system

Abstract

Provide a system. 【Solution means】 Means for collecting customer information, Means for analyzing the collected customer information using natural language processing technology and extracting customer sentiment and interests, Means for predicting market trends by time series analysis, Means for formulating an optimal sales strategy based on the analysis and prediction results, Means for automating advertising promotion and individualizing advertisements according to user groups, Means for optimizing information content according to user behavior, Means for tracking users' online behavior and optimizing advertisement delivery timing based on the data, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 as a 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] There is a need to effectively utilize the vast amount of customer data held by enterprises, promote personalization, and improve efficiency in digital marketing while rapidly adapting to changing market trends and optimizing advertising distribution. However, in these processes, specialized knowledge and a large amount of work are required, and many enterprises have problems in that they cannot adequately respond to this.

Means for Solving the Problems

[0005] This invention includes means for collecting customer data, means for analyzing the collected data using natural language processing technology to extract customer sentiment and interests, and means for predicting market trends through time series analysis. Furthermore, it includes means for formulating optimal marketing strategies based on these analysis and prediction results and automating ad delivery to achieve ad personalization according to customer segments, thereby enhancing and streamlining companies' digital marketing activities. In addition, it includes means for optimizing web content according to user behavior, enabling real-time monitoring and adjustment of advertising effectiveness, and solving challenges faced by companies.

[0006] "Customer data" refers to information collected by a company about its customers, including purchase history, inquiry history, and social media posts.

[0007] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is used for analyzing text data and extracting sentiment.

[0008] "Analysis" is the process of systematically organizing data and identifying trends and patterns, and is carried out to obtain information necessary for decision-making.

[0009] "Market trends" refer to market movements and changes in consumer purchasing behavior over a certain period, and are used to forecast demand for products and services.

[0010] "Strategic planning" is the process of formulating an action plan necessary to achieve pre-set goals, and includes making decisions to secure a company's competitive advantage.

[0011] "Automated ad delivery" is a technology that automates the process of delivering the right ads to the right customers with minimal human intervention.

[0012] Personalization is a technology that optimizes products, services, and content for specific customers based on their individual preferences and past behavior.

[0013] "Content optimization" is a technique that adjusts online content to be the most appealing and effective format for a given user, based on their behavioral data.

[0014] "Monitoring" is the process of constantly observing the current state of a system or process and making corrections or improvements as needed.

[0015] Clustering is a technique that groups data based on similarity and analyzes the characteristics of each group (cluster). [Brief explanation of the drawing]

[0016] [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] This 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] This shows an emotion map where multiple 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

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be described.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] 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.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is a system for highly automating and optimizing marketing strategies by utilizing customer and market data held by companies. This system consists of a server, terminals, and users, and operates as follows:

[0038] First, the server periodically collects customer data through the company's CRM system and social media APIs. Here, all relevant data is aggregated, including purchase history, customer profiles, and social media activity information. Based on this data, the server uses natural language processing technology to analyze the text data and extract customer sentiments and preferences.

[0039] Next, the server performs time-series analysis, using external market data and historical sales data to capture current market trends. Based on this information, it trains predictive models to forecast future consumer needs and demand. This process enables companies to respond quickly to market fluctuations and develop appropriate product strategies.

[0040] The server also has the capability to automatically generate optimal marketing strategies based on the insights it gains. This includes designing advertising campaigns, identifying target segments, and personalizing ad content. Furthermore, it connects to advertising delivery platforms to automatically deliver the most relevant ads to target customers.

[0041] On the other hand, the device tracks the user's online behavior (e.g., website clicks and browsing history) and sends this data to a server. This data is used to gain a deeper understanding of the user's interests and to optimize advertising and content.

[0042] For example, when a user visits an e-commerce site via their device, the server recommends relevant products based on their past browsing history. Furthermore, the server collects user comments and opinions from social media and displays advertisements on topics that may be of interest to the customer. These advertisements are delivered at the optimal time and with the most relevant content through the user's device.

[0043] This system enables companies to enhance personalized marketing activities and improve the customer experience. It also allows them to maximize the return on advertising spend and uncover new market opportunities.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server collects customer data from companies using CRM systems and social media APIs. This data includes customer purchase history, browsing history, inquiries, and social media interactions. Website log information is also collected.

[0047] Step 2:

[0048] The server applies natural language processing techniques to the collected data to extract customer emotions and interests from text information. This includes customer-provided reviews, feedback, and social media posts. By analyzing emotions such as positive and negative, the server reveals customers' latent needs.

[0049] Step 3:

[0050] The server performs time-series analysis based on historical sales data and market reports to predict market trends. This includes forecasting future consumer trends and demand fluctuations. The server uses this data to train machine learning models and forecast product demand.

[0051] Step 4:

[0052] The server generates the optimal marketing strategy for target customer segments based on analysis results and market forecasts. This includes determining which ads to deliver to which customers and through which channels. Ad campaigns are personalized, and the server automates the ad content.

[0053] Step 5:

[0054] The server connects to the advertising platform to deliver ads to target customers. During delivery, it monitors the effectiveness of the ads in real time (e.g., click-through rate, conversion rate) and adjusts the ad content and delivery settings as needed to maximize ad effectiveness.

[0055] Step 6:

[0056] The device tracks the user's website visits and online behavior, and sends this information to the server. The server uses this data to optimize web content to suit the user's preferences.

[0057] Step 7:

[0058] The server combines user behavior data with insights based on market forecasts to provide purchase recommendations and optimize content. Users can receive personalized product recommendations and promotions through their devices. This process allows users to enjoy a more personalized experience while improving the marketing efficiency of businesses.

[0059] (Example 1)

[0060] 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."

[0061] In today's business environment, developing swift and effective marketing strategies is crucial for companies to deepen customer relationships and maintain competitiveness. However, effectively utilizing vast amounts of customer and market data to deliver personalized advertising is a major challenge for many companies. Existing systems struggle to process data effectively and efficiently in terms of data collection and analysis, customer classification, and sales strategy planning and implementation.

[0062] 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.

[0063] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer sentiment and interests, and means for predicting market trends through time series analysis. This enables companies to effectively utilize data and formulate and implement optimal sales strategies. Furthermore, by delivering personalized advertisements to customers, it improves targeting accuracy and maximizes sales results.

[0064] "Customer information" refers to data that companies collect about their customers, including, for example, purchase history, personal profiles, and records of online activity.

[0065] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and is particularly used for analyzing text and audio data.

[0066] Time series analysis is a statistical method that analyzes the patterns of data fluctuations over time to predict future trends.

[0067] A "sales strategy" refers to the plans and policies used when selling products or services in the market, and includes things like target setting and promotional plans.

[0068] "Personalized advertising" is a technique for achieving more effective communication by adapting advertising content to the characteristics and preferences of customers.

[0069] "Online content" refers to all information and services viewed or used on the Internet, including websites, content, and applications.

[0070] "Collaborative filtering" is a method that provides personalized recommendations based on a user's past behavior patterns and similar behaviors of other users.

[0071] "Real-time monitoring" is a process that enables rapid decision-making by continuously observing and recording specific indicators or activities in real time.

[0072] "Dynamic adjustment" refers to a function that enhances flexibility by automatically changing systems and strategies in response to changes in conditions and circumstances.

[0073] This system is designed to enable companies to leverage customer information and market data to implement effective marketing strategies. The system consists of servers, terminals, and users.

[0074] The server collects customer information through the company's databases and APIs. This collected data includes, for example, purchase history from CRM systems, user profiles from user information management tools, and posts from social media APIs. Natural language processing techniques are applied to this text data to analyze customer sentiment and interests. This technique utilizes machine learning algorithms and pre-trained generative AI models.

[0075] Next, the server uses time-series data provided by external market data providers to predict market trends. The server leverages statistical algorithms to analyze market trends and build predictive models. This allows companies to foresee future consumer needs and optimize their sales strategies.

[0076] The server generates the optimal marketing strategy based on these analysis results. Generative AI models are used to personalize ad content, streamlining the planning and targeting of promotional activities. Ads are connected to the ad delivery platform and automatically delivered from the server.

[0077] Meanwhile, the device monitors the user's online behavior. For example, it collects data on the pages the user views and the links they click on websites and sends this data to the server. This data is used to measure the effectiveness of advertisements and optimize content.

[0078] Users can receive personalized content and advertisements based on their interests through their devices. For example, related products may be recommended based on the product categories the user has viewed, or advertisements based on topics that interest them may be displayed.

[0079] (Example of a prompt message)

[0080] "Perform sentiment analysis based on customer data and propose appropriate advertisements."

[0081] "Use past data to develop your next sales strategy."

[0082] This system will enable companies to conduct more precise marketing and deepen their engagement with consumers.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server collects customer information. It uses purchase history data and customer profile data from the company's internal CRM system, as well as user-generated data from external social media APIs, as input. This data is aggregated into a database to prepare for the next analysis stage. Specifically, it periodically retrieves data via API calls and inserts it into the database.

[0086] Step 2:

[0087] The server uses natural language processing (NLP) techniques to analyze the collected customer information. The text data collected in Step 1 is used as input. Specifically, a generative AI model is used to analyze the sentiment of the text and extract customer interests and trends. The output will be a sentiment score and areas of interest for each customer. This step involves applying machine learning algorithms to quantify the text data.

[0088] Step 3:

[0089] The server performs time series analysis to predict market trends. It uses external market trend data and the company's own historical sales data as input. Data processing involves trend analysis of time series data and the construction of a predictive model. The output provides future demand forecasts and changes in market needs. This process includes data smoothing and seasonality identification using statistical algorithms.

[0090] Step 4:

[0091] The server generates the optimal marketing strategy based on the analysis results. It utilizes customer sentiment data from Step 2 and market forecast data from Step 3 as inputs. This allows it to identify target segments and personalize ad content using a generative AI model. The output is an ad plan for each segment. In this step, the strategy formulation algorithm determines the ad content and delivery timing.

[0092] Step 5:

[0093] The device tracks the user's online behavior. It collects web visit data and click data as input. Specifically, it uses browser cookies and tracking pixels to record the user's behavioral patterns and sends this data to the server. The output is a history of each user's interests and activities. At this stage, behavioral data is collected in real time.

[0094] Step 6:

[0095] The server uses the collected user behavior data to evaluate the effectiveness of the ads and adjust the strategy as needed. The input is a combination of the behavior data collected in step 5 and the ad plan generated in step 4. This allows for the measurement of ad click-through rates and effectiveness, and the dynamic adjustment of the campaign. The output is the updated ad strategy. This step executes a strategy adjustment algorithm based on a feedback loop.

[0096] (Application Example 1)

[0097] 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."

[0098] Traditional marketing systems struggle to deliver ads at the optimal time for each customer and are unable to respond quickly to dynamic market fluctuations. Furthermore, they lack mechanisms for evaluating ad effectiveness in real time and making rapid adjustments, resulting in insufficient return on advertising spend. Moreover, there is a growing demand for personalized advertising based on users' online behavior.

[0099] 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.

[0100] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer sentiment and interests, means for predicting market trends through time-series analysis, means for automating advertising promotion and personalizing advertisements according to user groups, means for optimizing information content according to user behavior, and means for tracking users' online behavior and optimizing the timing of advertisement delivery based on that data. This enables the personalization of advertisements at the optimal timing for each user, improving the return on advertising spend and allowing for a rapid response to market trends.

[0101] "Customer information" refers to data held by a company about individuals or corporations, including purchase history, profiles, and social media activity information.

[0102] "Natural language processing technology" refers to computer science techniques that enable computers to understand, analyze, and utilize human language.

[0103] "Customer sentiment" refers to the feelings and emotions that consumers experience, and is a psychological reaction to products and services.

[0104] "Interest" refers to the degree of interest or curiosity that consumers show towards a particular product or service.

[0105] Time series analysis is a method of analyzing data that changes over time to predict future trends and tendencies.

[0106] "Market trends" refer to changes and trends in factors that affect economic activity, such as overall market demand and supply, price fluctuations, and the competitive landscape.

[0107] "Advertising promotion" refers to activities aimed at increasing awareness of products and services by delivering advertising messages to target consumer groups through various media.

[0108] A "user group" is a group of consumers who share common characteristics or interests, and is often a target group for marketing activities.

[0109] "Personalization" is the process of customizing information and services based on the needs and preferences of each individual consumer.

[0110] "Information content" refers to a collection of information provided in digital format, including text, images, and videos intended for education, entertainment, and informational purposes.

[0111] "Online behavior" refers to the specific actions and activities of consumers when using the internet, such as website browsing history and click history.

[0112] The system of this invention is configured with a server at its core. The server first periodically collects customer information from companies through CRM systems and social media APIs. The collected data is diverse, including purchase history and social media activity. The server analyzes this data using natural language processing techniques with a Python library to extract each customer's emotions and interests. In this process, for example, it can infer what types of products a customer is interested in from their purchase history, and identify emotions requiring urgent attention from their social media posts.

[0113] Furthermore, the server uses time series analysis to predict market trends. In this process, it models historical sales and market data using Python libraries such as numpy and pandas to provide timely market forecasts. This allows companies to predict future consumer needs and quickly adjust their marketing strategies.

[0114] Furthermore, the server automatically personalizes and optimizes ads based on the analysis results and connects to the advertising promotion platform to deliver ads to target customers at the appropriate time. For example, it tracks users' online behavior in real time and recommends the most relevant products when users access a website.

[0115] Furthermore, users' smartphones have an application installed that monitors their online behavior and sends data to a server. This application helps optimize ad delivery timing by collecting data and interacting with the server.

[0116] For example, the server can detect when a user uses the word "happy," determine that their purchase intent is high, and then deliver a targeted ad the following morning.

[0117] Examples of prompts include, "Extract happiness scores from the following dataset and provide an approach to design the optimal advertising strategy." These prompts, when combined with generative AI models, enable more advanced data analysis.

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The server periodically collects customer information through the company's CRM system and social media APIs. Inputs include customer purchase history and social media activity data. This data is stored in a database, providing foundational information for analyzing customer interests and behavioral trends.

[0121] Step 2:

[0122] The server uses a Python natural language processing library to extract sentiment and interest from collected customer data. The input is customer text data, and the output is the result of sentiment analysis based on that data. For example, this analyzes how keywords included in product reviews influence customer ratings.

[0123] Step 3:

[0124] The server uses Python's NumPy and pandas libraries to perform time series analysis and predict market trends. Inputs are historical sales and market data, and outputs are future demand forecasts. This process allows the server to predict future sales for each product, which can then be used for inventory management and marketing strategies.

[0125] Step 4:

[0126] The server connects to the advertising platform and automatically generates strategies for delivering personalized ads at the appropriate time. The input is sentiment analysis and market forecast information obtained in previous steps, and the output is a personalized advertising campaign. The server aims to optimize ads and attract the attention of target consumers.

[0127] Step 5:

[0128] The device monitors the user's online behavior in real time and sends that data to the server. The input is the user's clicks and browsing history, and the output is timing data for ad delivery based on that data. Specifically, it monitors which websites the user is visiting and displays ads in a timely manner that are relevant to that behavior.

[0129] Step 6:

[0130] Users receive personalized advertisements sent from the server on their devices. The input is the advertisement content, and the output is the user's response to it. After the advertisement is displayed, user actions (clicks, purchases, etc.) are collected again as data and used for future marketing strategies.

[0131] 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.

[0132] This invention is a system that enables personalized marketing strategies using customer data and user sentiment. This system consists of a server, sentiment engine, terminals, and users, and operates through the following process:

[0133] First, the server collects customer data from the company's CRM system and social media APIs. This includes a variety of customer information, such as purchase history, inquiries, browsing data, and social media activity. By collecting this data, a foundation is formed to understand basic customer preferences and patterns.

[0134] Next, using the information recognized by the emotion engine, the server analyzes the customer's text data to extract specific emotions. This involves using natural language processing techniques to assign emotion tags such as positive, negative, and neutral to the customer's text. This gives the server a foundation for a deep understanding of the user's preferences and tendencies.

[0135] Furthermore, the server uses time-series analysis to predict market trends from external market data and combines this with customer sentiment data to formulate optimal marketing strategies. This generates more sophisticated and personalized advertising campaigns. Based on the strategy, the server personalizes ad content according to customer segments and automates ad delivery.

[0136] Next, the device tracks the user's website behavior and sends the collected data to the server. This data includes behavioral information such as which products the user viewed and which content they clicked on. Based on this, the server uses an emotion engine to monitor the user's real-time emotions and dynamically optimize the web content.

[0137] As a concrete example, consider a scenario where a user is searching for a specific product on an e-commerce site. In this case, the server analyzes the user's emotions, and if it determines that the user is feeling positive, it recommends related products that match that emotion. Conversely, if the user expresses negative emotions, it provides emotionally sensitive follow-up emails or promotions. In this way, companies can implement more effective marketing strategies rooted in emotions.

[0138] This invention enables companies to personalize their interactions with customers, taking their emotions into consideration, thereby achieving higher marketing efficiency and improved customer satisfaction.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server collects customer data from the company's CRM system and social media APIs. This includes customer purchase history, inquiry data, and social media posts. The server regularly updates this data, creating a foundation for maintaining up-to-date customer information.

[0142] Step 2:

[0143] The server applies natural language processing techniques to the collected text data to extract customer emotions and interests. This process assigns emotion tags (positive, negative, neutral) through text analysis, allowing the server to understand the customer's current emotional state.

[0144] Step 3:

[0145] The emotion engine recognizes the user's emotions in real time and sends that data to the server. This allows the server to track the user's current emotional trends in detail.

[0146] Step 4:

[0147] The server predicts future market trends through time series analysis. In this process, it utilizes external market data and sales history to model upcoming trends and build highly accurate demand forecasts.

[0148] Step 5:

[0149] The server automatically generates the optimal marketing strategy by combining emotional data obtained from the emotion engine with market trend forecasts. This strategy includes designing targeted advertising content and scheduling its delivery to specific customer segments.

[0150] Step 6:

[0151] The device tracks the user's website browsing behavior and sends that data to the server. For example, this data might include the time spent viewing a specific product or the frequency of clicks.

[0152] Step 7:

[0153] The server seamlessly optimizes web content based on user behavior and emotional data. For example, if a user is in a positive emotional state, it will prominently display recommendations for related products and show more content that will pique their interest.

[0154] Step 8:

[0155] Users experience advertisements and product recommendations optimized for their own emotions and behavior on their devices. This provides a more personalized and intuitive purchasing experience.

[0156] Through this process, companies can achieve advanced, emotion-based personalization and improve the quality of the customer experience.

[0157] (Example 2)

[0158] 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".

[0159] Existing marketing systems struggle to personalize interactions while fully considering customer emotions and preferences, and there is a need to develop effective sales strategies that quickly reflect market trends. As a result, companies face the challenge of lacking the means to provide dynamic and personalized engagement.

[0160] 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.

[0161] In this invention, the server includes a device for collecting customer information, a device for analyzing the collected customer information using analytical methods to extract customer emotions and preferences, and a device for predicting market trends using a time-series model. This enables the rapid development of personalized marketing strategies that take into account the emotions and preferences of each individual customer, and optimizes individualized ad delivery and content display.

[0162] "Customer information" refers to data related to an individual or organization, such as their business transactions, behavioral history, preferences, and emotions.

[0163] "Analysis methods" refer to technical means and algorithms used to analyze collected data and derive specific insights or conclusions.

[0164] "Emotion" refers to the classification of a customer's psychological state, such as positive, negative, or neutral, which can be interpreted from their text and behavior.

[0165] "Preferences" refer to information about products, services, or areas of interest that customers seek.

[0166] A "time series model" refers to a method that uses time series data to analyze past patterns and trends and predict future trends and characteristics.

[0167] "Market trends" refer to tendencies that indicate changes in demand and supply in a particular industry or product category, consumer interests, and shifts in the competitive environment.

[0168] "Personalization" refers to the process of individually adjusting the products and services offered based on the characteristics and needs of each customer.

[0169] "Sales strategy" refers to the policies and plans for effectively delivering products and services to the market and maximizing revenue.

[0170] "Ad delivery" refers to the process of delivering advertising messages to a specific target audience.

[0171] "Personalization" refers to adjusting or modifying general content to suit a specific customer or situation.

[0172] "Content display optimization" refers to dynamically adjusting the display of information on web pages and applications based on user interests and behavior, in order to maximize their effectiveness.

[0173] This invention is a system that leverages customer data and user sentiment to realize personalized marketing strategies. This system consists of a server, an emotion engine, terminals, and users.

[0174] The server first collects customer information using the company's CRM system and social media APIs. This includes information such as purchase history, inquiries, browsing data, and social media activity. The collected data forms the basis for understanding the customer's basic preferences and behavioral patterns. Next, the server uses an emotion engine to analyze this data and leverages natural language processing techniques to extract sentiment tags such as positive, negative, and neutral from the customer's text.

[0175] Furthermore, the server uses time-series models to predict external market trends and combines them with customer sentiment data to formulate optimal sales strategies. This generates more sophisticated and personalized advertising campaigns. Based on this strategy, the server personalizes ad content according to customer groups and automates ad delivery.

[0176] Subsequently, the device tracks the user's behavior on the website and sends the collected data to the server. This data includes behavioral information such as which products the user viewed and which content they clicked on. Based on this, the server uses an emotion engine to evaluate the user's real-time emotions and dynamically optimize the displayed content.

[0177] A concrete example is a scenario where a user searches for a specific product on an online shop. In this case, the server uses a generative AI model to analyze the user's emotions. If it determines that the emotion is positive, it suggests related products that match that emotion. On the other hand, if the user expresses negative emotions, it provides emotionally sensitive follow-up emails or promotions. In this way, companies can implement more effective engagement strategies based on emotions.

[0178] An example of a prompt is, "Analyze the following customer review and extract the sentiment tag. Review: 'This product is easy to use and I am very satisfied.'" Based on this prompt, the generative AI model identifies positive sentiments.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The server collects data from the company's CRM system and social media APIs. Its inputs include customer purchase history, inquiry history, browsing data, and social media activity information. This data is retrieved via API requests. The server aggregates and stores this data, building a foundation for creating basic customer profiles.

[0182] Step 2:

[0183] The server uses an emotion engine to analyze this aggregated customer data. It uses the customer text data obtained in Step 1 as input. A generative AI model is used for natural language processing, extracting emotion tags such as positive, negative, and neutral. These output emotion tags form the basis for deepening customer understanding in marketing.

[0184] Step 3:

[0185] The server uses a time-series model to analyze external market data and predict future market trends. It uses historical market trend data and sentiment data extracted in step 2 as input. This model predicts, for example, purchasing patterns and seasonal market trends. As an output, an optimal sales strategy is formulated based on these insights.

[0186] Step 4:

[0187] The server generates personalized advertising campaigns based on the formulated sales strategy. Using a generative AI model, it constructs campaigns using prompt text as input. This results in compelling ad content tailored to specific customer segments. The output is then sent to an automated ad serving system.

[0188] Step 5:

[0189] The device tracks the user's behavior on websites and sends data to the server in real time. As input, it captures behavioral information such as which products the user viewed and which links they clicked. The device collects this data as digital events and sends it to the server, which then becomes input. As output, the server re-analyzes the user's sentiment based on this behavioral data.

[0190] Step 6:

[0191] The server re-evaluates user sentiment and dynamically optimizes web content. It reuses user behavior data obtained in step 5 and sentiment tags extracted in step 2 as input. This allows new information and promotions to be displayed and output to the user. For example, if a user is searching for a specific product in an online shop, positive sentiment will trigger related product suggestions, while negative sentiment will trigger corresponding promotions.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] Traditional marketing activities by companies have been limited in their ability to analyze customer information, predict market trends, and deliver advertisements based on individual user emotions and interests. This has resulted in insufficient improvement in customer satisfaction and maximization of sales effectiveness. Therefore, there has been a growing need to understand user emotions and preferences in real time and provide personalized advertisements and content accordingly.

[0195] 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.

[0196] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer emotions and interests, and means for predicting market trends through time-series analysis. This enables dynamic information display based on the user's emotions.

[0197] "Customer information" refers to data about individual customers, including a variety of information such as purchase history, inquiries, and browsing history.

[0198] "Natural language processing technology" refers to the algorithms and methods used by computers to analyze and understand human language.

[0199] "Customer emotions" refers to the emotional states, such as positive, negative, or neutral, that a customer exhibits.

[0200] "Interest" refers to a customer's preference for products or content that they find appealing.

[0201] Time series analysis is a statistical method used to predict future trends based on past data.

[0202] "Market trends" is a concept that refers to future changes and trends in a particular market.

[0203] "Sales strategy" refers to the plan or policy regarding how to deliver products or services to the market.

[0204] Automating advertising refers to the process of creating, delivering, and optimizing advertisements without human intervention.

[0205] A "customer group" is a concept that refers to a collection of customers who share specific attributes or patterns.

[0206] "Personalization" means tailoring products and services to individual customers.

[0207] The system for implementing this invention consists of a server, a terminal, and a user. The server uses natural language processing and time series analysis techniques to collect and analyze customer information and extract emotions. Specifically, the server is built using Python and utilizes NLP libraries (e.g., spaCy and transformers) to analyze collected text data and extract customer emotions and interests. It also uses a time series analysis library to predict market trends. The server uses the OpenAI® API to optimize advertisements and content and displays personalized advertisements to users.

[0208] The devices, such as smartphones and personal computers, are responsible for collecting user behavior data and transmitting it to servers. Every time a user visits a specific website or engages in social media activity, this data is tracked and transmitted as relevant information.

[0209] Users use the web daily on their smartphones and computers, and their behavioral data is collected in real time. For example, when a user shows positive emotions while browsing an e-commerce site for pet supplies, they will automatically receive push notifications advertising new pet food based on those emotions.

[0210] Examples of prompt messages are as follows:

[0211] "The user showed positive emotions while browsing pet supplies. Please recommend products that match those emotions. For example, information about trial campaigns for new pet food or toys."

[0212] The system of the present invention is effective in personalizing the customer experience and improving the effectiveness of advertisements provided by companies.

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The device tracks the user's website browsing data and social media activity. This includes collecting information such as pages visited, content clicked, and social media posts. The input data consists of user behavior information, and the output data is sent to the server.

[0216] Step 2:

[0217] The server receives user behavior data sent from the terminal and analyzes it using natural language processing techniques. Specifically, it identifies emotions from the collected text data and extracts emotion tags such as positive, negative, and neutral. The input is user behavior information, and the output is emotion tags.

[0218] Step 3:

[0219] The server uses time-series analysis to predict market trends. Based on historical data, it numerically predicts future market trends and performs further analysis in conjunction with sentiment tags. The input is historical market data and sentiment tags, and the output is predicted market trend data.

[0220] Step 4:

[0221] The server generates personalized advertisements based on sentiment data and market trend data obtained using a generative AI model. Next, it uses the OpenAI API to input optimal prompt messages and optimize advertisements and content for the user. The input is sentiment data and market trend data, and the output is personalized advertisements.

[0222] Step 5:

[0223] The device displays personalized advertisements sent from the server to the user. Here, the user can view newly optimized advertisements on their smartphone or computer. The input is the personalized advertisement from the server, and the output is the display of the advertisement to the user.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] [Second Embodiment]

[0228] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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".

[0240] This invention is a system for highly automating and optimizing marketing strategies by utilizing customer and market data held by companies. This system consists of a server, terminals, and users, and operates as follows:

[0241] First, the server periodically collects customer data through the company's CRM system and social media APIs. Here, all relevant data is aggregated, including purchase history, customer profiles, and social media activity information. Based on this data, the server uses natural language processing technology to analyze the text data and extract customer sentiments and preferences.

[0242] Next, the server performs time-series analysis, using external market data and historical sales data to capture current market trends. Based on this information, it trains predictive models to forecast future consumer needs and demand. This process enables companies to respond quickly to market fluctuations and develop appropriate product strategies.

[0243] The server also has the capability to automatically generate optimal marketing strategies based on the insights it gains. This includes designing advertising campaigns, identifying target segments, and personalizing ad content. Furthermore, it connects to advertising delivery platforms to automatically deliver the most relevant ads to target customers.

[0244] On the other hand, the device tracks the user's online behavior (e.g., website clicks and browsing history) and sends this data to a server. This data is used to gain a deeper understanding of the user's interests and to optimize advertising and content.

[0245] For example, when a user visits an e-commerce site via their device, the server recommends relevant products based on their past browsing history. Furthermore, the server collects user comments and opinions from social media and displays advertisements on topics that may be of interest to the customer. These advertisements are delivered at the optimal time and with the most relevant content through the user's device.

[0246] This system enables companies to enhance personalized marketing activities and improve the customer experience. It also allows them to maximize the return on advertising spend and uncover new market opportunities.

[0247] The following describes the processing flow.

[0248] Step 1:

[0249] The server collects customer data from companies using CRM systems and social media APIs. This data includes customer purchase history, browsing history, inquiries, and social media interactions. Website log information is also collected.

[0250] Step 2:

[0251] The server applies natural language processing techniques to the collected data to extract customer emotions and interests from text information. This includes customer-provided reviews, feedback, and social media posts. By analyzing emotions such as positive and negative, the server reveals customers' latent needs.

[0252] Step 3:

[0253] The server performs time-series analysis based on historical sales data and market reports to predict market trends. This includes forecasting future consumer trends and demand fluctuations. The server uses this data to train machine learning models and forecast product demand.

[0254] Step 4:

[0255] The server generates the optimal marketing strategy for target customer segments based on analysis results and market forecasts. This includes determining which ads to deliver to which customers and through which channels. Ad campaigns are personalized, and the server automates the ad content.

[0256] Step 5:

[0257] The server connects to the advertising platform to deliver ads to target customers. During delivery, it monitors the effectiveness of the ads in real time (e.g., click-through rate, conversion rate) and adjusts the ad content and delivery settings as needed to maximize ad effectiveness.

[0258] Step 6:

[0259] The device tracks the user's website visits and online behavior, and sends this information to the server. The server uses this data to optimize web content to suit the user's preferences.

[0260] Step 7:

[0261] The server combines user behavior data with insights based on market forecasts to provide purchase recommendations and optimize content. Users can receive personalized product recommendations and promotions through their devices. This process allows users to enjoy a more personalized experience while improving the marketing efficiency of businesses.

[0262] (Example 1)

[0263] 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."

[0264] In today's business environment, developing swift and effective marketing strategies is crucial for companies to deepen customer relationships and maintain competitiveness. However, effectively utilizing vast amounts of customer and market data to deliver personalized advertising is a major challenge for many companies. Existing systems struggle to process data effectively and efficiently in terms of data collection and analysis, customer classification, and sales strategy planning and implementation.

[0265] 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.

[0266] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer sentiment and interests, and means for predicting market trends through time series analysis. This enables companies to effectively utilize data and formulate and implement optimal sales strategies. Furthermore, by delivering personalized advertisements to customers, it improves targeting accuracy and maximizes sales results.

[0267] "Customer information" refers to data that companies collect about their customers, including, for example, purchase history, personal profiles, and records of online activity.

[0268] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and is particularly used for analyzing text and audio data.

[0269] Time series analysis is a statistical method that analyzes the patterns of data fluctuations over time to predict future trends.

[0270] A "sales strategy" refers to the plans and policies used when selling products or services in the market, and includes things like target setting and promotional plans.

[0271] "Personalized advertising" is a technique for achieving more effective communication by adapting advertising content to the characteristics and preferences of customers.

[0272] "Online content" refers to all information and services viewed or used on the Internet, including websites, content, and applications.

[0273] "Collaborative filtering" is a method that provides personalized recommendations based on a user's past behavior patterns and similar behaviors of other users.

[0274] "Real-time monitoring" is a process that enables rapid decision-making by continuously observing and recording specific indicators or activities in real time.

[0275] "Dynamic adjustment" refers to a function that enhances flexibility by automatically changing systems and strategies in response to changes in conditions and circumstances.

[0276] This system is designed to enable companies to leverage customer information and market data to implement effective marketing strategies. The system consists of servers, terminals, and users.

[0277] The server collects customer information through the company's databases and APIs. This collected data includes, for example, purchase history from CRM systems, user profiles from user information management tools, and posts from social media APIs. Natural language processing techniques are applied to this text data to analyze customer sentiment and interests. This technique utilizes machine learning algorithms and pre-trained generative AI models.

[0278] Next, the server uses time-series data provided by external market data providers to predict market trends. The server leverages statistical algorithms to analyze market trends and build predictive models. This allows companies to foresee future consumer needs and optimize their sales strategies.

[0279] The server generates the optimal marketing strategy based on these analysis results. Generative AI models are used to personalize ad content, streamlining the planning and targeting of promotional activities. Ads are connected to the ad delivery platform and automatically delivered from the server.

[0280] Meanwhile, the device monitors the user's online behavior. For example, it collects data on the pages the user views and the links they click on websites and sends this data to the server. This data is used to measure the effectiveness of advertisements and optimize content.

[0281] Users can receive personalized content and advertisements based on their interests via a terminal. As specific examples, related products may be recommended based on the product categories the users have browsed, or advertisements based on topics that are interesting may be displayed.

[0282] (Example of a prompt sentence)

[0283] "Perform sentiment analysis on customer information and propose appropriate advertisements."

[0284] "Utilize past data to construct the next sales strategy."

[0285] With this system, companies can conduct more accurate marketing and deepen their engagement with consumers.

[0286] The flow of the specific process in Example 1 will be described using FIG. 11.

[0287] Step 1:

[0288] The server collects customer information. As inputs, it uses purchase history data from the company's in-house CRM system, customer profile data, and user-posted data from external social media APIs. These data are aggregated in a database in preparation for the next analysis stage. As a specific operation, it periodically acquires data through API calls and performs the process of inserting the data into the database.

[0289] Step 2:

[0290] The server uses natural language processing (NLP) techniques to analyze the collected customer information. The text data collected in Step 1 is used as input. Specifically, a generative AI model is used to analyze the sentiment of the text and extract customer interests and trends. The output will be a sentiment score and areas of interest for each customer. This step involves applying machine learning algorithms to quantify the text data.

[0291] Step 3:

[0292] The server performs time series analysis to predict market trends. It uses external market trend data and the company's own historical sales data as input. Data processing involves trend analysis of time series data and the construction of a predictive model. The output provides future demand forecasts and changes in market needs. This process includes data smoothing and seasonality identification using statistical algorithms.

[0293] Step 4:

[0294] The server generates the optimal marketing strategy based on the analysis results. It utilizes customer sentiment data from Step 2 and market forecast data from Step 3 as inputs. This allows it to identify target segments and personalize ad content using a generative AI model. The output is an ad plan for each segment. In this step, the strategy formulation algorithm determines the ad content and delivery timing.

[0295] Step 5:

[0296] The device tracks the user's online behavior. It collects web visit data and click data as input. Specifically, it uses browser cookies and tracking pixels to record the user's behavioral patterns and sends this data to the server. The output is a history of each user's interests and activities. At this stage, behavioral data is collected in real time.

[0297] Step 6:

[0298] The server uses the collected user behavior data to evaluate the effectiveness of the ads and adjust the strategy as needed. The input is a combination of the behavior data collected in step 5 and the ad plan generated in step 4. This allows for the measurement of ad click-through rates and effectiveness, and the dynamic adjustment of the campaign. The output is the updated ad strategy. This step executes a strategy adjustment algorithm based on a feedback loop.

[0299] (Application Example 1)

[0300] 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."

[0301] Traditional marketing systems struggle to deliver ads at the optimal time for each customer and are unable to respond quickly to dynamic market fluctuations. Furthermore, they lack mechanisms for evaluating ad effectiveness in real time and making rapid adjustments, resulting in insufficient return on advertising spend. Moreover, there is a growing demand for personalized advertising based on users' online behavior.

[0302] 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.

[0303] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer sentiment and interests, means for predicting market trends through time-series analysis, means for automating advertising promotion and personalizing advertisements according to user groups, means for optimizing information content according to user behavior, and means for tracking users' online behavior and optimizing the timing of advertisement delivery based on that data. This enables the personalization of advertisements at the optimal timing for each user, improving the return on advertising spend and allowing for a rapid response to market trends.

[0304] "Customer information" refers to data related to individuals or legal entities held by an enterprise, including information such as purchase history, profiles, and activity information on social media.

[0305] "Natural language processing technology" is a technology in computer science for a computer to understand, analyze, and utilize human language.

[0306] "Customer sentiment" refers to the emotions and feelings held by consumers, which are the psychological reactions to products and services.

[0307] "Interest" refers to the degree of interest and curiosity shown by consumers towards specific products or services.

[0308] "Time series analysis" is a method for analyzing data that changes over time to predict future trends and tendencies.

[0309] "Market trend" refers to changes and trends in factors affecting economic activities, such as overall market demand, supply, price fluctuations, and competition situations.

[0310] "Advertising promotion" is an activity aimed at expanding the recognition of products or services, delivering advertising messages to target consumer groups through various media.

[0311] "User group" is a group of consumers with common characteristics and interests, and is often the target of marketing activities.

[0312] "Personalization" is a process of customizing information and services based on the needs and preferences of each individual consumer.

[0313] "Information content" is an aggregate of information provided in digital form, including text, images, videos, etc. for the purpose of education, entertainment, and information provision.

[0314] "Online behavior" refers to the specific actions and activities of consumers when using the internet, such as website browsing history and click history.

[0315] The system of this invention is configured with a server at its core. The server first periodically collects customer information from companies through CRM systems and social media APIs. The collected data is diverse, including purchase history and social media activity. The server analyzes this data using natural language processing techniques with a Python library to extract each customer's emotions and interests. In this process, for example, it can infer what types of products a customer is interested in from their purchase history, and identify emotions requiring urgent attention from their social media posts.

[0316] Furthermore, the server uses time series analysis to predict market trends. In this process, it models historical sales and market data using Python libraries such as numpy and pandas to provide timely market forecasts. This allows companies to predict future consumer needs and quickly adjust their marketing strategies.

[0317] Furthermore, the server automatically personalizes and optimizes ads based on the analysis results and connects to the advertising promotion platform to deliver ads to target customers at the appropriate time. For example, it tracks users' online behavior in real time and recommends the most relevant products when users access a website.

[0318] Furthermore, users' smartphones have an application installed that monitors their online behavior and sends data to a server. This application helps optimize ad delivery timing by collecting data and interacting with the server.

[0319] For example, the server can detect when a user uses the word "happy," determine that their purchase intent is high, and then deliver a targeted ad the following morning.

[0320] Examples of prompts include, "Extract happiness scores from the following dataset and provide an approach to design the optimal advertising strategy." These prompts, when combined with generative AI models, enable more advanced data analysis.

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The server periodically collects customer information through the company's CRM system and social media APIs. Inputs include customer purchase history and social media activity data. This data is stored in a database, providing foundational information for analyzing customer interests and behavioral trends.

[0324] Step 2:

[0325] The server uses a Python natural language processing library to extract sentiment and interest from collected customer data. The input is customer text data, and the output is the result of sentiment analysis based on that data. For example, this analyzes how keywords included in product reviews influence customer ratings.

[0326] Step 3:

[0327] The server uses Python's NumPy and pandas libraries to perform time series analysis and predict market trends. Inputs are historical sales and market data, and outputs are future demand forecasts. This process allows the server to predict future sales for each product, which can then be used for inventory management and marketing strategies.

[0328] Step 4:

[0329] The server connects to the advertising platform and automatically generates strategies for delivering personalized ads at the appropriate time. The input is sentiment analysis and market forecast information obtained in previous steps, and the output is a personalized advertising campaign. The server aims to optimize ads and attract the attention of target consumers.

[0330] Step 5:

[0331] The device monitors the user's online behavior in real time and sends that data to the server. The input is the user's clicks and browsing history, and the output is timing data for ad delivery based on that data. Specifically, it monitors which websites the user is visiting and displays ads in a timely manner that are relevant to that behavior.

[0332] Step 6:

[0333] Users receive personalized advertisements sent from the server on their devices. The input is the advertisement content, and the output is the user's response to it. After the advertisement is displayed, user actions (clicks, purchases, etc.) are collected again as data and used for future marketing strategies.

[0334] 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.

[0335] This invention is a system that enables personalized marketing strategies using customer data and user sentiment. This system consists of a server, sentiment engine, terminals, and users, and operates through the following process:

[0336] First, the server collects customer data from the company's CRM system and social media APIs. This includes a variety of customer information, such as purchase history, inquiries, browsing data, and social media activity. By collecting this data, a foundation is formed to understand basic customer preferences and patterns.

[0337] Next, using the information recognized by the emotion engine, the server analyzes the customer's text data to extract specific emotions. This involves using natural language processing techniques to assign emotion tags such as positive, negative, and neutral to the customer's text. This gives the server a foundation for a deep understanding of the user's preferences and tendencies.

[0338] Furthermore, the server uses time-series analysis to predict market trends from external market data and combines this with customer sentiment data to formulate optimal marketing strategies. This generates more sophisticated and personalized advertising campaigns. Based on the strategy, the server personalizes ad content according to customer segments and automates ad delivery.

[0339] Next, the device tracks the user's website behavior and sends the collected data to the server. This data includes behavioral information such as which products the user viewed and which content they clicked on. Based on this, the server uses an emotion engine to monitor the user's real-time emotions and dynamically optimize the web content.

[0340] As a concrete example, consider a scenario where a user is searching for a specific product on an e-commerce site. In this case, the server analyzes the user's emotions, and if it determines that the user is feeling positive, it recommends related products that match that emotion. Conversely, if the user expresses negative emotions, it provides emotionally sensitive follow-up emails or promotions. In this way, companies can implement more effective marketing strategies rooted in emotions.

[0341] This invention enables companies to personalize their interactions with customers, taking their emotions into consideration, thereby achieving higher marketing efficiency and improved customer satisfaction.

[0342] The following describes the processing flow.

[0343] Step 1:

[0344] The server collects customer data from the company's CRM system and social media APIs. This includes customer purchase history, inquiry data, and social media posts. The server regularly updates this data, creating a foundation for maintaining up-to-date customer information.

[0345] Step 2:

[0346] The server applies natural language processing techniques to the collected text data to extract customer emotions and interests. This process assigns emotion tags (positive, negative, neutral) through text analysis, allowing the server to understand the customer's current emotional state.

[0347] Step 3:

[0348] The emotion engine recognizes the user's emotions in real time and sends that data to the server. This allows the server to track the user's current emotional trends in detail.

[0349] Step 4:

[0350] The server predicts future market trends through time series analysis. In this process, it utilizes external market data and sales history to model upcoming trends and build highly accurate demand forecasts.

[0351] Step 5:

[0352] The server automatically generates the optimal marketing strategy by combining emotional data obtained from the emotion engine with market trend forecasts. This strategy includes designing targeted advertising content and scheduling its delivery to specific customer segments.

[0353] Step 6:

[0354] The device tracks the user's website browsing behavior and sends that data to the server. For example, this data might include the time spent viewing a specific product or the frequency of clicks.

[0355] Step 7:

[0356] The server seamlessly optimizes web content based on user behavior and emotional data. For example, if a user is in a positive emotional state, it will prominently display recommendations for related products and show more content that will pique their interest.

[0357] Step 8:

[0358] Users experience advertisements and product recommendations optimized for their own emotions and behavior on their devices. This provides a more personalized and intuitive purchasing experience.

[0359] Through this process, companies can achieve advanced, emotion-based personalization and improve the quality of the customer experience.

[0360] (Example 2)

[0361] 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".

[0362] Existing marketing systems struggle to personalize interactions while fully considering customer emotions and preferences, and there is a need to develop effective sales strategies that quickly reflect market trends. As a result, companies face the challenge of lacking the means to provide dynamic and personalized engagement.

[0363] 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.

[0364] In this invention, the server includes a device for collecting customer information, a device for analyzing the collected customer information using analytical methods to extract customer emotions and preferences, and a device for predicting market trends using a time-series model. This enables the rapid development of personalized marketing strategies that take into account the emotions and preferences of each individual customer, and optimizes individualized ad delivery and content display.

[0365] "Customer information" refers to data related to an individual or organization, such as their business transactions, behavioral history, preferences, and emotions.

[0366] "Analysis methods" refer to technical means and algorithms used to analyze collected data and derive specific insights or conclusions.

[0367] "Emotion" refers to the classification of a customer's psychological state, such as positive, negative, or neutral, which can be interpreted from their text and behavior.

[0368] "Preferences" refer to information about products, services, or areas of interest that customers seek.

[0369] A "time series model" refers to a method that uses time series data to analyze past patterns and trends and predict future trends and characteristics.

[0370] "Market trends" refer to tendencies that indicate changes in demand and supply in a particular industry or product category, consumer interests, and shifts in the competitive environment.

[0371] "Personalization" refers to the process of individually adjusting the products and services offered based on the characteristics and needs of each customer.

[0372] "Sales strategy" refers to the policies and plans for effectively delivering products and services to the market and maximizing revenue.

[0373] "Ad delivery" refers to the process of delivering advertising messages to a specific target audience.

[0374] "Personalization" refers to adjusting or modifying general content to suit a specific customer or situation.

[0375] "Content display optimization" refers to dynamically adjusting the display of information on web pages and applications based on user interests and behavior, in order to maximize their effectiveness.

[0376] This invention is a system that leverages customer data and user sentiment to realize personalized marketing strategies. This system consists of a server, an emotion engine, terminals, and users.

[0377] The server first collects customer information using the company's CRM system and social media APIs. This includes information such as purchase history, inquiries, browsing data, and social media activity. The collected data forms the basis for understanding the customer's basic preferences and behavioral patterns. Next, the server uses an emotion engine to analyze this data and leverages natural language processing techniques to extract sentiment tags such as positive, negative, and neutral from the customer's text.

[0378] Furthermore, the server uses time-series models to predict external market trends and combines them with customer sentiment data to formulate optimal sales strategies. This generates more sophisticated and personalized advertising campaigns. Based on this strategy, the server personalizes ad content according to customer groups and automates ad delivery.

[0379] Subsequently, the device tracks the user's behavior on the website and sends the collected data to the server. This data includes behavioral information such as which products the user viewed and which content they clicked on. Based on this, the server uses an emotion engine to evaluate the user's real-time emotions and dynamically optimize the displayed content.

[0380] A concrete example is a scenario where a user searches for a specific product on an online shop. In this case, the server uses a generative AI model to analyze the user's emotions. If it determines that the emotion is positive, it suggests related products that match that emotion. On the other hand, if the user expresses negative emotions, it provides emotionally sensitive follow-up emails or promotions. In this way, companies can implement more effective engagement strategies based on emotions.

[0381] An example of a prompt is, "Analyze the following customer review and extract the sentiment tag. Review: 'This product is easy to use and I am very satisfied.'" Based on this prompt, the generative AI model identifies positive sentiments.

[0382] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0383] Step 1:

[0384] The server collects data from the company's CRM system and social media APIs. Its inputs include customer purchase history, inquiry history, browsing data, and social media activity information. This data is retrieved via API requests. The server aggregates and stores this data, building a foundation for creating basic customer profiles.

[0385] Step 2:

[0386] The server uses an emotion engine to analyze this aggregated customer data. It uses the customer text data obtained in Step 1 as input. A generative AI model is used for natural language processing, extracting emotion tags such as positive, negative, and neutral. These output emotion tags form the basis for deepening customer understanding in marketing.

[0387] Step 3:

[0388] The server uses a time-series model to analyze external market data and predict future market trends. It uses historical market trend data and sentiment data extracted in step 2 as input. This model predicts, for example, purchasing patterns and seasonal market trends. As an output, an optimal sales strategy is formulated based on these insights.

[0389] Step 4:

[0390] The server generates personalized advertising campaigns based on the formulated sales strategy. Using a generative AI model, it constructs campaigns using prompt text as input. This results in compelling ad content tailored to specific customer segments. The output is then sent to an automated ad serving system.

[0391] Step 5:

[0392] The device tracks the user's behavior on websites and sends data to the server in real time. As input, it captures behavioral information such as which products the user viewed and which links they clicked. The device collects this data as digital events and sends it to the server, which then becomes input. As output, the server re-analyzes the user's sentiment based on this behavioral data.

[0393] Step 6:

[0394] The server re-evaluates user sentiment and dynamically optimizes web content. It reuses user behavior data obtained in step 5 and sentiment tags extracted in step 2 as input. This allows new information and promotions to be displayed and output to the user. For example, if a user is searching for a specific product in an online shop, positive sentiment will trigger related product suggestions, while negative sentiment will trigger corresponding promotions.

[0395] (Application Example 2)

[0396] 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."

[0397] Traditional marketing activities by companies have been limited in their ability to analyze customer information, predict market trends, and deliver advertisements based on individual user emotions and interests. This has resulted in insufficient improvement in customer satisfaction and maximization of sales effectiveness. Therefore, there has been a growing need to understand user emotions and preferences in real time and provide personalized advertisements and content accordingly.

[0398] 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.

[0399] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer emotions and interests, and means for predicting market trends through time-series analysis. This enables dynamic information display based on the user's emotions.

[0400] "Customer information" refers to data about individual customers, including a variety of information such as purchase history, inquiries, and browsing history.

[0401] "Natural language processing technology" refers to the algorithms and methods used by computers to analyze and understand human language.

[0402] "Customer emotions" refers to the emotional states, such as positive, negative, or neutral, that a customer exhibits.

[0403] "Interest" refers to a customer's preference for products or content that they find appealing.

[0404] Time series analysis is a statistical method used to predict future trends based on past data.

[0405] "Market trends" is a concept that refers to future changes and trends in a particular market.

[0406] "Sales strategy" refers to the plan or policy regarding how to deliver products or services to the market.

[0407] Automating advertising refers to the process of creating, delivering, and optimizing advertisements without human intervention.

[0408] A "customer group" is a concept that refers to a collection of customers who share specific attributes or patterns.

[0409] "Personalization" means tailoring products and services to individual customers.

[0410] The system for implementing this invention consists of a server, a terminal, and a user. The server uses natural language processing and time series analysis techniques to collect and analyze customer information and extract emotions. Specifically, the server is built using Python and utilizes NLP libraries (e.g., spaCy and transformers) to analyze collected text data and extract customer emotions and interests. It also uses a time series analysis library to predict market trends. The server uses the OpenAI API to optimize advertisements and content and displays personalized advertisements to users.

[0411] The devices, such as smartphones and personal computers, are responsible for collecting user behavior data and transmitting it to servers. Every time a user visits a specific website or engages in social media activity, this data is tracked and transmitted as relevant information.

[0412] Users use the web daily on their smartphones and computers, and their behavioral data is collected in real time. For example, when a user shows positive emotions while browsing an e-commerce site for pet supplies, they will automatically receive push notifications advertising new pet food based on those emotions.

[0413] Examples of prompt messages are as follows:

[0414] "The user showed positive emotions while browsing pet supplies. Please recommend products that match those emotions. For example, information about trial campaigns for new pet food or toys."

[0415] The system of the present invention is effective in personalizing the customer experience and improving the effectiveness of advertisements provided by companies.

[0416] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0417] Step 1:

[0418] The device tracks the user's website browsing data and social media activity. This includes collecting information such as pages visited, content clicked, and social media posts. The input data consists of user behavior information, and the output data is sent to the server.

[0419] Step 2:

[0420] The server receives user behavior data sent from the terminal and analyzes it using natural language processing techniques. Specifically, it identifies emotions from the collected text data and extracts emotion tags such as positive, negative, and neutral. The input is user behavior information, and the output is emotion tags.

[0421] Step 3:

[0422] The server uses time-series analysis to predict market trends. Based on historical data, it numerically predicts future market trends and performs further analysis in conjunction with sentiment tags. The input is historical market data and sentiment tags, and the output is predicted market trend data.

[0423] Step 4:

[0424] The server generates personalized advertisements based on sentiment data and market trend data obtained using a generative AI model. Next, it uses the OpenAI API to input optimal prompt messages and optimize advertisements and content for the user. The input is sentiment data and market trend data, and the output is personalized advertisements.

[0425] Step 5:

[0426] The device displays personalized advertisements sent from the server to the user. Here, the user can view newly optimized advertisements on their smartphone or computer. The input is the personalized advertisement from the server, and the output is the display of the advertisement to the user.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] [Third Embodiment]

[0431] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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".

[0443] This invention is a system for highly automating and optimizing marketing strategies by utilizing customer and market data held by companies. This system consists of a server, terminals, and users, and operates as follows:

[0444] First, the server periodically collects customer data through the company's CRM system and social media APIs. Here, all relevant data is aggregated, including purchase history, customer profiles, and social media activity information. Based on this data, the server uses natural language processing technology to analyze the text data and extract customer sentiments and preferences.

[0445] Next, the server performs time-series analysis, using external market data and historical sales data to capture current market trends. Based on this information, it trains predictive models to forecast future consumer needs and demand. This process enables companies to respond quickly to market fluctuations and develop appropriate product strategies.

[0446] The server also has the capability to automatically generate optimal marketing strategies based on the insights it gains. This includes designing advertising campaigns, identifying target segments, and personalizing ad content. Furthermore, it connects to advertising delivery platforms to automatically deliver the most relevant ads to target customers.

[0447] On the other hand, the device tracks the user's online behavior (e.g., website clicks and browsing history) and sends this data to a server. This data is used to gain a deeper understanding of the user's interests and to optimize advertising and content.

[0448] For example, when a user visits an e-commerce site via their device, the server recommends relevant products based on their past browsing history. Furthermore, the server collects user comments and opinions from social media and displays advertisements on topics that may be of interest to the customer. These advertisements are delivered at the optimal time and with the most relevant content through the user's device.

[0449] This system enables companies to enhance personalized marketing activities and improve the customer experience. It also allows them to maximize the return on advertising spend and uncover new market opportunities.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] The server collects customer data from companies using CRM systems and social media APIs. This data includes customer purchase history, browsing history, inquiries, and social media interactions. Website log information is also collected.

[0453] Step 2:

[0454] The server applies natural language processing techniques to the collected data to extract customer emotions and interests from text information. This includes customer-provided reviews, feedback, and social media posts. By analyzing emotions such as positive and negative, the server reveals customers' latent needs.

[0455] Step 3:

[0456] The server performs time-series analysis based on historical sales data and market reports to predict market trends. This includes forecasting future consumer trends and demand fluctuations. The server uses this data to train machine learning models and forecast product demand.

[0457] Step 4:

[0458] The server generates the optimal marketing strategy for target customer segments based on analysis results and market forecasts. This includes determining which ads to deliver to which customers and through which channels. Ad campaigns are personalized, and the server automates the ad content.

[0459] Step 5:

[0460] The server connects to the advertising platform to deliver ads to target customers. During delivery, it monitors the effectiveness of the ads in real time (e.g., click-through rate, conversion rate) and adjusts the ad content and delivery settings as needed to maximize ad effectiveness.

[0461] Step 6:

[0462] The device tracks the user's website visits and online behavior, and sends this information to the server. The server uses this data to optimize web content to suit the user's preferences.

[0463] Step 7:

[0464] The server combines user behavior data with insights based on market forecasts to provide purchase recommendations and optimize content. Users can receive personalized product recommendations and promotions through their devices. This process allows users to enjoy a more personalized experience while improving the marketing efficiency of businesses.

[0465] (Example 1)

[0466] 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."

[0467] In today's business environment, developing swift and effective marketing strategies is crucial for companies to deepen customer relationships and maintain competitiveness. However, effectively utilizing vast amounts of customer and market data to deliver personalized advertising is a major challenge for many companies. Existing systems struggle to process data effectively and efficiently in terms of data collection and analysis, customer classification, and sales strategy planning and implementation.

[0468] 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.

[0469] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer sentiment and interests, and means for predicting market trends through time series analysis. This enables companies to effectively utilize data and formulate and implement optimal sales strategies. Furthermore, by delivering personalized advertisements to customers, it improves targeting accuracy and maximizes sales results.

[0470] "Customer information" refers to data that companies collect about their customers, including, for example, purchase history, personal profiles, and records of online activity.

[0471] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and is particularly used for analyzing text and audio data.

[0472] Time series analysis is a statistical method that analyzes the patterns of data fluctuations over time to predict future trends.

[0473] A "sales strategy" refers to the plans and policies used when selling products or services in the market, and includes things like target setting and promotional plans.

[0474] "Personalized advertising" is a technique for achieving more effective communication by adapting advertising content to the characteristics and preferences of customers.

[0475] "Online content" refers to all information and services viewed or used on the Internet, including websites, content, and applications.

[0476] "Collaborative filtering" is a method that provides personalized recommendations based on a user's past behavior patterns and similar behaviors of other users.

[0477] "Real-time monitoring" is a process that enables rapid decision-making by continuously observing and recording specific indicators or activities in real time.

[0478] "Dynamic adjustment" refers to a function that enhances flexibility by automatically changing systems and strategies in response to changes in conditions and circumstances.

[0479] This system is designed to enable companies to leverage customer information and market data to implement effective marketing strategies. The system consists of servers, terminals, and users.

[0480] The server collects customer information through the company's databases and APIs. This collected data includes, for example, purchase history from CRM systems, user profiles from user information management tools, and posts from social media APIs. Natural language processing techniques are applied to this text data to analyze customer sentiment and interests. This technique utilizes machine learning algorithms and pre-trained generative AI models.

[0481] Next, the server uses time-series data provided by external market data providers to predict market trends. The server leverages statistical algorithms to analyze market trends and build predictive models. This allows companies to foresee future consumer needs and optimize their sales strategies.

[0482] The server generates the optimal marketing strategy based on these analysis results. Generative AI models are used to personalize ad content, streamlining the planning and targeting of promotional activities. Ads are connected to the ad delivery platform and automatically delivered from the server.

[0483] Meanwhile, the device monitors the user's online behavior. For example, it collects data on the pages the user views and the links they click on websites and sends this data to the server. This data is used to measure the effectiveness of advertisements and optimize content.

[0484] Users can receive personalized content and advertisements based on their interests through their devices. For example, related products may be recommended based on the product categories the user has viewed, or advertisements based on topics that interest them may be displayed.

[0485] (Example of a prompt message)

[0486] "Perform sentiment analysis based on customer data and propose appropriate advertisements."

[0487] "Use past data to develop your next sales strategy."

[0488] This system will enable companies to conduct more precise marketing and deepen their engagement with consumers.

[0489] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0490] Step 1:

[0491] The server collects customer information. It uses purchase history data and customer profile data from the company's internal CRM system, as well as user-generated data from external social media APIs, as input. This data is aggregated into a database to prepare for the next analysis stage. Specifically, it periodically retrieves data via API calls and inserts it into the database.

[0492] Step 2:

[0493] The server uses natural language processing (NLP) techniques to analyze the collected customer information. The text data collected in Step 1 is used as input. Specifically, a generative AI model is used to analyze the sentiment of the text and extract customer interests and trends. The output will be a sentiment score and areas of interest for each customer. This step involves applying machine learning algorithms to quantify the text data.

[0494] Step 3:

[0495] The server performs time series analysis to predict market trends. It uses external market trend data and the company's own historical sales data as input. Data processing involves trend analysis of time series data and the construction of a predictive model. The output provides future demand forecasts and changes in market needs. This process includes data smoothing and seasonality identification using statistical algorithms.

[0496] Step 4:

[0497] The server generates the optimal marketing strategy based on the analysis results. It utilizes customer sentiment data from Step 2 and market forecast data from Step 3 as inputs. This allows it to identify target segments and personalize ad content using a generative AI model. The output is an ad plan for each segment. In this step, the strategy formulation algorithm determines the ad content and delivery timing.

[0498] Step 5:

[0499] The device tracks the user's online behavior. It collects web visit data and click data as input. Specifically, it uses browser cookies and tracking pixels to record the user's behavioral patterns and sends this data to the server. The output is a history of each user's interests and activities. At this stage, behavioral data is collected in real time.

[0500] Step 6:

[0501] The server uses the collected user behavior data to evaluate the effectiveness of the ads and adjust the strategy as needed. The input is a combination of the behavior data collected in step 5 and the ad plan generated in step 4. This allows for the measurement of ad click-through rates and effectiveness, and the dynamic adjustment of the campaign. The output is the updated ad strategy. This step executes a strategy adjustment algorithm based on a feedback loop.

[0502] (Application Example 1)

[0503] 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."

[0504] Traditional marketing systems struggle to deliver ads at the optimal time for each customer and are unable to respond quickly to dynamic market fluctuations. Furthermore, they lack mechanisms for evaluating ad effectiveness in real time and making rapid adjustments, resulting in insufficient return on advertising spend. Moreover, there is a growing demand for personalized advertising based on users' online behavior.

[0505] 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.

[0506] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer sentiment and interests, means for predicting market trends through time-series analysis, means for automating advertising promotion and personalizing advertisements according to user groups, means for optimizing information content according to user behavior, and means for tracking users' online behavior and optimizing the timing of advertisement delivery based on that data. This enables the personalization of advertisements at the optimal timing for each user, improving the return on advertising spend and allowing for a rapid response to market trends.

[0507] "Customer information" refers to data held by a company about individuals or corporations, including purchase history, profiles, and social media activity information.

[0508] "Natural language processing technology" refers to computer science techniques that enable computers to understand, analyze, and utilize human language.

[0509] "Customer sentiment" refers to the feelings and emotions that consumers experience, and is a psychological reaction to products and services.

[0510] "Interest" refers to the degree of interest or curiosity that consumers show towards a particular product or service.

[0511] Time series analysis is a method of analyzing data that changes over time to predict future trends and tendencies.

[0512] "Market trends" refer to changes and trends in factors that affect economic activity, such as overall market demand and supply, price fluctuations, and the competitive landscape.

[0513] "Advertising promotion" refers to activities aimed at increasing awareness of products and services by delivering advertising messages to target consumer groups through various media.

[0514] A "user group" is a group of consumers who share common characteristics or interests, and is often a target group for marketing activities.

[0515] "Personalization" is the process of customizing information and services based on the needs and preferences of each individual consumer.

[0516] "Information content" refers to a collection of information provided in digital format, including text, images, and videos intended for education, entertainment, and informational purposes.

[0517] "Online behavior" refers to the specific actions and activities of consumers when using the internet, such as website browsing history and click history.

[0518] The system of this invention is configured with a server at its core. The server first periodically collects customer information from companies through CRM systems and social media APIs. The collected data is diverse, including purchase history and social media activity. The server analyzes this data using natural language processing techniques with a Python library to extract each customer's emotions and interests. In this process, for example, it can infer what types of products a customer is interested in from their purchase history, and identify emotions requiring urgent attention from their social media posts.

[0519] Furthermore, the server uses time series analysis to predict market trends. In this process, it models historical sales and market data using Python libraries such as numpy and pandas to provide timely market forecasts. This allows companies to predict future consumer needs and quickly adjust their marketing strategies.

[0520] Furthermore, the server automatically personalizes and optimizes ads based on the analysis results and connects to the advertising promotion platform to deliver ads to target customers at the appropriate time. For example, it tracks users' online behavior in real time and recommends the most relevant products when users access a website.

[0521] Furthermore, users' smartphones have an application installed that monitors their online behavior and sends data to a server. This application helps optimize ad delivery timing by collecting data and interacting with the server.

[0522] For example, the server can detect when a user uses the word "happy," determine that their purchase intent is high, and then deliver a targeted ad the following morning.

[0523] Examples of prompts include, "Extract happiness scores from the following dataset and provide an approach to design the optimal advertising strategy." These prompts, when combined with generative AI models, enable more advanced data analysis.

[0524] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0525] Step 1:

[0526] The server periodically collects customer information through the company's CRM system and social media APIs. Inputs include customer purchase history and social media activity data. This data is stored in a database, providing foundational information for analyzing customer interests and behavioral trends.

[0527] Step 2:

[0528] The server uses a Python natural language processing library to extract sentiment and interest from collected customer data. The input is customer text data, and the output is the result of sentiment analysis based on that data. For example, this analyzes how keywords included in product reviews influence customer ratings.

[0529] Step 3:

[0530] The server uses Python's NumPy and pandas libraries to perform time series analysis and predict market trends. Inputs are historical sales and market data, and outputs are future demand forecasts. This process allows the server to predict future sales for each product, which can then be used for inventory management and marketing strategies.

[0531] Step 4:

[0532] The server connects to the advertising platform and automatically generates strategies for delivering personalized ads at the appropriate time. The input is sentiment analysis and market forecast information obtained in previous steps, and the output is a personalized advertising campaign. The server aims to optimize ads and attract the attention of target consumers.

[0533] Step 5:

[0534] The device monitors the user's online behavior in real time and sends that data to the server. The input is the user's clicks and browsing history, and the output is timing data for ad delivery based on that data. Specifically, it monitors which websites the user is visiting and displays ads in a timely manner that are relevant to that behavior.

[0535] Step 6:

[0536] Users receive personalized advertisements sent from the server on their devices. The input is the advertisement content, and the output is the user's response to it. After the advertisement is displayed, user actions (clicks, purchases, etc.) are collected again as data and used for future marketing strategies.

[0537] 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.

[0538] This invention is a system that enables personalized marketing strategies using customer data and user sentiment. This system consists of a server, sentiment engine, terminals, and users, and operates through the following process:

[0539] First, the server collects customer data from the company's CRM system and social media APIs. This includes a variety of customer information, such as purchase history, inquiries, browsing data, and social media activity. By collecting this data, a foundation is formed to understand basic customer preferences and patterns.

[0540] Next, using the information recognized by the emotion engine, the server analyzes the customer's text data to extract specific emotions. This involves using natural language processing techniques to assign emotion tags such as positive, negative, and neutral to the customer's text. This gives the server a foundation for a deep understanding of the user's preferences and tendencies.

[0541] Furthermore, the server uses time-series analysis to predict market trends from external market data and combines this with customer sentiment data to formulate optimal marketing strategies. This generates more sophisticated and personalized advertising campaigns. Based on the strategy, the server personalizes ad content according to customer segments and automates ad delivery.

[0542] Next, the device tracks the user's website behavior and sends the collected data to the server. This data includes behavioral information such as which products the user viewed and which content they clicked on. Based on this, the server uses an emotion engine to monitor the user's real-time emotions and dynamically optimize the web content.

[0543] As a concrete example, consider a scenario where a user is searching for a specific product on an e-commerce site. In this case, the server analyzes the user's emotions, and if it determines that the user is feeling positive, it recommends related products that match that emotion. Conversely, if the user expresses negative emotions, it provides emotionally sensitive follow-up emails or promotions. In this way, companies can implement more effective marketing strategies rooted in emotions.

[0544] This invention enables companies to personalize their interactions with customers, taking their emotions into consideration, thereby achieving higher marketing efficiency and improved customer satisfaction.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] The server collects customer data from the company's CRM system and social media APIs. This includes customer purchase history, inquiry data, and social media posts. The server regularly updates this data, creating a foundation for maintaining up-to-date customer information.

[0548] Step 2:

[0549] The server applies natural language processing techniques to the collected text data to extract customer emotions and interests. This process assigns emotion tags (positive, negative, neutral) through text analysis, allowing the server to understand the customer's current emotional state.

[0550] Step 3:

[0551] The emotion engine recognizes the user's emotions in real time and sends that data to the server. This allows the server to track the user's current emotional trends in detail.

[0552] Step 4:

[0553] The server predicts future market trends through time series analysis. In this process, it utilizes external market data and sales history to model upcoming trends and build highly accurate demand forecasts.

[0554] Step 5:

[0555] The server automatically generates the optimal marketing strategy by combining emotional data obtained from the emotion engine with market trend forecasts. This strategy includes designing targeted advertising content and scheduling its delivery to specific customer segments.

[0556] Step 6:

[0557] The device tracks the user's website browsing behavior and sends that data to the server. For example, this data might include the time spent viewing a specific product or the frequency of clicks.

[0558] Step 7:

[0559] The server seamlessly optimizes web content based on user behavior and emotional data. For example, if a user is in a positive emotional state, it will prominently display recommendations for related products and show more content that will pique their interest.

[0560] Step 8:

[0561] Users experience advertisements and product recommendations optimized for their own emotions and behavior on their devices. This provides a more personalized and intuitive purchasing experience.

[0562] Through this process, companies can achieve advanced, emotion-based personalization and improve the quality of the customer experience.

[0563] (Example 2)

[0564] 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."

[0565] Existing marketing systems struggle to personalize interactions while fully considering customer emotions and preferences, and there is a need to develop effective sales strategies that quickly reflect market trends. As a result, companies face the challenge of lacking the means to provide dynamic and personalized engagement.

[0566] 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.

[0567] In this invention, the server includes a device for collecting customer information, a device for analyzing the collected customer information using analytical methods to extract customer emotions and preferences, and a device for predicting market trends using a time-series model. This enables the rapid development of personalized marketing strategies that take into account the emotions and preferences of each individual customer, and optimizes individualized ad delivery and content display.

[0568] "Customer information" refers to data related to an individual or organization, such as their business transactions, behavioral history, preferences, and emotions.

[0569] "Analysis methods" refer to technical means and algorithms used to analyze collected data and derive specific insights or conclusions.

[0570] "Emotion" refers to the classification of a customer's psychological state, such as positive, negative, or neutral, which can be interpreted from their text and behavior.

[0571] "Preferences" refer to information about products, services, or areas of interest that customers seek.

[0572] A "time series model" refers to a method that uses time series data to analyze past patterns and trends and predict future trends and characteristics.

[0573] "Market trends" refer to tendencies that indicate changes in demand and supply in a particular industry or product category, consumer interests, and shifts in the competitive environment.

[0574] "Personalization" refers to the process of individually adjusting the products and services offered based on the characteristics and needs of each customer.

[0575] "Sales strategy" refers to the policies and plans for effectively delivering products and services to the market and maximizing revenue.

[0576] "Ad delivery" refers to the process of delivering advertising messages to a specific target audience.

[0577] "Personalization" refers to adjusting or modifying general content to suit a specific customer or situation.

[0578] "Content display optimization" refers to dynamically adjusting the display of information on web pages and applications based on user interests and behavior, in order to maximize their effectiveness.

[0579] This invention is a system that leverages customer data and user sentiment to realize personalized marketing strategies. This system consists of a server, an emotion engine, terminals, and users.

[0580] The server first collects customer information using the company's CRM system and social media APIs. This includes information such as purchase history, inquiries, browsing data, and social media activity. The collected data forms the basis for understanding the customer's basic preferences and behavioral patterns. Next, the server uses an emotion engine to analyze this data and leverages natural language processing techniques to extract sentiment tags such as positive, negative, and neutral from the customer's text.

[0581] Furthermore, the server uses time-series models to predict external market trends and combines them with customer sentiment data to formulate optimal sales strategies. This generates more sophisticated and personalized advertising campaigns. Based on this strategy, the server personalizes ad content according to customer groups and automates ad delivery.

[0582] Subsequently, the device tracks the user's behavior on the website and sends the collected data to the server. This data includes behavioral information such as which products the user viewed and which content they clicked on. Based on this, the server uses an emotion engine to evaluate the user's real-time emotions and dynamically optimize the displayed content.

[0583] A concrete example is a scenario where a user searches for a specific product on an online shop. In this case, the server uses a generative AI model to analyze the user's emotions. If it determines that the emotion is positive, it suggests related products that match that emotion. On the other hand, if the user expresses negative emotions, it provides emotionally sensitive follow-up emails or promotions. In this way, companies can implement more effective engagement strategies based on emotions.

[0584] An example of a prompt is, "Analyze the following customer review and extract the sentiment tag. Review: 'This product is easy to use and I am very satisfied.'" Based on this prompt, the generative AI model identifies positive sentiments.

[0585] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0586] Step 1:

[0587] The server collects data from the company's CRM system and social media APIs. Its inputs include customer purchase history, inquiry history, browsing data, and social media activity information. This data is retrieved via API requests. The server aggregates and stores this data, building a foundation for creating basic customer profiles.

[0588] Step 2:

[0589] The server uses an emotion engine to analyze this aggregated customer data. It uses the customer text data obtained in Step 1 as input. A generative AI model is used for natural language processing, extracting emotion tags such as positive, negative, and neutral. These output emotion tags form the basis for deepening customer understanding in marketing.

[0590] Step 3:

[0591] The server uses a time-series model to analyze external market data and predict future market trends. It uses historical market trend data and sentiment data extracted in step 2 as input. This model predicts, for example, purchasing patterns and seasonal market trends. As an output, an optimal sales strategy is formulated based on these insights.

[0592] Step 4:

[0593] The server generates personalized advertising campaigns based on the formulated sales strategy. Using a generative AI model, it constructs campaigns using prompt text as input. This results in compelling ad content tailored to specific customer segments. The output is then sent to an automated ad serving system.

[0594] Step 5:

[0595] The device tracks the user's behavior on websites and sends data to the server in real time. As input, it captures behavioral information such as which products the user viewed and which links they clicked. The device collects this data as digital events and sends it to the server, which then becomes input. As output, the server re-analyzes the user's sentiment based on this behavioral data.

[0596] Step 6:

[0597] The server re-evaluates user sentiment and dynamically optimizes web content. It reuses user behavior data obtained in step 5 and sentiment tags extracted in step 2 as input. This allows new information and promotions to be displayed and output to the user. For example, if a user is searching for a specific product in an online shop, positive sentiment will trigger related product suggestions, while negative sentiment will trigger corresponding promotions.

[0598] (Application Example 2)

[0599] 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."

[0600] Traditional marketing activities by companies have been limited in their ability to analyze customer information, predict market trends, and deliver advertisements based on individual user emotions and interests. This has resulted in insufficient improvement in customer satisfaction and maximization of sales effectiveness. Therefore, there has been a growing need to understand user emotions and preferences in real time and provide personalized advertisements and content accordingly.

[0601] 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.

[0602] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer emotions and interests, and means for predicting market trends through time-series analysis. This enables dynamic information display based on the user's emotions.

[0603] "Customer information" refers to data about individual customers, including a variety of information such as purchase history, inquiries, and browsing history.

[0604] "Natural language processing technology" refers to the algorithms and methods used by computers to analyze and understand human language.

[0605] "Customer emotions" refers to the emotional states, such as positive, negative, or neutral, that a customer exhibits.

[0606] "Interest" refers to a customer's preference for products or content that they find appealing.

[0607] Time series analysis is a statistical method used to predict future trends based on past data.

[0608] "Market trends" is a concept that refers to future changes and trends in a particular market.

[0609] "Sales strategy" refers to the plan or policy regarding how to deliver products or services to the market.

[0610] Automating advertising refers to the process of creating, delivering, and optimizing advertisements without human intervention.

[0611] A "customer group" is a concept that refers to a collection of customers who share specific attributes or patterns.

[0612] "Personalization" means tailoring products and services to individual customers.

[0613] The system for implementing this invention consists of a server, a terminal, and a user. The server uses natural language processing and time series analysis techniques to collect and analyze customer information and extract emotions. Specifically, the server is built using Python and utilizes NLP libraries (e.g., spaCy and transformers) to analyze collected text data and extract customer emotions and interests. It also uses a time series analysis library to predict market trends. The server uses the OpenAI API to optimize advertisements and content and displays personalized advertisements to users.

[0614] The devices, such as smartphones and personal computers, are responsible for collecting user behavior data and transmitting it to servers. Every time a user visits a specific website or engages in social media activity, this data is tracked and transmitted as relevant information.

[0615] Users use the web daily on their smartphones and computers, and their behavioral data is collected in real time. For example, when a user shows positive emotions while browsing an e-commerce site for pet supplies, they will automatically receive push notifications advertising new pet food based on those emotions.

[0616] Examples of prompt messages are as follows:

[0617] "The user showed positive emotions while browsing pet supplies. Please recommend products that match those emotions. For example, information about trial campaigns for new pet food or toys."

[0618] The system of the present invention is effective in personalizing the customer experience and improving the effectiveness of advertisements provided by companies.

[0619] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0620] Step 1:

[0621] The device tracks the user's website browsing data and social media activity. This includes collecting information such as pages visited, content clicked, and social media posts. The input data consists of user behavior information, and the output data is sent to the server.

[0622] Step 2:

[0623] The server receives user behavior data sent from the terminal and analyzes it using natural language processing techniques. Specifically, it identifies emotions from the collected text data and extracts emotion tags such as positive, negative, and neutral. The input is user behavior information, and the output is emotion tags.

[0624] Step 3:

[0625] The server uses time-series analysis to predict market trends. Based on historical data, it numerically predicts future market trends and performs further analysis in conjunction with sentiment tags. The input is historical market data and sentiment tags, and the output is predicted market trend data.

[0626] Step 4:

[0627] The server generates personalized advertisements based on sentiment data and market trend data obtained using a generative AI model. Next, it uses the OpenAI API to input optimal prompt messages and optimize advertisements and content for the user. The input is sentiment data and market trend data, and the output is personalized advertisements.

[0628] Step 5:

[0629] The device displays personalized advertisements sent from the server to the user. Here, the user can view newly optimized advertisements on their smartphone or computer. The input is the personalized advertisement from the server, and the output is the display of the advertisement to the user.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] [Fourth Embodiment]

[0634] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0635] 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.

[0636] 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).

[0637] 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.

[0638] 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.

[0639] 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).

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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".

[0647] This invention is a system for highly automating and optimizing marketing strategies by utilizing customer and market data held by companies. This system consists of a server, terminals, and users, and operates as follows:

[0648] First, the server periodically collects customer data through the company's CRM system and social media APIs. Here, all relevant data is aggregated, including purchase history, customer profiles, and social media activity information. Based on this data, the server uses natural language processing technology to analyze the text data and extract customer sentiments and preferences.

[0649] Next, the server performs time-series analysis, using external market data and historical sales data to capture current market trends. Based on this information, it trains predictive models to forecast future consumer needs and demand. This process enables companies to respond quickly to market fluctuations and develop appropriate product strategies.

[0650] The server also has the capability to automatically generate optimal marketing strategies based on the insights it gains. This includes designing advertising campaigns, identifying target segments, and personalizing ad content. Furthermore, it connects to advertising delivery platforms to automatically deliver the most relevant ads to target customers.

[0651] On the other hand, the device tracks the user's online behavior (e.g., website clicks and browsing history) and sends this data to a server. This data is used to gain a deeper understanding of the user's interests and to optimize advertising and content.

[0652] For example, when a user visits an e-commerce site via their device, the server recommends relevant products based on their past browsing history. Furthermore, the server collects user comments and opinions from social media and displays advertisements on topics that may be of interest to the customer. These advertisements are delivered at the optimal time and with the most relevant content through the user's device.

[0653] This system enables companies to enhance personalized marketing activities and improve the customer experience. It also allows them to maximize the return on advertising spend and uncover new market opportunities.

[0654] The following describes the processing flow.

[0655] Step 1:

[0656] The server collects customer data from companies using CRM systems and social media APIs. This data includes customer purchase history, browsing history, inquiries, and social media interactions. Website log information is also collected.

[0657] Step 2:

[0658] The server applies natural language processing techniques to the collected data to extract customer emotions and interests from text information. This includes customer-provided reviews, feedback, and social media posts. By analyzing emotions such as positive and negative, the server reveals customers' latent needs.

[0659] Step 3:

[0660] The server performs time-series analysis based on historical sales data and market reports to predict market trends. This includes forecasting future consumer trends and demand fluctuations. The server uses this data to train machine learning models and forecast product demand.

[0661] Step 4:

[0662] The server generates the optimal marketing strategy for target customer segments based on analysis results and market forecasts. This includes determining which ads to deliver to which customers and through which channels. Ad campaigns are personalized, and the server automates the ad content.

[0663] Step 5:

[0664] The server connects to the advertising platform to deliver ads to target customers. During delivery, it monitors the effectiveness of the ads in real time (e.g., click-through rate, conversion rate) and adjusts the ad content and delivery settings as needed to maximize ad effectiveness.

[0665] Step 6:

[0666] The device tracks the user's website visits and online behavior, and sends this information to the server. The server uses this data to optimize web content to suit the user's preferences.

[0667] Step 7:

[0668] The server combines user behavior data with insights based on market forecasts to provide purchase recommendations and optimize content. Users can receive personalized product recommendations and promotions through their devices. This process allows users to enjoy a more personalized experience while improving the marketing efficiency of businesses.

[0669] (Example 1)

[0670] 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".

[0671] In today's business environment, developing swift and effective marketing strategies is crucial for companies to deepen customer relationships and maintain competitiveness. However, effectively utilizing vast amounts of customer and market data to deliver personalized advertising is a major challenge for many companies. Existing systems struggle to process data effectively and efficiently in terms of data collection and analysis, customer classification, and sales strategy planning and implementation.

[0672] 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.

[0673] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer sentiment and interests, and means for predicting market trends through time series analysis. This enables companies to effectively utilize data and formulate and implement optimal sales strategies. Furthermore, by delivering personalized advertisements to customers, it improves targeting accuracy and maximizes sales results.

[0674] "Customer information" refers to data that companies collect about their customers, including, for example, purchase history, personal profiles, and records of online activity.

[0675] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and is particularly used for analyzing text and audio data.

[0676] Time series analysis is a statistical method that analyzes the patterns of data fluctuations over time to predict future trends.

[0677] A "sales strategy" refers to the plans and policies used when selling products or services in the market, and includes things like target setting and promotional plans.

[0678] "Personalized advertising" is a technique for achieving more effective communication by adapting advertising content to the characteristics and preferences of customers.

[0679] "Online content" refers to all information and services viewed or used on the Internet, including websites, content, and applications.

[0680] "Collaborative filtering" is a method that provides personalized recommendations based on a user's past behavior patterns and similar behaviors of other users.

[0681] "Real-time monitoring" is a process that enables rapid decision-making by continuously observing and recording specific indicators or activities in real time.

[0682] "Dynamic adjustment" refers to a function that enhances flexibility by automatically changing systems and strategies in response to changes in conditions and circumstances.

[0683] This system is designed to enable companies to leverage customer information and market data to implement effective marketing strategies. The system consists of servers, terminals, and users.

[0684] The server collects customer information through the company's databases and APIs. This collected data includes, for example, purchase history from CRM systems, user profiles from user information management tools, and posts from social media APIs. Natural language processing techniques are applied to this text data to analyze customer sentiment and interests. This technique utilizes machine learning algorithms and pre-trained generative AI models.

[0685] Next, the server uses time-series data provided by external market data providers to predict market trends. The server leverages statistical algorithms to analyze market trends and build predictive models. This allows companies to foresee future consumer needs and optimize their sales strategies.

[0686] The server generates the optimal marketing strategy based on these analysis results. Generative AI models are used to personalize ad content, streamlining the planning and targeting of promotional activities. Ads are connected to the ad delivery platform and automatically delivered from the server.

[0687] Meanwhile, the device monitors the user's online behavior. For example, it collects data on the pages the user views and the links they click on websites and sends this data to the server. This data is used to measure the effectiveness of advertisements and optimize content.

[0688] Users can receive personalized content and advertisements based on their interests through their devices. For example, related products may be recommended based on the product categories the user has viewed, or advertisements based on topics that interest them may be displayed.

[0689] (Example of a prompt message)

[0690] "Perform sentiment analysis based on customer data and propose appropriate advertisements."

[0691] "Use past data to develop your next sales strategy."

[0692] This system will enable companies to conduct more precise marketing and deepen their engagement with consumers.

[0693] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0694] Step 1:

[0695] The server collects customer information. It uses purchase history data and customer profile data from the company's internal CRM system, as well as user-generated data from external social media APIs, as input. This data is aggregated into a database to prepare for the next analysis stage. Specifically, it periodically retrieves data via API calls and inserts it into the database.

[0696] Step 2:

[0697] The server uses natural language processing (NLP) techniques to analyze the collected customer information. The text data collected in Step 1 is used as input. Specifically, a generative AI model is used to analyze the sentiment of the text and extract customer interests and trends. The output will be a sentiment score and areas of interest for each customer. This step involves applying machine learning algorithms to quantify the text data.

[0698] Step 3:

[0699] The server performs time series analysis to predict market trends. It uses external market trend data and the company's own historical sales data as input. Data processing involves trend analysis of time series data and the construction of a predictive model. The output provides future demand forecasts and changes in market needs. This process includes data smoothing and seasonality identification using statistical algorithms.

[0700] Step 4:

[0701] The server generates the optimal marketing strategy based on the analysis results. It utilizes customer sentiment data from Step 2 and market forecast data from Step 3 as inputs. This allows it to identify target segments and personalize ad content using a generative AI model. The output is an ad plan for each segment. In this step, the strategy formulation algorithm determines the ad content and delivery timing.

[0702] Step 5:

[0703] The device tracks the user's online behavior. It collects web visit data and click data as input. Specifically, it uses browser cookies and tracking pixels to record the user's behavioral patterns and sends this data to the server. The output is a history of each user's interests and activities. At this stage, behavioral data is collected in real time.

[0704] Step 6:

[0705] The server uses the collected user behavior data to evaluate the effectiveness of the ads and adjust the strategy as needed. The input is a combination of the behavior data collected in step 5 and the ad plan generated in step 4. This allows for the measurement of ad click-through rates and effectiveness, and the dynamic adjustment of the campaign. The output is the updated ad strategy. This step executes a strategy adjustment algorithm based on a feedback loop.

[0706] (Application Example 1)

[0707] 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".

[0708] Traditional marketing systems struggle to deliver ads at the optimal time for each customer and are unable to respond quickly to dynamic market fluctuations. Furthermore, they lack mechanisms for evaluating ad effectiveness in real time and making rapid adjustments, resulting in insufficient return on advertising spend. Moreover, there is a growing demand for personalized advertising based on users' online behavior.

[0709] 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.

[0710] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer sentiment and interests, means for predicting market trends through time-series analysis, means for automating advertising promotion and personalizing advertisements according to user groups, means for optimizing information content according to user behavior, and means for tracking users' online behavior and optimizing the timing of advertisement delivery based on that data. This enables the personalization of advertisements at the optimal timing for each user, improving the return on advertising spend and allowing for a rapid response to market trends.

[0711] "Customer information" refers to data held by a company about individuals or corporations, including purchase history, profiles, and social media activity information.

[0712] "Natural language processing technology" refers to computer science techniques that enable computers to understand, analyze, and utilize human language.

[0713] "Customer sentiment" refers to the feelings and emotions that consumers experience, and is a psychological reaction to products and services.

[0714] "Interest" refers to the degree of interest or curiosity that consumers show towards a particular product or service.

[0715] Time series analysis is a method of analyzing data that changes over time to predict future trends and tendencies.

[0716] "Market trends" refer to changes and trends in factors that affect economic activity, such as overall market demand and supply, price fluctuations, and the competitive landscape.

[0717] "Advertising promotion" refers to activities aimed at increasing awareness of products and services by delivering advertising messages to target consumer groups through various media.

[0718] A "user group" is a group of consumers who share common characteristics or interests, and is often a target group for marketing activities.

[0719] "Personalization" is the process of customizing information and services based on the needs and preferences of each individual consumer.

[0720] "Information content" refers to a collection of information provided in digital format, including text, images, and videos intended for education, entertainment, and informational purposes.

[0721] "Online behavior" refers to the specific actions and activities of consumers when using the internet, such as website browsing history and click history.

[0722] The system of this invention is configured with a server at its core. The server first periodically collects customer information from companies through CRM systems and social media APIs. The collected data is diverse, including purchase history and social media activity. The server analyzes this data using natural language processing techniques with a Python library to extract each customer's emotions and interests. In this process, for example, it can infer what types of products a customer is interested in from their purchase history, and identify emotions requiring urgent attention from their social media posts.

[0723] Furthermore, the server uses time series analysis to predict market trends. In this process, it models historical sales and market data using Python libraries such as numpy and pandas to provide timely market forecasts. This allows companies to predict future consumer needs and quickly adjust their marketing strategies.

[0724] Furthermore, the server automatically personalizes and optimizes ads based on the analysis results and connects to the advertising promotion platform to deliver ads to target customers at the appropriate time. For example, it tracks users' online behavior in real time and recommends the most relevant products when users access a website.

[0725] Furthermore, users' smartphones have an application installed that monitors their online behavior and sends data to a server. This application helps optimize ad delivery timing by collecting data and interacting with the server.

[0726] For example, the server can detect when a user uses the word "happy," determine that their purchase intent is high, and then deliver a targeted ad the following morning.

[0727] Examples of prompts include, "Extract happiness scores from the following dataset and provide an approach to design the optimal advertising strategy." These prompts, when combined with generative AI models, enable more advanced data analysis.

[0728] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0729] Step 1:

[0730] The server periodically collects customer information through the company's CRM system and social media APIs. Inputs include customer purchase history and social media activity data. This data is stored in a database, providing foundational information for analyzing customer interests and behavioral trends.

[0731] Step 2:

[0732] The server uses a Python natural language processing library to extract sentiment and interest from collected customer data. The input is customer text data, and the output is the result of sentiment analysis based on that data. For example, this analyzes how keywords included in product reviews influence customer ratings.

[0733] Step 3:

[0734] The server uses Python's NumPy and pandas libraries to perform time series analysis and predict market trends. Inputs are historical sales and market data, and outputs are future demand forecasts. This process allows the server to predict future sales for each product, which can then be used for inventory management and marketing strategies.

[0735] Step 4:

[0736] The server connects to the advertising platform and automatically generates strategies for delivering personalized ads at the appropriate time. The input is sentiment analysis and market forecast information obtained in previous steps, and the output is a personalized advertising campaign. The server aims to optimize ads and attract the attention of target consumers.

[0737] Step 5:

[0738] The device monitors the user's online behavior in real time and sends that data to the server. The input is the user's clicks and browsing history, and the output is timing data for ad delivery based on that data. Specifically, it monitors which websites the user is visiting and displays ads in a timely manner that are relevant to that behavior.

[0739] Step 6:

[0740] Users receive personalized advertisements sent from the server on their devices. The input is the advertisement content, and the output is the user's response to it. After the advertisement is displayed, user actions (clicks, purchases, etc.) are collected again as data and used for future marketing strategies.

[0741] 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.

[0742] This invention is a system that enables personalized marketing strategies using customer data and user sentiment. This system consists of a server, sentiment engine, terminals, and users, and operates through the following process:

[0743] First, the server collects customer data from the company's CRM system and social media APIs. This includes a variety of customer information, such as purchase history, inquiries, browsing data, and social media activity. By collecting this data, a foundation is formed to understand basic customer preferences and patterns.

[0744] Next, using the information recognized by the emotion engine, the server analyzes the customer's text data to extract specific emotions. This involves using natural language processing techniques to assign emotion tags such as positive, negative, and neutral to the customer's text. This gives the server a foundation for a deep understanding of the user's preferences and tendencies.

[0745] Furthermore, the server uses time-series analysis to predict market trends from external market data and combines this with customer sentiment data to formulate optimal marketing strategies. This generates more sophisticated and personalized advertising campaigns. Based on the strategy, the server personalizes ad content according to customer segments and automates ad delivery.

[0746] Next, the device tracks the user's website behavior and sends the collected data to the server. This data includes behavioral information such as which products the user viewed and which content they clicked on. Based on this, the server uses an emotion engine to monitor the user's real-time emotions and dynamically optimize the web content.

[0747] As a concrete example, consider a scenario where a user is searching for a specific product on an e-commerce site. In this case, the server analyzes the user's emotions, and if it determines that the user is feeling positive, it recommends related products that match that emotion. Conversely, if the user expresses negative emotions, it provides emotionally sensitive follow-up emails or promotions. In this way, companies can implement more effective marketing strategies rooted in emotions.

[0748] This invention enables companies to personalize their interactions with customers, taking their emotions into consideration, thereby achieving higher marketing efficiency and improved customer satisfaction.

[0749] The following describes the processing flow.

[0750] Step 1:

[0751] The server collects customer data from the company's CRM system and social media APIs. This includes customer purchase history, inquiry data, and social media posts. The server regularly updates this data, creating a foundation for maintaining up-to-date customer information.

[0752] Step 2:

[0753] The server applies natural language processing techniques to the collected text data to extract customer emotions and interests. This process assigns emotion tags (positive, negative, neutral) through text analysis, allowing the server to understand the customer's current emotional state.

[0754] Step 3:

[0755] The emotion engine recognizes the user's emotions in real time and sends that data to the server. This allows the server to track the user's current emotional trends in detail.

[0756] Step 4:

[0757] The server predicts future market trends through time series analysis. In this process, it utilizes external market data and sales history to model upcoming trends and build highly accurate demand forecasts.

[0758] Step 5:

[0759] The server automatically generates the optimal marketing strategy by combining emotional data obtained from the emotion engine with market trend forecasts. This strategy includes designing targeted advertising content and scheduling its delivery to specific customer segments.

[0760] Step 6:

[0761] The device tracks the user's website browsing behavior and sends that data to the server. For example, this data might include the time spent viewing a specific product or the frequency of clicks.

[0762] Step 7:

[0763] The server seamlessly optimizes web content based on user behavior and emotional data. For example, if a user is in a positive emotional state, it will prominently display recommendations for related products and show more content that will pique their interest.

[0764] Step 8:

[0765] Users experience advertisements and product recommendations optimized for their own emotions and behavior on their devices. This provides a more personalized and intuitive purchasing experience.

[0766] Through this process, companies can achieve advanced, emotion-based personalization and improve the quality of the customer experience.

[0767] (Example 2)

[0768] 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".

[0769] Existing marketing systems struggle to personalize interactions while fully considering customer emotions and preferences, and there is a need to develop effective sales strategies that quickly reflect market trends. As a result, companies face the challenge of lacking the means to provide dynamic and personalized engagement.

[0770] 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.

[0771] In this invention, the server includes a device for collecting customer information, a device for analyzing the collected customer information using analytical methods to extract customer emotions and preferences, and a device for predicting market trends using a time-series model. This enables the rapid development of personalized marketing strategies that take into account the emotions and preferences of each individual customer, and optimizes individualized ad delivery and content display.

[0772] "Customer information" refers to data related to an individual or organization, such as their business transactions, behavioral history, preferences, and emotions.

[0773] "Analysis methods" refer to technical means and algorithms used to analyze collected data and derive specific insights or conclusions.

[0774] "Emotion" refers to the classification of a customer's psychological state, such as positive, negative, or neutral, which can be interpreted from their text and behavior.

[0775] "Preferences" refer to information about products, services, or areas of interest that customers seek.

[0776] A "time series model" refers to a method that uses time series data to analyze past patterns and trends and predict future trends and characteristics.

[0777] "Market trends" refer to tendencies that indicate changes in demand and supply in a particular industry or product category, consumer interests, and shifts in the competitive environment.

[0778] "Personalization" refers to the process of individually adjusting the products and services offered based on the characteristics and needs of each customer.

[0779] "Sales strategy" refers to the policies and plans for effectively delivering products and services to the market and maximizing revenue.

[0780] "Ad delivery" refers to the process of delivering advertising messages to a specific target audience.

[0781] "Personalization" refers to adjusting or modifying general content to suit a specific customer or situation.

[0782] "Content display optimization" refers to dynamically adjusting the display of information on web pages and applications based on user interests and behavior, in order to maximize their effectiveness.

[0783] This invention is a system that leverages customer data and user sentiment to realize personalized marketing strategies. This system consists of a server, an emotion engine, terminals, and users.

[0784] The server first collects customer information using the company's CRM system and social media APIs. This includes information such as purchase history, inquiries, browsing data, and social media activity. The collected data forms the basis for understanding the customer's basic preferences and behavioral patterns. Next, the server uses an emotion engine to analyze this data and leverages natural language processing techniques to extract sentiment tags such as positive, negative, and neutral from the customer's text.

[0785] Furthermore, the server uses time-series models to predict external market trends and combines them with customer sentiment data to formulate optimal sales strategies. This generates more sophisticated and personalized advertising campaigns. Based on this strategy, the server personalizes ad content according to customer groups and automates ad delivery.

[0786] Subsequently, the device tracks the user's behavior on the website and sends the collected data to the server. This data includes behavioral information such as which products the user viewed and which content they clicked on. Based on this, the server uses an emotion engine to evaluate the user's real-time emotions and dynamically optimize the displayed content.

[0787] A concrete example is a scenario where a user searches for a specific product on an online shop. In this case, the server uses a generative AI model to analyze the user's emotions. If it determines that the emotion is positive, it suggests related products that match that emotion. On the other hand, if the user expresses negative emotions, it provides emotionally sensitive follow-up emails or promotions. In this way, companies can implement more effective engagement strategies based on emotions.

[0788] An example of a prompt is, "Analyze the following customer review and extract the sentiment tag. Review: 'This product is easy to use and I am very satisfied.'" Based on this prompt, the generative AI model identifies positive sentiments.

[0789] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0790] Step 1:

[0791] The server collects data from the company's CRM system and social media APIs. Its inputs include customer purchase history, inquiry history, browsing data, and social media activity information. This data is retrieved via API requests. The server aggregates and stores this data, building a foundation for creating basic customer profiles.

[0792] Step 2:

[0793] The server uses an emotion engine to analyze this aggregated customer data. It uses the customer text data obtained in Step 1 as input. A generative AI model is used for natural language processing, extracting emotion tags such as positive, negative, and neutral. These output emotion tags form the basis for deepening customer understanding in marketing.

[0794] Step 3:

[0795] The server uses a time-series model to analyze external market data and predict future market trends. It uses historical market trend data and sentiment data extracted in step 2 as input. This model predicts, for example, purchasing patterns and seasonal market trends. As an output, an optimal sales strategy is formulated based on these insights.

[0796] Step 4:

[0797] The server generates personalized advertising campaigns based on the formulated sales strategy. Using a generative AI model, it constructs campaigns using prompt text as input. This results in compelling ad content tailored to specific customer segments. The output is then sent to an automated ad serving system.

[0798] Step 5:

[0799] The device tracks the user's behavior on websites and sends data to the server in real time. As input, it captures behavioral information such as which products the user viewed and which links they clicked. The device collects this data as digital events and sends it to the server, which then becomes input. As output, the server re-analyzes the user's sentiment based on this behavioral data.

[0800] Step 6:

[0801] The server re-evaluates user sentiment and dynamically optimizes web content. It reuses user behavior data obtained in step 5 and sentiment tags extracted in step 2 as input. This allows new information and promotions to be displayed and output to the user. For example, if a user is searching for a specific product in an online shop, positive sentiment will trigger related product suggestions, while negative sentiment will trigger corresponding promotions.

[0802] (Application Example 2)

[0803] 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".

[0804] Traditional marketing activities by companies have been limited in their ability to analyze customer information, predict market trends, and deliver advertisements based on individual user emotions and interests. This has resulted in insufficient improvement in customer satisfaction and maximization of sales effectiveness. Therefore, there has been a growing need to understand user emotions and preferences in real time and provide personalized advertisements and content accordingly.

[0805] 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.

[0806] In this invention, the server includes means for collecting customer information, means for analyzing the collected customer information using natural language processing technology to extract customer emotions and interests, and means for predicting market trends through time-series analysis. This enables dynamic information display based on the user's emotions.

[0807] "Customer information" refers to data about individual customers, including a variety of information such as purchase history, inquiries, and browsing history.

[0808] "Natural language processing technology" refers to the algorithms and methods used by computers to analyze and understand human language.

[0809] "Customer emotions" refers to the emotional states, such as positive, negative, or neutral, that a customer exhibits.

[0810] "Interest" refers to a customer's preference for products or content that they find appealing.

[0811] Time series analysis is a statistical method used to predict future trends based on past data.

[0812] "Market trends" is a concept that refers to future changes and trends in a particular market.

[0813] "Sales strategy" refers to the plan or policy regarding how to deliver products or services to the market.

[0814] Automating advertising refers to the process of creating, delivering, and optimizing advertisements without human intervention.

[0815] A "customer group" is a concept that refers to a collection of customers who share specific attributes or patterns.

[0816] "Personalization" means tailoring products and services to individual customers.

[0817] The system for implementing this invention consists of a server, a terminal, and a user. The server uses natural language processing and time series analysis techniques to collect and analyze customer information and extract emotions. Specifically, the server is built using Python and utilizes NLP libraries (e.g., spaCy and transformers) to analyze collected text data and extract customer emotions and interests. It also uses a time series analysis library to predict market trends. The server uses the OpenAI API to optimize advertisements and content and displays personalized advertisements to users.

[0818] The devices, such as smartphones and personal computers, are responsible for collecting user behavior data and transmitting it to servers. Every time a user visits a specific website or engages in social media activity, this data is tracked and transmitted as relevant information.

[0819] Users use the web daily on their smartphones and computers, and their behavioral data is collected in real time. For example, when a user shows positive emotions while browsing an e-commerce site for pet supplies, they will automatically receive push notifications advertising new pet food based on those emotions.

[0820] Examples of prompt messages are as follows:

[0821] "The user showed positive emotions while browsing pet supplies. Please recommend products that match those emotions. For example, information about trial campaigns for new pet food or toys."

[0822] The system of the present invention is effective in personalizing the customer experience and improving the effectiveness of advertisements provided by companies.

[0823] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0824] Step 1:

[0825] The device tracks the user's website browsing data and social media activity. This includes collecting information such as pages visited, content clicked, and social media posts. The input data consists of user behavior information, and the output data is sent to the server.

[0826] Step 2:

[0827] The server receives user behavior data sent from the terminal and analyzes it using natural language processing techniques. Specifically, it identifies emotions from the collected text data and extracts emotion tags such as positive, negative, and neutral. The input is user behavior information, and the output is emotion tags.

[0828] Step 3:

[0829] The server uses time-series analysis to predict market trends. Based on historical data, it numerically predicts future market trends and performs further analysis in conjunction with sentiment tags. The input is historical market data and sentiment tags, and the output is predicted market trend data.

[0830] Step 4:

[0831] The server generates personalized advertisements based on sentiment data and market trend data obtained using a generative AI model. Next, it uses the OpenAI API to input optimal prompt messages and optimize advertisements and content for the user. The input is sentiment data and market trend data, and the output is personalized advertisements.

[0832] Step 5:

[0833] The device displays personalized advertisements sent from the server to the user. Here, the user can view newly optimized advertisements on their smartphone or computer. The input is the personalized advertisement from the server, and the output is the display of the advertisement to the user.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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."

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] The following is further disclosed regarding the embodiments described above.

[0856] (Claim 1)

[0857] Means for collecting customer data,

[0858] A means of analyzing collected customer data using natural language processing technology to extract customer sentiment and interests,

[0859] A method for predicting market trends through time series analysis,

[0860] A means of formulating the optimal marketing strategy based on analysis and prediction results,

[0861] A means to automate ad delivery and personalize ads according to customer segments,

[0862] A means of optimizing web content according to user behavior,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, further comprising collaborative filtering means for clustering customer segments.

[0866] (Claim 3)

[0867] The system according to claim 1, further comprising means for monitoring the click-through rate and conversion rate of an advertisement in real time and dynamically adjusting the content and targeting conditions of the advertisement.

[0868] "Example 1"

[0869] (Claim 1)

[0870] Means for collecting customer information,

[0871] A means of analyzing collected customer information using natural language processing technology to extract customer emotions and interests,

[0872] A means of predicting market trends through time series analysis,

[0873] A means for generating an optimal sales strategy based on the results of analysis and prediction,

[0874] A method for automatically delivering ads and personalizing them according to customer segmentation,

[0875] Means to improve online content in response to user behavior,

[0876] A system that includes this.

[0877] (Claim 2)

[0878] The system according to claim 1, further comprising means for classifying customers by a collaborative filtering method.

[0879] (Claim 3)

[0880] The system according to claim 1, further comprising means for immediately monitoring the selection rate and performance rate of advertisements and dynamically adjusting the content and planning conditions of advertisements.

[0881] "Application Example 1"

[0882] (Claim 1)

[0883] Means for collecting customer information,

[0884] A means of analyzing collected customer information using natural language processing technology to extract customer sentiment and interests,

[0885] A method for predicting market trends through time series analysis,

[0886] A means of formulating the optimal sales strategy based on analysis and forecast results,

[0887] A means to automate ad promotion and personalize ads according to user groups,

[0888] A means of optimizing information content according to user behavior,

[0889] A means of tracking users' online behavior and optimizing ad delivery timing based on that data,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, further comprising means for classifying user groups by collaborative filtering.

[0893] (Claim 3)

[0894] The system according to claim 1, further comprising means for monitoring ad selection rates and conversion rates in real time and dynamically adjusting ad content and targeting conditions.

[0895] "Example 2 of combining an emotion engine"

[0896] (Claim 1)

[0897] A device for collecting customer information,

[0898] A device that analyzes collected customer information using analytical methods to extract customer emotions and preferences,

[0899] A device that predicts market trends using a time series model,

[0900] A device that formulates the optimal sales strategy based on analysis and prediction results,

[0901] A device that automates the distribution of advertisements and personalizes them according to customer groups,

[0902] A device that optimizes the displayed content according to the user's actions,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, further comprising a recommendation system for classifying customer groups.

[0906] (Claim 3)

[0907] The system according to claim 1, further comprising a device for immediately monitoring the response rate and conversion rate of advertisements and dynamically setting the content and target conditions of advertisements.

[0908] "Application example 2 when combining with an emotional engine"

[0909] (Claim 1)

[0910] Means for collecting customer information,

[0911] A means of analyzing collected customer information using natural language processing technology to extract customer emotions and interests,

[0912] A method for predicting market trends through time series analysis,

[0913] A means of formulating the optimal sales strategy based on analysis and forecast results,

[0914] A means to automate ad delivery and personalize ads according to customer groups,

[0915] A means of optimizing web content according to user behavior,

[0916] A means of dynamically displaying information based on the user's emotions,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, further comprising collaborative filtering means for classifying customer groups.

[0920] (Claim 3)

[0921] The system according to claim 1, further comprising means for monitoring the effectiveness of advertisements in real time and dynamically adjusting the content and targeting conditions of advertisements. [Explanation of Symbols]

[0922] 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. Means for collecting customer information, A means of analyzing collected customer information using natural language processing technology to extract customer sentiment and interests, A method for predicting market trends through time series analysis, A means of formulating the optimal sales strategy based on analysis and forecast results, A means to automate ad promotion and personalize ads according to user groups, A means of optimizing information content according to user behavior, A means of tracking users' online behavior and optimizing ad delivery timing based on that data, A system that includes this.

2. The system according to claim 1, further comprising means for classifying user groups by collaborative filtering.

3. The system according to claim 1, further comprising means for monitoring the ad selection rate and conversion rate in real time and dynamically adjusting the ad content and targeting conditions.

Images