system

Abstract

We provide the system. [Solution] A data collection method for automatically obtaining promotion-related information from different communication channels, A data integration method for centrally managing and consolidating acquired promotion-related information, A data analysis tool that uses machine learning algorithms to analyze integrated data and formulate effective promotion strategies, A means of providing the formulated promotion strategy to users, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern marketing, it is required to efficiently utilize a vast amount of promotion-related information obtained from diverse communication channels such as emails, SNS, websites, etc. These information sometimes have different formats and structures, making unified analysis difficult and having the problem of being unable to respond in real time. Also, when formulating a marketing strategy by utilizing past promotion data, it takes a lot of labor and time, and it is difficult to formulate effective measures. There is a need to provide means to solve these problems and enable marketing personnel to quickly and effectively formulate promotion strategies.

Means for Solving the Problems

[0005] This invention comprises a data collection means for automatically acquiring promotion-related information from different communication channels, and a data integration means for integrating and centrally managing the acquired information. It also includes a data analysis means for analyzing the integrated data using machine learning algorithms and proposing new measures based on the success factors of past promotions. Furthermore, by including a strategy provision means for quickly providing the formulated promotion strategy to the user, the invention streamlines the planning of promotion strategies and supports marketing activities. This enables users to implement appropriate marketing measures based on real-time data.

[0006] A "communication channel" refers to a medium or means of sending and receiving information, such as email, social networking services (SNS), or websites.

[0007] "Promotion-related information" refers to data collected for the purpose of promoting product sales, and examples include open rates, click-through rates, and engagement data.

[0008] "Data collection methods" refer to mechanisms and methods for automatically acquiring promotion-related information from different communication channels.

[0009] "Data integration means" refers to a system or method for centrally organizing and managing acquired promotion-related information.

[0010] "Data analysis methods" refer to mechanisms and methods for analyzing integrated promotion-related information and extracting meaningful insights.

[0011] A "machine learning algorithm" is a mathematical model or processing method that allows a computer to automatically learn from data and perform predictions and analyses.

[0012] "Strategy delivery methods" refer to mechanisms and methods for presenting promotional strategies formulated based on analysis to users.

[0013] A "user" is an individual or organization that operates the system and receives promotional strategy proposals to implement marketing measures. [Brief explanation of the drawing]

[0014] [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] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This 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 a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0017] 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.

[0018] 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.

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

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system for automatically collecting, integrating, and analyzing promotional information from different communication channels. The system mainly consists of a server, terminals, and users, each playing a specific role.

[0036] The server automatically retrieves promotion-related information from each communication channel via APIs. This eliminates the hassle of manually collecting data and enables real-time information gathering.

[0037] The acquired data is centrally managed by a server. The server unifies different data formats and builds a consistent database. This allows data from different channels to be seamlessly integrated and ready for analysis.

[0038] Next, the server analyzes the integrated data using machine learning algorithms. The analysis process also utilizes natural language processing techniques to process unstructured data and analyze the performance of past promotions. This step helps identify patterns of success and forms the basis for new promotional strategies.

[0039] After formulating the strategy, the server provides the results to the user via the terminal. The user reviews the presented strategy, makes modifications as needed, and then implements the final marketing measures.

[0040] As a concrete example, consider a company planning a campaign for a new product. Based on existing data, the server identifies the success factors of similar past campaigns and presents users with optimal posting times and effective message content for social media. Users can then consider the suggestions and use them to help implement the actual campaign.

[0041] In this way, the present invention streamlines the entire marketing process and supports data-driven strategic decision-making.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects promotional information from various communication channels via APIs. This includes open rates from email services, interaction data from social media, and website visit data. The server periodically calls the APIs to retrieve the latest data and saves it to local storage.

[0045] Step 2:

[0046] The server standardizes the data it collects and stores it in a centralized database. Data with different formats and structures is converted into a common format and organized using keys such as customer IDs and campaign IDs. This unifies the data in a way that is suitable for subsequent analysis processes.

[0047] Step 3:

[0048] The server preprocesses the data to ensure the necessary quality for analysis. Preprocessing includes filtering out unnecessary data using natural language processing techniques and imputing missing values ​​using statistical methods. After cleansing, the dataset is ready for analysis.

[0049] Step 4:

[0050] The server analyzes the data using machine learning algorithms. Clustering and classification techniques are used to identify success factors and common patterns in past promotions. The analysis results are then compiled to support recommended strategies.

[0051] Step 5:

[0052] The server generates a new promotional strategy based on the analysis results and provides it to the user via their terminal. The generated strategy is visualized on a dashboard and presented with quantitative indicators showing the predicted effect of each strategy. The user then evaluates the validity of the strategy based on this.

[0053] Step 6:

[0054] Users review the promotional strategies proposed by the server and make adjustments based on their own insights. Referring to the information on the dashboard, users finalize the strategy, fine-tune the target audience, and then use this strategy to implement the actual campaign.

[0055] (Example 1)

[0056] 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."

[0057] Today, consumer interests and purchasing behavior are changing rapidly, making it crucial for businesses to reach consumers at the right time. However, collecting, managing, and analyzing promotional information from various communication channels in a consistent manner is extremely labor-intensive when done manually, making real-time decision-making difficult. Solving this challenge will enable businesses to build more effective marketing strategies and reach consumers quickly.

[0058] 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.

[0059] In this invention, the server includes information gathering means for automatically acquiring promotion-related information from different communication media, information aggregation means for integrating and centrally managing the acquired promotion-related information, and information analysis means for analyzing the integrated information using machine learning techniques to generate effective promotion strategies. This enables companies to integrate and analyze information from diverse communication media in real time and quickly formulate promotion strategies that are in line with consumer behavior.

[0060] "Communication media" refers to channels and platforms for sending and receiving information, and specifically includes the internet, social networking services (SNS), and email.

[0061] "Promotion-related information" refers to information related to the promotion of products and services, and includes data such as advertisements, campaigns, and sales information.

[0062] "Information gathering means" refers to methods and technologies for automatically acquiring promotional information from different communication media.

[0063] "Information aggregation means" refers to methods and technologies for integrating collected promotion-related information and managing it in a unified format.

[0064] "Information analysis means" refers to methods and technologies for analyzing integrated information using machine learning techniques to generate effective promotional strategies.

[0065] "Means of providing strategies" refers to the methods and technologies for providing the generated promotional strategies to users.

[0066] In order to implement this invention, it is necessary to build a system in which servers, terminals, and users cooperate with each other to collect, integrate, and analyze promotion-related information from various communication media.

[0067] The server plays a central role, automatically collecting information from various communication channels. This includes obtaining information from social networking platforms such as Twitter and Instagram using web APIs. Specifically, it can utilize scraping scripts developed in Python or cloud-based services.

[0068] The collected data is converted to a unified format on the server and stored in a database. For example, database software such as MySQL® or PostgreSQL is used to integrate different data formats. During this process, data cleaning is performed, such as filling in missing data and removing duplicate data.

[0069] The server applies machine learning techniques to the integrated data and performs analysis. For this purpose, it utilizes libraries such as TENSORFLOW® and PyTorch to perform natural language processing. Specifically, it uses BERT and GPT models to analyze unstructured data, for example, to extract patterns from past promotional activities.

[0070] The analysis results are sent from the server to the terminal and presented to the user in a dashboard format. This allows users to review new promotional strategy proposals based on past success stories and formulate measures based on them.

[0071] For example, by having a user input a prompt such as, "What are the characteristics of the most effective promotions in the past three months?" into the system, specific guidance can be obtained from the analyzed data. Following this guidance, users can receive assistance in developing and implementing appropriate promotional plans tailored to consumer behavior.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server collects promotional information from various communication channels. Using API keys from each social media platform as input, it collects post data related to specific keywords and hashtags. This operation is performed by a Python scraping script, yielding the raw data as output.

[0075] Step 2:

[0076] The server integrates the collected raw data and stores it in a database. The input is the raw data obtained in step 1. The data is converted from JSON format to CSV format and saved to a MySQL database. As part of the data cleaning process, missing values ​​are filled in and duplicates are removed. This creates a consistent dataset as the output.

[0077] Step 3:

[0078] The server performs analysis on the integrated data. The dataset prepared in step 2 is used as input. In this step, a machine learning model is trained using TensorFlow, and unstructured data is analyzed using natural language processing techniques. For example, the BERT model is used to extract topics and sentiment from posts, and the analysis results are obtained as output.

[0079] Step 4:

[0080] The server sends the analysis results to the terminal and provides them to the user. The input is the analysis results obtained in step 3. The data received on the terminal is visualized in a dashboard format. Based on the data visualizing the factors that contributed to past promotional success, the user can consider new promotional strategies. This output enables the user to plan effective marketing measures.

[0081] (Application Example 1)

[0082] 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."

[0083] In marketing activities, efficiently collecting and analyzing sales promotion information from different communication channels is crucial. However, traditional methods often involve manual processes, which are time-consuming and labor-intensive. Furthermore, while learning from past sales promotion data and developing effective plans in real time would lead to more efficient marketing activities, there has been a lack of means to achieve this.

[0084] 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.

[0085] In this invention, the server includes information gathering means for automatically acquiring sales promotion information from different communication paths, information integration means for integrating and centrally managing the acquired information, information analysis means for analyzing the integrated information using machine learning processing to formulate an effective sales promotion plan, and interface means for presenting the formulated plan and allowing users to review and modify it using a smartphone. This enables efficient collection and integration of information from different communication paths, and real-time sales promotion plan formulation by utilizing learning from past activity data.

[0086] "Information gathering means" refers to technologies for automatically acquiring sales promotion information from different communication channels.

[0087] "Information integration means" refers to technology that centrally manages and stores collected sales promotion information in a unified format.

[0088] "Information analysis means" refers to technologies that use integrated information to perform machine learning processing and formulate effective sales promotion plans.

[0089] "Plan delivery means" refers to the technology for providing and presenting a formulated sales promotion plan to users.

[0090] "Interface means" refers to technology that provides a function on a user's information terminal to review and revise the presented sales promotion plan.

[0091] The system for carrying out this invention consists of a server, an information terminal, and a user.

[0092] The server is designed to automatically collect sales promotion information from multiple communication channels. The collected information is centrally integrated into a database on the server. This is done using APIs from services such as social networking services (SNS) and email servers. The server also has the functionality to build a consistent database using the integrated information as a means of information integration.

[0093] Subsequently, the server uses machine learning libraries such as Python and TensorFlow as information analysis tools to analyze the integrated information. This analysis utilizes natural language processing techniques to process even unstructured information. As a result of the analysis, an effective sales promotion plan is generated, and the server provides this plan to the user in the next step.

[0094] On the user's side, a smartphone is used as an information terminal, allowing them to review the sales promotion plan provided through the interface and make modifications if necessary. For example, a user might analyze that placing a social media ad at 11 AM is most effective and be advised that using the phrase "weekend-only sale" would be beneficial. In this way, a concrete sales strategy is formulated in real time, enabling users to take practical action.

[0095] An example of a prompt message would be: "Based on the analysis of advertising data, please tell us which time slots are most effective for our target audience, and provide us with phrases and messages that have been successful in past campaigns."

[0096] This system enables the development of efficient and precise marketing strategies, replacing traditional manual data collection and analysis.

[0097] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0098] Step 1:

[0099] The server acquires sales promotion information from multiple communication channels. It uses APIs from social media and email servers as input to collect promotional data from various channels. The output is stored on the server as both structured and unstructured data.

[0100] Step 2:

[0101] The server integrates the collected data and builds a centralized database. Data processing is performed to standardize the data format, resulting in a consistent database output. This allows for the seamless integration of data in different formats.

[0102] Step 3:

[0103] The server analyzes data using Python and TensorFlow. It uses integrated data as input and employs machine learning algorithms to analyze the effectiveness of sales promotions. Through data calculations, action items related to effective sales promotion plans are output.

[0104] Step 4:

[0105] The server sends the analysis results to the smartphone terminal. The visualized results are provided to the user through an interface, and the user reviews the plan. Each element in the plan is presented as a concrete, actionable strategic step.

[0106] Step 5:

[0107] Users review the submitted sales promotion plan on their smartphones and make modifications as needed. They can also utilize prompts to gain new insights from the AI ​​model. The output is the campaign strategy finalized by the user.

[0108] Step 6:

[0109] Based on the user's final decision, a sales promotion campaign is executed, and the results are sent back to the server as data for the next cycle. This process enables continuous strategic improvement.

[0110] 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.

[0111] This invention is a system that automatically collects promotion-related information from different communication channels, integrates and analyzes that information, and then formulates and provides an effective promotion strategy. This system incorporates an emotion engine that recognizes user emotions, enabling the optimization of promotions according to the user's emotional state.

[0112] A system typically consists of a server, terminals, and users. The server collects information from communication channels and centralizes it in a database. The collected data is converted into a unified format within the server, and preprocessing is performed to correct any inconsistencies in the information.

[0113] The emotion engine is built into the server and analyzes emotions from acquired data and the user's past responses. It utilizes natural language processing technology to understand emotional trends, including unstructured data. This analysis provides crucial foundational data for generating promotional content optimized for each user.

[0114] As a concrete example, when an online shop launches a sales campaign for a new product, the server analyzes the user's emotional tendencies based on past purchase history, product reviews, and social media posts. If the emotion engine determines that a particular user is interested in the new product category, the server sends a customized promotional message to that user via their device. This message reflects the user's current emotional state and aims to improve click-through rates and purchase rates.

[0115] Through this process, the present invention enables the personalization of promotions that take user emotions into account, thereby maximizing the effectiveness of marketing. Using this system, marketing professionals can develop and implement more precise strategies more quickly.

[0116] The following describes the processing flow.

[0117] Step 1:

[0118] The server collects promotional information from various communication channels via APIs. This includes email campaign statistics, social media post engagement, and website visitor data. The server automates the process of periodically polling these data sources to collect the latest information.

[0119] Step 2:

[0120] The server integrates the collected information and converts it into a common data format. Diverse data formats obtained from different sources are recorded in a consistent database, and data cleansing is performed as needed. This prepares a dataset suitable for analysis.

[0121] Step 3:

[0122] The server uses an emotion engine to analyze the user's emotional state. Here, natural language processing is used to infer the user's mood and motivation level from data such as the user's past behavior, social networking service (SSN) posts, and product reviews.

[0123] Step 4:

[0124] The server runs machine learning algorithms to learn successful patterns from past promotional data and develop new promotional strategies. Furthermore, it takes into account the emotional state obtained by the emotion engine to generate content and messaging that is best suited to the user.

[0125] Step 5:

[0126] The server provides users with the formulated promotional strategies via their devices. Users can visually review these strategies and projected results on a dashboard and optimize their strategies based on the provided data.

[0127] Step 6:

[0128] The user reviews the strategy provided by the server, makes adjustments as needed, and then implements the marketing measures. Customized promotional messages are sent to target users configured using the device.

[0129] (Example 2)

[0130] 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 will be referred to as the "terminal."

[0131] In today's commercial environment, companies seek promotional strategies that efficiently capture consumer attention through diverse information channels. However, integrating and effectively analyzing this information to generate personalized messages based on consumer sentiment is challenging. This challenge is particularly highlighted by the lack of means to extract useful sentiment data from vast amounts of information, including unstructured data, and to immediately provide personalized promotional content to consumers.

[0132] 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.

[0133] In this invention, the server includes information gathering means for automatically acquiring promotion-related information from different information transmission channels; information integration means for integrating and centrally managing the acquired promotion-related information; information analysis means for analyzing the sentiment of information, including unstructured data, using natural language processing technology with the integrated information; content generation means for generating user-specific promotion content using a generation AI model based on the analyzed information; and transmission means for immediately transmitting the generated promotion content to the user terminal. This makes it possible to quickly and effectively implement promotion strategies based on consumer sentiment and maximize consumer interest.

[0134] "Information gathering means" is a general term for technologies and devices that automatically acquire promotion-related information from different information transmission channels.

[0135] "Information integration means" refers to a method or apparatus for integrating and organizing acquired promotion-related information in order to manage it centrally.

[0136] "Natural language processing technology" refers to computer technology that uses computers to analyze human language data and understand its meaning.

[0137] "Information analysis tools" are methods and devices for analyzing integrated information to evaluate consumer emotions and behavior.

[0138] A "generative AI model" is a type of artificial intelligence program that generates new data or content based on input data.

[0139] "Content generation means" refers to processes and devices for creating user-specific promotional content using a generation AI model.

[0140] "Means of transmission" refers to the communication methods and technologies used to deliver generated promotional content to users' devices.

[0141] A "terminal" refers to a device or apparatus used by a user to receive information.

[0142] To implement this invention, the components of a server, a terminal, and a user are required. The server is responsible for the functions of data collection, data integration, information analysis, promotional content generation, and transmission.

[0143] The server automatically collects promotional information from various information channels, such as the internet, social media platforms, and email systems. Data collection often utilizes techniques such as API access and web scraping.

[0144] Data integration involves using a database management system to convert data from different formats into a unified format for centralized management. During this process, data preprocessing is performed, including imputation of missing values ​​and removal of duplicate data.

[0145] The server utilizes a built-in sentiment analysis engine to analyze users' emotions from collected information. It uses natural language processing techniques, such as open-source natural language processing libraries or custom algorithms, to extract significant emotional patterns from unstructured data.

[0146] Using a generative AI model, personalized promotional content is generated based on analyzed sentiment information. The generative AI model employs industry-standard deep learning algorithms and utilizes prompts to customize messages. An example of a prompt would be, "Generate a message about the next product campaign based on past data."

[0147] The generated promotional content is sent to the user's device in real time. The device displays the received promotional message, encouraging the user to make a purchase. Push notifications and email distribution services are used as means of conveying this information.

[0148] As a concrete example, the server analyzes past consumer behavior data and creates special discount coupons that are likely to interest users when a new product is launched. These coupons are instantly displayed on the user's device while they are browsing a specific product, helping to encourage purchases.

[0149] This allows the server to efficiently implement effective and personalized promotional strategies for users.

[0150] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0151] Step 1:

[0152] The server collects promotional information from various information channels. Inputs include text data and image data obtained from the internet and social media APIs. The server receives this information in different formats and converts it to a specified data format. This process prepares the data from each source for unified processing. Data collection includes specifying specific keywords and hashtags to efficiently gather highly relevant data.

[0153] Step 2:

[0154] The server integrates and centralizes the collected data. The input data is stored in a database. The server converts each piece of data into a common format and performs data cleansing to remove redundancy and duplication. This process includes, for example, unifying different timestamp formats and normalizing text data. As a result, a clean dataset suitable for analysis is constructed.

[0155] Step 3:

[0156] The server analyzes user emotions from integrated data. Input includes integrated text and metadata. The server utilizes natural language processing techniques to analyze user emotional states with high accuracy. For example, it classifies emotions into positive, negative, and neutral categories and evaluates liking for specific products. Output includes user emotional tendencies and segmented emotional data. This analysis is performed using emotion dictionaries and emotion classification algorithms.

[0157] Step 4:

[0158] The server generates promotional content using a generative AI model based on the results of sentiment analysis. Input includes sentiment data and the user's past interaction history. The generative AI model utilizes prompts to create personalized messages tailored to the user. This step involves generating specific campaign content that reflects product details and user interests. The output is a customized promotional message.

[0159] Step 5:

[0160] The server sends the generated promotional message to the device. The input includes the generated message and the user's contact information. The device then takes action to immediately notify the user of the received message, including sending push notifications or emails. The output is the successful delivery of the promotion to the user. The user can view the message received via the device and participate in the campaign.

[0161] (Application Example 2)

[0162] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0163] To effectively utilize information automatically acquired through communication channels for promotional purposes, it is necessary to quickly provide personalized strategies tailored to the individual user's situation and preferences. However, conventional methods cannot grasp the user's situation in detail and can only propose a uniform strategy, which presents a challenge in adequately increasing user satisfaction.

[0164] 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.

[0165] In this invention, the server includes data acquisition means for automatically acquiring information from different communication channels, data integration means for integrating and managing the acquired information, and sentiment analysis means for analyzing the user's state and generating suggestions appropriate to that state. This makes it possible to individually provide optimal promotional strategies according to the user's state and improve user satisfaction.

[0166] "Data acquisition means" refers to a component that has the function of automatically acquiring promotion-related information from different communication channels.

[0167] A "data integration mechanism" is a component that has the function of integrating and centrally managing acquired promotion-related information.

[0168] "Data analysis tools" refer to the components that analyze integrated data using machine learning algorithms and have the function of formulating effective promotional strategies.

[0169] A "strategy delivery tool" is a component that has the function of providing the formulated promotion strategy to users.

[0170] "Emotion analysis means" refers to a component that analyzes user input information, infers the user's state, and generates suggestions appropriate to that state.

[0171] The system for realizing this invention consists of a server, terminals, and users. The server automatically acquires promotion-related information from different communication channels using data acquisition means. This information is then integrated and centrally managed by data integration means. The integrated data is analyzed by data analysis means using machine learning algorithms to formulate an effective promotion strategy. The formulated strategy is provided to users through strategy provision means.

[0172] The core of the system, sentiment analysis, is performed based on user input information collected from the terminal, such as text and images. The sentiment analysis method uses natural language processing and computer vision technologies to analyze the user's state and generate personalized suggestions tailored to that state. Specifically, it uses Google's Cloud Natural Language API to analyze the sentiment of text and OpenCV and Dlib to analyze facial expressions from camera footage.

[0173] For example, if a user makes a positive post such as "A new casual shirt makes me feel great!" while using a specific online shopping app on their smartphone, sentiment analysis will detect a positive emotion from this post. Based on this result, products that are suitable for the user will be recommended. This process is executed by inputting an example prompt message into the generative AI model: "Generate the best product recommendations when a positive emotion is detected, based on the user's latest purchase history data and current social media posts." This makes it possible to achieve promotions optimized for the user's emotional state.

[0174] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0175] Step 1:

[0176] The server retrieves promotional information from different communication channels. The input is information transmitted through these channels, and the output is a dataset of the retrieved information. Automated data collection methods are used in this process.

[0177] Step 2:

[0178] The server integrates and centrally manages the acquired information. The input is the dataset acquired in step 1, and the output is the integrated dataset. Data integration means are used to remove duplicates and missing data and to format the data.

[0179] Step 3:

[0180] The server analyzes the integrated data using machine learning algorithms. The input is the integrated dataset, and the output is the analysis results. The data analysis tools extract specific patterns and trends to formulate effective promotional strategies. In this step, machine learning libraries are used to extract data features.

[0181] Step 4:

[0182] The device collects user input information and performs real-time sentiment analysis. Input includes user text and facial expressions, while output is the analyzed emotional state. This information is processed using natural language processing and computer vision technologies.

[0183] Step 5:

[0184] The server generates a personalized promotional strategy based on the sentiment analysis results and sends it to the terminal. The input is the sentiment analysis results from step 4 and the promotional strategy from step 3, and the output is promotional content optimized for the user.

[0185] Step 6:

[0186] Users receive and review promotional strategies provided through their devices. Input is the promotional content sent from the server, while output is user feedback and actions. This information is delivered to the user through the user interface.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] [Second Embodiment]

[0191] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0192] 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.

[0193] 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).

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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".

[0203] This invention is a system for automatically collecting, integrating, and analyzing promotional information from different communication channels. The system mainly consists of a server, terminals, and users, each playing a specific role.

[0204] The server automatically retrieves promotion-related information from each communication channel via APIs. This eliminates the hassle of manually collecting data and enables real-time information gathering.

[0205] The acquired data is centrally managed by a server. The server unifies different data formats and builds a consistent database. This allows data from different channels to be seamlessly integrated and ready for analysis.

[0206] Next, the server analyzes the integrated data using machine learning algorithms. The analysis process also utilizes natural language processing techniques to process unstructured data and analyze the performance of past promotions. This step helps identify patterns of success and forms the basis for new promotional strategies.

[0207] After formulating the strategy, the server provides the results to the user via the terminal. The user reviews the presented strategy, makes modifications as needed, and then implements the final marketing measures.

[0208] As a concrete example, consider a company planning a campaign for a new product. Based on existing data, the server identifies the success factors of similar past campaigns and presents users with optimal posting times and effective message content for social media. Users can then consider the suggestions and use them to help implement the actual campaign.

[0209] In this way, the present invention streamlines the entire marketing process and supports data-driven strategic decision-making.

[0210] The following describes the processing flow.

[0211] Step 1:

[0212] The server collects promotional information from various communication channels via APIs. This includes open rates from email services, interaction data from social media, and website visit data. The server periodically calls the APIs to retrieve the latest data and saves it to local storage.

[0213] Step 2:

[0214] The server standardizes the data it collects and stores it in a centralized database. Data with different formats and structures is converted into a common format and organized using keys such as customer IDs and campaign IDs. This unifies the data in a way that is suitable for subsequent analysis processes.

[0215] Step 3:

[0216] The server preprocesses the data to ensure the necessary quality for analysis. Preprocessing includes filtering out unnecessary data using natural language processing techniques and imputing missing values ​​using statistical methods. After cleansing, the dataset is ready for analysis.

[0217] Step 4:

[0218] The server analyzes the data using machine learning algorithms. Clustering and classification techniques are used to identify success factors and common patterns in past promotions. The analysis results are then compiled to support recommended strategies.

[0219] Step 5:

[0220] The server generates a new promotional strategy based on the analysis results and provides it to the user via their terminal. The generated strategy is visualized on a dashboard and presented with quantitative indicators showing the predicted effect of each strategy. The user then evaluates the validity of the strategy based on this.

[0221] Step 6:

[0222] Users review the promotional strategies proposed by the server and make adjustments based on their own insights. Referring to the information on the dashboard, users finalize the strategy, fine-tune the target audience, and then use this strategy to implement the actual campaign.

[0223] (Example 1)

[0224] 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."

[0225] Today, consumer interests and purchasing behavior are changing rapidly, making it crucial for businesses to reach consumers at the right time. However, collecting, managing, and analyzing promotional information from various communication channels in a consistent manner is extremely labor-intensive when done manually, making real-time decision-making difficult. Solving this challenge will enable businesses to build more effective marketing strategies and reach consumers quickly.

[0226] 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.

[0227] In this invention, the server includes information gathering means for automatically acquiring promotion-related information from different communication media, information aggregation means for integrating and centrally managing the acquired promotion-related information, and information analysis means for analyzing the integrated information using machine learning techniques to generate effective promotion strategies. This enables companies to integrate and analyze information from diverse communication media in real time and quickly formulate promotion strategies that are in line with consumer behavior.

[0228] "Communication media" refers to channels and platforms for sending and receiving information, and specifically includes the internet, social networking services (SNS), and email.

[0229] "Promotion-related information" refers to information related to the promotion of products and services, and includes data such as advertisements, campaigns, and sales information.

[0230] "Information gathering means" refers to methods and technologies for automatically acquiring promotional information from different communication media.

[0231] "Information aggregation means" refers to methods and technologies for integrating collected promotion-related information and managing it in a unified format.

[0232] "Information analysis means" refers to methods and technologies for analyzing integrated information using machine learning techniques to generate effective promotional strategies.

[0233] "Means of providing strategies" refers to the methods and technologies for providing the generated promotional strategies to users.

[0234] In order to implement this invention, it is necessary to build a system in which servers, terminals, and users cooperate with each other to collect, integrate, and analyze promotion-related information from various communication media.

[0235] The server plays a central role, automatically collecting information from various communication channels. This includes obtaining information from social networking platforms such as Twitter and Instagram using web APIs. Specifically, it can utilize scraping scripts developed in Python or cloud-based services.

[0236] The collected data is converted to a unified format on the server and stored in a database. For example, database software such as MySQL or PostgreSQL is used to integrate different data formats. During this process, data cleaning is performed, such as filling in missing data and removing duplicate data.

[0237] The server applies machine learning techniques to the integrated data and performs analysis. To do this, it utilizes libraries such as TensorFlow and PyTorch for natural language processing. Specifically, it uses BERT and GPT models to analyze unstructured data, for example, to extract patterns from past promotional activities.

[0238] The analysis results are sent from the server to the terminal and presented to the user in a dashboard format. This allows users to review new promotional strategy proposals based on past success stories and formulate measures based on them.

[0239] For example, by having a user input a prompt such as, "What are the characteristics of the most effective promotions in the past three months?" into the system, specific guidance can be obtained from the analyzed data. Following this guidance, users can receive assistance in developing and implementing appropriate promotional plans tailored to consumer behavior.

[0240] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0241] Step 1:

[0242] The server collects promotional information from various communication channels. Using API keys from each social media platform as input, it collects post data related to specific keywords and hashtags. This operation is performed by a Python scraping script, yielding the raw data as output.

[0243] Step 2:

[0244] The server integrates the collected raw data and stores it in a database. The input is the raw data obtained in step 1. The data is converted from JSON format to CSV format and saved to a MySQL database. As part of the data cleaning process, missing values ​​are filled in and duplicates are removed. This creates a consistent dataset as the output.

[0245] Step 3:

[0246] The server performs analysis on the integrated data. The dataset prepared in step 2 is used as input. In this step, a machine learning model is trained using TensorFlow, and unstructured data is analyzed using natural language processing techniques. For example, the BERT model is used to extract topics and sentiment from posts, and the analysis results are obtained as output.

[0247] Step 4:

[0248] The server sends the analysis results to the terminal and provides them to the user. The input is the analysis results obtained in step 3. The data received on the terminal is visualized in a dashboard format. Based on the data visualizing the factors that contributed to past promotional success, the user can consider new promotional strategies. This output enables the user to plan effective marketing measures.

[0249] (Application Example 1)

[0250] 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."

[0251] In marketing activities, efficiently collecting and analyzing sales promotion information from different communication channels is crucial. However, traditional methods often involve manual processes, which are time-consuming and labor-intensive. Furthermore, while learning from past sales promotion data and developing effective plans in real time would lead to more efficient marketing activities, there has been a lack of means to achieve this.

[0252] 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.

[0253] In this invention, the server includes information gathering means for automatically acquiring sales promotion information from different communication paths, information integration means for integrating and centrally managing the acquired information, information analysis means for analyzing the integrated information using machine learning processing to formulate an effective sales promotion plan, and interface means for presenting the formulated plan and allowing users to review and modify it using a smartphone. This enables efficient collection and integration of information from different communication paths, and real-time sales promotion plan formulation by utilizing learning from past activity data.

[0254] "Information gathering means" refers to technologies for automatically acquiring sales promotion information from different communication channels.

[0255] "Information integration means" refers to technology that centrally manages and stores collected sales promotion information in a unified format.

[0256] "Information analysis means" refers to technologies that use integrated information to perform machine learning processing and formulate effective sales promotion plans.

[0257] "Plan delivery means" refers to the technology for providing and presenting a formulated sales promotion plan to users.

[0258] "Interface means" refers to technology that provides a function on a user's information terminal to review and revise the presented sales promotion plan.

[0259] The system for carrying out this invention consists of a server, an information terminal, and a user.

[0260] The server is designed to automatically collect sales promotion information from multiple communication channels. The collected information is centrally integrated into a database on the server. This is done using APIs from services such as social networking services (SNS) and email servers. The server also has the functionality to build a consistent database using the integrated information as a means of information integration.

[0261] Subsequently, the server uses machine learning libraries such as Python and TensorFlow as information analysis tools to analyze the integrated information. This analysis utilizes natural language processing techniques to process even unstructured information. As a result of the analysis, an effective sales promotion plan is generated, and the server provides this plan to the user in the next step.

[0262] On the user's side, a smartphone is used as an information terminal, allowing them to review the sales promotion plan provided through the interface and make modifications if necessary. For example, a user might analyze that placing a social media ad at 11 AM is most effective and be advised that using the phrase "weekend-only sale" would be beneficial. In this way, a concrete sales strategy is formulated in real time, enabling users to take practical action.

[0263] An example of a prompt message would be: "Based on the analysis of advertising data, please tell us which time slots are most effective for our target audience, and provide us with phrases and messages that have been successful in past campaigns."

[0264] This system enables the development of efficient and precise marketing strategies, replacing traditional manual data collection and analysis.

[0265] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0266] Step 1:

[0267] The server acquires sales promotion information from multiple communication channels. It uses APIs from social media and email servers as input to collect promotional data from various channels. The output is stored on the server as both structured and unstructured data.

[0268] Step 2:

[0269] The server integrates the collected data and builds a centralized database. Data processing is performed to standardize the data format, resulting in a consistent database output. This allows for the seamless integration of data in different formats.

[0270] Step 3:

[0271] The server analyzes data using Python and TensorFlow. It uses integrated data as input and employs machine learning algorithms to analyze the effectiveness of sales promotions. Through data calculations, action items related to effective sales promotion plans are output.

[0272] Step 4:

[0273] The server sends the analysis results to the smartphone terminal. The visualized results are provided to the user through an interface, and the user reviews the plan. Each element in the plan is presented as a concrete, actionable strategic step.

[0274] Step 5:

[0275] Users review the submitted sales promotion plan on their smartphones and make modifications as needed. They can also utilize prompts to gain new insights from the AI ​​model. The output is the campaign strategy finalized by the user.

[0276] Step 6:

[0277] Based on the user's final decision, a sales promotion campaign is executed, and the results are sent back to the server as data for the next cycle. This process enables continuous strategic improvement.

[0278] 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.

[0279] This invention is a system that automatically collects promotion-related information from different communication channels, integrates and analyzes that information, and then formulates and provides an effective promotion strategy. This system incorporates an emotion engine that recognizes user emotions, enabling the optimization of promotions according to the user's emotional state.

[0280] A system typically consists of a server, terminals, and users. The server collects information from communication channels and centralizes it in a database. The collected data is converted into a unified format within the server, and preprocessing is performed to correct any inconsistencies in the information.

[0281] The emotion engine is built into the server and analyzes emotions from acquired data and the user's past responses. It utilizes natural language processing technology to understand emotional trends, including unstructured data. This analysis provides crucial foundational data for generating promotional content optimized for each user.

[0282] As a concrete example, when an online shop launches a sales campaign for a new product, the server analyzes the user's emotional tendencies based on past purchase history, product reviews, and social media posts. If the emotion engine determines that a particular user is interested in the new product category, the server sends a customized promotional message to that user via their device. This message reflects the user's current emotional state and aims to improve click-through rates and purchase rates.

[0283] Through this process, the present invention enables the personalization of promotions that take user emotions into account, thereby maximizing the effectiveness of marketing. Using this system, marketing professionals can develop and implement more precise strategies more quickly.

[0284] The following describes the process flow.

[0285] Step 1:

[0286] The server collects promotion-related information via the API from different communication channels. This includes statistical data of email campaigns, post reactions on SNS, and website visitor data. The server periodically polls these data sources and automates the process of collecting the latest information.

[0287] Step 2:

[0288] The server integrates the collected information and converts it into a common data format. It records data in various formats obtained from different information sources in a consistent database and performs data cleansing as needed. This prepares a dataset suitable for analysis.

[0289] Step 3:

[0290] The server uses an emotion engine to analyze the user's emotional state. Here, natural language processing is utilized from the user's past behavior data, SSN post content, product reviews, etc. to infer the user's mood and motivation level.

[0291] Step 4:

[0292] The server runs a machine learning algorithm to learn successful patterns from past promotion data and formulates new promotion strategies. Furthermore, considering the emotional state obtained by the emotion engine, it generates the most suitable content and messaging for the user.

[0293] Step 5:

[0294] The server provides the formulated promotion strategies to the user through the terminal. The user visually confirms these strategies and predicted results on the dashboard and optimizes the strategies based on the provided data.

[0295] Step 6:

[0296] The user reviews the strategy provided by the server, makes adjustments as needed, and then implements the marketing measures. Customized promotional messages are sent to target users configured using the device.

[0297] (Example 2)

[0298] 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".

[0299] In today's commercial environment, companies seek promotional strategies that efficiently capture consumer attention through diverse information channels. However, integrating and effectively analyzing this information to generate personalized messages based on consumer sentiment is challenging. This challenge is particularly highlighted by the lack of means to extract useful sentiment data from vast amounts of information, including unstructured data, and to immediately provide personalized promotional content to consumers.

[0300] 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.

[0301] In this invention, the server includes: an information collection means for automatically acquiring promotion-related information from different information transmission channels; an information integration means for integrating and centrally managing the acquired promotion-related information; an information analysis means for leveraging natural language processing technology to analyze the sentiment of information including unstructured data using the integrated information; a content generation means for generating promotion content tailored to the user using a generated AI model based on the analyzed information; and a transmission means for immediately transmitting the generated promotion content to the user terminal. Thereby, it becomes possible to quickly and effectively implement a promotion strategy based on the sentiment of consumers and maximize the interest of consumers.

[0302] The "information collection means" is a general term for technologies and devices for automatically acquiring promotion-related information from different information transmission channels.

[0303] The "information integration means" is a method or device for integrating and organizing the acquired promotion-related information for centralized management.

[0304] "Natural language processing technology" refers to computer technology for analyzing human language data by a computer to understand its meaning.

[0305] The "information analysis means" is a method or device for analyzing the integrated information to evaluate the sentiment and behavior of consumers.

[0306] The "generated AI model" is a type of artificial intelligence program for generating new data or content based on input data.

[0307] The "content generation means" is a process or device for creating promotion content tailored to the user using the generated AI model.

[0308] The "transmission means" refers to communication means and technologies for delivering the generated promotion content to the user's terminal.

[0309] A "terminal" refers to a device or apparatus used by a user to receive information.

[0310] To implement this invention, the components of a server, a terminal, and a user are required. The server is responsible for the functions of data collection, data integration, information analysis, promotional content generation, and transmission.

[0311] The server automatically collects promotional information from various information channels, such as the internet, social media platforms, and email systems. Data collection often utilizes techniques such as API access and web scraping.

[0312] Data integration involves using a database management system to convert data from different formats into a unified format for centralized management. During this process, data preprocessing is performed, including imputation of missing values ​​and removal of duplicate data.

[0313] The server utilizes a built-in sentiment analysis engine to analyze users' emotions from collected information. It uses natural language processing techniques, such as open-source natural language processing libraries or custom algorithms, to extract significant emotional patterns from unstructured data.

[0314] Using a generative AI model, personalized promotional content is generated based on analyzed sentiment information. The generative AI model employs industry-standard deep learning algorithms and utilizes prompts to customize messages. An example of a prompt would be, "Generate a message about the next product campaign based on past data."

[0315] The generated promotional content is sent to the user's device in real time. The device displays the received promotional message, encouraging the user to make a purchase. Push notifications and email distribution services are used as means of conveying this information.

[0316] As a concrete example, the server analyzes past consumer behavior data and creates special discount coupons that are likely to interest users when a new product is launched. These coupons are instantly displayed on the user's device while they are browsing a specific product, helping to encourage purchases.

[0317] This allows the server to efficiently implement effective and personalized promotional strategies for users.

[0318] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0319] Step 1:

[0320] The server collects promotional information from various information channels. Inputs include text data and image data obtained from the internet and social media APIs. The server receives this information in different formats and converts it to a specified data format. This process prepares the data from each source for unified processing. Data collection includes specifying specific keywords and hashtags to efficiently gather highly relevant data.

[0321] Step 2:

[0322] The server integrates and centralizes the collected data. The input data is stored in a database. The server converts each piece of data into a common format and performs data cleansing to remove redundancy and duplication. This process includes, for example, unifying different timestamp formats and normalizing text data. As a result, a clean dataset suitable for analysis is constructed.

[0323] Step 3:

[0324] The server analyzes user emotions from integrated data. Input includes integrated text and metadata. The server utilizes natural language processing techniques to analyze user emotional states with high accuracy. For example, it classifies emotions into positive, negative, and neutral categories and evaluates liking for specific products. Output includes user emotional tendencies and segmented emotional data. This analysis is performed using emotion dictionaries and emotion classification algorithms.

[0325] Step 4:

[0326] The server generates promotional content using a generative AI model based on the results of sentiment analysis. Input includes sentiment data and the user's past interaction history. The generative AI model utilizes prompts to create personalized messages tailored to the user. This step involves generating specific campaign content that reflects product details and user interests. The output is a customized promotional message.

[0327] Step 5:

[0328] The server sends the generated promotional message to the device. The input includes the generated message and the user's contact information. The device then takes action to immediately notify the user of the received message, including sending push notifications or emails. The output is the successful delivery of the promotion to the user. The user can view the message received via the device and participate in the campaign.

[0329] (Application Example 2)

[0330] 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."

[0331] To effectively utilize information automatically acquired through communication channels for promotional purposes, it is necessary to quickly provide personalized strategies tailored to the individual user's situation and preferences. However, conventional methods cannot grasp the user's situation in detail and can only propose a uniform strategy, which presents a challenge in adequately increasing user satisfaction.

[0332] 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.

[0333] In this invention, the server includes data acquisition means for automatically acquiring information from different communication channels, data integration means for integrating and managing the acquired information, and sentiment analysis means for analyzing the user's state and generating suggestions appropriate to that state. This makes it possible to individually provide optimal promotional strategies according to the user's state and improve user satisfaction.

[0334] "Data acquisition means" refers to a component that has the function of automatically acquiring promotion-related information from different communication channels.

[0335] A "data integration mechanism" is a component that has the function of integrating and centrally managing acquired promotion-related information.

[0336] "Data analysis tools" refer to the components that analyze integrated data using machine learning algorithms and have the function of formulating effective promotional strategies.

[0337] A "strategy delivery tool" is a component that has the function of providing the formulated promotion strategy to users.

[0338] "Emotion analysis means" refers to a component that analyzes user input information, infers the user's state, and generates suggestions appropriate to that state.

[0339] The system for realizing this invention consists of a server, terminals, and users. The server automatically acquires promotion-related information from different communication channels using data acquisition means. This information is then integrated and centrally managed by data integration means. The integrated data is analyzed by data analysis means using machine learning algorithms to formulate an effective promotion strategy. The formulated strategy is provided to users through strategy provision means.

[0340] The core of the system, sentiment analysis, is performed based on user input information collected from the terminal, such as text and images. The sentiment analysis method uses natural language processing and computer vision technologies to analyze the user's state and generate personalized suggestions tailored to that state. Specifically, it uses Google's Cloud Natural Language API to analyze the sentiment of text and OpenCV and Dlib to analyze facial expressions from camera footage.

[0341] For example, if a user makes a positive post such as "A new casual shirt makes me feel great!" while using a specific online shopping app on their smartphone, sentiment analysis will detect a positive emotion from this post. Based on this result, products that are suitable for the user will be recommended. This process is executed by inputting an example prompt message into the generative AI model: "Generate the best product recommendations when a positive emotion is detected, based on the user's latest purchase history data and current social media posts." This makes it possible to achieve promotions optimized for the user's emotional state.

[0342] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0343] Step 1:

[0344] The server retrieves promotional information from different communication channels. The input is information transmitted through these channels, and the output is a dataset of the retrieved information. Automated data collection methods are used in this process.

[0345] Step 2:

[0346] The server integrates and centrally manages the acquired information. The input is the dataset acquired in step 1, and the output is the integrated dataset. Data integration means are used to remove duplicates and missing data and to format the data.

[0347] Step 3:

[0348] The server analyzes the integrated data using machine learning algorithms. The input is the integrated dataset, and the output is the analysis results. The data analysis tools extract specific patterns and trends to formulate effective promotional strategies. In this step, machine learning libraries are used to extract data features.

[0349] Step 4:

[0350] The device collects user input information and performs real-time sentiment analysis. Input includes user text and facial expressions, while output is the analyzed emotional state. This information is processed using natural language processing and computer vision technologies.

[0351] Step 5:

[0352] The server generates a personalized promotional strategy based on the sentiment analysis results and sends it to the terminal. The input is the sentiment analysis results from step 4 and the promotional strategy from step 3, and the output is promotional content optimized for the user.

[0353] Step 6:

[0354] Users receive and review promotional strategies provided through their devices. Input is the promotional content sent from the server, while output is user feedback and actions. This information is delivered to the user through the user interface.

[0355] 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.

[0356] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0357] 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.

[0358] [Third Embodiment]

[0359] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0360] 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.

[0361] 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).

[0362] 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.

[0363] 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.

[0364] 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).

[0365] 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.

[0366] 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.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] 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".

[0371] This invention is a system for automatically collecting, integrating, and analyzing promotional information from different communication channels. The system mainly consists of a server, terminals, and users, each playing a specific role.

[0372] The server automatically retrieves promotion-related information from each communication channel via APIs. This eliminates the hassle of manually collecting data and enables real-time information gathering.

[0373] The acquired data is centrally managed by a server. The server unifies different data formats and builds a consistent database. This allows data from different channels to be seamlessly integrated and ready for analysis.

[0374] Next, the server analyzes the integrated data using machine learning algorithms. The analysis process also utilizes natural language processing techniques to process unstructured data and analyze the performance of past promotions. This step helps identify patterns of success and forms the basis for new promotional strategies.

[0375] After formulating the strategy, the server provides the results to the user via the terminal. The user reviews the presented strategy, makes modifications as needed, and then implements the final marketing measures.

[0376] As a concrete example, consider a company planning a campaign for a new product. Based on existing data, the server identifies the success factors of similar past campaigns and presents users with optimal posting times and effective message content for social media. Users can then consider the suggestions and use them to help implement the actual campaign.

[0377] In this way, the present invention streamlines the entire marketing process and supports data-driven strategic decision-making.

[0378] The following describes the processing flow.

[0379] Step 1:

[0380] The server collects promotional information from various communication channels via APIs. This includes open rates from email services, interaction data from social media, and website visit data. The server periodically calls the APIs to retrieve the latest data and saves it to local storage.

[0381] Step 2:

[0382] The server standardizes the data it collects and stores it in a centralized database. Data with different formats and structures is converted into a common format and organized using keys such as customer IDs and campaign IDs. This unifies the data in a way that is suitable for subsequent analysis processes.

[0383] Step 3:

[0384] The server preprocesses the data to ensure the necessary quality for analysis. Preprocessing includes filtering out unnecessary data using natural language processing techniques and imputing missing values ​​using statistical methods. After cleansing, the dataset is ready for analysis.

[0385] Step 4:

[0386] The server analyzes the data using machine learning algorithms. Clustering and classification techniques are used to identify success factors and common patterns in past promotions. The analysis results are then compiled to support recommended strategies.

[0387] Step 5:

[0388] The server generates a new promotional strategy based on the analysis results and provides it to the user via their terminal. The generated strategy is visualized on a dashboard and presented with quantitative indicators showing the predicted effect of each strategy. The user then evaluates the validity of the strategy based on this.

[0389] Step 6:

[0390] Users review the promotional strategies proposed by the server and make adjustments based on their own insights. Referring to the information on the dashboard, users finalize the strategy, fine-tune the target audience, and then use this strategy to implement the actual campaign.

[0391] (Example 1)

[0392] 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."

[0393] Today, consumer interests and purchasing behavior are changing rapidly, making it crucial for businesses to reach consumers at the right time. However, collecting, managing, and analyzing promotional information from various communication channels in a consistent manner is extremely labor-intensive when done manually, making real-time decision-making difficult. Solving this challenge will enable businesses to build more effective marketing strategies and reach consumers quickly.

[0394] 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.

[0395] In this invention, the server includes information gathering means for automatically acquiring promotion-related information from different communication media, information aggregation means for integrating and centrally managing the acquired promotion-related information, and information analysis means for analyzing the integrated information using machine learning techniques to generate effective promotion strategies. This enables companies to integrate and analyze information from diverse communication media in real time and quickly formulate promotion strategies that are in line with consumer behavior.

[0396] "Communication media" refers to channels and platforms for sending and receiving information, and specifically includes the internet, social networking services (SNS), and email.

[0397] "Promotion-related information" refers to information related to the promotion of products and services, and includes data such as advertisements, campaigns, and sales information.

[0398] "Information gathering means" refers to methods and technologies for automatically acquiring promotional information from different communication media.

[0399] "Information aggregation means" refers to methods and technologies for integrating collected promotion-related information and managing it in a unified format.

[0400] "Information analysis means" refers to methods and technologies for analyzing integrated information using machine learning techniques to generate effective promotional strategies.

[0401] "Means of providing strategies" refers to the methods and technologies for providing the generated promotional strategies to users.

[0402] In order to implement this invention, it is necessary to build a system in which servers, terminals, and users cooperate with each other to collect, integrate, and analyze promotion-related information from various communication media.

[0403] The server plays a central role, automatically collecting information from various communication channels. This includes obtaining information from social networking platforms such as Twitter and Instagram using web APIs. Specifically, it can utilize scraping scripts developed in Python or cloud-based services.

[0404] The collected data is converted to a unified format on the server and stored in a database. For example, database software such as MySQL or PostgreSQL is used to integrate different data formats. During this process, data cleaning is performed, such as filling in missing data and removing duplicate data.

[0405] The server applies machine learning techniques to the integrated data and performs analysis. To do this, it utilizes libraries such as TensorFlow and PyTorch for natural language processing. Specifically, it uses BERT and GPT models to analyze unstructured data, for example, to extract patterns from past promotional activities.

[0406] The analysis results are sent from the server to the terminal and presented to the user in a dashboard format. This allows users to review new promotional strategy proposals based on past success stories and formulate measures based on them.

[0407] For example, by having a user input a prompt such as, "What are the characteristics of the most effective promotions in the past three months?" into the system, specific guidance can be obtained from the analyzed data. Following this guidance, users can receive assistance in developing and implementing appropriate promotional plans tailored to consumer behavior.

[0408] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0409] Step 1:

[0410] The server collects promotional information from various communication channels. Using API keys from each social media platform as input, it collects post data related to specific keywords and hashtags. This operation is performed by a Python scraping script, yielding the raw data as output.

[0411] Step 2:

[0412] The server integrates the collected raw data and stores it in a database. The input is the raw data obtained in step 1. The data is converted from JSON format to CSV format and saved to a MySQL database. As part of the data cleaning process, missing values ​​are filled in and duplicates are removed. This creates a consistent dataset as the output.

[0413] Step 3:

[0414] The server performs analysis on the integrated data. The dataset prepared in step 2 is used as input. In this step, a machine learning model is trained using TensorFlow, and unstructured data is analyzed using natural language processing techniques. For example, the BERT model is used to extract topics and sentiment from posts, and the analysis results are obtained as output.

[0415] Step 4:

[0416] The server sends the analysis results to the terminal and provides them to the user. The input is the analysis results obtained in step 3. The data received on the terminal is visualized in a dashboard format. Based on the data visualizing the factors that contributed to past promotional success, the user can consider new promotional strategies. This output enables the user to plan effective marketing measures.

[0417] (Application Example 1)

[0418] 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."

[0419] In marketing activities, efficiently collecting and analyzing sales promotion information from different communication channels is crucial. However, traditional methods often involve manual processes, which are time-consuming and labor-intensive. Furthermore, while learning from past sales promotion data and developing effective plans in real time would lead to more efficient marketing activities, there has been a lack of means to achieve this.

[0420] 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.

[0421] In this invention, the server includes information gathering means for automatically acquiring sales promotion information from different communication paths, information integration means for integrating and centrally managing the acquired information, information analysis means for analyzing the integrated information using machine learning processing to formulate an effective sales promotion plan, and interface means for presenting the formulated plan and allowing users to review and modify it using a smartphone. This enables efficient collection and integration of information from different communication paths, and real-time sales promotion plan formulation by utilizing learning from past activity data.

[0422] "Information gathering means" refers to technologies for automatically acquiring sales promotion information from different communication channels.

[0423] "Information integration means" refers to technology that centrally manages and stores collected sales promotion information in a unified format.

[0424] "Information analysis means" refers to technologies that use integrated information to perform machine learning processing and formulate effective sales promotion plans.

[0425] "Plan delivery means" refers to the technology for providing and presenting a formulated sales promotion plan to users.

[0426] "Interface means" refers to technology that provides a function on a user's information terminal to review and revise the presented sales promotion plan.

[0427] The system for carrying out this invention consists of a server, an information terminal, and a user.

[0428] The server is designed to automatically collect sales promotion information from multiple communication channels. The collected information is centrally integrated into a database on the server. This is done using APIs from services such as social networking services (SNS) and email servers. The server also has the functionality to build a consistent database using the integrated information as a means of information integration.

[0429] Subsequently, the server uses machine learning libraries such as Python and TensorFlow as information analysis tools to analyze the integrated information. This analysis utilizes natural language processing techniques to process even unstructured information. As a result of the analysis, an effective sales promotion plan is generated, and the server provides this plan to the user in the next step.

[0430] On the user's side, a smartphone is used as an information terminal, allowing them to review the sales promotion plan provided through the interface and make modifications if necessary. For example, a user might analyze that placing a social media ad at 11 AM is most effective and be advised that using the phrase "weekend-only sale" would be beneficial. In this way, a concrete sales strategy is formulated in real time, enabling users to take practical action.

[0431] An example of a prompt message would be: "Based on the analysis of advertising data, please tell us which time slots are most effective for our target audience, and provide us with phrases and messages that have been successful in past campaigns."

[0432] This system enables the development of efficient and precise marketing strategies, replacing traditional manual data collection and analysis.

[0433] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0434] Step 1:

[0435] The server acquires sales promotion information from multiple communication channels. It uses APIs from social media and email servers as input to collect promotional data from various channels. The output is stored on the server as both structured and unstructured data.

[0436] Step 2:

[0437] The server integrates the collected data and builds a centralized database. Data processing is performed to standardize the data format, resulting in a consistent database output. This allows for the seamless integration of data in different formats.

[0438] Step 3:

[0439] The server analyzes data using Python and TensorFlow. It uses integrated data as input and employs machine learning algorithms to analyze the effectiveness of sales promotions. Through data calculations, action items related to effective sales promotion plans are output.

[0440] Step 4:

[0441] The server sends the analysis results to the smartphone terminal. The visualized results are provided to the user through an interface, and the user reviews the plan. Each element in the plan is presented as a concrete, actionable strategic step.

[0442] Step 5:

[0443] Users review the submitted sales promotion plan on their smartphones and make modifications as needed. They can also utilize prompts to gain new insights from the AI ​​model. The output is the campaign strategy finalized by the user.

[0444] Step 6:

[0445] Based on the user's final decision, a sales promotion campaign is executed, and the results are sent back to the server as data for the next cycle. This process enables continuous strategic improvement.

[0446] 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.

[0447] This invention is a system that automatically collects promotion-related information from different communication channels, integrates and analyzes that information, and then formulates and provides an effective promotion strategy. This system incorporates an emotion engine that recognizes user emotions, enabling the optimization of promotions according to the user's emotional state.

[0448] A system typically consists of a server, terminals, and users. The server collects information from communication channels and centralizes it in a database. The collected data is converted into a unified format within the server, and preprocessing is performed to correct any inconsistencies in the information.

[0449] The emotion engine is built into the server and analyzes emotions from acquired data and the user's past responses. It utilizes natural language processing technology to understand emotional trends, including unstructured data. This analysis provides crucial foundational data for generating promotional content optimized for each user.

[0450] As a concrete example, when an online shop launches a sales campaign for a new product, the server analyzes the user's emotional tendencies based on past purchase history, product reviews, and social media posts. If the emotion engine determines that a particular user is interested in the new product category, the server sends a customized promotional message to that user via their device. This message reflects the user's current emotional state and aims to improve click-through rates and purchase rates.

[0451] Through this process, the present invention enables the personalization of promotions that take user emotions into account, thereby maximizing the effectiveness of marketing. Using this system, marketing professionals can develop and implement more precise strategies more quickly.

[0452] The following describes the processing flow.

[0453] Step 1:

[0454] The server collects promotional information from various communication channels via APIs. This includes email campaign statistics, social media post engagement, and website visitor data. The server automates the process of periodically polling these data sources to collect the latest information.

[0455] Step 2:

[0456] The server integrates the collected information and converts it into a common data format. Diverse data formats obtained from different sources are recorded in a consistent database, and data cleansing is performed as needed. This prepares a dataset suitable for analysis.

[0457] Step 3:

[0458] The server uses an emotion engine to analyze the user's emotional state. Here, natural language processing is used to infer the user's mood and motivation level from data such as the user's past behavior, social networking service (SSN) posts, and product reviews.

[0459] Step 4:

[0460] The server runs machine learning algorithms to learn successful patterns from past promotional data and develop new promotional strategies. Furthermore, it takes into account the emotional state obtained by the emotion engine to generate content and messaging that is best suited to the user.

[0461] Step 5:

[0462] The server provides users with the formulated promotional strategies via their devices. Users can visually review these strategies and projected results on a dashboard and optimize their strategies based on the provided data.

[0463] Step 6:

[0464] The user reviews the strategy provided by the server, makes adjustments as needed, and then implements the marketing measures. Customized promotional messages are sent to target users configured using the device.

[0465] (Example 2)

[0466] 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."

[0467] In today's commercial environment, companies seek promotional strategies that efficiently capture consumer attention through diverse information channels. However, integrating and effectively analyzing this information to generate personalized messages based on consumer sentiment is challenging. This challenge is particularly highlighted by the lack of means to extract useful sentiment data from vast amounts of information, including unstructured data, and to immediately provide personalized promotional content to consumers.

[0468] 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.

[0469] In this invention, the server includes information gathering means for automatically acquiring promotion-related information from different information transmission channels; information integration means for integrating and centrally managing the acquired promotion-related information; information analysis means for analyzing the sentiment of information, including unstructured data, using natural language processing technology with the integrated information; content generation means for generating user-specific promotion content using a generation AI model based on the analyzed information; and transmission means for immediately transmitting the generated promotion content to the user terminal. This makes it possible to quickly and effectively implement promotion strategies based on consumer sentiment and maximize consumer interest.

[0470] "Information gathering means" is a general term for technologies and devices that automatically acquire promotion-related information from different information transmission channels.

[0471] "Information integration means" refers to a method or apparatus for integrating and organizing acquired promotion-related information in order to manage it centrally.

[0472] "Natural language processing technology" refers to computer technology that uses computers to analyze human language data and understand its meaning.

[0473] "Information analysis tools" are methods and devices for analyzing integrated information to evaluate consumer emotions and behavior.

[0474] A "generative AI model" is a type of artificial intelligence program that generates new data or content based on input data.

[0475] "Content generation means" refers to processes and devices for creating user-specific promotional content using a generation AI model.

[0476] "Means of transmission" refers to the communication methods and technologies used to deliver generated promotional content to users' devices.

[0477] A "terminal" refers to a device or apparatus used by a user to receive information.

[0478] To implement this invention, the components of a server, a terminal, and a user are required. The server is responsible for the functions of data collection, data integration, information analysis, promotional content generation, and transmission.

[0479] The server automatically collects promotional information from various information channels, such as the internet, social media platforms, and email systems. Data collection often utilizes techniques such as API access and web scraping.

[0480] Data integration involves using a database management system to convert data from different formats into a unified format for centralized management. During this process, data preprocessing is performed, including imputation of missing values ​​and removal of duplicate data.

[0481] The server utilizes a built-in sentiment analysis engine to analyze users' emotions from collected information. It uses natural language processing techniques, such as open-source natural language processing libraries or custom algorithms, to extract significant emotional patterns from unstructured data.

[0482] Using a generative AI model, personalized promotional content is generated based on analyzed sentiment information. The generative AI model employs industry-standard deep learning algorithms and utilizes prompts to customize messages. An example of a prompt would be, "Generate a message about the next product campaign based on past data."

[0483] The generated promotional content is sent to the user's device in real time. The device displays the received promotional message, encouraging the user to make a purchase. Push notifications and email distribution services are used as means of conveying this information.

[0484] As a concrete example, the server analyzes past consumer behavior data and creates special discount coupons that are likely to interest users when a new product is launched. These coupons are instantly displayed on the user's device while they are browsing a specific product, helping to encourage purchases.

[0485] This allows the server to efficiently implement effective and personalized promotional strategies for users.

[0486] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0487] Step 1:

[0488] The server collects promotional information from various information channels. Inputs include text data and image data obtained from the internet and social media APIs. The server receives this information in different formats and converts it to a specified data format. This process prepares the data from each source for unified processing. Data collection includes specifying specific keywords and hashtags to efficiently gather highly relevant data.

[0489] Step 2:

[0490] The server integrates and centralizes the collected data. The input data is stored in a database. The server converts each piece of data into a common format and performs data cleansing to remove redundancy and duplication. This process includes, for example, unifying different timestamp formats and normalizing text data. As a result, a clean dataset suitable for analysis is constructed.

[0491] Step 3:

[0492] The server analyzes user emotions from integrated data. Input includes integrated text and metadata. The server utilizes natural language processing techniques to analyze user emotional states with high accuracy. For example, it classifies emotions into positive, negative, and neutral categories and evaluates liking for specific products. Output includes user emotional tendencies and segmented emotional data. This analysis is performed using emotion dictionaries and emotion classification algorithms.

[0493] Step 4:

[0494] The server generates promotional content using a generative AI model based on the results of sentiment analysis. Input includes sentiment data and the user's past interaction history. The generative AI model utilizes prompts to create personalized messages tailored to the user. This step involves generating specific campaign content that reflects product details and user interests. The output is a customized promotional message.

[0495] Step 5:

[0496] The server sends the generated promotional message to the device. The input includes the generated message and the user's contact information. The device then takes action to immediately notify the user of the received message, including sending push notifications or emails. The output is the successful delivery of the promotion to the user. The user can view the message received via the device and participate in the campaign.

[0497] (Application Example 2)

[0498] 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."

[0499] To effectively utilize information automatically acquired through communication channels for promotional purposes, it is necessary to quickly provide personalized strategies tailored to the individual user's situation and preferences. However, conventional methods cannot grasp the user's situation in detail and can only propose a uniform strategy, which presents a challenge in adequately increasing user satisfaction.

[0500] 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.

[0501] In this invention, the server includes data acquisition means for automatically acquiring information from different communication channels, data integration means for integrating and managing the acquired information, and sentiment analysis means for analyzing the user's state and generating suggestions appropriate to that state. This makes it possible to individually provide optimal promotional strategies according to the user's state and improve user satisfaction.

[0502] "Data acquisition means" refers to a component that has the function of automatically acquiring promotion-related information from different communication channels.

[0503] A "data integration mechanism" is a component that has the function of integrating and centrally managing acquired promotion-related information.

[0504] "Data analysis tools" refer to the components that analyze integrated data using machine learning algorithms and have the function of formulating effective promotional strategies.

[0505] A "strategy delivery tool" is a component that has the function of providing the formulated promotion strategy to users.

[0506] "Emotion analysis means" refers to a component that analyzes user input information, infers the user's state, and generates suggestions appropriate to that state.

[0507] The system for realizing this invention consists of a server, terminals, and users. The server automatically acquires promotion-related information from different communication channels using data acquisition means. This information is then integrated and centrally managed by data integration means. The integrated data is analyzed by data analysis means using machine learning algorithms to formulate an effective promotion strategy. The formulated strategy is provided to users through strategy provision means.

[0508] The core of the system, sentiment analysis, is performed based on user input information collected from the terminal, such as text and images. The sentiment analysis method uses natural language processing and computer vision technologies to analyze the user's state and generate personalized suggestions tailored to that state. Specifically, it uses Google's Cloud Natural Language API to analyze the sentiment of text and OpenCV and Dlib to analyze facial expressions from camera footage.

[0509] For example, if a user makes a positive post such as "A new casual shirt makes me feel great!" while using a specific online shopping app on their smartphone, sentiment analysis will detect a positive emotion from this post. Based on this result, products that are suitable for the user will be recommended. This process is executed by inputting an example prompt message into the generative AI model: "Generate the best product recommendations when a positive emotion is detected, based on the user's latest purchase history data and current social media posts." This makes it possible to achieve promotions optimized for the user's emotional state.

[0510] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0511] Step 1:

[0512] The server retrieves promotional information from different communication channels. The input is information transmitted through these channels, and the output is a dataset of the retrieved information. Automated data collection methods are used in this process.

[0513] Step 2:

[0514] The server integrates and centrally manages the acquired information. The input is the dataset acquired in step 1, and the output is the integrated dataset. Data integration means are used to remove duplicates and missing data and to format the data.

[0515] Step 3:

[0516] The server analyzes the integrated data using machine learning algorithms. The input is the integrated dataset, and the output is the analysis results. The data analysis tools extract specific patterns and trends to formulate effective promotional strategies. In this step, machine learning libraries are used to extract data features.

[0517] Step 4:

[0518] The device collects user input information and performs real-time sentiment analysis. Input includes user text and facial expressions, while output is the analyzed emotional state. This information is processed using natural language processing and computer vision technologies.

[0519] Step 5:

[0520] The server generates a personalized promotional strategy based on the sentiment analysis results and sends it to the terminal. The input is the sentiment analysis results from step 4 and the promotional strategy from step 3, and the output is promotional content optimized for the user.

[0521] Step 6:

[0522] Users receive and review promotional strategies provided through their devices. Input is the promotional content sent from the server, while output is user feedback and actions. This information is delivered to the user through the user interface.

[0523] 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.

[0524] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0525] 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.

[0526] [Fourth Embodiment]

[0527] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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).

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] 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.

[0538] 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.

[0539] 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".

[0540] This invention is a system for automatically collecting, integrating, and analyzing promotional information from different communication channels. The system mainly consists of a server, terminals, and users, each playing a specific role.

[0541] The server automatically retrieves promotion-related information from each communication channel via APIs. This eliminates the hassle of manually collecting data and enables real-time information gathering.

[0542] The acquired data is centrally managed by a server. The server unifies different data formats and builds a consistent database. This allows data from different channels to be seamlessly integrated and ready for analysis.

[0543] Next, the server analyzes the integrated data using machine learning algorithms. The analysis process also utilizes natural language processing techniques to process unstructured data and analyze the performance of past promotions. This step helps identify patterns of success and forms the basis for new promotional strategies.

[0544] After formulating the strategy, the server provides the results to the user via the terminal. The user reviews the presented strategy, makes modifications as needed, and then implements the final marketing measures.

[0545] As a concrete example, consider a company planning a campaign for a new product. Based on existing data, the server identifies the success factors of similar past campaigns and presents users with optimal posting times and effective message content for social media. Users can then consider the suggestions and use them to help implement the actual campaign.

[0546] In this way, the present invention streamlines the entire marketing process and supports data-driven strategic decision-making.

[0547] The following describes the processing flow.

[0548] Step 1:

[0549] The server collects promotional information from various communication channels via APIs. This includes open rates from email services, interaction data from social media, and website visit data. The server periodically calls the APIs to retrieve the latest data and saves it to local storage.

[0550] Step 2:

[0551] The server standardizes the data it collects and stores it in a centralized database. Data with different formats and structures is converted into a common format and organized using keys such as customer IDs and campaign IDs. This unifies the data in a way that is suitable for subsequent analysis processes.

[0552] Step 3:

[0553] The server preprocesses the data to ensure the necessary quality for analysis. Preprocessing includes filtering out unnecessary data using natural language processing techniques and imputing missing values ​​using statistical methods. After cleansing, the dataset is ready for analysis.

[0554] Step 4:

[0555] The server analyzes the data using machine learning algorithms. Clustering and classification techniques are used to identify success factors and common patterns in past promotions. The analysis results are then compiled to support recommended strategies.

[0556] Step 5:

[0557] The server generates a new promotional strategy based on the analysis results and provides it to the user via their terminal. The generated strategy is visualized on a dashboard and presented with quantitative indicators showing the predicted effect of each strategy. The user then evaluates the validity of the strategy based on this.

[0558] Step 6:

[0559] Users review the promotional strategies proposed by the server and make adjustments based on their own insights. Referring to the information on the dashboard, users finalize the strategy, fine-tune the target audience, and then use this strategy to implement the actual campaign.

[0560] (Example 1)

[0561] 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".

[0562] Today, consumer interests and purchasing behavior are changing rapidly, making it crucial for businesses to reach consumers at the right time. However, collecting, managing, and analyzing promotional information from various communication channels in a consistent manner is extremely labor-intensive when done manually, making real-time decision-making difficult. Solving this challenge will enable businesses to build more effective marketing strategies and reach consumers quickly.

[0563] 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.

[0564] In this invention, the server includes information gathering means for automatically acquiring promotion-related information from different communication media, information aggregation means for integrating and centrally managing the acquired promotion-related information, and information analysis means for analyzing the integrated information using machine learning techniques to generate effective promotion strategies. This enables companies to integrate and analyze information from diverse communication media in real time and quickly formulate promotion strategies that are in line with consumer behavior.

[0565] "Communication media" refers to channels and platforms for sending and receiving information, and specifically includes the internet, social networking services (SNS), and email.

[0566] "Promotion-related information" refers to information related to the promotion of products and services, and includes data such as advertisements, campaigns, and sales information.

[0567] "Information gathering means" refers to methods and technologies for automatically acquiring promotional information from different communication media.

[0568] "Information aggregation means" refers to methods and technologies for integrating collected promotion-related information and managing it in a unified format.

[0569] "Information analysis means" refers to methods and technologies for analyzing integrated information using machine learning techniques to generate effective promotional strategies.

[0570] "Means of providing strategies" refers to the methods and technologies for providing the generated promotional strategies to users.

[0571] In order to implement this invention, it is necessary to build a system in which servers, terminals, and users cooperate with each other to collect, integrate, and analyze promotion-related information from various communication media.

[0572] The server plays a central role, automatically collecting information from various communication channels. This includes obtaining information from social networking platforms such as Twitter and Instagram using web APIs. Specifically, it can utilize scraping scripts developed in Python or cloud-based services.

[0573] The collected data is converted to a unified format on the server and stored in a database. For example, database software such as MySQL or PostgreSQL is used to integrate different data formats. During this process, data cleaning is performed, such as filling in missing data and removing duplicate data.

[0574] The server applies machine learning techniques to the integrated data and performs analysis. To do this, it utilizes libraries such as TensorFlow and PyTorch for natural language processing. Specifically, it uses BERT and GPT models to analyze unstructured data, for example, to extract patterns from past promotional activities.

[0575] The analysis results are sent from the server to the terminal and presented to the user in a dashboard format. This allows users to review new promotional strategy proposals based on past success stories and formulate measures based on them.

[0576] For example, by having a user input a prompt such as, "What are the characteristics of the most effective promotions in the past three months?" into the system, specific guidance can be obtained from the analyzed data. Following this guidance, users can receive assistance in developing and implementing appropriate promotional plans tailored to consumer behavior.

[0577] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0578] Step 1:

[0579] The server collects promotional information from various communication channels. Using API keys from each social media platform as input, it collects post data related to specific keywords and hashtags. This operation is performed by a Python scraping script, yielding the raw data as output.

[0580] Step 2:

[0581] The server integrates the collected raw data and stores it in a database. The input is the raw data obtained in step 1. The data is converted from JSON format to CSV format and saved to a MySQL database. As part of the data cleaning process, missing values ​​are filled in and duplicates are removed. This creates a consistent dataset as the output.

[0582] Step 3:

[0583] The server performs analysis on the integrated data. The dataset prepared in step 2 is used as input. In this step, a machine learning model is trained using TensorFlow, and unstructured data is analyzed using natural language processing techniques. For example, the BERT model is used to extract topics and sentiment from posts, and the analysis results are obtained as output.

[0584] Step 4:

[0585] The server sends the analysis results to the terminal and provides them to the user. The input is the analysis results obtained in step 3. The data received on the terminal is visualized in a dashboard format. Based on the data visualizing the factors that contributed to past promotional success, the user can consider new promotional strategies. This output enables the user to plan effective marketing measures.

[0586] (Application Example 1)

[0587] 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".

[0588] In marketing activities, efficiently collecting and analyzing sales promotion information from different communication channels is crucial. However, traditional methods often involve manual processes, which are time-consuming and labor-intensive. Furthermore, while learning from past sales promotion data and developing effective plans in real time would lead to more efficient marketing activities, there has been a lack of means to achieve this.

[0589] 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.

[0590] In this invention, the server includes information gathering means for automatically acquiring sales promotion information from different communication paths, information integration means for integrating and centrally managing the acquired information, information analysis means for analyzing the integrated information using machine learning processing to formulate an effective sales promotion plan, and interface means for presenting the formulated plan and allowing users to review and modify it using a smartphone. This enables efficient collection and integration of information from different communication paths, and real-time sales promotion plan formulation by utilizing learning from past activity data.

[0591] "Information gathering means" refers to technologies for automatically acquiring sales promotion information from different communication channels.

[0592] "Information integration means" refers to technology that centrally manages and stores collected sales promotion information in a unified format.

[0593] "Information analysis means" refers to technologies that use integrated information to perform machine learning processing and formulate effective sales promotion plans.

[0594] "Plan delivery means" refers to the technology for providing and presenting a formulated sales promotion plan to users.

[0595] "Interface means" refers to technology that provides a function on a user's information terminal to review and revise the presented sales promotion plan.

[0596] The system for carrying out this invention consists of a server, an information terminal, and a user.

[0597] The server is designed to automatically collect sales promotion information from multiple communication channels. The collected information is centrally integrated into a database on the server. This is done using APIs from services such as social networking services (SNS) and email servers. The server also has the functionality to build a consistent database using the integrated information as a means of information integration.

[0598] Subsequently, the server uses machine learning libraries such as Python and TensorFlow as information analysis tools to analyze the integrated information. This analysis utilizes natural language processing techniques to process even unstructured information. As a result of the analysis, an effective sales promotion plan is generated, and the server provides this plan to the user in the next step.

[0599] On the user's side, a smartphone is used as an information terminal, allowing them to review the sales promotion plan provided through the interface and make modifications if necessary. For example, a user might analyze that placing a social media ad at 11 AM is most effective and be advised that using the phrase "weekend-only sale" would be beneficial. In this way, a concrete sales strategy is formulated in real time, enabling users to take practical action.

[0600] An example of a prompt message would be: "Based on the analysis of advertising data, please tell us which time slots are most effective for our target audience, and provide us with phrases and messages that have been successful in past campaigns."

[0601] This system enables the development of efficient and precise marketing strategies, replacing traditional manual data collection and analysis.

[0602] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0603] Step 1:

[0604] The server acquires sales promotion information from multiple communication channels. It uses APIs from social media and email servers as input to collect promotional data from various channels. The output is stored on the server as both structured and unstructured data.

[0605] Step 2:

[0606] The server integrates the collected data and builds a centralized database. Data processing is performed to standardize the data format, resulting in a consistent database output. This allows for the seamless integration of data in different formats.

[0607] Step 3:

[0608] The server analyzes data using Python and TensorFlow. It uses integrated data as input and employs machine learning algorithms to analyze the effectiveness of sales promotions. Through data calculations, action items related to effective sales promotion plans are output.

[0609] Step 4:

[0610] The server sends the analysis results to the smartphone terminal. The visualized results are provided to the user through an interface, and the user reviews the plan. Each element in the plan is presented as a concrete, actionable strategic step.

[0611] Step 5:

[0612] Users review the submitted sales promotion plan on their smartphones and make modifications as needed. They can also utilize prompts to gain new insights from the AI ​​model. The output is the campaign strategy finalized by the user.

[0613] Step 6:

[0614] Based on the user's final decision, a sales promotion campaign is executed, and the results are sent back to the server as data for the next cycle. This process enables continuous strategic improvement.

[0615] 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.

[0616] This invention is a system that automatically collects promotion-related information from different communication channels, integrates and analyzes that information, and then formulates and provides an effective promotion strategy. This system incorporates an emotion engine that recognizes user emotions, enabling the optimization of promotions according to the user's emotional state.

[0617] A system typically consists of a server, terminals, and users. The server collects information from communication channels and centralizes it in a database. The collected data is converted into a unified format within the server, and preprocessing is performed to correct any inconsistencies in the information.

[0618] The emotion engine is built into the server and analyzes emotions from acquired data and the user's past responses. It utilizes natural language processing technology to understand emotional trends, including unstructured data. This analysis provides crucial foundational data for generating promotional content optimized for each user.

[0619] As a concrete example, when an online shop launches a sales campaign for a new product, the server analyzes the user's emotional tendencies based on past purchase history, product reviews, and social media posts. If the emotion engine determines that a particular user is interested in the new product category, the server sends a customized promotional message to that user via their device. This message reflects the user's current emotional state and aims to improve click-through rates and purchase rates.

[0620] Through this process, the present invention enables the personalization of promotions that take user emotions into account, thereby maximizing the effectiveness of marketing. Using this system, marketing professionals can develop and implement more precise strategies more quickly.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] The server collects promotional information from various communication channels via APIs. This includes email campaign statistics, social media post engagement, and website visitor data. The server automates the process of periodically polling these data sources to collect the latest information.

[0624] Step 2:

[0625] The server integrates the collected information and converts it into a common data format. Diverse data formats obtained from different sources are recorded in a consistent database, and data cleansing is performed as needed. This prepares a dataset suitable for analysis.

[0626] Step 3:

[0627] The server uses an emotion engine to analyze the user's emotional state. Here, natural language processing is used to infer the user's mood and motivation level from data such as the user's past behavior, social networking service (SSN) posts, and product reviews.

[0628] Step 4:

[0629] The server runs machine learning algorithms to learn successful patterns from past promotional data and develop new promotional strategies. Furthermore, it takes into account the emotional state obtained by the emotion engine to generate content and messaging that is best suited to the user.

[0630] Step 5:

[0631] The server provides users with the formulated promotional strategies via their devices. Users can visually review these strategies and projected results on a dashboard and optimize their strategies based on the provided data.

[0632] Step 6:

[0633] The user reviews the strategy provided by the server, makes adjustments as needed, and then implements the marketing measures. Customized promotional messages are sent to target users configured using the device.

[0634] (Example 2)

[0635] 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".

[0636] In today's commercial environment, companies seek promotional strategies that efficiently capture consumer attention through diverse information channels. However, integrating and effectively analyzing this information to generate personalized messages based on consumer sentiment is challenging. This challenge is particularly highlighted by the lack of means to extract useful sentiment data from vast amounts of information, including unstructured data, and to immediately provide personalized promotional content to consumers.

[0637] 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.

[0638] In this invention, the server includes information gathering means for automatically acquiring promotion-related information from different information transmission channels; information integration means for integrating and centrally managing the acquired promotion-related information; information analysis means for analyzing the sentiment of information, including unstructured data, using natural language processing technology with the integrated information; content generation means for generating user-specific promotion content using a generation AI model based on the analyzed information; and transmission means for immediately transmitting the generated promotion content to the user terminal. This makes it possible to quickly and effectively implement promotion strategies based on consumer sentiment and maximize consumer interest.

[0639] "Information gathering means" is a general term for technologies and devices that automatically acquire promotion-related information from different information transmission channels.

[0640] "Information integration means" refers to a method or apparatus for integrating and organizing acquired promotion-related information in order to manage it centrally.

[0641] "Natural language processing technology" refers to computer technology that uses computers to analyze human language data and understand its meaning.

[0642] "Information analysis tools" are methods and devices for analyzing integrated information to evaluate consumer emotions and behavior.

[0643] A "generative AI model" is a type of artificial intelligence program that generates new data or content based on input data.

[0644] "Content generation means" refers to processes and devices for creating user-specific promotional content using a generation AI model.

[0645] "Means of transmission" refers to the communication methods and technologies used to deliver generated promotional content to users' devices.

[0646] A "terminal" refers to a device or apparatus used by a user to receive information.

[0647] To implement this invention, the components of a server, a terminal, and a user are required. The server is responsible for the functions of data collection, data integration, information analysis, promotional content generation, and transmission.

[0648] The server automatically collects promotional information from various information channels, such as the internet, social media platforms, and email systems. Data collection often utilizes techniques such as API access and web scraping.

[0649] Data integration involves using a database management system to convert data from different formats into a unified format for centralized management. During this process, data preprocessing is performed, including imputation of missing values ​​and removal of duplicate data.

[0650] The server utilizes a built-in sentiment analysis engine to analyze users' emotions from collected information. It uses natural language processing techniques, such as open-source natural language processing libraries or custom algorithms, to extract significant emotional patterns from unstructured data.

[0651] Using a generative AI model, personalized promotional content is generated based on analyzed sentiment information. The generative AI model employs industry-standard deep learning algorithms and utilizes prompts to customize messages. An example of a prompt would be, "Generate a message about the next product campaign based on past data."

[0652] The generated promotional content is sent to the user's device in real time. The device displays the received promotional message, encouraging the user to make a purchase. Push notifications and email distribution services are used as means of conveying this information.

[0653] As a concrete example, the server analyzes past consumer behavior data and creates special discount coupons that are likely to interest users when a new product is launched. These coupons are instantly displayed on the user's device while they are browsing a specific product, helping to encourage purchases.

[0654] This allows the server to efficiently implement effective and personalized promotional strategies for users.

[0655] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0656] Step 1:

[0657] The server collects promotional information from various information channels. Inputs include text data and image data obtained from the internet and social media APIs. The server receives this information in different formats and converts it to a specified data format. This process prepares the data from each source for unified processing. Data collection includes specifying specific keywords and hashtags to efficiently gather highly relevant data.

[0658] Step 2:

[0659] The server integrates and centralizes the collected data. The input data is stored in a database. The server converts each piece of data into a common format and performs data cleansing to remove redundancy and duplication. This process includes, for example, unifying different timestamp formats and normalizing text data. As a result, a clean dataset suitable for analysis is constructed.

[0660] Step 3:

[0661] The server analyzes user emotions from integrated data. Input includes integrated text and metadata. The server utilizes natural language processing techniques to analyze user emotional states with high accuracy. For example, it classifies emotions into positive, negative, and neutral categories and evaluates liking for specific products. Output includes user emotional tendencies and segmented emotional data. This analysis is performed using emotion dictionaries and emotion classification algorithms.

[0662] Step 4:

[0663] The server generates promotional content using a generative AI model based on the results of sentiment analysis. Input includes sentiment data and the user's past interaction history. The generative AI model utilizes prompts to create personalized messages tailored to the user. This step involves generating specific campaign content that reflects product details and user interests. The output is a customized promotional message.

[0664] Step 5:

[0665] The server sends the generated promotional message to the device. The input includes the generated message and the user's contact information. The device then takes action to immediately notify the user of the received message, including sending push notifications or emails. The output is the successful delivery of the promotion to the user. The user can view the message received via the device and participate in the campaign.

[0666] (Application Example 2)

[0667] 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".

[0668] To effectively utilize information automatically acquired through communication channels for promotional purposes, it is necessary to quickly provide personalized strategies tailored to the individual user's situation and preferences. However, conventional methods cannot grasp the user's situation in detail and can only propose a uniform strategy, which presents a challenge in adequately increasing user satisfaction.

[0669] 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.

[0670] In this invention, the server includes data acquisition means for automatically acquiring information from different communication channels, data integration means for integrating and managing the acquired information, and sentiment analysis means for analyzing the user's state and generating suggestions appropriate to that state. This makes it possible to individually provide optimal promotional strategies according to the user's state and improve user satisfaction.

[0671] "Data acquisition means" refers to a component that has the function of automatically acquiring promotion-related information from different communication channels.

[0672] A "data integration mechanism" is a component that has the function of integrating and centrally managing acquired promotion-related information.

[0673] "Data analysis tools" refer to the components that analyze integrated data using machine learning algorithms and have the function of formulating effective promotional strategies.

[0674] A "strategy delivery tool" is a component that has the function of providing the formulated promotion strategy to users.

[0675] "Emotion analysis means" refers to a component that analyzes user input information, infers the user's state, and generates suggestions appropriate to that state.

[0676] The system for realizing this invention consists of a server, terminals, and users. The server automatically acquires promotion-related information from different communication channels using data acquisition means. This information is then integrated and centrally managed by data integration means. The integrated data is analyzed by data analysis means using machine learning algorithms to formulate an effective promotion strategy. The formulated strategy is provided to users through strategy provision means.

[0677] The core of the system, sentiment analysis, is performed based on user input information collected from the terminal, such as text and images. The sentiment analysis method uses natural language processing and computer vision technologies to analyze the user's state and generate personalized suggestions tailored to that state. Specifically, it uses Google's Cloud Natural Language API to analyze the sentiment of text and OpenCV and Dlib to analyze facial expressions from camera footage.

[0678] For example, if a user makes a positive post such as "A new casual shirt makes me feel great!" while using a specific online shopping app on their smartphone, sentiment analysis will detect a positive emotion from this post. Based on this result, products that are suitable for the user will be recommended. This process is executed by inputting an example prompt message into the generative AI model: "Generate the best product recommendations when a positive emotion is detected, based on the user's latest purchase history data and current social media posts." This makes it possible to achieve promotions optimized for the user's emotional state.

[0679] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0680] Step 1:

[0681] The server retrieves promotional information from different communication channels. The input is information transmitted through these channels, and the output is a dataset of the retrieved information. Automated data collection methods are used in this process.

[0682] Step 2:

[0683] The server integrates and centrally manages the acquired information. The input is the dataset acquired in step 1, and the output is the integrated dataset. Data integration means are used to remove duplicates and missing data and to format the data.

[0684] Step 3:

[0685] The server analyzes the integrated data using machine learning algorithms. The input is the integrated dataset, and the output is the analysis results. The data analysis tools extract specific patterns and trends to formulate effective promotional strategies. In this step, machine learning libraries are used to extract data features.

[0686] Step 4:

[0687] The device collects user input information and performs real-time sentiment analysis. Input includes user text and facial expressions, while output is the analyzed emotional state. This information is processed using natural language processing and computer vision technologies.

[0688] Step 5:

[0689] The server generates a personalized promotional strategy based on the sentiment analysis results and sends it to the terminal. The input is the sentiment analysis results from step 4 and the promotional strategy from step 3, and the output is promotional content optimized for the user.

[0690] Step 6:

[0691] Users receive and review promotional strategies provided through their devices. Input is the promotional content sent from the server, while output is user feedback and actions. This information is delivered to the user through the user interface.

[0692] 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.

[0693] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0694] 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.

[0695] 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.

[0696] 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.

[0697] 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.

[0698] 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.

[0699] 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.

[0700] 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."

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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.

[0706] 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.

[0707] 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.

[0708] 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.

[0709] 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.

[0710] 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.

[0711] 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.

[0712] 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.

[0713] The following is further disclosed regarding the embodiments described above.

[0714] (Claim 1)

[0715] A data collection method for automatically obtaining promotion-related information from different communication channels,

[0716] A data integration method for centrally managing and consolidating acquired promotion-related information,

[0717] A data analysis tool that uses machine learning algorithms to analyze integrated data and formulate effective promotion strategies,

[0718] A means of providing the formulated promotion strategy to users,

[0719] A system that includes this.

[0720] (Claim 2)

[0721] The system according to claim 1, wherein the data analysis means has the function of processing unstructured data using natural language processing technology.

[0722] (Claim 3)

[0723] The system according to claim 1, wherein the strategy provisioning means has the function of proposing new measures in real time based on the success factors of past promotions.

[0724] "Example 1"

[0725] (Claim 1)

[0726] Information gathering means for automatically obtaining promotion-related information from different communication media,

[0727] An information aggregation means for integrating and centrally managing acquired promotion-related information,

[0728] An information analysis tool for generating effective promotional strategies by analyzing integrated information using machine learning methods,

[0729] A means of providing the generated promotional strategies to users,

[0730] A system that includes this.

[0731] (Claim 2)

[0732] The system according to claim 1, wherein the information analysis means has the function of processing unstructured information using natural language processing technology.

[0733] (Claim 3)

[0734] The system according to claim 1, wherein the means for providing the measures has the function of immediately proposing new initiatives based on the elements of past promotional success.

[0735] "Application Example 1"

[0736] (Claim 1)

[0737] Information gathering means for automatically obtaining sales promotion information from different communication channels,

[0738] An information integration means for integrating and centrally managing acquired sales promotion information,

[0739] An information analysis tool that analyzes integrated information using machine learning processing to formulate an effective sales promotion plan,

[0740] A means of providing the formulated sales promotion plan to users,

[0741] An interface means for reviewing and modifying the presented sales promotion plan on a user information terminal,

[0742] A system that includes this.

[0743] (Claim 2)

[0744] The system according to claim 1, wherein the information analysis means has the function of processing unstructured information using language processing technology.

[0745] (Claim 3)

[0746] The system according to claim 1, wherein the plan provision means has a function to propose a new plan in real time based on the success factors of past sales promotion activities, and further has a function to present successful patterns through optimal ad placement times and message content based on past activity data using a smartphone.

[0747] "Example 2 of combining an emotion engine"

[0748] (Claim 1)

[0749] Information gathering means for automatically obtaining promotion-related information from different information transmission channels,

[0750] An information integration method for consolidating and centrally managing acquired promotion-related information,

[0751] An information analysis method that utilizes integrated information and natural language processing techniques to analyze the sentiment of information, including unstructured data,

[0752] A content generation means for generating user-specific promotional content using an AI model based on analyzed information,

[0753] A means for immediately sending the generated promotional content to the user's terminal,

[0754] A system that includes this.

[0755] (Claim 2)

[0756] The system according to claim 1, wherein the information analysis means has the function of analyzing the emotional state of the user from the collected information and generating optimized promotional content.

[0757] (Claim 3)

[0758] The system according to claim 1, wherein the transmission means has a function to notify the user terminal in real time of a message containing special discount information that reflects the user's interests.

[0759] "Application example 2 when combining with an emotional engine"

[0760] (Claim 1)

[0761] A data acquisition method for automatically obtaining promotion-related information from different communication channels,

[0762] A data integration method for centrally managing and consolidating acquired promotion-related information,

[0763] A data analysis tool that uses machine learning algorithms to analyze integrated data and formulate effective promotion strategies,

[0764] A means of providing the formulated promotion strategy to users,

[0765] An emotion analysis method for analyzing the user's state and generating suggestions appropriate to that state,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, wherein the data analysis means has the function of processing unstructured data using natural language processing technology, and the sentiment analysis means has the function of inferring a state from input information.

[0769] (Claim 3)

[0770] The system according to claim 1, wherein the strategy provision means has a function to propose new measures in real time based on the success factors of past proposals, and a function to provide personalized guidance based on sentiment analysis results. [Explanation of symbols]

[0771] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method for automatically obtaining promotion-related information from different communication channels, A data integration method for centrally managing and consolidating acquired promotion-related information, A data analysis tool that uses machine learning algorithms to analyze integrated data and formulate effective promotion strategies, A means of providing the formulated promotion strategy to users, A system that includes this.

2. The system according to claim 1, wherein the data analysis means has the function of processing unstructured data using natural language processing technology.

3. The system according to claim 1, wherein the strategy provision means has a function to propose new measures in real time based on the success factors of past promotions.

Images