

[0383] (Application Example 2)

[0384] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0385] Modern marketing requires accurately capturing the diverse intentions and emotions of consumers and effectively delivering advertisements in increasingly competitive markets. However, traditional methods have been unable to adequately analyze real-time changes in consumer emotions or the actions of competitors, posing challenges to the timely optimization of advertising campaigns. Therefore, a new system is needed to realize strategic marketing that takes consumer emotions into consideration.

[0386] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0387] In this invention, the server includes means for collecting consumer data and analyzing consumer intent, emotions, and trends using natural language processing technology; means for proposing optimal ad delivery and budget allocation based on past campaign data; and means for monitoring the activities of competitors and predicting market changes. This makes it possible to optimize advertising campaigns based on the emotional state of consumers.

[0388] "Consumer data" refers to a collection of information obtained from consumers' online activities, purchase history, and statements on social media.

[0389] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0390] "Consumer intent" refers to the purpose or motivation behind a consumer's actions or purchases.

[0391] "Emotions" refer to the positive, negative, or neutral feelings that consumers have towards a given situation or piece of information.

[0392] A "trend" is a temporary tendency or fashion that attracts the interest and attention of consumers.

[0393] "Advertising distribution" is the activity of presenting advertisements to a specific target audience and is part of a company's marketing strategy.

[0394] "Budget allocation" is a plan for distributing limited resources in the most optimal way, and is a method of financial management in advertising activities.

[0395] "Competitor activity" refers to the strategies and actions of other companies operating in the same market, and is a factor that influences the formulation of one's own company's strategy.

[0396] "Market changes" refer to major market movements such as fluctuations in consumer demand and changes in the competitive environment.

[0397] "Personalized messaging" refers to communication content that is tailored based on the individual consumer's preferences and behavioral history.

[0398] "Advertising campaign optimization" is the process of optimizing the content, timing, and targeting of advertisements in order to achieve marketing goals.

[0399] "Industry trends" refer to long-term changes or tendencies observed across a particular industry or sector.

[0400] The system that implements this application is built as an application that runs on a smartphone. The server collects consumer data in real time through APIs from social networking services and online stores. The collected data is analyzed using natural language processing technology and an emotion engine. This analysis uses natural language processing libraries such as NLTK and SpaCy, and an emotion analysis engine such as IBM Watson Natural Language Understanding.

[0401] The server extracts consumer intent, emotions, and trends from the analysis results. Based on this, it proposes optimal ad delivery and budget allocation by comparing it with past campaign data. Furthermore, it monitors the activities of competitors and continuously updates industry trends. This information is sent to the user's device and helps optimize ad campaigns and generate personalized messages, especially based on the sentiment analysis results.

[0402] Users can review the provided suggestions and flexibly adjust advertising strategies through the terminal application. In this way, it is possible to achieve a timely marketing approach based on consumer emotions.

[0403] As a concrete example, during a summer sale, one beverage manufacturer analyzed consumer feedback on social media using the phrase "Refreshing Summer" and distributed limited-time coupon advertisements at the moment when positive sentiment surged. This method has been shown to improve marketing effectiveness.

[0404] An example of a prompt message is, "For this month's product campaign, perform sentiment analysis based on data obtained from social media and develop the optimal advertising strategy." This effectively supports decision-making by utilizing generative AI models.

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The server collects consumer data in real time using APIs from social media and online stores. This data includes consumer posts and reviews. The input is text data via API, and the output is raw data that can be analyzed.

[0408] Step 2:

[0409] The server uses natural language processing techniques to clean and structure the collected consumer data. It removes noise from the raw input data and performs part-of-speech analysis. The output is structured data suitable for sentiment analysis.

[0410] Step 3:

[0411] The server feeds naturally language-processed data into a sentiment analysis engine to identify consumer emotions (positive, negative, or neutral). The input is structured text data, and the output is each emotion label and its score.

[0412] Step 4:

[0413] The server generates an optimal ad delivery and budget allocation strategy by comparing sentiment analysis results with historical campaign data. Specifically, it analyzes sentiment fluctuations at each time point and suggests effective timing for ad investment. Inputs are sentiment labels and scores, and historical data, while output is strategy recommendation data.

[0414] Step 5:

[0415] The terminal receives strategic proposals from the server and presents them to the user in a dashboard format. The user can then adjust their advertising campaign based on this information. The input is strategic proposal data, and the output is visualized dashboard information.

[0416] Step 6:

[0417] Users adjust and execute advertising strategies via their devices. Specifically, they configure ad content and delivery timing based on the provided strategy and launch the actual campaign. Input is the user's instructions, and output is the updated campaign settings information.

[0418] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0419] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0420] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0424] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0425] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0426] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0427] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0428] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0429] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0430] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0431] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0432] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0433] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0434] This invention is a system designed to support marketing activities and primarily operates through a program running on a server. The server collects and analyzes diverse consumer data. Specifically, it acquires data in real time from social media and online stores and analyzes consumer intentions and emotions using natural language processing technology. Using these results, the server predicts trends and provides them to the user's device as visual information.

[0435] Furthermore, the server optimizes ad delivery and budget allocation based on past campaign data. This includes analyzing the success factors of similar campaigns and applying them to the current advertising strategy.

[0436] Regarding the activities of competing companies, the server collects data from specific sources, analyzes it, and predicts market changes. These analysis results can be viewed on the terminal to help improve marketing strategies.

[0437] To enable customized marketing for each customer, the server automatically generates personalized messages and offers based on each customer's profile. This allows users to attract customers more effectively.

[0438] Finally, after the marketing campaign is implemented, the server analyzes its effectiveness based on the data obtained and proposes the next strategy. Users receive this information in real time through their devices, allowing them to quickly take action in line with market trends.

[0439] As a concrete example, when a store launches a new product, the server analyzes data from similar past successful campaigns and suggests the optimal advertising media and target audience to the user's terminal. Based on the provided report, the user can quickly adjust the campaign content to maximize its effectiveness. This system dramatically improves the accuracy and speed of marketing strategies.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] The server collects real-time data through APIs from social media platforms and online stores. This data includes consumer posts, reviews, and purchase history.

[0443] Step 2:

[0444] The server uses natural language processing technology to analyze collected consumer data and extract consumer intentions, emotions, and trends. This analysis identifies each consumer's interests and concerns.

[0445] Step 3:

[0446] The server uses the analyzed data to compare it with past campaign data and proposes optimized ad delivery and budget allocation. It extracts the characteristics of successful campaigns and suggests similar strategies.

[0447] Step 4:

[0448] The server crawls the activities of competitors and updates models that predict market changes. It provides information to re-evaluate marketing strategies while taking into account changes in the competitive landscape.

[0449] Step 5:

[0450] The server generates personalized messages and offers based on customer profiles, enabling communication optimized for each individual customer.

[0451] Step 6:

[0452] The server analyzes the results of implemented marketing initiatives and measures their effectiveness. The analysis results are displayed visually on a dashboard.

[0453] Step 7:

[0454] Users can review reports generated by the server via their devices and decide on their next strategy. Based on the suggested improvements, users can quickly adjust their marketing measures.

[0455] (Example 1)

[0456] Next, we will describe Example 1. 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."

[0457] Traditional marketing systems struggled to grasp individual intentions and emotions in detail, making it difficult to provide timely and appropriate information to target customers. Furthermore, they failed to fully utilize data from past sales promotion activities, making optimal advertising distribution and budget allocation challenging. Additionally, the lack of objective criteria for efficiently analyzing the trends of similar businesses and predicting market changes hindered the rapid improvement of business strategies.

[0458] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0459] This invention includes a server that collects personal data from a digital platform and analyzes individuals' intentions, emotions, and trends using natural language processing technology; means for proposing optimal advertising implementation and budget allocation based on past sales promotion activity data; and means for monitoring the behavior of similar businesses and predicting changes in the business environment. This enables personalized information provision, improves the efficiency of advertising delivery strategies and budget allocation, and allows for rapid strategic adjustments in the market.

[0460] A "digital platform" is an internet-based environment for collecting consumer data online, including social media and online stores.

[0461] "Personal data" refers to information that indicates consumer behavior and trends, and includes data that identifies a specific individual, such as online purchase history and interaction data.

[0462] "Natural language processing technology" is an information processing technology that uses computers to analyze human language and understand its linguistic features, emotions, and intentions.

[0463] "Sales promotion activity data" refers to records related to advertising campaigns and marketing activities conducted in the past, and is data that can be used for measuring effectiveness and making improvements.

[0464] "Competitors of the same type" refers to competing companies that provide similar goods or services in the same industry or market.

[0465] "Customized information" refers to messages and offers that are appropriately tailored based on the individual consumer's needs and profile.

[0466] "Visual tools" are software or technologies used to visually present the results of an analysis, including charts and graphs.

[0467] Modes for carrying out the invention

[0468] This invention is an advanced system for optimizing marketing strategies, and its main components include a server, terminals, and users. Specific implementation methods are described below.

[0469] The server first collects data from others on digital platforms. This includes using Python scripts to retrieve data from social media APIs and online stores. The collected data is stored in JSON format and later used for analysis.

[0470] Next, the server analyzes the collected data using natural language processing technology. By using the Google Cloud Natural Language API, it efficiently extracts individual intentions, emotions, and trends. Through this data analysis, the server reveals consumers' latent needs.

[0471] Data processing libraries such as Pandas and NumPy are used to analyze past sales promotion activity data. Based on this, the server proposes the optimal advertising strategy and budget allocation to the terminal. For example, it selects the optimal media based on the conversion rate of advertisements.

[0472] To analyze the activities of competitors, the server uses RSS readers and news APIs to collect and analyze data from similar businesses. This allows for accurate prediction of market fluctuations and the competitive landscape.

[0473] The server uses a generative AI model to generate customized messages. For example, by inputting "Create a special offer message for female customers in their 20s" as a prompt based on a specific consumer profile, a message tailored to the purpose will be generated.

[0474] Finally, the server displays the analysis results visually using a visual tool. By using visualization libraries such as Matplotlib and sending the generated charts and graphs to the terminal, users can utilize this information in real time and quickly adjust their marketing strategies.

[0475] This invention enables users to conduct more precise and effective marketing activities, thereby enhancing their competitive advantage in the market.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The server collects personal data from digital platforms. Specifically, it uses a Python script to send requests to social networking service (SNS) APIs and retrieves consumer posting data in JSON format. The input is the SNS API endpoint, and the output is the retrieved JSON data. The server stores this data as a base database for analysis.

[0479] Step 2:

[0480] The server analyzes the collected data using natural language processing technology. It sends the data to the Google Cloud Natural Language API to analyze consumer intent and sentiment. The input is the JSON data collected in step 1, and the output is metadata of the analyzed intent and sentiment. This provides information about consumer interests and demand forecasting.

[0481] Step 3:

[0482] The server analyzes the optimal strategy using past sales promotion activity data. It uses Pandas to read past campaign records and NumPy to perform statistical analysis. The input is historical campaign data in CSV format, and the output is an optimal advertising plan and budget allocation proposal. The calculated data is sent to the terminal as a suggestion.

[0483] Step 4:

[0484] The server monitors the activities of competitors and predicts changes in the business environment. It collects and analyzes the latest competitive information from RSS feeds and news APIs. Input is information from RSS feeds and news APIs, and output is competitive trends and market fluctuation predictions. These prediction results are also sent to terminals, which users can use for strategic planning.

[0485] Step 5:

[0486] The server generates personalized messages using a generative AI model. Based on a specific customer profile, prompt sentences are input to the generative AI model. The input is a prompt sentence such as "Create a special offer message for female customers in their 20s," and the output is the generated message. This provides users with effective marketing messages.

[0487] Step 6:

[0488] The server visually represents the analysis results using a visual tool and sends them to the terminal. For example, it uses Matplotlib to convert the data into charts and graphs. The input is the analysis results from steps 2 to 5, and the output is the visualized data. The terminal displays this, allowing the user to utilize the information in real time.

[0489] (Application Example 1)

[0490] Next, we will explain Application Example 1. In the following explanation, 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."

[0491] In marketing activities, there is a need to understand consumer behavior and competitor trends in real time and to propose the most suitable products and advertisements to individual consumers based on this data. However, there is a lack of methods to quickly and effectively analyze diverse consumer data and technologies to automatically propose personalized marketing strategies. Therefore, an efficient system is needed to increase consumer purchasing intent and maintain and improve competitiveness.

[0492] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0493] In this invention, the server includes means for collecting consumer data and analyzing consumer intentions, emotions, and trends using natural language processing technology; means for proposing optimal advertising transmission and budget management based on past advertising activity data; and means for monitoring the activities of competitors and predicting market changes. This enables effective product recommendations and optimized advertising delivery for individual consumers.

[0494] "Consumer data" refers to data that includes a variety of information used in marketing activities, such as consumer behavior, intentions, emotions, and purchase history.

[0495] "Natural language processing technology" is a technology that uses computers to understand and analyze human language, and is used for analyzing text data and understanding consumers' intentions and emotions.

[0496] "Advertising transmission" refers to the activity of notifying consumers of information about products and services, and is a means of delivering messages optimized based on consumers' interests.

[0497] "Budget management" is the process of optimizing the allocation of funds to advertising in marketing activities, with the aim of using resources efficiently.

[0498] "Competitor activity" refers to the activities and strategies of competitors within the same market. Understanding this information allows us to predict market changes and business opportunities.

[0499] "Product recommendation" is a technical method used to increase purchasing intent by presenting products and services that are most suitable for consumers based on their preferences.

[0500] "Ad delivery optimization" is the process in marketing activities to deliver advertisements to target consumers in the most effective way, with the aim of maximizing the effectiveness of the advertisements.

[0501] The system for realizing this invention is comprised of a combination of multiple advanced technologies. The server plays a central role in storing and analyzing diverse data collected from consumers. This data includes consumer purchase history, online behavior history, and social media reactions. This data is analyzed using natural language processing technology to extract consumer intentions, emotions, and trend information.

[0502] The server also references a database of past advertising activities and uses machine learning algorithms to suggest optimal advertising delivery strategies and budget management. Specifically, it has the ability to automatically generate effective product recommendations and promotional offers for each target consumer group. This function ensures that personalized advertisements are delivered to individual consumers.

[0503] On the device side, the resulting analytical information is provided to the user in a visual format. This includes intuitive data visualization through a dashboard and real-time suggestion notifications. Based on personalized information, users can quickly make marketing strategy decisions and evaluate and improve the effectiveness of each measure.

[0504] For example, if a consumer is found to have a tendency to purchase new electronic devices, the server will recommend the latest gadget models relevant to that consumer and offer special discounts. This system can improve the accuracy of product selection by using a generative AI model to set a prompt such as "Which product is best suited for this consumer?"

[0505] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0506] Step 1:

[0507] The server collects consumer behavior history, purchase history, and real-time data from social media. It receives data from various data sources as input and stores it in a database. During this process, data preprocessing, such as removing duplicate data and standardizing formats, is performed to maintain data integrity.

[0508] Step 2:

[0509] The server applies natural language processing techniques to the collected data to analyze consumer intentions, sentiments, and trends. It receives text data as input and uses a natural language processing engine to obtain analysis results. Specifically, this includes text summarization and sentiment analysis.

[0510] Step 3:

[0511] The server analyzes past advertising data using machine learning algorithms to formulate the optimal advertising delivery strategy. It receives historical campaign data as input and trains a model to identify success factors. The output is the advertising delivery pattern most effective for the target consumer.

[0512] Step 4:

[0513] The server collects information on competitors' activities from time-series data and news feeds to predict market trends. It receives the latest industry data from various sources as input, analyzes it, and automatically generates reports to predict market changes.

[0514] Step 5:

[0515] The server creates personalized product suggestions and advertisements based on the consumer's profile. It receives analyzed consumer sentiment and purchase history as input, and uses a generative AI model to recommend products using the prompt "What product is best suited for this consumer?". The output is a personalized product offer for the user.

[0516] Step 6:

[0517] The terminal visually presents analysis results and product recommendations obtained from the server to the user. It receives analysis results from the server as input, visualizes the data on a user-friendly dashboard, and notifies the user in real time.

[0518] Step 7:

[0519] Users make quick decisions and adjust marketing strategies based on the information presented on their devices. As input, they refer to visual information and offers from their devices to gather material for developing their next marketing initiatives. The output is the planned marketing plan.

[0520] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0521] This invention is a marketing support system that combines consumer data analysis with an emotion engine. The server collects consumer posts and reviews in real time through APIs of social media and online stores. This data is analyzed using natural language processing technology and an emotion engine to extract consumer intentions, emotions, and more detailed trend information. The emotion engine precisely recognizes emotional elements such as positive, negative, and neutral from consumer posts, and the server uses this to improve the accuracy of predicting consumer behavior.

[0522] These analysis results are compared with past campaign data, allowing for more effective suggestions regarding ad delivery and budget allocation. Users can receive suggested strategies from the server via their devices and flexibly adjust their marketing measures.

[0523] Furthermore, the server builds customer profiles through consumer purchase history and other data, and generates personalized messages and offers based on that information. These messages, incorporating the results of the emotion engine, accurately address customer expectations and circumstances, thereby improving customer engagement.

[0524] Furthermore, the system constantly monitors the actions of competitors and displays market trend reports on the device, including the results of competitive data analysis using an emotion engine. Users can utilize this to respond quickly to the competitive environment.

[0525] As a concrete example, a strategy is employed in which consumer comments on social media regarding a particular product are analyzed using an emotion engine, and advertisements are concentrated on the moment when positive emotions are at their peak. Such timely responses can maximize the effectiveness of marketing. In this way, the present invention realizes marketing support that accurately reflects consumer needs and emotions.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The server collects real-time consumer posting data from social media platforms using APIs. This allows for the rapid acquisition of the latest consumer trends and opinions.

[0529] Step 2:

[0530] The server analyzes consumer posts collected using natural language processing technology to extract consumer intentions, interests, and behavioral patterns. The analysis results are then used for sentiment analysis in the next step.

[0531] Step 3:

[0532] The server applies a sentiment engine to the collected data, classifying the sentiment of each post into positive, negative, or neutral categories. This clarifies consumer sentiment trends.

[0533] Step 4:

[0534] The server integrates natural language processing and sentiment engine analysis results to gain a detailed understanding of consumer trends. It then displays the latest trend information as a dashboard on the user's device.

[0535] Step 5:

[0536] The server references past campaign data and leverages sentiment data to generate suggestions for optimizing ad delivery and budget allocation. This makes it possible to develop strategies that align with consumer emotions.

[0537] Step 6:

[0538] Users can view various suggestions displayed on the server's dashboard via their devices and adjust their marketing strategies accordingly. They can also make immediate modifications based on the server's suggestions as needed.

[0539] Step 7:

[0540] The server monitors the results of marketing initiatives and evaluates their effectiveness along with sentiment data. The evaluation results are analyzed for future initiatives and provided as feedback to the terminal.

[0541] Step 8:

[0542] Users utilize the evaluation results provided on their devices to make decisions regarding future strategies. Furthermore, users continuously gain insights based on sentiment data provided by the server, which helps them evolve their marketing strategies.

[0543] (Example 2)

[0544] Next, we will describe Example 2. 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."

[0545] In today's digital age, accurately analyzing consumer data and formulating more effective marketing strategies is crucial. However, traditional methods have struggled to efficiently collect data and conduct precise analyses of consumer emotions and behavior, making effective personalization difficult. Furthermore, quickly tracking competitors' activities and responding flexibly to market changes has also been a challenge.

[0546] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0547] In this invention, the server includes means for collecting information and analyzing users' intentions, emotions, and behaviors using natural language processing technology; means for preprocessing data and classifying data using an emotion engine; and means for predicting user behavior and using machine learning models. This enables highly accurate analysis of consumer data, rapid formulation of marketing strategies, and flexible response to market changes.

[0548] "Consumer data" refers to all information generated by consumers on digital platforms, including purchase history, posts, and reviews.

[0549] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, making it possible to analyze text and classify emotions.

[0550] An "emotion engine" is a system that uses natural language processing to identify and classify emotions from a user's text data.

[0551] "Users" refers to individuals or groups who provide information through this system, and specifically to consumers who engage in purchasing behavior or online activities.

[0552] "Data preprocessing" refers to the process of removing noise and normalizing acquired data in order to convert it into an analyzable format.

[0553] A "machine learning model" is a collection of algorithms that learn patterns from data and use them for prediction and classification.

[0554] "Personalized notifications" refer to customized messages that provide specific information based on an individual user's profile and behavior.

[0555] A "competitive entity" refers to another legal entity that operates in the same market or industry and is in a competitive relationship with the other entity.

[0556] This invention is a system that utilizes an emotion engine in consumer data analysis to formulate effective marketing strategies. The system is primarily implemented using servers and terminals.

[0557] The server collects data via APIs from social media and online stores. This collected data is preprocessed using natural language processing libraries (e.g., spaCy, NLTK) and then analyzed by an emotion engine. The emotion engine uses BERT and other similar generative AI models to subdivide emotions into positive, negative, and neutral. This allows for a precise understanding of the emotions behind consumers' posts.

[0558] Based on the analysis results, the server uses machine learning models (e.g., Random Forest, XGBoost) to predict consumer behavior and generate optimal ad delivery and resource allocation strategies. The server also generates personalized notifications based on the user's purchase history and sends them to the device. These notifications include personalized content that reflects the individual consumer's profile and sentiment data.

[0559] Users can use interactive dashboards presented from the server via their devices to review and adjust the provided marketing strategies. The devices also display market trends and competitor data, enabling users to quickly develop strategies that adapt to constantly changing market conditions.

[0560] One concrete example involves analyzing consumer social media posts about a new product. The emotion engine analyzes these posts and concentrates ad delivery at times when positive emotions are heightened, maximizing marketing effectiveness. This implementation enables strategies that accurately capture consumer intentions and emotions.

[0561] Examples of prompts to input into a generative AI model are as follows:

[0562] "Please analyze consumer social media posts about the new product XX based on the following points: Clearly indicate changes in consumer intent and emotion, including sentiment classification (positive, negative, neutral) and trend analysis. Also, compare this data with past campaign data and create suggestions for the optimal timing of ad delivery."

[0563] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0564] Step 1:

[0565] The server collects consumer posts and reviews via APIs from social media and online stores. API endpoints and authentication credentials are required as input. At this stage, the latest posted data from each platform is output. This operation enables real-time information retrieval.

[0566] Step 2:

[0567] The server preprocesses the collected data. Here, it takes the raw data collected as input and performs normalization and de-noise removal. This includes, for example, removing HTML tags and interpreting emojis. The preprocessed, clean text data is output. This process creates an analyzable dataset.

[0568] Step 3:

[0569] The server analyzes pre-processed data using an emotion engine. It receives clean, pre-processed data as input and uses a generative AI model (e.g., BERT) to classify its sentiment. The output is a sentiment label (positive, negative, neutral) for each post. This analysis allows for a highly accurate understanding of consumer sentiment.

[0570] Step 4:

[0571] The server predicts consumer behavior based on the analysis results. It uses sentiment-labeled data as input and performs prediction calculations using a machine learning model (e.g., Random Forest). The predicted consumer behavior and purchase intent are output. This prediction helps in developing appropriate strategies.

[0572] Step 5:

[0573] The server generates marketing strategies based on consumer behavior predictions and historical campaign data. It combines behavioral prediction data and historical data as input to propose the optimal advertising schedule and resource allocation. At this stage, it outputs guidelines for specific strategy development.

[0574] Step 6:

[0575] The terminal receives strategies generated by the server and presents them to the user. It receives strategy information sent from the server as input and displays it on the dashboard. As output, the user receives a real-time interface to view and adjust the strategies.

[0576] Step 7:

[0577] The server generates personalized notifications based on the consumer's purchase history. The input consists of purchase history and sentiment analysis data. Based on this, a message optimized for each individual user is automatically created and output as a notification. This step achieves consumer personalization.

[0578] Step 8:

[0579] The server analyzes market trends using information on competing companies and generates reports. The input information is data on the trends of competing companies. An emotion engine and market analysis tools are used for the analysis, resulting in a comprehensive market report. Users can view this report on their terminals and use it to inform their strategies.

[0580] (Application Example 2)

[0581] Next, we will explain application example 2. In the following explanation, 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."

[0582] Modern marketing requires accurately capturing the diverse intentions and emotions of consumers and effectively delivering advertisements in increasingly competitive markets. However, traditional methods have been unable to adequately analyze real-time changes in consumer emotions or the actions of competitors, posing challenges to the timely optimization of advertising campaigns. Therefore, a new system is needed to realize strategic marketing that takes consumer emotions into consideration.

[0583] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0584] In this invention, the server includes means for collecting consumer data and analyzing consumer intent, emotions, and trends using natural language processing technology; means for proposing optimal ad delivery and budget allocation based on past campaign data; and means for monitoring the activities of competitors and predicting market changes. This makes it possible to optimize advertising campaigns based on the emotional state of consumers.

[0585] "Consumer data" refers to a collection of information obtained from consumers' online activities, purchase history, and statements on social media.

[0586] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0587] "Consumer intent" refers to the purpose or motivation behind a consumer's actions or purchases.

[0588] "Emotions" refer to the positive, negative, or neutral feelings that consumers have towards a given situation or piece of information.

[0589] A "trend" is a temporary tendency or fashion that attracts the interest and attention of consumers.

[0590] "Advertising distribution" is the activity of presenting advertisements to a specific target audience and is part of a company's marketing strategy.

[0591] "Budget allocation" is a plan for distributing limited resources in the most optimal way, and is a method of financial management in advertising activities.

[0592] "Competitor activity" refers to the strategies and actions of other companies operating in the same market, and is a factor that influences the formulation of one's own company's strategy.

[0593] "Market changes" refer to major market movements such as fluctuations in consumer demand and changes in the competitive environment.

[0594] "Personalized messaging" refers to communication content that is tailored based on the individual consumer's preferences and behavioral history.

[0595] "Advertising campaign optimization" is the process of optimizing the content, timing, and targeting of advertisements in order to achieve marketing goals.

[0596] "Industry trends" refer to long-term changes or tendencies observed across a particular industry or sector.

[0597] The system that implements this application is built as an application that runs on a smartphone. The server collects consumer data in real time through APIs from social networking services and online stores. The collected data is analyzed using natural language processing technology and an emotion engine. This analysis uses natural language processing libraries such as NLTK and SpaCy, and an emotion analysis engine such as IBM Watson Natural Language Understanding.

[0598] The server extracts consumer intent, emotions, and trends from the analysis results. Based on this, it proposes optimal ad delivery and budget allocation by comparing it with past campaign data. Furthermore, it monitors the activities of competitors and continuously updates industry trends. This information is sent to the user's device and helps optimize ad campaigns and generate personalized messages, especially based on the sentiment analysis results.

[0599] Users can review the provided suggestions and flexibly adjust advertising strategies through the terminal application. In this way, it is possible to achieve a timely marketing approach based on consumer emotions.

[0600] As a concrete example, during a summer sale, one beverage manufacturer analyzed consumer feedback on social media using the phrase "Refreshing Summer" and distributed limited-time coupon advertisements at the moment when positive sentiment surged. This method has been shown to improve marketing effectiveness.

[0601] An example of a prompt message is, "For this month's product campaign, perform sentiment analysis based on data obtained from social media and develop the optimal advertising strategy." This effectively supports decision-making by utilizing generative AI models.

[0602] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0603] Step 1:

[0604] The server collects consumer data in real time using APIs from social media and online stores. This data includes consumer posts and reviews. The input is text data via API, and the output is raw data that can be analyzed.

[0605] Step 2:

[0606] The server uses natural language processing techniques to clean and structure the collected consumer data. It removes noise from the raw input data and performs part-of-speech analysis. The output is structured data suitable for sentiment analysis.

[0607] Step 3:

[0608] The server feeds naturally language-processed data into a sentiment analysis engine to identify consumer emotions (positive, negative, or neutral). The input is structured text data, and the output is each emotion label and its score.

[0609] Step 4:

[0610] The server generates an optimal ad delivery and budget allocation strategy by comparing sentiment analysis results with historical campaign data. Specifically, it analyzes sentiment fluctuations at each time point and suggests effective timing for ad investment. Inputs are sentiment labels and scores, and historical data, while output is strategy recommendation data.

[0611] Step 5:

[0612] The terminal receives strategic proposals from the server and presents them to the user in a dashboard format. The user can then adjust their advertising campaign based on this information. The input is strategic proposal data, and the output is visualized dashboard information.

[0613] Step 6:

[0614] Users adjust and execute advertising strategies via their devices. Specifically, they configure ad content and delivery timing based on the provided strategy and launch the actual campaign. Input is the user's instructions, and output is the updated campaign settings information.

[0615] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0616] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0617] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0618] [Fourth Embodiment]

[0619] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0620] As shown in Figure 7, the 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.

[0621] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0622] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0623] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0624] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0625] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0626] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0627] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0628] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0629] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0630] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0631] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0632] This invention is a system designed to support marketing activities and primarily operates through a program running on a server. The server collects and analyzes diverse consumer data. Specifically, it acquires data in real time from social media and online stores and analyzes consumer intentions and emotions using natural language processing technology. Using these results, the server predicts trends and provides them to the user's device as visual information.

[0633] Furthermore, the server optimizes ad delivery and budget allocation based on past campaign data. This includes analyzing the success factors of similar campaigns and applying them to the current advertising strategy.

[0634] Regarding the activities of competing companies, the server collects data from specific sources, analyzes it, and predicts market changes. These analysis results can be viewed on the terminal to help improve marketing strategies.

[0635] To enable customized marketing for each customer, the server automatically generates personalized messages and offers based on each customer's profile. This allows users to attract customers more effectively.

[0636] Finally, after the marketing campaign is implemented, the server analyzes its effectiveness based on the data obtained and proposes the next strategy. Users receive this information in real time through their devices, allowing them to quickly take action in line with market trends.

[0637] As a concrete example, when a store launches a new product, the server analyzes data from similar past successful campaigns and suggests the optimal advertising media and target audience to the user's terminal. Based on the provided report, the user can quickly adjust the campaign content to maximize its effectiveness. This system dramatically improves the accuracy and speed of marketing strategies.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] The server collects real-time data through APIs from social media platforms and online stores. This data includes consumer posts, reviews, and purchase history.

[0641] Step 2:

[0642] The server uses natural language processing technology to analyze collected consumer data and extract consumer intentions, emotions, and trends. This analysis identifies each consumer's interests and concerns.

[0643] Step 3:

[0644] The server uses the analyzed data to compare it with past campaign data and proposes optimized ad delivery and budget allocation. It extracts the characteristics of successful campaigns and suggests similar strategies.

[0645] Step 4:

[0646] The server crawls the activities of competitors and updates models that predict market changes. It provides information to re-evaluate marketing strategies while taking into account changes in the competitive landscape.

[0647] Step 5:

[0648] The server generates personalized messages and offers based on customer profiles, enabling communication optimized for each individual customer.

[0649] Step 6:

[0650] The server analyzes the results of implemented marketing initiatives and measures their effectiveness. The analysis results are displayed visually on a dashboard.

[0651] Step 7:

[0652] Users can review reports generated by the server via their devices and decide on their next strategy. Based on the suggested improvements, users can quickly adjust their marketing measures.

[0653] (Example 1)

[0654] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0655] Traditional marketing systems struggled to grasp individual intentions and emotions in detail, making it difficult to provide timely and appropriate information to target customers. Furthermore, they failed to fully utilize data from past sales promotion activities, making optimal advertising distribution and budget allocation challenging. Additionally, the lack of objective criteria for efficiently analyzing the trends of similar businesses and predicting market changes hindered the rapid improvement of business strategies.

[0656] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0657] This invention includes a server that collects personal data from a digital platform and analyzes individuals' intentions, emotions, and trends using natural language processing technology; means for proposing optimal advertising implementation and budget allocation based on past sales promotion activity data; and means for monitoring the behavior of similar businesses and predicting changes in the business environment. This enables personalized information provision, improves the efficiency of advertising delivery strategies and budget allocation, and allows for rapid strategic adjustments in the market.

[0658] A "digital platform" is an internet-based environment for collecting consumer data online, including social media and online stores.

[0659] "Personal data" refers to information that indicates consumer behavior and trends, and includes data that identifies a specific individual, such as online purchase history and interaction data.

[0660] "Natural language processing technology" is an information processing technology that uses computers to analyze human language and understand its linguistic features, emotions, and intentions.

[0661] "Sales promotion activity data" refers to records related to advertising campaigns and marketing activities conducted in the past, and is data that can be used for measuring effectiveness and making improvements.

[0662] "Competitors of the same type" refers to competing companies that provide similar goods or services in the same industry or market.

[0663] "Customized information" refers to messages and offers that are appropriately tailored based on the individual consumer's needs and profile.

[0664] "Visual tools" are software or technologies used to visually present the results of an analysis, including charts and graphs.

[0665] Modes for carrying out the invention

[0666] This invention is an advanced system for optimizing marketing strategies, and its main components include a server, terminals, and users. Specific implementation methods are described below.

[0667] The server first collects data from others on digital platforms. This includes using Python scripts to retrieve data from social media APIs and online stores. The collected data is stored in JSON format and later used for analysis.

[0668] Next, the server analyzes the collected data using natural language processing technology. By using the Google Cloud Natural Language API, it efficiently extracts individual intentions, emotions, and trends. Through this data analysis, the server reveals consumers' latent needs.

[0669] Data processing libraries such as Pandas and NumPy are used to analyze past sales promotion activity data. Based on this, the server proposes the optimal advertising strategy and budget allocation to the terminal. For example, it selects the optimal media based on the conversion rate of advertisements.

[0670] To analyze the activities of competitors, the server uses RSS readers and news APIs to collect and analyze data from similar businesses. This allows for accurate prediction of market fluctuations and the competitive landscape.

[0671] The server uses a generative AI model to generate customized messages. For example, by inputting "Create a special offer message for female customers in their 20s" as a prompt based on a specific consumer profile, a message tailored to the purpose will be generated.

[0672] Finally, the server displays the analysis results visually using a visual tool. By using visualization libraries such as Matplotlib and sending the generated charts and graphs to the terminal, users can utilize this information in real time and quickly adjust their marketing strategies.

[0673] This invention enables users to conduct more precise and effective marketing activities, thereby enhancing their competitive advantage in the market.

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] The server collects personal data from digital platforms. Specifically, it uses a Python script to send requests to social networking service (SNS) APIs and retrieves consumer posting data in JSON format. The input is the SNS API endpoint, and the output is the retrieved JSON data. The server stores this data as a base database for analysis.

[0677] Step 2:

[0678] The server analyzes the collected data using natural language processing technology. It sends the data to the Google Cloud Natural Language API to analyze consumer intent and sentiment. The input is the JSON data collected in step 1, and the output is metadata of the analyzed intent and sentiment. This provides information about consumer interests and demand forecasting.

[0679] Step 3:

[0680] The server analyzes the optimal strategy using past sales promotion activity data. It uses Pandas to read past campaign records and NumPy to perform statistical analysis. The input is historical campaign data in CSV format, and the output is an optimal advertising plan and budget allocation proposal. The calculated data is sent to the terminal as a suggestion.

[0681] Step 4:

[0682] The server monitors the activities of competitors and predicts changes in the business environment. It collects and analyzes the latest competitive information from RSS feeds and news APIs. Input is information from RSS feeds and news APIs, and output is competitive trends and market fluctuation predictions. These prediction results are also sent to terminals, which users can use for strategic planning.

[0683] Step 5:

[0684] The server generates personalized messages using a generative AI model. Based on a specific customer profile, prompt sentences are input to the generative AI model. The input is a prompt sentence such as "Create a special offer message for female customers in their 20s," and the output is the generated message. This provides users with effective marketing messages.

[0685] Step 6:

[0686] The server visually represents the analysis results using a visual tool and sends them to the terminal. For example, it uses Matplotlib to convert the data into charts and graphs. The input is the analysis results from steps 2 to 5, and the output is the visualized data. The terminal displays this, allowing the user to utilize the information in real time.

[0687] (Application Example 1)

[0688] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0689] In marketing activities, there is a need to understand consumer behavior and competitor trends in real time and to propose the most suitable products and advertisements to individual consumers based on this data. However, there is a lack of methods to quickly and effectively analyze diverse consumer data and technologies to automatically propose personalized marketing strategies. Therefore, an efficient system is needed to increase consumer purchasing intent and maintain and improve competitiveness.

[0690] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0691] In this invention, the server includes means for collecting consumer data and analyzing consumer intentions, emotions, and trends using natural language processing technology; means for proposing optimal advertising transmission and budget management based on past advertising activity data; and means for monitoring the activities of competitors and predicting market changes. This enables effective product recommendations and optimized advertising delivery for individual consumers.

[0692] "Consumer data" refers to data that includes a variety of information used in marketing activities, such as consumer behavior, intentions, emotions, and purchase history.

[0693] "Natural language processing technology" is a technology that uses computers to understand and analyze human language, and is used for analyzing text data and understanding consumers' intentions and emotions.

[0694] "Advertising transmission" refers to the activity of notifying consumers of information about products and services, and is a means of delivering messages optimized based on consumers' interests.

[0695] "Budget management" is the process of optimizing the allocation of funds to advertising in marketing activities, with the aim of using resources efficiently.

[0696] "Competitor activity" refers to the activities and strategies of competitors within the same market. Understanding this information allows us to predict market changes and business opportunities.

[0697] "Product recommendation" is a technical method used to increase purchasing intent by presenting products and services that are most suitable for consumers based on their preferences.

[0698] "Ad delivery optimization" is the process in marketing activities to deliver advertisements to target consumers in the most effective way, with the aim of maximizing the effectiveness of the advertisements.

[0699] The system for realizing this invention is comprised of a combination of multiple advanced technologies. The server plays a central role in storing and analyzing diverse data collected from consumers. This data includes consumer purchase history, online behavior history, and social media reactions. This data is analyzed using natural language processing technology to extract consumer intentions, emotions, and trend information.

[0700] The server also references a database of past advertising activities and uses machine learning algorithms to suggest optimal advertising delivery strategies and budget management. Specifically, it has the ability to automatically generate effective product recommendations and promotional offers for each target consumer group. This function ensures that personalized advertisements are delivered to individual consumers.

[0701] On the device side, the resulting analytical information is provided to the user in a visual format. This includes intuitive data visualization through a dashboard and real-time suggestion notifications. Based on personalized information, users can quickly make marketing strategy decisions and evaluate and improve the effectiveness of each measure.

[0702] For example, if a consumer is found to have a tendency to purchase new electronic devices, the server will recommend the latest gadget models relevant to that consumer and offer special discounts. This system can improve the accuracy of product selection by using a generative AI model to set a prompt such as "Which product is best suited for this consumer?"

[0703] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0704] Step 1:

[0705] The server collects consumer behavior history, purchase history, and real-time data from social media. It receives data from various data sources as input and stores it in a database. During this process, data preprocessing, such as removing duplicate data and standardizing formats, is performed to maintain data integrity.

[0706] Step 2:

[0707] The server applies natural language processing techniques to the collected data to analyze consumer intentions, sentiments, and trends. It receives text data as input and uses a natural language processing engine to obtain analysis results. Specifically, this includes text summarization and sentiment analysis.

[0708] Step 3:

[0709] The server analyzes past advertising data using machine learning algorithms to formulate the optimal advertising delivery strategy. It receives historical campaign data as input and trains a model to identify success factors. The output is the advertising delivery pattern most effective for the target consumer.

[0710] Step 4:

[0711] The server collects information on competitors' activities from time-series data and news feeds to predict market trends. It receives the latest industry data from various sources as input, analyzes it, and automatically generates reports to predict market changes.

[0712] Step 5:

[0713] The server creates personalized product suggestions and advertisements based on the consumer's profile. It receives analyzed consumer sentiment and purchase history as input, and uses a generative AI model to recommend products using the prompt "What product is best suited for this consumer?". The output is a personalized product offer for the user.

[0714] Step 6:

[0715] The terminal visually presents analysis results and product recommendations obtained from the server to the user. It receives analysis results from the server as input, visualizes the data on a user-friendly dashboard, and notifies the user in real time.

[0716] Step 7:

[0717] Users make quick decisions and adjust marketing strategies based on the information presented on their devices. As input, they refer to visual information and offers from their devices to gather material for developing their next marketing initiatives. The output is the planned marketing plan.

[0718] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0719] This invention is a marketing support system that combines consumer data analysis with an emotion engine. The server collects consumer posts and reviews in real time through APIs of social media and online stores. This data is analyzed using natural language processing technology and an emotion engine to extract consumer intentions, emotions, and more detailed trend information. The emotion engine precisely recognizes emotional elements such as positive, negative, and neutral from consumer posts, and the server uses this to improve the accuracy of predicting consumer behavior.

[0720] These analysis results are compared with past campaign data, allowing for more effective suggestions regarding ad delivery and budget allocation. Users can receive suggested strategies from the server via their devices and flexibly adjust their marketing measures.

[0721] Furthermore, the server builds customer profiles through consumer purchase history and other data, and generates personalized messages and offers based on that information. These messages, incorporating the results of the emotion engine, accurately address customer expectations and circumstances, thereby improving customer engagement.

[0722] Furthermore, the system constantly monitors the actions of competitors and displays market trend reports on the device, including the results of competitive data analysis using an emotion engine. Users can utilize this to respond quickly to the competitive environment.

[0723] As a concrete example, a strategy is employed in which consumer comments on social media regarding a particular product are analyzed using an emotion engine, and advertisements are concentrated on the moment when positive emotions are at their peak. Such timely responses can maximize the effectiveness of marketing. In this way, the present invention realizes marketing support that accurately reflects consumer needs and emotions.

[0724] The following describes the processing flow.

[0725] Step 1:

[0726] The server collects real-time consumer posting data from social media platforms using APIs. This allows for the rapid acquisition of the latest consumer trends and opinions.

[0727] Step 2:

[0728] The server analyzes consumer posts collected using natural language processing technology to extract consumer intentions, interests, and behavioral patterns. The analysis results are then used for sentiment analysis in the next step.

[0729] Step 3:

[0730] The server applies a sentiment engine to the collected data, classifying the sentiment of each post into positive, negative, or neutral categories. This clarifies consumer sentiment trends.

[0731] Step 4:

[0732] The server integrates natural language processing and sentiment engine analysis results to gain a detailed understanding of consumer trends. It then displays the latest trend information as a dashboard on the user's device.

[0733] Step 5:

[0734] The server references past campaign data and leverages sentiment data to generate suggestions for optimizing ad delivery and budget allocation. This makes it possible to develop strategies that align with consumer emotions.

[0735] Step 6:

[0736] Users can view various suggestions displayed on the server's dashboard via their devices and adjust their marketing strategies accordingly. They can also make immediate modifications based on the server's suggestions as needed.

[0737] Step 7:

[0738] The server monitors the results of marketing initiatives and evaluates their effectiveness along with sentiment data. The evaluation results are analyzed for future initiatives and provided as feedback to the terminal.

[0739] Step 8:

[0740] Users utilize the evaluation results provided on their devices to make decisions regarding future strategies. Furthermore, users continuously gain insights based on sentiment data provided by the server, which helps them evolve their marketing strategies.

[0741] (Example 2)

[0742] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0743] In today's digital age, accurately analyzing consumer data and formulating more effective marketing strategies is crucial. However, traditional methods have struggled to efficiently collect data and conduct precise analyses of consumer emotions and behavior, making effective personalization difficult. Furthermore, quickly tracking competitors' activities and responding flexibly to market changes has also been a challenge.

[0744] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0745] In this invention, the server includes means for collecting information and analyzing users' intentions, emotions, and behaviors using natural language processing technology; means for preprocessing data and classifying data using an emotion engine; and means for predicting user behavior and using machine learning models. This enables highly accurate analysis of consumer data, rapid formulation of marketing strategies, and flexible response to market changes.

[0746] "Consumer data" refers to all information generated by consumers on digital platforms, including purchase history, posts, and reviews.

[0747] "Natural language processing technology" is a technology that enables computers to understand and analyze human language, making it possible to analyze text and classify emotions.

[0748] An "emotion engine" is a system that uses natural language processing to identify and classify emotions from a user's text data.

[0749] "Users" refers to individuals or groups who provide information through this system, and specifically to consumers who engage in purchasing behavior or online activities.

[0750] "Data preprocessing" refers to the process of removing noise and normalizing acquired data in order to convert it into an analyzable format.

[0751] A "machine learning model" is a collection of algorithms that learn patterns from data and use them for prediction and classification.

[0752] "Personalized notifications" refer to customized messages that provide specific information based on an individual user's profile and behavior.

[0753] A "competitive entity" refers to another legal entity that operates in the same market or industry and is in a competitive relationship with the other entity.

[0754] This invention is a system that utilizes an emotion engine in consumer data analysis to formulate effective marketing strategies. The system is primarily implemented using servers and terminals.

[0755] The server collects data via APIs from social media and online stores. This collected data is preprocessed using natural language processing libraries (e.g., spaCy, NLTK) and then analyzed by an emotion engine. The emotion engine uses BERT and other similar generative AI models to subdivide emotions into positive, negative, and neutral. This allows for a precise understanding of the emotions behind consumers' posts.

[0756] Based on the analysis results, the server uses machine learning models (e.g., Random Forest, XGBoost) to predict consumer behavior and generate optimal ad delivery and resource allocation strategies. The server also generates personalized notifications based on the user's purchase history and sends them to the device. These notifications include personalized content that reflects the individual consumer's profile and sentiment data.

[0757] Users can use interactive dashboards presented from the server via their devices to review and adjust the provided marketing strategies. The devices also display market trends and competitor data, enabling users to quickly develop strategies that adapt to constantly changing market conditions.

[0758] One concrete example involves analyzing consumer social media posts about a new product. The emotion engine analyzes these posts and concentrates ad delivery at times when positive emotions are heightened, maximizing marketing effectiveness. This implementation enables strategies that accurately capture consumer intentions and emotions.

[0759] Examples of prompts to input into a generative AI model are as follows:

[0760] "Please analyze consumer social media posts about the new product XX based on the following points: Clearly indicate changes in consumer intent and emotion, including sentiment classification (positive, negative, neutral) and trend analysis. Also, compare this data with past campaign data and create suggestions for the optimal timing of ad delivery."

[0761] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0762] Step 1:

[0763] The server collects consumer posts and reviews via APIs from social media and online stores. API endpoints and authentication credentials are required as input. At this stage, the latest posted data from each platform is output. This operation enables real-time information retrieval.

[0764] Step 2:

[0765] The server preprocesses the collected data. Here, it takes the raw data collected as input and performs normalization and de-noise removal. This includes, for example, removing HTML tags and interpreting emojis. The preprocessed, clean text data is output. This process creates an analyzable dataset.

[0766] Step 3:

[0767] The server analyzes pre-processed data using an emotion engine. It receives clean, pre-processed data as input and uses a generative AI model (e.g., BERT) to classify its sentiment. The output is a sentiment label (positive, negative, neutral) for each post. This analysis allows for a highly accurate understanding of consumer sentiment.

[0768] Step 4:

[0769] The server predicts consumer behavior based on the analysis results. It uses sentiment-labeled data as input and performs prediction calculations using a machine learning model (e.g., Random Forest). The predicted consumer behavior and purchase intent are output. This prediction helps in developing appropriate strategies.

[0770] Step 5:

[0771] The server generates marketing strategies based on consumer behavior predictions and historical campaign data. It combines behavioral prediction data and historical data as input to propose the optimal advertising schedule and resource allocation. At this stage, it outputs guidelines for specific strategy development.

[0772] Step 6:

[0773] The terminal receives strategies generated by the server and presents them to the user. It receives strategy information sent from the server as input and displays it on the dashboard. As output, the user receives a real-time interface to view and adjust the strategies.

[0774] Step 7:

[0775] The server generates personalized notifications based on the consumer's purchase history. The input consists of purchase history and sentiment analysis data. Based on this, a message optimized for each individual user is automatically created and output as a notification. This step achieves consumer personalization.

[0776] Step 8:

[0777] The server analyzes market trends using information on competing companies and generates reports. The input information is data on the trends of competing companies. An emotion engine and market analysis tools are used for the analysis, resulting in a comprehensive market report. Users can view this report on their terminals and use it to inform their strategies.

[0778] (Application Example 2)

[0779] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0780] Modern marketing requires accurately capturing the diverse intentions and emotions of consumers and effectively delivering advertisements in increasingly competitive markets. However, traditional methods have been unable to adequately analyze real-time changes in consumer emotions or the actions of competitors, posing challenges to the timely optimization of advertising campaigns. Therefore, a new system is needed to realize strategic marketing that takes consumer emotions into consideration.

[0781] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0782] In this invention, the server includes means for collecting consumer data and analyzing consumer intent, emotions, and trends using natural language processing technology; means for proposing optimal ad delivery and budget allocation based on past campaign data; and means for monitoring the activities of competitors and predicting market changes. This makes it possible to optimize advertising campaigns based on the emotional state of consumers.

[0783] "Consumer data" refers to a collection of information obtained from consumers' online activities, purchase history, and statements on social media.

[0784] "Natural language processing technology" refers to the technology that enables computers to understand, analyze, and generate human language.

[0785] "Consumer intent" refers to the purpose or motivation behind a consumer's actions or purchases.

[0786] "Emotions" refer to the positive, negative, or neutral feelings that consumers have towards a given situation or piece of information.

[0787] A "trend" is a temporary tendency or fashion that attracts the interest and attention of consumers.

[0788] "Advertising distribution" is the activity of presenting advertisements to a specific target audience and is part of a company's marketing strategy.

[0789] "Budget allocation" is a plan for distributing limited resources in the most optimal way, and is a method of financial management in advertising activities.

[0790] "Competitor activity" refers to the strategies and actions of other companies operating in the same market, and is a factor that influences the formulation of one's own company's strategy.

[0791] "Market changes" refer to major market movements such as fluctuations in consumer demand and changes in the competitive environment.

[0792] "Personalized messaging" refers to communication content that is tailored based on the individual consumer's preferences and behavioral history.

[0793] "Advertising campaign optimization" is the process of optimizing the content, timing, and targeting of advertisements in order to achieve marketing goals.

[0794] "Industry trends" refer to long-term changes or tendencies observed across a particular industry or sector.

[0795] The system that implements this application is built as an application that runs on a smartphone. The server collects consumer data in real time through APIs from social networking services and online stores. The collected data is analyzed using natural language processing technology and an emotion engine. This analysis uses natural language processing libraries such as NLTK and SpaCy, and an emotion analysis engine such as IBM Watson Natural Language Understanding.

[0796] The server extracts consumer intent, emotions, and trends from the analysis results. Based on this, it proposes optimal ad delivery and budget allocation by comparing it with past campaign data. Furthermore, it monitors the activities of competitors and continuously updates industry trends. This information is sent to the user's device and helps optimize ad campaigns and generate personalized messages, especially based on the sentiment analysis results.

[0797] Users can review the provided suggestions and flexibly adjust advertising strategies through the terminal application. In this way, it is possible to achieve a timely marketing approach based on consumer emotions.

[0798] As a concrete example, during a summer sale, one beverage manufacturer analyzed consumer feedback on social media using the phrase "Refreshing Summer" and distributed limited-time coupon advertisements at the moment when positive sentiment surged. This method has been shown to improve marketing effectiveness.

[0799] An example of a prompt message is, "For this month's product campaign, perform sentiment analysis based on data obtained from social media and develop the optimal advertising strategy." This effectively supports decision-making by utilizing generative AI models.

[0800] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0801] Step 1:

[0802] The server collects consumer data in real time using APIs from social media and online stores. This data includes consumer posts and reviews. The input is text data via API, and the output is raw data that can be analyzed.

[0803] Step 2:

[0804] The server uses natural language processing techniques to clean and structure the collected consumer data. It removes noise from the raw input data and performs part-of-speech analysis. The output is structured data suitable for sentiment analysis.

[0805] Step 3:

[0806] The server feeds naturally language-processed data into a sentiment analysis engine to identify consumer emotions (positive, negative, or neutral). The input is structured text data, and the output is each emotion label and its score.

[0807] Step 4:

[0808] The server generates an optimal ad delivery and budget allocation strategy by comparing sentiment analysis results with historical campaign data. Specifically, it analyzes sentiment fluctuations at each time point and suggests effective timing for ad investment. Inputs are sentiment labels and scores, and historical data, while output is strategy recommendation data.

[0809] Step 5:

[0810] The terminal receives strategic proposals from the server and presents them to the user in a dashboard format. The user can then adjust their advertising campaign based on this information. The input is strategic proposal data, and the output is visualized dashboard information.

[0811] Step 6:

[0812] Users adjust and execute advertising strategies via their devices. Specifically, they configure ad content and delivery timing based on the provided strategy and launch the actual campaign. Input is the user's instructions, and output is the updated campaign settings information.

[0813] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0814] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0815] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0816] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0817] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0818] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0819] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0820] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0821] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0822] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0823] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0824] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0825] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0826] 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.

[0827] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0828] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0829] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0830] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0831] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0832] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0833] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0834] The following is further disclosed regarding the embodiments described above.

[0835] (Claim 1)

[0836] A means for collecting consumer data and analyzing consumer intentions, emotions, and trends using natural language processing technology,

[0837] A method to propose optimal ad delivery and budget allocation based on past campaign data,

[0838] A means of monitoring the actions of competitors and predicting market changes,

[0839] A means of generating personalized messages for each customer,

[0840] A means of evaluating the effectiveness of marketing measures and proposing the next strategy,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, which creates a customer profile based on the consumer's purchase history and performs personalization.

[0844] (Claim 3)

[0845] The system according to claim 1, which performs trend analysis and market forecasting using information on competitors and presents the results on a dashboard.

[0846] "Example 1"

[0847] (Claim 1)

[0848] A means of collecting personal data from digital platforms and analyzing individuals' intentions, emotions, and trends using natural language processing technology,

[0849] A method for proposing optimal advertising implementation and budget allocation based on past sales promotion activity data,

[0850] A means of monitoring the actions of similar businesses and predicting changes in the business environment,

[0851] A means of generating information customized for each individual,

[0852] A means to verify the effectiveness of the utilization activities and to propose the following policies,

[0853] A means of visually presenting processing results using visual tools,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, which creates personal characteristics based on an individual's purchase history and performs customization.

[0857] (Claim 3)

[0858] The system according to claim 1, which utilizes information from similar businesses to perform trend analysis and environmental forecasting, and presents the results using a visualization tool.

[0859] "Application Example 1"

[0860] (Claim 1)

[0861] A device that collects consumer data and analyzes consumer intentions, emotions, and trends using natural language processing technology,

[0862] A device that proposes optimal advertising transmission and budget management based on past advertising activity data,

[0863] A device that monitors the actions of competing companies and predicts market changes,

[0864] A device that generates customized messages for each customer,

[0865] A device that analyzes purchasing trends based on sales history and provides personalized product recommendations,

[0866] A device for evaluating the effectiveness of a marketing strategy and suggesting the next strategy,

[0867] A system that includes this.

[0868] (Claim 2)

[0869] The system according to claim 1, which creates customer information based on consumer purchase records and performs personalization.

[0870] (Claim 3)

[0871] The system according to claim 1, which performs trend analysis and market forecasting using information on competitors and presents the results using a visualization system.

[0872] "Example 2 of combining an emotion engine"

[0873] (Claim 1)

[0874] A means for collecting information and analyzing users' intentions, emotions, and behaviors using natural language processing technology,

[0875] A means of proposing optimal advertising distribution and resource allocation based on past activity data,

[0876] A means of monitoring the activities of competing companies and predicting market changes,

[0877] A means of generating personalized notifications for each user,

[0878] A means of evaluating the effectiveness of action plans and proposing the next strategy,

[0879] A method for preprocessing data and classifying it using an emotion engine,

[0880] Methods for predicting user behavior and using machine learning models,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, which creates specific information based on the user's purchase history and performs personalized processing.

[0884] (Claim 3)

[0885] The system according to claim 1, which performs trend analysis and market forecasting using information on competing corporations and displays the results on a display screen.

[0886] "Application example 2 of combining emotional engines"

[0887] (Claim 1)

[0888] A means for collecting consumer data and analyzing consumer intentions, emotions, and trends using natural language processing technology,

[0889] A method to propose optimal ad delivery and budget allocation based on past campaign data,

[0890] A means of monitoring the actions of competitors and predicting market changes,

[0891] A means of generating personalized messages for each customer,

[0892] A means of evaluating the effectiveness of marketing measures and proposing the next strategy,

[0893] A means of proposing strategies to optimize advertising campaigns based on sentiment analysis results,

[0894] A means of displaying industry trends based on competitive information and sentiment analysis results,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, which creates a customer profile based on the consumer's purchase history and performs personalization.

[0898] (Claim 3)

[0899] The system according to claim 1, which performs trend analysis and market forecasting using information on competitors and presents the results on a dashboard. [Explanation of symbols]

[0900] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A device that collects consumer data and analyzes consumer intentions, emotions, and trends using natural language processing technology, A device that proposes optimal advertising transmission and budget management based on past advertising activity data, A device that monitors the actions of competing companies and predicts market changes, A device that generates customized messages for each customer, A device that analyzes purchasing trends based on sales history and provides personalized product recommendations, A device for evaluating the effectiveness of a marketing strategy and suggesting the next strategy, A system that includes this.

2. The system according to claim 1, which creates customer information based on consumer purchase records and performs personalization.

3. The system according to claim 1, which performs trend analysis and market forecasting using information on competitors and presents the results using a visualization system.

Images