system

Abstract

We provide the system. [Solution] A means of automatically collecting information from different types of data media, A method for analyzing unstructured information using natural language processing, Methods for preprocessing data and training models with machine learning techniques, A means of proposing effective placement and timing for advertising strategies, A device that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the digital age, efficient and effective sales promotion through various communication media is an important issue for enterprises. However, it is difficult to centrally manage and analyze a large amount of information obtained from each medium and quickly formulate an optimal strategy. Therefore, there is a need for a system that can effectively analyze large-scale and diverse data including unstructured data and automatically propose an optimal strategy for sales promotion.

Means for Solving the Problems

[0005] This invention provides a means for automatically collecting information from different types of communication media and a means for analyzing unstructured data using natural language processing. Furthermore, it solves the above problem by providing a system that automatically proposes optimal sales promotion strategies using means for preprocessing data and training a model with a machine learning algorithm. This system uses authentication information for secure information collection and divides the data into training data and test data when the machine learning algorithm is being trained, enabling highly accurate proposals.

[0006] "Communication media" refers to various platforms and channels intended for the transmission of information, including email, social networking services, websites, and advertising media.

[0007] The term "collection" refers to the process of acquiring necessary data from various communication media and storing it in a centralized manner.

[0008] "Natural language processing" is a technology that enables computers to understand and analyze human language, and it includes the process of extracting useful information from text data.

[0009] "Unstructured data" refers to data that does not have a fixed format or structure, and includes text, images, videos, audio, and other similar content.

[0010] "Preprocessing" refers to a series of preparatory tasks that transform raw data into a format suitable for analysis and machine learning, and includes data cleansing and feature engineering.

[0011] A "machine learning algorithm" is a computational method used to learn patterns and rules from data and make future predictions and decisions; it is used to build models.

[0012] "Sales promotion" refers to a series of activities and strategies aimed at stimulating demand for products and services and encouraging customers to make purchases.

[0013] "Proposal" means indicating the optimal course of action or method based on the collected and analyzed data.

[0014] A "system" is a collection of hardware and software components that combine the above means and processes to achieve a specific function. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the language used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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), etc.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the 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.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention relates to a system for collecting and analyzing information from various communication media and proposing optimal sales promotion strategies. Embodiments of this system are described below.

[0037] First, the server collects information from various communication media, including email, social networking services, websites, and advertising media. This involves using APIs to retrieve data in a specific format for each medium and establishing a secure connection. The collected data is then stored in an integrated database.

[0038] Next, the server uses natural language processing to analyze unstructured text information such as user reviews and comments. This analysis includes sentiment analysis and key phrase extraction, and then converts the text data into structured data.

[0039] The server then preprocesses the analyzed data. This involves data cleansing to remove noise and missing values, as well as data normalization to prepare the data for machine learning.

[0040] Next, the server trains a machine learning model using the pre-processed data. This allows it to learn effective patterns and parameters for sales promotion. Machine learning improves the model's accuracy by leveraging past success stories and data with high engagement.

[0041] The server then uses these learning results to automatically suggest the optimal sales promotion strategies for each communication medium. These suggestions are provided to the user in real time, allowing the user to formulate the content and strategies of their sales promotion campaigns based on this information.

[0042] For example, when a user promotes a new product B through social media, the server suggests the optimal posting time and content type based on past data and natural language processing results. This suggests that the user can increase engagement and conduct more effective promotions.

[0043] This system helps users optimize their sales activities quickly and efficiently by automatically handling everything from information gathering to strategic proposals.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server accesses APIs from various communication platforms, such as email, social networking services, websites, and advertising media, to collect promotional data. It securely authenticates using API keys and credentials, and retrieves data in real time.

[0047] Step 2:

[0048] The server stores the collected data in an integrated database. Even if the data is in different formats, it is formatted to conform to a common database schema, and the storage process is completed.

[0049] Step 3:

[0050] The server uses natural language processing tools to analyze the text of unstructured data such as user reviews and comments. This process involves tokenizing the text data, performing sentiment analysis, extracting key phrases, and organizing it into structured data.

[0051] Step 4:

[0052] The server performs data preprocessing and cleansing on the acquired and analyzed data. It handles missing values ​​and removes noise to adjust the data to a normal state. It also transforms the data into a format suitable for machine learning through categorical variable encoding and scaling.

[0053] Step 5:

[0054] The server inputs pre-processed data into a machine learning algorithm to train a model for predicting promotional effectiveness. The data is split into training and test data, and the model's accuracy is evaluated and improved based on past successful promotions.

[0055] Step 6:

[0056] The server leverages a trained model to generate optimal sales promotion strategies based on the latest collected data. These suggestions include specific instructions on selecting effective strategies and adjusting their timing.

[0057] Step 7:

[0058] Users receive optimized suggestions from the server and plan and execute promotional campaigns based on them. Following the suggested strategy, users can create promotional content and implement promotions at specified times.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In today's information society, efficiently collecting useful data from diverse information sources and using it to formulate optimal strategies remains a significant challenge. In particular, analyzing unstructured data and utilizing it for sales promotion activities requires considerable effort and expertise. Furthermore, ensuring the reliability of acquired information and processing it securely is also a crucial challenge.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for automatically acquiring data from different types of information media, means for analyzing unstructured information using natural language processing technology, and means for formatting the information and training a model using machine learning methods. This enables the automation of everything from information gathering and analysis to the formulation of optimal sales promotion strategies, making it possible to utilize information efficiently and reliably.

[0064] An "information medium" refers to the means or platforms used to transmit and receive data and information.

[0065] "Automatic data acquisition" refers to the process by which programs or systems collect information without human intervention.

[0066] "Natural language processing technology" refers to the technologies and methodologies used to enable computers to understand and analyze the language that humans use in everyday life.

[0067] "Unstructured information" refers to information that does not conform to a fixed data model and exists in a free-form state.

[0068] "Data formatting" refers to the cleaning and formatting of raw data to transform it into a format suitable for analysis and machine learning.

[0069] "Machine learning techniques" refer to methods and algorithms that enable computers to learn from data and improve at specific tasks.

[0070] "Training a model" refers to the process of applying machine learning algorithms to given data to enable the model to make predictions and classifications.

[0071] A "sales promotion strategy" refers to the actions and tactics planned to increase the sales of a product or service.

[0072] "Storing information in an integrated data storage device" refers to the process of storing collected data in a centralized database or storage system and managing it consistently.

[0073] "Identifying the emotional characteristics of information" refers to the technique of analyzing the emotional nuances contained within data or text and classifying the type of emotion associated with them.

[0074] "Improving the reliability of information during the preprocessing stage" refers to the process of enhancing data accuracy and consistency through data cleansing and filtering.

[0075] This invention is a system that efficiently collects, analyzes, and proposes data from various information media. It is basically operated with a server-centric configuration.

[0076] The server is connected to the internet and automatically retrieves necessary data from email, social networking services, websites, advertising media, etc., via APIs. To ensure security, a secure connection is established using authentication credentials. The collected data is stored in an integrated database, ensuring consistent data management.

[0077] The server then uses natural language processing techniques to analyze the unstructured text data. This involves using natural language processing libraries and platforms (e.g., NLTK, SpaCy) to identify sentiment within the data and extract key phrases.

[0078] Subsequently, the server processes the information to enable model training using machine learning techniques. Data cleansing and noise reduction are performed during this process. Furthermore, common libraries (e.g., TENSORFLOW®, PyTorch) are used to train the machine learning model, learning patterns and parameters related to sales promotion.

[0079] Based on trained models, the server proposes optimal sales promotion strategies for each information medium. These proposals are provided to the user in real time, allowing the user to develop specific promotional strategies based on them.

[0080] For example, if a user is considering a social media promotion for a new product, the server analyzes historical data and trend information to suggest optimized posting times and content styles. This allows the user to design a campaign that maximizes engagement.

[0081] An example of a prompt to input into the generating AI model is, "Please suggest the optimal content style and posting time for promoting a new product." This allows the system to provide metrics for efficient sales promotion.

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

[0083] Step 1:

[0084] The server retrieves data from various information sources, including email, social networking services, websites, and advertising media. This process utilizes APIs from each source to collect data in a standardized format. Input here consists of API queries and requests, and the server communicates with these sources using authentication credentials while maintaining security. The retrieved data is in an unstructured or semi-structured format and is stored in an integrated database.

[0085] Step 2:

[0086] The server analyzes unstructured data from text data stored in the database using natural language processing techniques. The input for this step is the stored text data, and the output is structured information. Specifically, the server uses software libraries (such as NLTK and SpaCy) to perform sentiment analysis and extract key phrases. For example, it classifies user reviews into positive, negative, and neutral sentiments.

[0087] Step 3:

[0088] The server processes the analyzed data, taking structured information as input. It removes noise and missing values, transforming the data into a format optimized for machine learning. The output is cleansed and standardized data. Specifically, the server uses data cleansing tools to remove outliers and normalize the data.

[0089] Step 4:

[0090] The server trains a machine learning model using the formatted data. The input for this step is cleansed data, and the output is a trained model. The server uses machine learning libraries (such as TensorFlow or PyTorch) to generate a model that learns patterns and trends related to sales promotion strategies. For example, it uses data from past successful promotions to predict future trends.

[0091] Step 5:

[0092] The server proposes the optimal sales promotion strategy based on a trained model. The input to this process is a pre-trained model, and the output generates suggestions that are provided to the user. The server creates suggestions in real time and provides specific recommendations to the user. For example, based on a prompt such as "Please suggest the optimal content style and posting time for promoting a new product," the server will suggest post content, timing, and other relevant information.

[0093] (Application Example 1)

[0094] 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."

[0095] In today's information society, extracting useful information from vast amounts of data and formulating effective advertising strategies is challenging. In particular, rapidly and accurately analyzing unstructured information obtained from various data sources and proposing optimal ad placement and broadcasting times is a crucial challenge that must be addressed to maximize advertising effectiveness.

[0096] 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.

[0097] In this invention, the server includes means for automatically collecting information from different types of data media, means for analyzing unstructured information using natural language processing, means for preprocessing data and training models with machine learning techniques, and means for proposing effective placement and timing of advertising strategies. This makes it possible to efficiently and automatically formulate an optimal advertising strategy.

[0098] "Data media" refers to various forms of material or non-material means used to transmit information.

[0099] "Information" refers to meaningful content about facts, concepts, or instructions that is transmitted through a data medium.

[0100] "Unstructured information" refers to data such as free-form text, images, and audio that does not conform to standard database formats.

[0101] "Natural language processing" refers to the techniques or methods for analyzing and understanding human language mechanically.

[0102] "Preprocessing" refers to a series of data transformation operations to convert raw data into a format suitable for analysis and machine learning.

[0103] "Machine learning technology" is a field of technology that includes the development of algorithms and statistical models that enable computers to improve their performance through experience.

[0104] A "model" is an abstract or mathematical representation constructed using machine learning to approximate complex phenomena in the real world.

[0105] An "advertising strategy" is a plan or method for effectively promoting a specific product or service to a target audience.

[0106] "Placement" refers to the process or state that determines the position or order in which an advertisement is displayed to a user.

[0107] "Time" refers to the specific time or period during which an advertisement is delivered or displayed.

[0108] To implement this invention, a server must first automatically collect information from different types of data media. The collected information is structured using a data analysis library such as Pandas, and then the unstructured information is analyzed using a natural language processing library (e.g., NLTK or Transformers). This enables sentiment analysis and key phrase extraction of the data.

[0109] Next, the server trains the model using machine learning techniques. The machine learning algorithms used are Logistic Regression and other classification models, implemented using libraries such as Sci-kit Learn. Model training involves splitting the data into training and evaluation sets based on data preprocessing. Once training is complete, the model will have the ability to suggest effective placement and timing for advertising strategies.

[0110] The device displays these advertising strategy suggestions to the user in real time. Based on these suggestions, the user can develop more effective advertising campaigns. For example, when promoting seasonal products, the system can suggest advertising placements through specific media at specific dates and times, based on past success stories.

[0111] An example of a prompt using a generative AI model is a specific question such as, "Analyze past sales promotion campaign data to tell me which types of advertisements are most effective on which days and times." This allows users to quickly and efficiently develop the optimal sales promotion strategy.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server automatically collects information from different types of data media using APIs. Inputs are API endpoints for each data medium, and outputs are streaming data in formats such as JSON. Upon receiving this data, the server converts it into a DataFrame using the Pandas library, organizing it into a unified format.

[0115] Step 2:

[0116] The server uses a natural language processing library to analyze the collected unstructured information. The input is the data frame obtained in the previous step, and the output is the analyzed data, including sentiment scores and key phrase extraction results. The server performs sentiment analysis and converts the text data into structured data.

[0117] Step 3:

[0118] The server preprocesses the analyzed data to prepare it for training a machine learning model. The input is the analyzed data, and the output is a dataset split into training data and evaluation data. The server cleanses and normalizes the data to prepare it for model learning.

[0119] Step 4:

[0120] The server trains machine learning algorithms using libraries such as Sci-kit Learn to build a model for proposing advertising strategies. The input is pre-processed training data, and the output is the trained machine learning model. The server improves the accuracy of the model through the training process.

[0121] Step 5:

[0122] The device uses a trained model to suggest optimal placement and timing for advertising strategies to the user in real time. The input is the goals and conditions of the advertising campaign specified by the user, and the output is the suggested advertising strategy. The device helps the user make decisions about building their advertising campaigns based on these suggestions.

[0123] Step 6:

[0124] Based on the proposed advertising strategy, the user designs and executes the optimal campaign. The input is the details of the proposal obtained from the device, and the output is the executed advertising campaign. The user uses this information to formulate advertising measures aimed at achieving higher results.

[0125] 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.

[0126] This invention relates to a system that analyzes user emotions based on data acquired from communication media and proposes an optimal sales promotion strategy that takes these emotions into account. The system includes processes for information gathering, natural language processing, emotion engine development, machine learning model training, and strategy proposal.

[0127] First, the server collects data from various communication channels—for example, email, social networks, websites, and advertising media. This collection includes using APIs to retrieve data in real time. The data is accessed via secure authentication credentials and stored in an integrated database.

[0128] Next, the server analyzes the unstructured data within the collected data using natural language processing tools. This analysis involves tokenizing text information and sentiment analysis, extracting user sentiment from user reviews and comments, and processing it into structured data.

[0129] The newly introduced emotion engine runs on the server and analyzes and classifies user emotions in detail based on the results of natural language processing. Furthermore, it can track changes in these emotions over time and dynamically update the emotion analysis results. This allows for the exploration of more specific and user-friendly sales promotion approaches.

[0130] During data preprocessing, the server normalizes the analyzed data and prepares it for model training using machine learning algorithms. Data cleansing removes unnecessary data, and the data is split into training and test sets. Based on this, the model is trained to identify successful promotional patterns, and the model's accuracy is improved.

[0131] Ultimately, leveraging the insights gained from the emotion engine, the server proposes new sales promotion strategies. These suggestions reflect users' emotional tendencies and include optimizing content, format, and timing. For example, based on data from past success stories of the target product, effective messaging and advertising formats are suggested to reach users in a specific emotional state.

[0132] This system provides support to users in quickly optimizing their sales activities by handling everything from information gathering and sentiment recognition to strategic proposals in a consistent manner.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server connects to APIs of multiple communication channels, such as email, social networking services, websites, and advertising platforms, to collect information. During this process, it establishes secure connections using API keys and authentication credentials, and retrieves promotion-related data in real time.

[0136] Step 2:

[0137] The server stores the collected data in an integrated database. Although data obtained from various sources is often in different formats, a unified database schema is used to format it, enabling consistent analysis.

[0138] Step 3:

[0139] The server activates a natural language processing engine to analyze the collected unstructured data (e.g., user reviews and comments). The data is tokenized, sentiment analysis is performed, and important key phrases are extracted, transforming it into structured data.

[0140] Step 4:

[0141] The server activates an emotion engine based on the analysis results to recognize and classify the user's emotions in detail. Furthermore, it tracks changes in the user's emotional state and incorporates the results into the analysis to provide up-to-date emotional insights.

[0142] Step 5:

[0143] The server performs data preprocessing, removing noise and missing values, and cleansing the data. The preprocessed data is then split into training and test sets and converted into a format suitable for training machine learning models.

[0144] Step 6:

[0145] The server trains a model using machine learning algorithms. During training, it utilizes past promotional performance data to teach the model successful patterns and effective promotional methods. This improves the model's predictive accuracy.

[0146] Step 7:

[0147] The server proposes optimal sales promotion strategies based on sentiment analysis results obtained from the sentiment engine. These proposals include advertising content tailored to each user's emotional state and the optimal delivery timing.

[0148] Step 8:

[0149] Users review optimized suggestions provided by the server and implement those strategies. The suggestions are updated in real time, allowing users to continuously gain information to improve the performance of their promotional campaigns.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] Traditional sales promotion systems struggle to accurately analyze user emotions and incorporate them into sales strategies, making it difficult to quickly propose individually optimized promotional strategies. Therefore, there is a challenge in effectively increasing customer purchasing intent.

[0153] 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.

[0154] In this invention, the server includes means for automatically collecting data from different types of information media, means for analyzing unstructured information using natural language processing, and means for analyzing user emotions and dynamically updating the emotion analysis results. This makes it possible to quickly propose optimal sales promotion strategies based on user emotions.

[0155] "Information media" refers to various communication channels and platforms from which data is collected, including, for example, email, social networks, websites, and advertising media.

[0156] "Data" refers to any form of information, such as unstructured or structured text, images, and audio, collected from information media.

[0157] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language, particularly in text analysis and sentiment analysis.

[0158] "User sentiment" refers to information that identifies an emotional state by analyzing the positive, negative, and neutral responses that users exhibit.

[0159] A "sales promotion strategy" refers to a plan or method for promoting the sale of goods or services and increasing customer interest and purchasing intent.

[0160] A "server" refers to a central computing system used for collecting, analyzing, and processing data to generate sales promotion strategies.

[0161] "Dynamic updating" means correcting and modifying information and analysis results in real time in response to situations and data that change over time.

[0162] This invention is a system that analyzes user emotions based on data collected from information media and proposes an optimal sales promotion strategy accordingly. A specific embodiment of this system is described below.

[0163] The server collects data from various information sources, including email, social networks, websites, and advertising media. This data collection utilizes APIs, and software-wise, authentication technologies such as OAuth and API keys are used to securely retrieve the data. This data is stored in an integrated database for later analysis.

[0164] Next, the server analyzes the collected unstructured data using natural language processing tools. Software-wise, it utilizes open-source natural language processing libraries and cloud-based analytics services to tokenize text data and perform sentiment analysis. This process extracts sentiments such as positive, negative, and neutral, and structures the data.

[0165] The emotion engine, which runs on the server, analyzes the user's emotions in detail based on the results of natural language processing. By tracking changes in emotions over time and dynamically updating the analysis results, it is possible to obtain more accurate emotion data.

[0166] As a concrete example, suppose a retail company is considering a campaign to launch a new product. The server collects and analyzes relevant user comments on social media and, based on the results, suggests advertising messages that are suitable for users who are "excited." For example, a message such as "This new product is the best choice that will exceed your expectations!" is shown to be effective.

[0167] An example of a prompt might be: "In a new running shoe campaign for a sporting goods store, explain how to analyze user sentiment and propose a sales promotion strategy to increase purchase intent. Specifically, demonstrate how to analyze changes in sentiment and suggest effective messaging and advertising formats."

[0168] This system allows users to more accurately grasp customer needs and refine their sales promotion strategies.

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

[0170] Step 1:

[0171] The server collects data from various information sources. Inputs include data obtained from APIs such as email, social networks, websites, and advertising media. Specifically, the server authenticates using OAuth or API keys through these APIs and retrieves the necessary data in real time. The output is raw, unprocessed data stored in an integrated database.

[0172] Step 2:

[0173] The server analyzes the collected data using natural language processing (NLP) tools. The input is the raw, unprocessed data collected in step 1. Specifically, the server uses an NLP library to tokenize the text, tag parts of speech, and perform sentiment analysis. This extracts sentiment information from user comments and reviews, and the output is structured data categorized as "positive," "negative," or "neutral."

[0174] Step 3:

[0175] The emotion engine, located on the server, analyzes the emotion data obtained by the NLP tool in detail and tracks changes. The input is the structured emotion data output in step 2. Specifically, the server analyzes changes in emotion over time and dynamically updates the results. This output is data that shows the user's emotional tendencies over a specific period.

[0176] Step 4:

[0177] The server preprocesses the data obtained from the emotion engine to prepare it for training the learning model. The input is the emotion tendency data obtained in step 3. Specifically, the server cleans this data and splits it into a training set and a test set. The output is clean data that is ready for model training.

[0178] Step 5:

[0179] The server trains a machine learning model and proposes the optimal sales promotion strategy that takes into account the user's emotional tendencies. The input is the training data prepared in step 4. Specifically, the server runs the model using the training data and discovers successful promotional patterns. The output is a sales promotion strategy proposal that includes content and advertising format tailored to the user's specific emotional state.

[0180] Step 6:

[0181] The user implements actual marketing strategies using suggestions from the server and optimizes sales activities. The input is the sales promotion strategy suggested by the server in step 5. Specifically, the user plans and executes advertising campaigns based on the suggestions and delivers effective messaging to target users. The output is improved performance as a result of the sales promotion activities.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] In modern society, consumer purchasing behavior is diversifying, and personalized promotions are required that go beyond mere product quality and price, taking into account consumers' emotions and circumstances. However, traditional sales strategies mainly rely on general statistical information and historical data, making it difficult to make suggestions that resonate with the emotions of individual consumers. Therefore, there is a need to develop a system that automatically proposes sales promotion strategies that take into account the emotional state of users.

[0185] 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.

[0186] In this invention, the server includes means for automatically collecting information from different types of communication media, means for analyzing unstructured data using natural language processing, means for preprocessing the data and training a model with a machine learning algorithm, and means for proposing personalized promotions based on the user's emotional state. This makes it possible to propose sales promotion strategies that take into account the emotional state of each individual consumer.

[0187] "Communication medium" refers to the means or methods used to transmit information. Examples include email, social networks, and websites.

[0188] Natural language processing (NLP) is a technology that enables computers to understand, analyze, and generate natural language used by humans. Examples include text tokenization and sentiment analysis.

[0189] "Unstructured data" refers to data that does not follow a fixed format or model. This typically includes text, images, and audio files.

[0190] A "machine learning algorithm" refers to a set of techniques that use data for computers to learn and perform pattern detection and prediction.

[0191] "Training a model" is the process of using data to train a machine learning algorithm and build a model that can solve a specific problem.

[0192] "Emotional state" refers to the subjective emotional state a user is experiencing at a particular point in time.

[0193] "Personalized promotions" refer to sales promotion activities such as advertisements, discounts, and coupons that are optimized for specific conditions based on each user's emotions and preferences.

[0194] This invention provides a system that proposes personalized promotions based on the user's emotional state. This system mainly consists of a server, a terminal, and a user interface.

[0195] The server is implemented in programming languages ​​such as Python and processes data using libraries such as numpy and pandas. NLTK and textblob are used for natural language processing. These tools are used to analyze communication data collected from email and social media to identify user sentiment.

[0196] The analyzed data is processed by machine learning algorithms such as scikit-learn to learn from the user's past purchasing behavior and select appropriate promotions. This allows for the effective suggestion of the most relevant promotions to the user.

[0197] For example, if a user posts "I had a great day today!" through their device, the server analyzes that emotion as positive and suggests related events and product promotions.

[0198] An example of a prompt message to use with a generative AI model is, "Suggest a suitable promotion if the user is showing positive emotions."

[0199] In this way, by providing users with sales promotion strategies tailored to their emotional state, this system enables more effective marketing than conventional methods based on statistical information.

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The server collects data from communication media such as email and social media via an API. The input data is in an unstructured format and accessed using secure authentication credentials. The collected data is stored in an integrated database.

[0203] Step 2:

[0204] The server performs natural language processing on the collected unstructured data. This tokenizes the text information and analyzes the emotions the user is expressing. For example, it extracts positive emotions from the text "I had fun today!". The analysis results are stored as structured data.

[0205] Step 3:

[0206] The server inputs the results of natural language processing into an emotion engine, which then analyzes the user's emotional state in detail. Changes in emotions over time are also tracked. The emotional state is dynamically updated, and the analysis results are output.

[0207] Step 4:

[0208] The server uses machine learning algorithms to train a model of user behavior from the collected data. The data is first cleansed and then split into training and test data. Through this process, effective promotional methods are learned based on past consumer behavior and emotional states.

[0209] Step 5:

[0210] The server selects and suggests the most suitable promotions to the user based on trained models and sentiment analysis results. For example, it recommends event or travel-related products to users in a positive emotional state. This process utilizes a generative AI model, inputting a prompt ("Suggest suitable promotions when the user is showing positive emotions.") into the generative AI system to generate the optimal promotions.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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).

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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".

[0227] This invention relates to a system for collecting and analyzing information from various communication media and proposing optimal sales promotion strategies. Embodiments of this system are described below.

[0228] First, the server collects information from various communication media, including email, social networking services, websites, and advertising media. This involves using APIs to retrieve data in a specific format for each medium and establishing a secure connection. The collected data is then stored in an integrated database.

[0229] Next, the server uses natural language processing to analyze unstructured text information such as user reviews and comments. This analysis includes sentiment analysis and key phrase extraction, and then converts the text data into structured data.

[0230] The server then preprocesses the analyzed data. This involves data cleansing to remove noise and missing values, as well as data normalization to prepare the data for machine learning.

[0231] Next, the server trains a machine learning model using the pre-processed data. This allows it to learn effective patterns and parameters for sales promotion. Machine learning improves the model's accuracy by leveraging past success stories and data with high engagement.

[0232] The server then uses these learning results to automatically suggest the optimal sales promotion strategies for each communication medium. These suggestions are provided to the user in real time, allowing the user to formulate the content and strategies of their sales promotion campaigns based on this information.

[0233] For example, when a user promotes a new product B through social media, the server suggests the optimal posting time and content type based on past data and natural language processing results. This suggests that the user can increase engagement and conduct more effective promotions.

[0234] This system helps users optimize their sales activities quickly and efficiently by automatically handling everything from information gathering to strategic proposals.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The server accesses APIs from various communication platforms, such as email, social networking services, websites, and advertising media, to collect promotional data. It securely authenticates using API keys and credentials, and retrieves data in real time.

[0238] Step 2:

[0239] The server stores the collected data in an integrated database. Even if the data is in different formats, it is formatted to conform to a common database schema, and the storage process is completed.

[0240] Step 3:

[0241] The server uses natural language processing tools to analyze the text of unstructured data such as user reviews and comments. This process involves tokenizing the text data, performing sentiment analysis, extracting key phrases, and organizing it into structured data.

[0242] Step 4:

[0243] The server performs data preprocessing and cleansing on the acquired and analyzed data. It handles missing values ​​and removes noise to adjust the data to a normal state. It also transforms the data into a format suitable for machine learning through categorical variable encoding and scaling.

[0244] Step 5:

[0245] The server inputs pre-processed data into a machine learning algorithm to train a model for predicting promotional effectiveness. The data is split into training and test data, and the model's accuracy is evaluated and improved based on past successful promotions.

[0246] Step 6:

[0247] The server leverages a trained model to generate optimal sales promotion strategies based on the latest collected data. These suggestions include specific instructions on selecting effective strategies and adjusting their timing.

[0248] Step 7:

[0249] Users receive optimized suggestions from the server and plan and execute promotional campaigns based on them. Following the suggested strategy, users can create promotional content and implement promotions at specified times.

[0250] (Example 1)

[0251] 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."

[0252] In today's information society, efficiently collecting useful data from diverse information sources and using it to formulate optimal strategies remains a significant challenge. In particular, analyzing unstructured data and utilizing it for sales promotion activities requires considerable effort and expertise. Furthermore, ensuring the reliability of acquired information and processing it securely is also a crucial challenge.

[0253] 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.

[0254] In this invention, the server includes means for automatically acquiring data from different types of information media, means for analyzing unstructured information using natural language processing technology, and means for formatting the information and training a model using machine learning methods. This enables the automation of everything from information gathering and analysis to the formulation of optimal sales promotion strategies, making it possible to utilize information efficiently and reliably.

[0255] An "information medium" refers to the means or platforms used to transmit and receive data and information.

[0256] "Automatic data acquisition" refers to the process by which programs or systems collect information without human intervention.

[0257] "Natural language processing technology" refers to the technologies and methodologies used to enable computers to understand and analyze the language that humans use in everyday life.

[0258] "Unstructured information" refers to information that does not conform to a fixed data model and exists in a free-form state.

[0259] "Data formatting" refers to the cleaning and formatting of raw data to transform it into a format suitable for analysis and machine learning.

[0260] "Machine learning techniques" refer to methods and algorithms that enable computers to learn from data and improve at specific tasks.

[0261] "Training a model" refers to the process of applying machine learning algorithms to given data to enable the model to make predictions and classifications.

[0262] A "sales promotion strategy" refers to the actions and tactics planned to increase the sales of a product or service.

[0263] "Storing information in an integrated data storage device" refers to the process of storing collected data in a centralized database or storage system and managing it consistently.

[0264] "Identifying the emotional characteristics of information" refers to the technique of analyzing the emotional nuances contained within data or text and classifying the type of emotion associated with them.

[0265] "Improving the reliability of information during the preprocessing stage" refers to the process of enhancing data accuracy and consistency through data cleansing and filtering.

[0266] This invention is a system that efficiently collects, analyzes, and proposes data from various information media. It is basically operated with a server-centric configuration.

[0267] The server is connected to the internet and automatically retrieves necessary data from email, social networking services, websites, advertising media, etc., via APIs. To ensure security, a secure connection is established using authentication credentials. The collected data is stored in an integrated database, ensuring consistent data management.

[0268] The server then uses natural language processing techniques to analyze the unstructured text data. This involves using natural language processing libraries and platforms (e.g., NLTK, SpaCy) to identify sentiment within the data and extract key phrases.

[0269] Subsequently, the server processes the information to enable model training using machine learning techniques. Data cleansing and noise reduction are performed during this process. Furthermore, common libraries (e.g., TensorFlow, PyTorch) are used to train the machine learning model, learning patterns and parameters related to sales promotion.

[0270] Based on trained models, the server proposes optimal sales promotion strategies for each information medium. These proposals are provided to the user in real time, allowing the user to develop specific promotional strategies based on them.

[0271] For example, if a user is considering a social media promotion for a new product, the server analyzes historical data and trend information to suggest optimized posting times and content styles. This allows the user to design a campaign that maximizes engagement.

[0272] An example of a prompt to input into the generating AI model is, "Please suggest the optimal content style and posting time for promoting a new product." This allows the system to provide metrics for efficient sales promotion.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] The server retrieves data from various information sources, including email, social networking services, websites, and advertising media. This process utilizes APIs from each source to collect data in a standardized format. Input here consists of API queries and requests, and the server communicates with these sources using authentication credentials while maintaining security. The retrieved data is in an unstructured or semi-structured format and is stored in an integrated database.

[0276] Step 2:

[0277] The server analyzes unstructured data from text data stored in the database using natural language processing techniques. The input for this step is the stored text data, and the output is structured information. Specifically, the server uses software libraries (such as NLTK and SpaCy) to perform sentiment analysis and extract key phrases. For example, it classifies user reviews into positive, negative, and neutral sentiments.

[0278] Step 3:

[0279] The server performs formatting processing on the analyzed data. The input here is structured information. It deletes noise and missing values and converts the data into a form optimal for machine learning. As output, cleansed and standardized data is obtained. As a specific operation, the server uses a data cleansing tool to remove outliers and normalize the data.

[0280] Step 4:

[0281] The server trains a machine learning model using the formatted data. The input for this step is the cleansed data, and the output is the trained model. The server uses a machine learning library (such as TensorFlow or PyTorch) to generate a model that has learned patterns and trends related to sales promotion strategies. For example, it uses data from past successful promotions to predict future trends.

[0282] Step 5:

[0283] The server proposes an optimal sales promotion strategy based on the trained model. The input for this process is the learned model, and the output is a proposal generated and provided to the user. The server creates the proposal in real time and provides specific recommendations to the user. For example, based on a prompt sentence such as "Please propose the optimal content style and posting time for the promotion of new products" to the user, it performs an operation to propose posting content and timing, etc.

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] In a modern information society, it is difficult to extract useful information from a vast amount of data and formulate an effective advertising strategy. In particular, quickly and accurately analyzing unstructured information obtained from different data media and proposing optimal advertising placement and transmission time are important issues to be solved in maximizing advertising effectiveness.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0288] In this invention, the server includes means for automatically collecting information from different types of data media, means for analyzing unstructured information using natural language processing, means for preprocessing data and training a model using machine learning techniques, and means for proposing effective placement and time of an advertising strategy. Thereby, it becomes possible to efficiently and automatically formulate an optimal advertising strategy.

[0289] A "data medium" is various forms of physical or non-physical means used for transmitting information.

[0290] "Information" is meaningful content about facts, concepts, or instructions transmitted via a data medium.

[0291] "Unstructured information" is data such as free-form text, images, and audio that does not conform to the normal database format.

[0292] "Natural language processing" is a technology or method for analyzing human language and mechanically understanding it.

[0293] "Preprocessing" is a series of data conversion operations for converting raw data into a form suitable for analysis and machine learning.

[0294] "Machine learning technology" is a technical field that includes the development of algorithms and statistical models for a computer to improve its performance through experience.

[0295] A "model" is an abstract or mathematical representation constructed using machine learning to approximate complex phenomena in the real world.

[0296] An "advertising strategy" is a plan or method for effectively promoting a specific product or service to a target audience.

[0297] "Placement" refers to the process or state that determines the position or order in which an advertisement is displayed to a user.

[0298] "Time" refers to the specific time or period during which an advertisement is delivered or displayed.

[0299] To implement this invention, a server must first automatically collect information from different types of data media. The collected information is structured using a data analysis library such as Pandas, and then the unstructured information is analyzed using a natural language processing library (e.g., NLTK or Transformers). This enables sentiment analysis and key phrase extraction of the data.

[0300] Next, the server trains the model using machine learning techniques. The machine learning algorithms used are Logistic Regression and other classification models, implemented using libraries such as Sci-kit Learn. Model training involves splitting the data into training and evaluation sets based on data preprocessing. Once training is complete, the model will have the ability to suggest effective placement and timing for advertising strategies.

[0301] The device displays these advertising strategy suggestions to the user in real time. Based on these suggestions, the user can develop more effective advertising campaigns. For example, when promoting seasonal products, the system can suggest advertising placements through specific media at specific dates and times, based on past success stories.

[0302] As an example of a prompt sentence using a generative AI model, a specific query such as "Analyze past sales promotion campaign data and tell me which types of advertisements are most effective on which days of the week and at what times." can be cited. By doing so, the user can quickly and efficiently formulate an optimal sales promotion strategy.

[0303] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0304] Step 1:

[0305] The server automatically collects information from different types of data media using an API. The input is the API endpoint of each data media, and the output is streaming data such as JSON format. When the server receives this data, it converts it into a data frame using the Pandas library and arranges it in a unified format.

[0306] Step 2:

[0307] The server analyzes the collected unstructured information using a natural language processing library. The input is the data frame obtained in the previous step, and the output is the analyzed data including sentiment scores and key phrase extraction results. The server performs sentiment analysis and converts the text data into structured data.

[0308] Step 3:

[0309] The server preprocesses the analyzed data to prepare for training a model using machine learning techniques. The input is the analyzed data, and the output is a data set divided into training data and evaluation data. The server performs data cleaning and normalization to arrange the data in a format that can be learned by the model.

[0310] Step 4:

[0311] The server trains machine learning algorithms using libraries such as Sci-kit Learn to build a model for proposing advertising strategies. The input is pre-processed training data, and the output is the trained machine learning model. The server improves the accuracy of the model through the training process.

[0312] Step 5:

[0313] The device uses a trained model to suggest optimal placement and timing for advertising strategies to the user in real time. The input is the goals and conditions of the advertising campaign specified by the user, and the output is the suggested advertising strategy. The device helps the user make decisions about building their advertising campaigns based on these suggestions.

[0314] Step 6:

[0315] Based on the proposed advertising strategy, the user designs and executes the optimal campaign. The input is the details of the proposal obtained from the device, and the output is the executed advertising campaign. The user uses this information to formulate advertising measures aimed at achieving higher results.

[0316] 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.

[0317] This invention relates to a system that analyzes user emotions based on data acquired from communication media and proposes an optimal sales promotion strategy that takes these emotions into account. The system includes processes for information gathering, natural language processing, emotion engine development, machine learning model training, and strategy proposal.

[0318] First, the server collects data from various communication channels—for example, email, social networks, websites, and advertising media. This collection includes using APIs to retrieve data in real time. The data is accessed via secure authentication credentials and stored in an integrated database.

[0319] Next, the server analyzes the unstructured data within the collected data using natural language processing tools. This analysis involves tokenizing text information and sentiment analysis, extracting user sentiment from user reviews and comments, and processing it into structured data.

[0320] The newly introduced emotion engine runs on the server and analyzes and classifies user emotions in detail based on the results of natural language processing. Furthermore, it can track changes in these emotions over time and dynamically update the emotion analysis results. This allows for the exploration of more specific and user-friendly sales promotion approaches.

[0321] During data preprocessing, the server normalizes the analyzed data and prepares it for model training using machine learning algorithms. Data cleansing removes unnecessary data, and the data is split into training and test sets. Based on this, the model is trained to identify successful promotional patterns, and the model's accuracy is improved.

[0322] Ultimately, leveraging the insights gained from the emotion engine, the server proposes new sales promotion strategies. These suggestions reflect users' emotional tendencies and include optimizing content, format, and timing. For example, based on data from past success stories of the target product, effective messaging and advertising formats are suggested to reach users in a specific emotional state.

[0323] This system provides support to users in quickly optimizing their sales activities by handling everything from information gathering and sentiment recognition to strategic proposals in a consistent manner.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] The server connects to APIs of multiple communication channels, such as email, social networking services, websites, and advertising platforms, to collect information. During this process, it establishes secure connections using API keys and authentication credentials, and retrieves promotion-related data in real time.

[0327] Step 2:

[0328] The server stores the collected data in an integrated database. Although data obtained from various sources is often in different formats, a unified database schema is used to format it, enabling consistent analysis.

[0329] Step 3:

[0330] The server activates a natural language processing engine to analyze the collected unstructured data (e.g., user reviews and comments). The data is tokenized, sentiment analysis is performed, and important key phrases are extracted, transforming it into structured data.

[0331] Step 4:

[0332] The server activates an emotion engine based on the analysis results to recognize and classify the user's emotions in detail. Furthermore, it tracks changes in the user's emotional state and incorporates the results into the analysis to provide up-to-date emotional insights.

[0333] Step 5:

[0334] The server performs data preprocessing, removing noise and missing values, and cleansing the data. The preprocessed data is then split into training and test sets and converted into a format suitable for training machine learning models.

[0335] Step 6:

[0336] The server trains a model using machine learning algorithms. During training, it utilizes past promotional performance data to teach the model successful patterns and effective promotional methods. This improves the model's predictive accuracy.

[0337] Step 7:

[0338] The server proposes optimal sales promotion strategies based on sentiment analysis results obtained from the sentiment engine. These proposals include advertising content tailored to each user's emotional state and the optimal delivery timing.

[0339] Step 8:

[0340] Users review optimized suggestions provided by the server and implement those strategies. The suggestions are updated in real time, allowing users to continuously gain information to improve the performance of their promotional campaigns.

[0341] (Example 2)

[0342] 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".

[0343] Traditional sales promotion systems struggle to accurately analyze user emotions and incorporate them into sales strategies, making it difficult to quickly propose individually optimized promotional strategies. Therefore, there is a challenge in effectively increasing customer purchasing intent.

[0344] 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.

[0345] In this invention, the server includes means for automatically collecting data from different types of information media, means for analyzing unstructured information using natural language processing, and means for analyzing user emotions and dynamically updating the emotion analysis results. This makes it possible to quickly propose optimal sales promotion strategies based on user emotions.

[0346] "Information media" refers to various communication channels and platforms from which data is collected, including, for example, email, social networks, websites, and advertising media.

[0347] "Data" refers to any form of information, such as unstructured or structured text, images, and audio, collected from information media.

[0348] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language, particularly in text analysis and sentiment analysis.

[0349] "User sentiment" refers to information that identifies an emotional state by analyzing the positive, negative, and neutral responses that users exhibit.

[0350] A "sales promotion strategy" refers to a plan or method for promoting the sale of goods or services and increasing customer interest and purchasing intent.

[0351] A "server" refers to a central computing system used for collecting, analyzing, and processing data to generate sales promotion strategies.

[0352] "Dynamic updating" means correcting and modifying information and analysis results in real time in response to situations and data that change over time.

[0353] This invention is a system that analyzes user emotions based on data collected from information media and proposes an optimal sales promotion strategy accordingly. A specific embodiment of this system is described below.

[0354] The server collects data from various information sources, including email, social networks, websites, and advertising media. This data collection utilizes APIs, and software-wise, authentication technologies such as OAuth and API keys are used to securely retrieve the data. This data is stored in an integrated database for later analysis.

[0355] Next, the server analyzes the collected unstructured data using natural language processing tools. Software-wise, it utilizes open-source natural language processing libraries and cloud-based analytics services to tokenize text data and perform sentiment analysis. This process extracts sentiments such as positive, negative, and neutral, and structures the data.

[0356] The emotion engine, which runs on the server, analyzes the user's emotions in detail based on the results of natural language processing. By tracking changes in emotions over time and dynamically updating the analysis results, it is possible to obtain more accurate emotion data.

[0357] As a concrete example, suppose a retail company is considering a campaign to launch a new product. The server collects and analyzes relevant user comments on social media and, based on the results, suggests advertising messages that are suitable for users who are "excited." For example, a message such as "This new product is the best choice that will exceed your expectations!" is shown to be effective.

[0358] An example of a prompt might be: "In a new running shoe campaign for a sporting goods store, explain how to analyze user sentiment and propose a sales promotion strategy to increase purchase intent. Specifically, demonstrate how to analyze changes in sentiment and suggest effective messaging and advertising formats."

[0359] This system allows users to more accurately grasp customer needs and refine their sales promotion strategies.

[0360] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0361] Step 1:

[0362] The server collects data from various information sources. Inputs include data obtained from APIs such as email, social networks, websites, and advertising media. Specifically, the server authenticates using OAuth or API keys through these APIs and retrieves the necessary data in real time. The output is raw, unprocessed data stored in an integrated database.

[0363] Step 2:

[0364] The server analyzes the collected data using natural language processing (NLP) tools. The input is the raw, unprocessed data collected in step 1. Specifically, the server uses an NLP library to tokenize the text, tag parts of speech, and perform sentiment analysis. This extracts sentiment information from user comments and reviews, and the output is structured data categorized as "positive," "negative," or "neutral."

[0365] Step 3:

[0366] The emotion engine, located on the server, analyzes the emotion data obtained by the NLP tool in detail and tracks changes. The input is the structured emotion data output in step 2. Specifically, the server analyzes changes in emotion over time and dynamically updates the results. This output is data that shows the user's emotional tendencies over a specific period.

[0367] Step 4:

[0368] The server preprocesses the data obtained from the emotion engine to prepare it for training the learning model. The input is the emotion tendency data obtained in step 3. Specifically, the server cleans this data and splits it into a training set and a test set. The output is clean data that is ready for model training.

[0369] Step 5:

[0370] The server trains a machine learning model and proposes the optimal sales promotion strategy that takes into account the user's emotional tendencies. The input is the training data prepared in step 4. Specifically, the server runs the model using the training data and discovers successful promotional patterns. The output is a sales promotion strategy proposal that includes content and advertising format tailored to the user's specific emotional state.

[0371] Step 6:

[0372] The user implements actual marketing strategies using suggestions from the server and optimizes sales activities. The input is the sales promotion strategy suggested by the server in step 5. Specifically, the user plans and executes advertising campaigns based on the suggestions and delivers effective messaging to target users. The output is improved performance as a result of the sales promotion activities.

[0373] (Application Example 2)

[0374] 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."

[0375] In modern society, consumer purchasing behavior is diversifying, and personalized promotions are required that go beyond mere product quality and price, taking into account consumers' emotions and circumstances. However, traditional sales strategies mainly rely on general statistical information and historical data, making it difficult to make suggestions that resonate with the emotions of individual consumers. Therefore, there is a need to develop a system that automatically proposes sales promotion strategies that take into account the emotional state of users.

[0376] 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.

[0377] In this invention, the server includes means for automatically collecting information from different types of communication media, means for analyzing unstructured data using natural language processing, means for preprocessing the data and training a model with a machine learning algorithm, and means for proposing personalized promotions based on the user's emotional state. This makes it possible to propose sales promotion strategies that take into account the emotional state of each individual consumer.

[0378] "Communication medium" refers to the means or methods used to transmit information. Examples include email, social networks, and websites.

[0379] Natural language processing (NLP) is a technology that enables computers to understand, analyze, and generate natural language used by humans. Examples include text tokenization and sentiment analysis.

[0380] "Unstructured data" refers to data that does not follow a fixed format or model. This typically includes text, images, and audio files.

[0381] A "machine learning algorithm" refers to a set of techniques that use data for computers to learn and perform pattern detection and prediction.

[0382] "Training a model" is the process of using data to train a machine learning algorithm and build a model that can solve a specific problem.

[0383] "Emotional state" refers to the subjective emotional state a user is experiencing at a particular point in time.

[0384] "Personalized promotions" refer to sales promotion activities such as advertisements, discounts, and coupons that are optimized for specific conditions based on each user's emotions and preferences.

[0385] This invention provides a system that proposes personalized promotions based on the user's emotional state. This system mainly consists of a server, a terminal, and a user interface.

[0386] The server is implemented in programming languages ​​such as Python and processes data using libraries such as numpy and pandas. NLTK and textblob are used for natural language processing. These tools are used to analyze communication data collected from email and social media to identify user sentiment.

[0387] The analyzed data is processed by machine learning algorithms such as scikit-learn to learn from the user's past purchasing behavior and select appropriate promotions. This allows for the effective suggestion of the most relevant promotions to the user.

[0388] For example, if a user posts "I had a great day today!" through their device, the server analyzes that emotion as positive and suggests related events and product promotions.

[0389] An example of a prompt message to use with a generative AI model is, "Suggest a suitable promotion if the user is showing positive emotions."

[0390] In this way, by providing users with sales promotion strategies tailored to their emotional state, this system enables more effective marketing than conventional methods based on statistical information.

[0391] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0392] Step 1:

[0393] The server collects data from communication media such as email and social media via an API. The input data is in an unstructured format and accessed using secure authentication credentials. The collected data is stored in an integrated database.

[0394] Step 2:

[0395] The server performs natural language processing on the collected unstructured data. This tokenizes the text information and analyzes the emotions the user is expressing. For example, it extracts positive emotions from the text "I had fun today!". The analysis results are stored as structured data.

[0396] Step 3:

[0397] The server inputs the results of natural language processing into an emotion engine, which then analyzes the user's emotional state in detail. Changes in emotions over time are also tracked. The emotional state is dynamically updated, and the analysis results are output.

[0398] Step 4:

[0399] The server uses machine learning algorithms to train a model of user behavior from the collected data. The data is first cleansed and then split into training and test data. Through this process, effective promotional methods are learned based on past consumer behavior and emotional states.

[0400] Step 5:

[0401] The server selects and suggests the most suitable promotions to the user based on trained models and sentiment analysis results. For example, it recommends event or travel-related products to users in a positive emotional state. This process utilizes a generative AI model, inputting a prompt ("Suggest suitable promotions when the user is showing positive emotions.") into the generative AI system to generate the optimal promotions.

[0402] 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.

[0403] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0404] 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.

[0405] [Third Embodiment]

[0406] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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".

[0418] This invention relates to a system for collecting and analyzing information from various communication media and proposing optimal sales promotion strategies. Embodiments of this system are described below.

[0419] First, the server collects information from various communication media, including email, social networking services, websites, and advertising media. This involves using APIs to retrieve data in a specific format for each medium and establishing a secure connection. The collected data is then stored in an integrated database.

[0420] Next, the server uses natural language processing to analyze unstructured text information such as user reviews and comments. This analysis includes sentiment analysis and key phrase extraction, and then converts the text data into structured data.

[0421] The server then preprocesses the analyzed data. This involves data cleansing to remove noise and missing values, as well as data normalization to prepare the data for machine learning.

[0422] Next, the server trains a machine learning model using the pre-processed data. This allows it to learn effective patterns and parameters for sales promotion. Machine learning improves the model's accuracy by leveraging past success stories and data with high engagement.

[0423] The server then uses these learning results to automatically suggest the optimal sales promotion strategies for each communication medium. These suggestions are provided to the user in real time, allowing the user to formulate the content and strategies of their sales promotion campaigns based on this information.

[0424] For example, when a user promotes a new product B through social media, the server suggests the optimal posting time and content type based on past data and natural language processing results. This suggests that the user can increase engagement and conduct more effective promotions.

[0425] This system helps users optimize their sales activities quickly and efficiently by automatically handling everything from information gathering to strategic proposals.

[0426] The following describes the processing flow.

[0427] Step 1:

[0428] The server accesses APIs from various communication platforms, such as email, social networking services, websites, and advertising media, to collect promotional data. It securely authenticates using API keys and credentials, and retrieves data in real time.

[0429] Step 2:

[0430] The server stores the collected data in an integrated database. Even if the data is in different formats, it is formatted to conform to a common database schema, and the storage process is completed.

[0431] Step 3:

[0432] The server uses natural language processing tools to analyze the text of unstructured data such as user reviews and comments. This process involves tokenizing the text data, performing sentiment analysis, extracting key phrases, and organizing it into structured data.

[0433] Step 4:

[0434] The server performs data preprocessing and cleansing on the acquired and analyzed data. It handles missing values ​​and removes noise to adjust the data to a normal state. It also transforms the data into a format suitable for machine learning through categorical variable encoding and scaling.

[0435] Step 5:

[0436] The server inputs pre-processed data into a machine learning algorithm to train a model for predicting promotional effectiveness. The data is split into training and test data, and the model's accuracy is evaluated and improved based on past successful promotions.

[0437] Step 6:

[0438] The server leverages a trained model to generate optimal sales promotion strategies based on the latest collected data. These suggestions include specific instructions on selecting effective strategies and adjusting their timing.

[0439] Step 7:

[0440] Users receive optimized suggestions from the server and plan and execute promotional campaigns based on them. Following the suggested strategy, users can create promotional content and implement promotions at specified times.

[0441] (Example 1)

[0442] 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."

[0443] In today's information society, efficiently collecting useful data from diverse information sources and using it to formulate optimal strategies remains a significant challenge. In particular, analyzing unstructured data and utilizing it for sales promotion activities requires considerable effort and expertise. Furthermore, ensuring the reliability of acquired information and processing it securely is also a crucial challenge.

[0444] 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.

[0445] In this invention, the server includes means for automatically acquiring data from different types of information media, means for analyzing unstructured information using natural language processing technology, and means for formatting the information and training a model using machine learning methods. This enables the automation of everything from information gathering and analysis to the formulation of optimal sales promotion strategies, making it possible to utilize information efficiently and reliably.

[0446] An "information medium" refers to the means or platforms used to transmit and receive data and information.

[0447] "Automatic data acquisition" refers to the process by which programs or systems collect information without human intervention.

[0448] "Natural language processing technology" refers to the technologies and methodologies used to enable computers to understand and analyze the language that humans use in everyday life.

[0449] "Unstructured information" refers to information that does not conform to a fixed data model and exists in a free-form state.

[0450] "Data formatting" refers to the cleaning and formatting of raw data to transform it into a format suitable for analysis and machine learning.

[0451] "Machine learning techniques" refer to methods and algorithms that enable computers to learn from data and improve at specific tasks.

[0452] "Training a model" refers to the process of applying machine learning algorithms to given data to enable the model to make predictions and classifications.

[0453] A "sales promotion strategy" refers to the actions and tactics planned to increase the sales of a product or service.

[0454] "Storing information in an integrated data storage device" refers to the process of storing collected data in a centralized database or storage system and managing it consistently.

[0455] "Identifying the emotional characteristics of information" refers to the technique of analyzing the emotional nuances contained within data or text and classifying the type of emotion associated with them.

[0456] "Improving the reliability of information during the preprocessing stage" refers to the process of enhancing data accuracy and consistency through data cleansing and filtering.

[0457] This invention is a system that efficiently collects, analyzes, and proposes data from various information media. It is basically operated with a server-centric configuration.

[0458] The server is connected to the internet and automatically retrieves necessary data from email, social networking services, websites, advertising media, etc., via APIs. To ensure security, a secure connection is established using authentication credentials. The collected data is stored in an integrated database, ensuring consistent data management.

[0459] The server then uses natural language processing techniques to analyze the unstructured text data. This involves using natural language processing libraries and platforms (e.g., NLTK, SpaCy) to identify sentiment within the data and extract key phrases.

[0460] Subsequently, the server processes the information to enable model training using machine learning techniques. Data cleansing and noise reduction are performed during this process. Furthermore, common libraries (e.g., TensorFlow, PyTorch) are used to train the machine learning model, learning patterns and parameters related to sales promotion.

[0461] Based on trained models, the server proposes optimal sales promotion strategies for each information medium. These proposals are provided to the user in real time, allowing the user to develop specific promotional strategies based on them.

[0462] For example, if a user is considering a social media promotion for a new product, the server analyzes historical data and trend information to suggest optimized posting times and content styles. This allows the user to design a campaign that maximizes engagement.

[0463] An example of a prompt to input into the generating AI model is, "Please suggest the optimal content style and posting time for promoting a new product." This allows the system to provide metrics for efficient sales promotion.

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The server retrieves data from various information sources, including email, social networking services, websites, and advertising media. This process utilizes APIs from each source to collect data in a standardized format. Input here consists of API queries and requests, and the server communicates with these sources using authentication credentials while maintaining security. The retrieved data is in an unstructured or semi-structured format and is stored in an integrated database.

[0467] Step 2:

[0468] The server analyzes unstructured data from text data stored in the database using natural language processing techniques. The input for this step is the stored text data, and the output is structured information. Specifically, the server uses software libraries (such as NLTK and SpaCy) to perform sentiment analysis and extract key phrases. For example, it classifies user reviews into positive, negative, and neutral sentiments.

[0469] Step 3:

[0470] The server processes the analyzed data, taking structured information as input. It removes noise and missing values, transforming the data into a format optimized for machine learning. The output is cleansed and standardized data. Specifically, the server uses data cleansing tools to remove outliers and normalize the data.

[0471] Step 4:

[0472] The server trains a machine learning model using the formatted data. The input for this step is cleansed data, and the output is a trained model. The server uses machine learning libraries (such as TensorFlow or PyTorch) to generate a model that learns patterns and trends related to sales promotion strategies. For example, it uses data from past successful promotions to predict future trends.

[0473] Step 5:

[0474] The server proposes the optimal sales promotion strategy based on a trained model. The input to this process is a pre-trained model, and the output generates suggestions that are provided to the user. The server creates suggestions in real time and provides specific recommendations to the user. For example, based on a prompt such as "Please suggest the optimal content style and posting time for promoting a new product," the server will suggest post content, timing, and other relevant information.

[0475] (Application Example 1)

[0476] 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."

[0477] In today's information society, extracting useful information from vast amounts of data and formulating effective advertising strategies is challenging. In particular, rapidly and accurately analyzing unstructured information obtained from various data sources and proposing optimal ad placement and broadcasting times is a crucial challenge that must be addressed to maximize advertising effectiveness.

[0478] 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.

[0479] In this invention, the server includes means for automatically collecting information from different types of data media, means for analyzing unstructured information using natural language processing, means for preprocessing data and training models with machine learning techniques, and means for proposing effective placement and timing of advertising strategies. This makes it possible to efficiently and automatically formulate an optimal advertising strategy.

[0480] "Data media" refers to various forms of material or non-material means used to transmit information.

[0481] "Information" refers to meaningful content about facts, concepts, or instructions that is transmitted through a data medium.

[0482] "Unstructured information" refers to data such as free-form text, images, and audio that does not conform to standard database formats.

[0483] "Natural language processing" refers to the techniques or methods for analyzing and understanding human language mechanically.

[0484] "Preprocessing" refers to a series of data transformation operations to convert raw data into a format suitable for analysis and machine learning.

[0485] "Machine learning technology" is a field of technology that includes the development of algorithms and statistical models that enable computers to improve their performance through experience.

[0486] A "model" is an abstract or mathematical representation constructed using machine learning to approximate complex phenomena in the real world.

[0487] An "advertising strategy" is a plan or method for effectively promoting a specific product or service to a target audience.

[0488] "Placement" refers to the process or state that determines the position or order in which an advertisement is displayed to a user.

[0489] "Time" refers to the specific time or period during which an advertisement is delivered or displayed.

[0490] To implement this invention, a server must first automatically collect information from different types of data media. The collected information is structured using a data analysis library such as Pandas, and then the unstructured information is analyzed using a natural language processing library (e.g., NLTK or Transformers). This enables sentiment analysis and key phrase extraction of the data.

[0491] Next, the server trains the model using machine learning techniques. The machine learning algorithms used are Logistic Regression and other classification models, implemented using libraries such as Sci-kit Learn. Model training involves splitting the data into training and evaluation sets based on data preprocessing. Once training is complete, the model will have the ability to suggest effective placement and timing for advertising strategies.

[0492] The device displays these advertising strategy suggestions to the user in real time. Based on these suggestions, the user can develop more effective advertising campaigns. For example, when promoting seasonal products, the system can suggest advertising placements through specific media at specific dates and times, based on past success stories.

[0493] An example of a prompt using a generative AI model is a specific question such as, "Analyze past sales promotion campaign data to tell me which types of advertisements are most effective on which days and times." This allows users to quickly and efficiently develop the optimal sales promotion strategy.

[0494] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0495] Step 1:

[0496] The server automatically collects information from different types of data media using APIs. Inputs are API endpoints for each data medium, and outputs are streaming data in formats such as JSON. Upon receiving this data, the server converts it into a DataFrame using the Pandas library, organizing it into a unified format.

[0497] Step 2:

[0498] The server uses a natural language processing library to analyze the collected unstructured information. The input is the data frame obtained in the previous step, and the output is the analyzed data, including sentiment scores and key phrase extraction results. The server performs sentiment analysis and converts the text data into structured data.

[0499] Step 3:

[0500] The server preprocesses the analyzed data to prepare it for training a machine learning model. The input is the analyzed data, and the output is a dataset split into training data and evaluation data. The server cleanses and normalizes the data to prepare it for model learning.

[0501] Step 4:

[0502] The server trains machine learning algorithms using libraries such as Sci-kit Learn to build a model for proposing advertising strategies. The input is pre-processed training data, and the output is the trained machine learning model. The server improves the accuracy of the model through the training process.

[0503] Step 5:

[0504] The device uses a trained model to suggest optimal placement and timing for advertising strategies to the user in real time. The input is the goals and conditions of the advertising campaign specified by the user, and the output is the suggested advertising strategy. The device helps the user make decisions about building their advertising campaigns based on these suggestions.

[0505] Step 6:

[0506] Based on the proposed advertising strategy, the user designs and executes the optimal campaign. The input is the details of the proposal obtained from the device, and the output is the executed advertising campaign. The user uses this information to formulate advertising measures aimed at achieving higher results.

[0507] 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.

[0508] This invention relates to a system that analyzes user emotions based on data acquired from communication media and proposes an optimal sales promotion strategy that takes these emotions into account. The system includes processes for information gathering, natural language processing, emotion engine development, machine learning model training, and strategy proposal.

[0509] First, the server collects data from various communication channels—for example, email, social networks, websites, and advertising media. This collection includes using APIs to retrieve data in real time. The data is accessed via secure authentication credentials and stored in an integrated database.

[0510] Next, the server analyzes the unstructured data within the collected data using natural language processing tools. This analysis involves tokenizing text information and sentiment analysis, extracting user sentiment from user reviews and comments, and processing it into structured data.

[0511] The newly introduced emotion engine runs on the server and analyzes and classifies user emotions in detail based on the results of natural language processing. Furthermore, it can track changes in these emotions over time and dynamically update the emotion analysis results. This allows for the exploration of more specific and user-friendly sales promotion approaches.

[0512] During data preprocessing, the server normalizes the analyzed data and prepares it for model training using machine learning algorithms. Data cleansing removes unnecessary data, and the data is split into training and test sets. Based on this, the model is trained to identify successful promotional patterns, and the model's accuracy is improved.

[0513] Ultimately, leveraging the insights gained from the emotion engine, the server proposes new sales promotion strategies. These suggestions reflect users' emotional tendencies and include optimizing content, format, and timing. For example, based on data from past success stories of the target product, effective messaging and advertising formats are suggested to reach users in a specific emotional state.

[0514] This system provides support to users in quickly optimizing their sales activities by handling everything from information gathering and sentiment recognition to strategic proposals in a consistent manner.

[0515] The following describes the processing flow.

[0516] Step 1:

[0517] The server connects to APIs of multiple communication channels, such as email, social networking services, websites, and advertising platforms, to collect information. During this process, it establishes secure connections using API keys and authentication credentials, and retrieves promotion-related data in real time.

[0518] Step 2:

[0519] The server stores the collected data in an integrated database. Although data obtained from various sources is often in different formats, a unified database schema is used to format it, enabling consistent analysis.

[0520] Step 3:

[0521] The server activates a natural language processing engine to analyze the collected unstructured data (e.g., user reviews and comments). The data is tokenized, sentiment analysis is performed, and important key phrases are extracted, transforming it into structured data.

[0522] Step 4:

[0523] The server activates an emotion engine based on the analysis results to recognize and classify the user's emotions in detail. Furthermore, it tracks changes in the user's emotional state and incorporates the results into the analysis to provide up-to-date emotional insights.

[0524] Step 5:

[0525] The server performs data preprocessing, removing noise and missing values, and cleansing the data. The preprocessed data is then split into training and test sets and converted into a format suitable for training machine learning models.

[0526] Step 6:

[0527] The server trains a model using machine learning algorithms. During training, it utilizes past promotional performance data to teach the model successful patterns and effective promotional methods. This improves the model's predictive accuracy.

[0528] Step 7:

[0529] The server proposes optimal sales promotion strategies based on sentiment analysis results obtained from the sentiment engine. These proposals include advertising content tailored to each user's emotional state and the optimal delivery timing.

[0530] Step 8:

[0531] Users review optimized suggestions provided by the server and implement those strategies. The suggestions are updated in real time, allowing users to continuously gain information to improve the performance of their promotional campaigns.

[0532] (Example 2)

[0533] 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."

[0534] Traditional sales promotion systems struggle to accurately analyze user emotions and incorporate them into sales strategies, making it difficult to quickly propose individually optimized promotional strategies. Therefore, there is a challenge in effectively increasing customer purchasing intent.

[0535] 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.

[0536] In this invention, the server includes means for automatically collecting data from different types of information media, means for analyzing unstructured information using natural language processing, and means for analyzing user emotions and dynamically updating the emotion analysis results. This makes it possible to quickly propose optimal sales promotion strategies based on user emotions.

[0537] "Information media" refers to various communication channels and platforms from which data is collected, including, for example, email, social networks, websites, and advertising media.

[0538] "Data" refers to any form of information, such as unstructured or structured text, images, and audio, collected from information media.

[0539] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language, particularly in text analysis and sentiment analysis.

[0540] "User sentiment" refers to information that identifies an emotional state by analyzing the positive, negative, and neutral responses that users exhibit.

[0541] A "sales promotion strategy" refers to a plan or method for promoting the sale of goods or services and increasing customer interest and purchasing intent.

[0542] A "server" refers to a central computing system used for collecting, analyzing, and processing data to generate sales promotion strategies.

[0543] "Dynamic updating" means correcting and modifying information and analysis results in real time in response to situations and data that change over time.

[0544] This invention is a system that analyzes user emotions based on data collected from information media and proposes an optimal sales promotion strategy accordingly. A specific embodiment of this system is described below.

[0545] The server collects data from various information sources, including email, social networks, websites, and advertising media. This data collection utilizes APIs, and software-wise, authentication technologies such as OAuth and API keys are used to securely retrieve the data. This data is stored in an integrated database for later analysis.

[0546] Next, the server analyzes the collected unstructured data using natural language processing tools. Software-wise, it utilizes open-source natural language processing libraries and cloud-based analytics services to tokenize text data and perform sentiment analysis. This process extracts sentiments such as positive, negative, and neutral, and structures the data.

[0547] The emotion engine, which runs on the server, analyzes the user's emotions in detail based on the results of natural language processing. By tracking changes in emotions over time and dynamically updating the analysis results, it is possible to obtain more accurate emotion data.

[0548] As a concrete example, suppose a retail company is considering a campaign to launch a new product. The server collects and analyzes relevant user comments on social media and, based on the results, suggests advertising messages that are suitable for users who are "excited." For example, a message such as "This new product is the best choice that will exceed your expectations!" is shown to be effective.

[0549] An example of a prompt might be: "In a new running shoe campaign for a sporting goods store, explain how to analyze user sentiment and propose a sales promotion strategy to increase purchase intent. Specifically, demonstrate how to analyze changes in sentiment and suggest effective messaging and advertising formats."

[0550] This system allows users to more accurately grasp customer needs and refine their sales promotion strategies.

[0551] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0552] Step 1:

[0553] The server collects data from various information sources. Inputs include data obtained from APIs such as email, social networks, websites, and advertising media. Specifically, the server authenticates using OAuth or API keys through these APIs and retrieves the necessary data in real time. The output is raw, unprocessed data stored in an integrated database.

[0554] Step 2:

[0555] The server analyzes the collected data using natural language processing (NLP) tools. The input is the raw, unprocessed data collected in step 1. Specifically, the server uses an NLP library to tokenize the text, tag parts of speech, and perform sentiment analysis. This extracts sentiment information from user comments and reviews, and the output is structured data categorized as "positive," "negative," or "neutral."

[0556] Step 3:

[0557] The emotion engine, located on the server, analyzes the emotion data obtained by the NLP tool in detail and tracks changes. The input is the structured emotion data output in step 2. Specifically, the server analyzes changes in emotion over time and dynamically updates the results. This output is data that shows the user's emotional tendencies over a specific period.

[0558] Step 4:

[0559] The server preprocesses the data obtained from the emotion engine to prepare it for training the learning model. The input is the emotion tendency data obtained in step 3. Specifically, the server cleans this data and splits it into a training set and a test set. The output is clean data that is ready for model training.

[0560] Step 5:

[0561] The server trains a machine learning model and proposes the optimal sales promotion strategy that takes into account the user's emotional tendencies. The input is the training data prepared in step 4. Specifically, the server runs the model using the training data and discovers successful promotional patterns. The output is a sales promotion strategy proposal that includes content and advertising format tailored to the user's specific emotional state.

[0562] Step 6:

[0563] The user implements actual marketing strategies using suggestions from the server and optimizes sales activities. The input is the sales promotion strategy suggested by the server in step 5. Specifically, the user plans and executes advertising campaigns based on the suggestions and delivers effective messaging to target users. The output is improved performance as a result of the sales promotion activities.

[0564] (Application Example 2)

[0565] 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."

[0566] In modern society, consumer purchasing behavior is diversifying, and personalized promotions are required that go beyond mere product quality and price, taking into account consumers' emotions and circumstances. However, traditional sales strategies mainly rely on general statistical information and historical data, making it difficult to make suggestions that resonate with the emotions of individual consumers. Therefore, there is a need to develop a system that automatically proposes sales promotion strategies that take into account the emotional state of users.

[0567] 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.

[0568] In this invention, the server includes means for automatically collecting information from different types of communication media, means for analyzing unstructured data using natural language processing, means for preprocessing the data and training a model with a machine learning algorithm, and means for proposing personalized promotions based on the user's emotional state. This makes it possible to propose sales promotion strategies that take into account the emotional state of each individual consumer.

[0569] "Communication medium" refers to the means or methods used to transmit information. Examples include email, social networks, and websites.

[0570] Natural language processing (NLP) is a technology that enables computers to understand, analyze, and generate natural language used by humans. Examples include text tokenization and sentiment analysis.

[0571] "Unstructured data" refers to data that does not follow a fixed format or model. This typically includes text, images, and audio files.

[0572] A "machine learning algorithm" refers to a set of techniques that use data for computers to learn and perform pattern detection and prediction.

[0573] "Training a model" is the process of using data to train a machine learning algorithm and build a model that can solve a specific problem.

[0574] "Emotional state" refers to the subjective emotional state a user is experiencing at a particular point in time.

[0575] "Personalized promotions" refer to sales promotion activities such as advertisements, discounts, and coupons that are optimized for specific conditions based on each user's emotions and preferences.

[0576] This invention provides a system that proposes personalized promotions based on the user's emotional state. This system mainly consists of a server, a terminal, and a user interface.

[0577] The server is implemented in programming languages ​​such as Python and processes data using libraries such as numpy and pandas. NLTK and textblob are used for natural language processing. These tools are used to analyze communication data collected from email and social media to identify user sentiment.

[0578] The analyzed data is processed by machine learning algorithms such as scikit-learn to learn from the user's past purchasing behavior and select appropriate promotions. This allows for the effective suggestion of the most relevant promotions to the user.

[0579] For example, if a user posts "I had a great day today!" through their device, the server analyzes that emotion as positive and suggests related events and product promotions.

[0580] An example of a prompt message to use with a generative AI model is, "Suggest a suitable promotion if the user is showing positive emotions."

[0581] In this way, by providing users with sales promotion strategies tailored to their emotional state, this system enables more effective marketing than conventional methods based on statistical information.

[0582] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0583] Step 1:

[0584] The server collects data from communication media such as email and social media via an API. The input data is in an unstructured format and accessed using secure authentication credentials. The collected data is stored in an integrated database.

[0585] Step 2:

[0586] The server performs natural language processing on the collected unstructured data. This tokenizes the text information and analyzes the emotions the user is expressing. For example, it extracts positive emotions from the text "I had fun today!". The analysis results are stored as structured data.

[0587] Step 3:

[0588] The server inputs the results of natural language processing into an emotion engine, which then analyzes the user's emotional state in detail. Changes in emotions over time are also tracked. The emotional state is dynamically updated, and the analysis results are output.

[0589] Step 4:

[0590] The server uses machine learning algorithms to train a model of user behavior from the collected data. The data is first cleansed and then split into training and test data. Through this process, effective promotional methods are learned based on past consumer behavior and emotional states.

[0591] Step 5:

[0592] The server selects and suggests the most suitable promotions to the user based on trained models and sentiment analysis results. For example, it recommends event or travel-related products to users in a positive emotional state. This process utilizes a generative AI model, inputting a prompt ("Suggest suitable promotions when the user is showing positive emotions.") into the generative AI system to generate the optimal promotions.

[0593] 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.

[0594] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0595] 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.

[0596] [Fourth Embodiment]

[0597] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0598] 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.

[0599] 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).

[0600] 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.

[0601] 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.

[0602] 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).

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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.

[0609] 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".

[0610] This invention relates to a system for collecting and analyzing information from various communication media and proposing optimal sales promotion strategies. Embodiments of this system are described below.

[0611] First, the server collects information from various communication media, including email, social networking services, websites, and advertising media. This involves using APIs to retrieve data in a specific format for each medium and establishing a secure connection. The collected data is then stored in an integrated database.

[0612] Next, the server uses natural language processing to analyze unstructured text information such as user reviews and comments. This analysis includes sentiment analysis and key phrase extraction, and then converts the text data into structured data.

[0613] The server then preprocesses the analyzed data. This involves data cleansing to remove noise and missing values, as well as data normalization to prepare the data for machine learning.

[0614] Next, the server trains a machine learning model using the pre-processed data. This allows it to learn effective patterns and parameters for sales promotion. Machine learning improves the model's accuracy by leveraging past success stories and data with high engagement.

[0615] The server then uses these learning results to automatically suggest the optimal sales promotion strategies for each communication medium. These suggestions are provided to the user in real time, allowing the user to formulate the content and strategies of their sales promotion campaigns based on this information.

[0616] For example, when a user promotes a new product B through social media, the server suggests the optimal posting time and content type based on past data and natural language processing results. This suggests that the user can increase engagement and conduct more effective promotions.

[0617] This system helps users optimize their sales activities quickly and efficiently by automatically handling everything from information gathering to strategic proposals.

[0618] The following describes the processing flow.

[0619] Step 1:

[0620] The server accesses APIs from various communication platforms, such as email, social networking services, websites, and advertising media, to collect promotional data. It securely authenticates using API keys and credentials, and retrieves data in real time.

[0621] Step 2:

[0622] The server stores the collected data in an integrated database. Even if the data is in different formats, it is formatted to conform to a common database schema, and the storage process is completed.

[0623] Step 3:

[0624] The server uses natural language processing tools to analyze the text of unstructured data such as user reviews and comments. This process involves tokenizing the text data, performing sentiment analysis, extracting key phrases, and organizing it into structured data.

[0625] Step 4:

[0626] The server performs data preprocessing and cleansing on the acquired and analyzed data. It handles missing values ​​and removes noise to adjust the data to a normal state. It also transforms the data into a format suitable for machine learning through categorical variable encoding and scaling.

[0627] Step 5:

[0628] The server inputs pre-processed data into a machine learning algorithm to train a model for predicting promotional effectiveness. The data is split into training and test data, and the model's accuracy is evaluated and improved based on past successful promotions.

[0629] Step 6:

[0630] The server leverages a trained model to generate optimal sales promotion strategies based on the latest collected data. These suggestions include specific instructions on selecting effective strategies and adjusting their timing.

[0631] Step 7:

[0632] Users receive optimized suggestions from the server and plan and execute promotional campaigns based on them. Following the suggested strategy, users can create promotional content and implement promotions at specified times.

[0633] (Example 1)

[0634] 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".

[0635] In today's information society, efficiently collecting useful data from diverse information sources and using it to formulate optimal strategies remains a significant challenge. In particular, analyzing unstructured data and utilizing it for sales promotion activities requires considerable effort and expertise. Furthermore, ensuring the reliability of acquired information and processing it securely is also a crucial challenge.

[0636] 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.

[0637] In this invention, the server includes means for automatically acquiring data from different types of information media, means for analyzing unstructured information using natural language processing technology, and means for formatting the information and training a model using machine learning methods. This enables the automation of everything from information gathering and analysis to the formulation of optimal sales promotion strategies, making it possible to utilize information efficiently and reliably.

[0638] An "information medium" refers to the means or platforms used to transmit and receive data and information.

[0639] "Automatic data acquisition" refers to the process by which programs or systems collect information without human intervention.

[0640] "Natural language processing technology" refers to the technologies and methodologies used to enable computers to understand and analyze the language that humans use in everyday life.

[0641] "Unstructured information" refers to information that does not conform to a fixed data model and exists in a free-form state.

[0642] "Data formatting" refers to the cleaning and formatting of raw data to transform it into a format suitable for analysis and machine learning.

[0643] "Machine learning techniques" refer to methods and algorithms that enable computers to learn from data and improve at specific tasks.

[0644] "Training a model" refers to the process of applying machine learning algorithms to given data to enable the model to make predictions and classifications.

[0645] A "sales promotion strategy" refers to the actions and tactics planned to increase the sales of a product or service.

[0646] "Storing information in an integrated data storage device" refers to the process of storing collected data in a centralized database or storage system and managing it consistently.

[0647] "Identifying the emotional characteristics of information" refers to the technique of analyzing the emotional nuances contained within data or text and classifying the type of emotion associated with them.

[0648] "Improving the reliability of information during the preprocessing stage" refers to the process of enhancing data accuracy and consistency through data cleansing and filtering.

[0649] This invention is a system that efficiently collects, analyzes, and proposes data from various information media. It is basically operated with a server-centric configuration.

[0650] The server is connected to the internet and automatically retrieves necessary data from email, social networking services, websites, advertising media, etc., via APIs. To ensure security, a secure connection is established using authentication credentials. The collected data is stored in an integrated database, ensuring consistent data management.

[0651] The server then uses natural language processing techniques to analyze the unstructured text data. This involves using natural language processing libraries and platforms (e.g., NLTK, SpaCy) to identify sentiment within the data and extract key phrases.

[0652] Subsequently, the server processes the information to enable model training using machine learning techniques. Data cleansing and noise reduction are performed during this process. Furthermore, common libraries (e.g., TensorFlow, PyTorch) are used to train the machine learning model, learning patterns and parameters related to sales promotion.

[0653] Based on trained models, the server proposes optimal sales promotion strategies for each information medium. These proposals are provided to the user in real time, allowing the user to develop specific promotional strategies based on them.

[0654] For example, if a user is considering a social media promotion for a new product, the server analyzes historical data and trend information to suggest optimized posting times and content styles. This allows the user to design a campaign that maximizes engagement.

[0655] An example of a prompt to input into the generating AI model is, "Please suggest the optimal content style and posting time for promoting a new product." This allows the system to provide metrics for efficient sales promotion.

[0656] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0657] Step 1:

[0658] The server retrieves data from various information sources, including email, social networking services, websites, and advertising media. This process utilizes APIs from each source to collect data in a standardized format. Input here consists of API queries and requests, and the server communicates with these sources using authentication credentials while maintaining security. The retrieved data is in an unstructured or semi-structured format and is stored in an integrated database.

[0659] Step 2:

[0660] The server analyzes unstructured data from text data stored in the database using natural language processing techniques. The input for this step is the stored text data, and the output is structured information. Specifically, the server uses software libraries (such as NLTK and SpaCy) to perform sentiment analysis and extract key phrases. For example, it classifies user reviews into positive, negative, and neutral sentiments.

[0661] Step 3:

[0662] The server processes the analyzed data, taking structured information as input. It removes noise and missing values, transforming the data into a format optimized for machine learning. The output is cleansed and standardized data. Specifically, the server uses data cleansing tools to remove outliers and normalize the data.

[0663] Step 4:

[0664] The server trains a machine learning model using the formatted data. The input for this step is cleansed data, and the output is a trained model. The server uses machine learning libraries (such as TensorFlow or PyTorch) to generate a model that learns patterns and trends related to sales promotion strategies. For example, it uses data from past successful promotions to predict future trends.

[0665] Step 5:

[0666] The server proposes the optimal sales promotion strategy based on a trained model. The input to this process is a pre-trained model, and the output generates suggestions that are provided to the user. The server creates suggestions in real time and provides specific recommendations to the user. For example, based on a prompt such as "Please suggest the optimal content style and posting time for promoting a new product," the server will suggest post content, timing, and other relevant information.

[0667] (Application Example 1)

[0668] 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".

[0669] In today's information society, extracting useful information from vast amounts of data and formulating effective advertising strategies is challenging. In particular, rapidly and accurately analyzing unstructured information obtained from various data sources and proposing optimal ad placement and broadcasting times is a crucial challenge that must be addressed to maximize advertising effectiveness.

[0670] 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.

[0671] In this invention, the server includes means for automatically collecting information from different types of data media, means for analyzing unstructured information using natural language processing, means for preprocessing data and training models with machine learning techniques, and means for proposing effective placement and timing of advertising strategies. This makes it possible to efficiently and automatically formulate an optimal advertising strategy.

[0672] "Data media" refers to various forms of material or non-material means used to transmit information.

[0673] "Information" refers to meaningful content about facts, concepts, or instructions that is transmitted through a data medium.

[0674] "Unstructured information" refers to data such as free-form text, images, and audio that does not conform to standard database formats.

[0675] "Natural language processing" refers to the techniques or methods for analyzing and understanding human language mechanically.

[0676] "Preprocessing" refers to a series of data transformation operations to convert raw data into a format suitable for analysis and machine learning.

[0677] "Machine learning technology" is a field of technology that includes the development of algorithms and statistical models that enable computers to improve their performance through experience.

[0678] A "model" is an abstract or mathematical representation constructed using machine learning to approximate complex phenomena in the real world.

[0679] An "advertising strategy" is a plan or method for effectively promoting a specific product or service to a target audience.

[0680] "Placement" refers to the process or state that determines the position or order in which an advertisement is displayed to a user.

[0681] "Time" refers to the specific time or period during which an advertisement is delivered or displayed.

[0682] To implement this invention, a server must first automatically collect information from different types of data media. The collected information is structured using a data analysis library such as Pandas, and then the unstructured information is analyzed using a natural language processing library (e.g., NLTK or Transformers). This enables sentiment analysis and key phrase extraction of the data.

[0683] Next, the server trains the model using machine learning techniques. The machine learning algorithms used are Logistic Regression and other classification models, implemented using libraries such as Sci-kit Learn. Model training involves splitting the data into training and evaluation sets based on data preprocessing. Once training is complete, the model will have the ability to suggest effective placement and timing for advertising strategies.

[0684] The device displays these advertising strategy suggestions to the user in real time. Based on these suggestions, the user can develop more effective advertising campaigns. For example, when promoting seasonal products, the system can suggest advertising placements through specific media at specific dates and times, based on past success stories.

[0685] An example of a prompt using a generative AI model is a specific question such as, "Analyze past sales promotion campaign data to tell me which types of advertisements are most effective on which days and times." This allows users to quickly and efficiently develop the optimal sales promotion strategy.

[0686] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0687] Step 1:

[0688] The server automatically collects information from different types of data media using APIs. Inputs are API endpoints for each data medium, and outputs are streaming data in formats such as JSON. Upon receiving this data, the server converts it into a DataFrame using the Pandas library, organizing it into a unified format.

[0689] Step 2:

[0690] The server uses a natural language processing library to analyze the collected unstructured information. The input is the data frame obtained in the previous step, and the output is the analyzed data, including sentiment scores and key phrase extraction results. The server performs sentiment analysis and converts the text data into structured data.

[0691] Step 3:

[0692] The server preprocesses the analyzed data to prepare it for training a machine learning model. The input is the analyzed data, and the output is a dataset split into training data and evaluation data. The server cleanses and normalizes the data to prepare it for model learning.

[0693] Step 4:

[0694] The server trains machine learning algorithms using libraries such as Sci-kit Learn to build a model for proposing advertising strategies. The input is pre-processed training data, and the output is the trained machine learning model. The server improves the accuracy of the model through the training process.

[0695] Step 5:

[0696] The device uses a trained model to suggest optimal placement and timing for advertising strategies to the user in real time. The input is the goals and conditions of the advertising campaign specified by the user, and the output is the suggested advertising strategy. The device helps the user make decisions about building their advertising campaigns based on these suggestions.

[0697] Step 6:

[0698] Based on the proposed advertising strategy, the user designs and executes the optimal campaign. The input is the details of the proposal obtained from the device, and the output is the executed advertising campaign. The user uses this information to formulate advertising measures aimed at achieving higher results.

[0699] 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.

[0700] This invention relates to a system that analyzes user emotions based on data acquired from communication media and proposes an optimal sales promotion strategy that takes these emotions into account. The system includes processes for information gathering, natural language processing, emotion engine development, machine learning model training, and strategy proposal.

[0701] First, the server collects data from various communication channels—for example, email, social networks, websites, and advertising media. This collection includes using APIs to retrieve data in real time. The data is accessed via secure authentication credentials and stored in an integrated database.

[0702] Next, the server analyzes the unstructured data within the collected data using natural language processing tools. This analysis involves tokenizing text information and sentiment analysis, extracting user sentiment from user reviews and comments, and processing it into structured data.

[0703] The newly introduced emotion engine runs on the server and analyzes and classifies user emotions in detail based on the results of natural language processing. Furthermore, it can track changes in these emotions over time and dynamically update the emotion analysis results. This allows for the exploration of more specific and user-friendly sales promotion approaches.

[0704] During data preprocessing, the server normalizes the analyzed data and prepares it for model training using machine learning algorithms. Data cleansing removes unnecessary data, and the data is split into training and test sets. Based on this, the model is trained to identify successful promotional patterns, and the model's accuracy is improved.

[0705] Ultimately, leveraging the insights gained from the emotion engine, the server proposes new sales promotion strategies. These suggestions reflect users' emotional tendencies and include optimizing content, format, and timing. For example, based on data from past success stories of the target product, effective messaging and advertising formats are suggested to reach users in a specific emotional state.

[0706] This system provides support to users in quickly optimizing their sales activities by handling everything from information gathering and sentiment recognition to strategic proposals in a consistent manner.

[0707] The following describes the processing flow.

[0708] Step 1:

[0709] The server connects to APIs of multiple communication channels, such as email, social networking services, websites, and advertising platforms, to collect information. During this process, it establishes secure connections using API keys and authentication credentials, and retrieves promotion-related data in real time.

[0710] Step 2:

[0711] The server stores the collected data in an integrated database. Although data obtained from various sources is often in different formats, a unified database schema is used to format it, enabling consistent analysis.

[0712] Step 3:

[0713] The server activates a natural language processing engine to analyze the collected unstructured data (e.g., user reviews and comments). The data is tokenized, sentiment analysis is performed, and important key phrases are extracted, transforming it into structured data.

[0714] Step 4:

[0715] The server activates an emotion engine based on the analysis results to recognize and classify the user's emotions in detail. Furthermore, it tracks changes in the user's emotional state and incorporates the results into the analysis to provide up-to-date emotional insights.

[0716] Step 5:

[0717] The server performs data preprocessing, removing noise and missing values, and cleansing the data. The preprocessed data is then split into training and test sets and converted into a format suitable for training machine learning models.

[0718] Step 6:

[0719] The server trains a model using machine learning algorithms. During training, it utilizes past promotional performance data to teach the model successful patterns and effective promotional methods. This improves the model's predictive accuracy.

[0720] Step 7:

[0721] The server proposes optimal sales promotion strategies based on sentiment analysis results obtained from the sentiment engine. These proposals include advertising content tailored to each user's emotional state and the optimal delivery timing.

[0722] Step 8:

[0723] Users review optimized suggestions provided by the server and implement those strategies. The suggestions are updated in real time, allowing users to continuously gain information to improve the performance of their promotional campaigns.

[0724] (Example 2)

[0725] 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".

[0726] Traditional sales promotion systems struggle to accurately analyze user emotions and incorporate them into sales strategies, making it difficult to quickly propose individually optimized promotional strategies. Therefore, there is a challenge in effectively increasing customer purchasing intent.

[0727] 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.

[0728] In this invention, the server includes means for automatically collecting data from different types of information media, means for analyzing unstructured information using natural language processing, and means for analyzing user emotions and dynamically updating the emotion analysis results. This makes it possible to quickly propose optimal sales promotion strategies based on user emotions.

[0729] "Information media" refers to various communication channels and platforms from which data is collected, including, for example, email, social networks, websites, and advertising media.

[0730] "Data" refers to any form of information, such as unstructured or structured text, images, and audio, collected from information media.

[0731] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language, particularly in text analysis and sentiment analysis.

[0732] "User sentiment" refers to information that identifies an emotional state by analyzing the positive, negative, and neutral responses that users exhibit.

[0733] A "sales promotion strategy" refers to a plan or method for promoting the sale of goods or services and increasing customer interest and purchasing intent.

[0734] A "server" refers to a central computing system used for collecting, analyzing, and processing data to generate sales promotion strategies.

[0735] "Dynamic updating" means correcting and modifying information and analysis results in real time in response to situations and data that change over time.

[0736] This invention is a system that analyzes user emotions based on data collected from information media and proposes an optimal sales promotion strategy accordingly. A specific embodiment of this system is described below.

[0737] The server collects data from various information sources, including email, social networks, websites, and advertising media. This data collection utilizes APIs, and software-wise, authentication technologies such as OAuth and API keys are used to securely retrieve the data. This data is stored in an integrated database for later analysis.

[0738] Next, the server analyzes the collected unstructured data using natural language processing tools. Software-wise, it utilizes open-source natural language processing libraries and cloud-based analytics services to tokenize text data and perform sentiment analysis. This process extracts sentiments such as positive, negative, and neutral, and structures the data.

[0739] The emotion engine, which runs on the server, analyzes the user's emotions in detail based on the results of natural language processing. By tracking changes in emotions over time and dynamically updating the analysis results, it is possible to obtain more accurate emotion data.

[0740] As a concrete example, suppose a retail company is considering a campaign to launch a new product. The server collects and analyzes relevant user comments on social media and, based on the results, suggests advertising messages that are suitable for users who are "excited." For example, a message such as "This new product is the best choice that will exceed your expectations!" is shown to be effective.

[0741] An example of a prompt might be: "In a new running shoe campaign for a sporting goods store, explain how to analyze user sentiment and propose a sales promotion strategy to increase purchase intent. Specifically, demonstrate how to analyze changes in sentiment and suggest effective messaging and advertising formats."

[0742] This system allows users to more accurately grasp customer needs and refine their sales promotion strategies.

[0743] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0744] Step 1:

[0745] The server collects data from various information sources. Inputs include data obtained from APIs such as email, social networks, websites, and advertising media. Specifically, the server authenticates using OAuth or API keys through these APIs and retrieves the necessary data in real time. The output is raw, unprocessed data stored in an integrated database.

[0746] Step 2:

[0747] The server analyzes the collected data using natural language processing (NLP) tools. The input is the raw, unprocessed data collected in step 1. Specifically, the server uses an NLP library to tokenize the text, tag parts of speech, and perform sentiment analysis. This extracts sentiment information from user comments and reviews, and the output is structured data categorized as "positive," "negative," or "neutral."

[0748] Step 3:

[0749] The emotion engine, located on the server, analyzes the emotion data obtained by the NLP tool in detail and tracks changes. The input is the structured emotion data output in step 2. Specifically, the server analyzes changes in emotion over time and dynamically updates the results. This output is data that shows the user's emotional tendencies over a specific period.

[0750] Step 4:

[0751] The server preprocesses the data obtained from the emotion engine to prepare it for training the learning model. The input is the emotion tendency data obtained in step 3. Specifically, the server cleans this data and splits it into a training set and a test set. The output is clean data that is ready for model training.

[0752] Step 5:

[0753] The server trains a machine learning model and proposes the optimal sales promotion strategy that takes into account the user's emotional tendencies. The input is the training data prepared in step 4. Specifically, the server runs the model using the training data and discovers successful promotional patterns. The output is a sales promotion strategy proposal that includes content and advertising format tailored to the user's specific emotional state.

[0754] Step 6:

[0755] The user implements actual marketing strategies using suggestions from the server and optimizes sales activities. The input is the sales promotion strategy suggested by the server in step 5. Specifically, the user plans and executes advertising campaigns based on the suggestions and delivers effective messaging to target users. The output is improved performance as a result of the sales promotion activities.

[0756] (Application Example 2)

[0757] 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".

[0758] In modern society, consumer purchasing behavior is diversifying, and personalized promotions are required that go beyond mere product quality and price, taking into account consumers' emotions and circumstances. However, traditional sales strategies mainly rely on general statistical information and historical data, making it difficult to make suggestions that resonate with the emotions of individual consumers. Therefore, there is a need to develop a system that automatically proposes sales promotion strategies that take into account the emotional state of users.

[0759] 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.

[0760] In this invention, the server includes means for automatically collecting information from different types of communication media, means for analyzing unstructured data using natural language processing, means for preprocessing the data and training a model with a machine learning algorithm, and means for proposing personalized promotions based on the user's emotional state. This makes it possible to propose sales promotion strategies that take into account the emotional state of each individual consumer.

[0761] "Communication medium" refers to the means or methods used to transmit information. Examples include email, social networks, and websites.

[0762] Natural language processing (NLP) is a technology that enables computers to understand, analyze, and generate natural language used by humans. Examples include text tokenization and sentiment analysis.

[0763] "Unstructured data" refers to data that does not follow a fixed format or model. This typically includes text, images, and audio files.

[0764] A "machine learning algorithm" refers to a set of techniques that use data for computers to learn and perform pattern detection and prediction.

[0765] "Training a model" is the process of using data to train a machine learning algorithm and build a model that can solve a specific problem.

[0766] "Emotional state" refers to the subjective emotional state a user is experiencing at a particular point in time.

[0767] "Personalized promotions" refer to sales promotion activities such as advertisements, discounts, and coupons that are optimized for specific conditions based on each user's emotions and preferences.

[0768] This invention provides a system that proposes personalized promotions based on the user's emotional state. This system mainly consists of a server, a terminal, and a user interface.

[0769] The server is implemented in programming languages ​​such as Python and processes data using libraries such as numpy and pandas. NLTK and textblob are used for natural language processing. These tools are used to analyze communication data collected from email and social media to identify user sentiment.

[0770] The analyzed data is processed by machine learning algorithms such as scikit-learn to learn from the user's past purchasing behavior and select appropriate promotions. This allows for the effective suggestion of the most relevant promotions to the user.

[0771] For example, if a user posts "I had a great day today!" through their device, the server analyzes that emotion as positive and suggests related events and product promotions.

[0772] An example of a prompt message to use with a generative AI model is, "Suggest a suitable promotion if the user is showing positive emotions."

[0773] In this way, by providing users with sales promotion strategies tailored to their emotional state, this system enables more effective marketing than conventional methods based on statistical information.

[0774] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0775] Step 1:

[0776] The server collects data from communication media such as email and social media via an API. The input data is in an unstructured format and accessed using secure authentication credentials. The collected data is stored in an integrated database.

[0777] Step 2:

[0778] The server performs natural language processing on the collected unstructured data. This tokenizes the text information and analyzes the emotions the user is expressing. For example, it extracts positive emotions from the text "I had fun today!". The analysis results are stored as structured data.

[0779] Step 3:

[0780] The server inputs the results of natural language processing into an emotion engine, which then analyzes the user's emotional state in detail. Changes in emotions over time are also tracked. The emotional state is dynamically updated, and the analysis results are output.

[0781] Step 4:

[0782] The server uses machine learning algorithms to train a model of user behavior from the collected data. The data is first cleansed and then split into training and test data. Through this process, effective promotional methods are learned based on past consumer behavior and emotional states.

[0783] Step 5:

[0784] The server selects and suggests the most suitable promotions to the user based on trained models and sentiment analysis results. For example, it recommends event or travel-related products to users in a positive emotional state. This process utilizes a generative AI model, inputting a prompt ("Suggest suitable promotions when the user is showing positive emotions.") into the generative AI system to generate the optimal promotions.

[0785] 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.

[0786] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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."

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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 as being incorporated by reference.

[0806] The following is further disclosed regarding the embodiments described above.

[0807] (Claim 1)

[0808] A means of automatically collecting information from different types of communication media,

[0809] A method for analyzing unstructured data using natural language processing,

[0810] Methods for preprocessing data and training models with machine learning algorithms,

[0811] A means to automatically suggest the optimal sales promotion strategy,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, further comprising means for using authentication information to securely collect the aforementioned information.

[0815] (Claim 3)

[0816] The system according to claim 1, further comprising means for splitting data into training data and test data when the machine learning algorithm is being trained.

[0817] "Example 1"

[0818] (Claim 1)

[0819] A means of automatically acquiring data from different types of information media,

[0820] A method for analyzing unstructured information using natural language processing technology,

[0821] Methods for formatting and processing information and training a model using machine learning techniques,

[0822] A means of automatically suggesting suitable sales promotion strategies,

[0823] A means for storing the collected information in an integrated data storage device,

[0824] A means of identifying the emotional characteristics of information based on the analysis results,

[0825] Means for improving the reliability of information in the preprocessing stage,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, further comprising means for using authentication data to securely obtain the aforementioned data.

[0829] (Claim 3)

[0830] The system according to claim 1, further comprising means for dividing information into training data and evaluation data when the machine learning method is trained.

[0831] "Application Example 1"

[0832] (Claim 1)

[0833] A means of automatically collecting information from different types of data media,

[0834] A method for analyzing unstructured information using natural language processing,

[0835] Methods for preprocessing data and training models with machine learning techniques,

[0836] A means of proposing effective placement and timing for advertising strategies,

[0837] A device that includes this.

[0838] (Claim 2)

[0839] The apparatus according to claim 1, further comprising means for using authentication data to securely collect the aforementioned information.

[0840] (Claim 3)

[0841] The apparatus according to claim 1, further comprising means for dividing information into training data and evaluation data when the machine learning technique is being trained.

[0842] "Example 2 of combining an emotion engine"

[0843] (Claim 1)

[0844] A means of automatically collecting data from different types of information media,

[0845] A means of analyzing unstructured information using natural language processing,

[0846] Methods for preprocessing data and training a learning model,

[0847] A means of analyzing user emotions and dynamically updating the emotion analysis results,

[0848] A means to automatically propose the optimal sales promotion strategy,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, further comprising means for using authentication information to securely collect the aforementioned data.

[0852] (Claim 3)

[0853] The system according to claim 1, further comprising means for splitting data into training data and test data when the learning model is being trained.

[0854] "Application example 2 when combining with an emotional engine"

[0855] (Claim 1)

[0856] A means of automatically collecting information from different types of communication media,

[0857] A method for analyzing unstructured data using natural language processing,

[0858] Methods for preprocessing data and training models with machine learning algorithms,

[0859] A means of proposing personalized promotions based on the user's emotional state,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, further comprising means for using authentication information to securely collect the aforementioned information.

[0863] (Claim 3)

[0864] The system according to claim 1, further comprising means for splitting data into training data and test data when the machine learning algorithm is being trained. [Explanation of Symbols]

[0865] 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 means of automatically collecting information from different types of data media, A method for analyzing unstructured information using natural language processing, Methods for preprocessing data and training models with machine learning techniques, A means of proposing effective placement and timing for advertising strategies, A device that includes this.

2. The apparatus according to claim 1, further comprising means for using authentication data to securely collect the aforementioned information.

3. The apparatus according to claim 1, further comprising means for dividing information into training data and evaluation data when the machine learning technique is being trained.

Images