system

Abstract

We provide the system. [Solution] A means for collecting user-generated message data from a communication terminal, A means for storing and analyzing the collected message data, A method for analyzing stored message data using natural language processing techniques and extracting trends, A means of providing extracted trends to partner companies, A means of formulating a product development strategy in collaboration with partner companies, One method is to set a certain percentage of the sales generated from the developed product as a joint development fee, A system that includes means for collecting user feedback and improving products based on that feedback.

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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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 modern market, consumers' preferences and trends are changing rapidly. In order for companies to respond appropriately and maintain competitiveness, quick and accurate data analysis is necessary. However, many companies do not have effective means to appropriately capture consumers' real-time opinions and trends, and it is particularly difficult to obtain important feedback, especially in new product development. Furthermore, while the efficiency and accuracy in data collection and analysis are questioned, there is a demand for a system that breaks away from data sales and links to a specific product development process.

Means for Solving the Problems

[0005] This invention relates to a system for analyzing user message data collected from communication terminals and extracting trends. The system includes means for collecting user-generated message data from communication terminals and means for storing and analyzing the collected message data. Furthermore, it includes means for analyzing the stored message data using natural language processing technology and extracting trends. It also includes means for providing the extracted trends to partner companies and means for formulating a joint product development strategy with partner companies, thereby setting a certain percentage of the sales obtained from the developed products as joint development costs. Finally, it includes means for collecting user feedback and improving products based on that feedback. This enables timely and accurate understanding of consumers' real-time opinions and trends, facilitating rapid product development and market launch.

[0006] "Message data" refers to data such as text messages, images, and audio sent by a user from a communication terminal.

[0007] A "communication terminal" refers to electronic devices used by users, such as smartphones, tablets, and personal computers.

[0008] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0009] A "trend" refers to the general preference or interest of consumers over a specific period of time.

[0010] A "partner company" is a company that collaborates with the system administrator to develop products based on data analysis results.

[0011] A "product development strategy" is a plan and method for introducing a new product to the market.

[0012] "Joint development costs" are expenses set aside to share the costs involved in product development.

[0013] "Feedback" refers to the opinions, impressions, and suggestions for improvement that users provide regarding a product they have used. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine.

Embodiments for Carrying Out the Invention

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

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

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

[0018] In the following embodiments, 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.

[0019] 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, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

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

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

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

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0035] This invention is a system that collects user message data from communication terminals, extracts trends based on that data, and uses them to aid in product development. This system consists of the user's communication terminal, a server that collects and analyzes the data, and a partner company that develops the product.

[0036] The system operates as follows:

[0037] Collection of message data

[0038] User

[0039] Users use their communication devices (smartphones and tablets) to conduct daily communication using LINE and other messaging apps. Users give prior consent to participate in the system and grant permission for data collection.

[0040] terminal

[0041] The device collects user-generated message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases.

[0042] server

[0043] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[0044] Trend Analysis

[0045] Next, we will perform a trend analysis.

[0046] server

[0047] The server applies natural language processing (NLP) techniques to the stored message data. This analyzes the meaning of the text data and extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, this will be recognized as a trend.

[0048] Data filtering and aggregation

[0049] The extracted data is further refined and analyzed.

[0050] server

[0051] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Next, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0052] Formulating a product development strategy

[0053] Based on the analysis results, we will develop specific products.

[0054] server

[0055] The server provides trend information to partner companies, including detailed analysis reports and proposals.

[0056] Partner companies

[0057] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[0058] Revenue sharing settings

[0059] We will establish a sales revenue sharing agreement for the jointly developed product.

[0060] server

[0061] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[0062] Prototype testing and feedback gathering

[0063] Partner companies

[0064] The partner company will create a prototype of the developed product and prepare it for market launch.

[0065] User

[0066] Users use the prototype and provide feedback via a communication device. For example, they might offer specific suggestions such as, "The fabric could be a little softer."

[0067] server

[0068] The server collects and analyzes feedback. The results are then provided back to partner companies to help improve the product.

[0069] This invention makes it possible to capture consumer preferences in real time and proceed with product development quickly and accurately, thereby enhancing market competitiveness.

[0070] The following describes the processing flow.

[0071] Step 1:

[0072] User

[0073] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[0074] Step 2:

[0075] terminal

[0076] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[0077] Step 3:

[0078] server

[0079] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[0080] Step 4:

[0081] server

[0082] The server analyzes the stored message data using natural language processing (NLP) techniques. Specifically, it utilizes techniques such as morphological analysis, entity recognition, and sentiment analysis to understand the meaning and sentiment of each data point.

[0083] Step 5:

[0084] server

[0085] The server extracts frequently occurring apparel-related words and keywords related to sweets and cooking from the analysis results. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, it will be recognized as a trend.

[0086] Step 6:

[0087] server

[0088] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0089] Step 7:

[0090] server

[0091] The server provides trend information to partner companies, including detailed analysis reports and proposals.

[0092] Step 8:

[0093] Partner companies

[0094] Partner companies hold internal product development meetings based on the trend information they receive. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, product design and manufacturing processes proceed.

[0095] Step 9:

[0096] server

[0097] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[0098] Step 10:

[0099] Partner companies

[0100] The partner company will create a prototype of the developed product and prepare it for market launch.

[0101] Step 11:

[0102] User

[0103] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[0104] Step 12:

[0105] terminal

[0106] The device collects feedback messages from users and sends them back to the server.

[0107] Step 13:

[0108] server

[0109] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes.

[0110] In this way, through a series of steps, LINE message data is utilized to grasp real-time consumer opinions and trends, enabling rapid and effective product development based on that information.

[0111] (Example 1)

[0112] 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."

[0113] In today's world, quickly and accurately understanding consumer preferences and trends is crucial for maintaining a competitive advantage. However, traditional systems have struggled to collect and analyze consumer interests and trends in real time and incorporate them into product development. Furthermore, there has been a lack of mechanisms to effectively collect feedback from consumers and utilize it for product improvement. As a result, companies have found it difficult to respond quickly to market trends, which could lead to a decline in competitiveness.

[0114] 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.

[0115] In this invention, the server includes means for collecting text message data generated by users from a communication device, means for storing and anonymizing the collected message data, means for analyzing the stored message data using natural language processing technology and extracting trends, means for filtering the recognized trends and retaining only highly reliable data, means for providing the extracted trends to partner companies, means for formulating product development strategies in collaboration with partner companies, means for setting a percentage of sales obtained from the developed product as joint development costs, and means for collecting user feedback and improving the product based on that feedback. This makes it possible to grasp user preferences and trends in real time and reflect them in product development quickly and accurately.

[0116] A "communication device" is a device used by users to generate and send text messages. This includes smartphones, tablets, and personal computers.

[0117] "User" refers to a person or individual who uses a communication device to generate text messages.

[0118] "Text message data" refers to character-based information generated and transmitted by users using communication devices. This includes the content sent in text messaging applications.

[0119] "Collection" refers to the process of obtaining text message data from a communication device and sending that data to a server.

[0120] "Saving" refers to the process of accumulating collected text message data in a database.

[0121] "Anonymization" is the process of removing personal information from collected text message data and transforming the data into a form that cannot be linked to an individual.

[0122] "Natural language processing technology" refers to the techniques that enable computers to understand and analyze human language. This includes algorithms for analyzing the meaning of text and performing syntactic and grammatical analysis.

[0123] "Trends" refer to frequently occurring keywords and phrases related to specific products or themes that emerge from the analysis of collected text message data.

[0124] "Filtering" is the process of removing noise from recognized trend data and selecting only meaningful data.

[0125] A "partner company" refers to a company or organization that collaborates with this system to develop products.

[0126] A "product development strategy" refers to the product development plan and policies formulated jointly with partner companies. This strategy is formulated based on analyzed trend information.

[0127] "Joint development costs" refer to expenses set as a certain percentage of the sales generated from the developed product. This is part of the compensation for the product developed through the collaboration between the system and partner companies.

[0128] "Feedback" refers to the opinions and impressions that users provide after using a developed product. This includes specific comments on areas for improvement and the user experience.

[0129] This invention is a system that collects text message data generated from users' communication devices, analyzes it to extract trends, and uses them for product development. This system consists of the user's communication device, a server that collects and analyzes the data, and partner companies that develop products.

[0130] Data collection

[0131] User actions

[0132] Users use their own communication devices (smartphones and tablets) to exchange text messages on a daily basis. Users themselves must consent to the handling of the collected data.

[0133] Terminal operation

[0134] The device collects user-generated text message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases, and the data is sent to the server in real time. For example, collection may be based on keyword lists such as "pistachio color" or "oversize."

[0135] Data storage and anonymization

[0136] Server Operations

[0137] The server receives message data sent from each terminal and stores it in a secure database. During this process, the collected data is anonymized to protect personal information. Data anonymity is ensured by replacing user IDs with random identifiers.

[0138] Trend Analysis

[0139] Server Operations

[0140] The semantic analysis of text is performed by applying natural language processing (NLP) techniques to the stored data. Techniques such as BERT (Bidirectional Encoder Representations from Transformers) are used in this process. Frequently occurring words are extracted and recognized as trends.

[0141] Data filtering and aggregation

[0142] Server Operations

[0143] From the analyzed trend data, noise is filtered out, and only meaningful data is retained. Statistical information is generated based on reliable trend data, and the frequency and importance of occurrences are evaluated.

[0144] Formulating a product development strategy

[0145] Server and partner company operations

[0146] The server provides trend information to partner companies, and together they formulate product development strategies. For example, a development project for a "pistachio-colored oversized sweater" might be launched.

[0147] Revenue sharing settings

[0148] Server Operations

[0149] The percentage of joint development costs will be determined based on the product's sales. For example, 10% of sales will be allocated as development costs and reflected in the contract.

[0150] Prototype testing and feedback gathering

[0151] Operation by partner companies

[0152] The partner company will create a prototype of the developed product and prepare it for market launch.

[0153] User actions

[0154] Users provide feedback via their devices using the prototypes. Specific feedback, such as "The fabric could be a little softer," is provided.

[0155] Server Operations

[0156] The server collects and analyzes user feedback. The results of the feedback are then provided back to partner companies to help improve the product.

[0157] Examples of specific cases and prompts for generative AI models.

[0158] Specific example

[0159] A message sent by a user to a friend on LINE, saying "Apparently pistachio-colored clothes are popular lately," is collected. This message is analyzed by a server, and the trending keyword "pistachio color" is extracted. Partner companies then proceed with product development based on this information.

[0160] Example of a prompt

[0161] "Please analyze recent trends regarding popular colors from messages sent by users on LINE."

[0162] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0163] Step 1: Prepare for data collection

[0164] User actions

[0165] Users use their communication devices to exchange text messages on a daily basis. Prior to this, they are prompted to grant permission for data collection, and they give their consent.

[0166] input

[0167] User permission and consent.

[0168] output

[0169] Data collection is ready.

[0170] Step 2: Collect message connections

[0171] Terminal operation

[0172] The device begins collecting user-generated text message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases (e.g., "pistachio color," "oversize"). The collected data is sent to the server in real time.

[0173] input

[0174] Text message data generated by the device.

[0175] Data processing

[0176] Filtering based on a keyword list.

[0177] output

[0178] Filtered message data is sent to the server.

[0179] Step 3: Data storage and anonymization

[0180] Server Operations

[0181] The server receives message data sent from each terminal and stores it in a secure database. Before storage, the data is anonymized and user IDs are replaced with random identifiers.

[0182] input

[0183] Message data sent from the device.

[0184] Data processing

[0185] Anonymization process (replacement of user IDs with random identifiers).

[0186] output

[0187] Anonymized message data is stored in a database.

[0188] Step 4: Trend Analysis

[0189] Server Operations

[0190] The server applies natural language processing (NLP) techniques to the stored message data to analyze the meaning of the text. Specifically, it uses methods such as BERT (Bidirectional Encoder Representations from Transformers). It extracts frequently occurring keywords and recognizes them as trends.

[0191] input

[0192] Anonymized message data.

[0193] Data processing

[0194] Text semantic analysis and keyword extraction using natural language processing technology.

[0195] output

[0196] Recognized trending keywords.

[0197] Step 5: Filtering and Aggregating Data

[0198] Server Operations

[0199] The server filters out noise data (irrelevant information) from the analyzed trend data, retaining only meaningful data. Next, it evaluates the frequency and importance of each keyword based on the aggregated results.

[0200] input

[0201] Recognized trending keywords.

[0202] Data processing

[0203] Filtering of noise data and aggregation of occurrence frequencies.

[0204] output

[0205] A list of trending keywords that have been evaluated.

[0206] Step 6: Formulate a product development strategy

[0207] Server and partner company operations

[0208] The server generates trend information as an analysis report and provides it to partner companies. Based on this information, partner companies hold product development meetings and formulate product development strategies. For example, a development project for a "pistachio-colored oversized sweater" might be launched.

[0209] input

[0210] A list of trending keywords that have been evaluated.

[0211] Data processing

[0212] Generation of analysis reports and proposals.

[0213] output

[0214] Formulating product development strategies and launching projects.

[0215] Step 7: Setting up revenue sharing

[0216] Server Operations

[0217] The server sets the percentage of joint development costs based on the sales of the developed product. For example, it might enter into an agreement with a partner company to distribute 10% of sales as development costs.

[0218] input

[0219] Product sales data.

[0220] Data processing

[0221] Calculation of the joint development cost ratio and its inclusion in the contract.

[0222] output

[0223] Revenue sharing setup complete.

[0224] Step 8: Test the prototype and gather feedback

[0225] Operation by partner companies

[0226] The partner company will create a prototype of the developed product and prepare it for market launch.

[0227] input

[0228] Product development strategy and design data.

[0229] Data processing

[0230] Prototype creation and test scenario development.

[0231] output

[0232] Prototype completed and testing begins.

[0233] User actions

[0234] Users use the prototype and provide feedback via a communication device. For example, they can send specific opinions such as, "The fabric could be a little softer."

[0235] input

[0236] Impressions of using the prototype.

[0237] Data processing

[0238] Gathering feedback and classifying specific opinions.

[0239] output

[0240] User feedback data.

[0241] Server Operations

[0242] The server collects and analyzes user feedback. The results are then provided back to partner companies to help improve the product.

[0243] input

[0244] User feedback data.

[0245] Data processing

[0246] Feedback analysis and identification of areas for improvement.

[0247] output

[0248] Feedback report for product improvement.

[0249] The above outlines the specific processing steps of this system. This system makes it possible to grasp user preferences and trends in real time and reflect them quickly and accurately in product development.

[0250] (Application Example 1)

[0251] 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."

[0252] Conventional trend extraction systems have difficulty reflecting user preferences in real time and are unable to respond to consumers' rapid purchasing intentions. Furthermore, they lack a mechanism to actively utilize the extracted trend information for product recommendations, making it difficult for end users to quickly and easily find specific products.

[0253] 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.

[0254] In this invention, the server includes means for collecting message data generated by users from communication terminals; means for storing and analyzing the collected message data; means for analyzing the stored message data using natural language processing technology and extracting trends; means for providing the extracted trends to partner companies; means for formulating product development strategies in collaboration with partner companies; means for setting a certain percentage of the sales obtained from the developed products as joint development costs; means for collecting user feedback and improving products based on that feedback; means for providing an application that recommends related products to users in real time based on trends; and means for providing users with links to purchase the recommended products. This enables product recommendations that quickly reflect user preferences, allowing consumers to intuitively and quickly discover and purchase related products.

[0255] A "communication terminal" is a device used to collect message data generated by users, and refers to smartphones, tablets, and other similar devices.

[0256] "Message data" refers to data such as text messages and chat content entered by users on their communication devices.

[0257] "Means of collection" refers to the technical means of capturing and storing message data from communication terminals.

[0258] "Means of preservation" refers to technical means for retaining collected message data over a long period of time.

[0259] "Means of analysis" refers to data processing techniques used to extract trends from stored message data.

[0260] "Natural language processing technology" refers to artificial intelligence and text analysis technologies used to analyze meaning from collected message data and extract trends.

[0261] "Trends" refer to keywords and phrases that frequently appear in message data, indicating tendencies that reflect consumer preferences.

[0262] "Partner companies" refer to companies that cooperate in product development based on collected trend information.

[0263] A "product development strategy" refers to a specific plan or policy for developing new products based on trend information.

[0264] "Joint development costs" refer to expenses that are shared between partner companies based on the sales of the developed product.

[0265] "Feedback" refers to the opinions and evaluations that users provide about prototypes or products.

[0266] "Improvement" refers to the act of enhancing the quality and functionality of a product based on collected feedback.

[0267] "Related products" refer to products suggested to users based on extracted trends.

[0268] "Real-time" refers to processing that occurs instantly without delay.

[0269] An "application" refers to software installed on a communication device that provides a specific function.

[0270] "To recommend" refers to the act of selecting and presenting products that match the user's preferences.

[0271] A "link" refers to a URL or button that a user can click to purchase a recommended product.

[0272] This invention relates to a system that collects message data from a user's communication terminal, performs analysis and trend extraction, and provides product recommendations based on those trends. This system is implemented using the following hardware and software.

[0273] The server first collects message data from the communication terminal. Users use messaging applications (e.g., LINE or WhatsApp) on their communication terminals to exchange messages on a daily basis. During the collection process, users must grant permission for data collection in advance.

[0274] Next, the collected message data is sent to a server and stored in a database. The data is anonymized to ensure the protection of personal information.

[0275] The server uses natural language processing (NLP) techniques to analyze the stored message data. For example, the Google Cloud Natural Language API can be used to perform semantic analysis on text data.

[0276] The analysis extracts frequently occurring keywords and phrases as trends. This trend information is further filtered to remove noise data. Only highly reliable trend keywords are retained during this process.

[0277] The server provides extracted trend information to partner companies, supporting them in formulating product development strategies. Based on the provided trends, partner companies hold product development meetings, and for example, a development project for a "pistachio-colored oversized sweater" might be launched.

[0278] Furthermore, the server provides an application for recommending related products to users in real time based on trend information. This application is installed on the smartphone and presents recommended products based on trends extracted from the user's message data. The recommended products also provide links that allow users to directly purchase them, enabling quick purchases.

[0279] As a specific example, when a user sends a message saying "I want a new pistachio-colored sweater", "pistachio color" is extracted as a trend word from that message. Then, "sweaters related to pistachio color" are searched through the product recommendation API and recommended to the user. The user can directly purchase the product by clicking on the recommended product link.

[0280] Examples of prompt sentences to input into the generative AI model include the following:

[0281] User's message: I want a new pistachio-colored sweater

[0282] Extract trend words from this message and recommend related products.

[0283] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0284] Step 1:

[0285] The terminal collects the message data generated by the user. In this process, the terminal obtains the message data from the user in the background and preferentially collects data containing specific keywords or phrases. The input is the message data by the user, and the output is the raw message data collected.

[0286] Step 2:

[0287] The device sends the collected message data to the server. During transmission, the data is protected by end-to-end encryption and anonymized to protect personal information. The input is the message data collected by the device, and the output is the encrypted and anonymized message data.

[0288] Step 3:

[0289] The server stores received message data in a secure database. During this process, the data is anonymized, protecting the user's personal information. The input is encrypted and anonymized message data, and the output is the message data stored in the database.

[0290] Step 4:

[0291] The server performs natural language processing (NLP) techniques on the stored message data. Specifically, it uses the Google Cloud Natural Language API to perform semantic analysis of the text data. The input is message data stored in the database, and the output is extracted keywords and trending words.

[0292] Step 5:

[0293] The server generates trend information based on keywords extracted using natural language processing. Trends are identified by counting the frequency of the extracted keywords and evaluating their importance. The input is the extracted keywords, and the output is the generated trend information.

[0294] Step 6:

[0295] The server provides the generated trend information to partner companies. The information provided includes the frequency of trending words and detailed analysis reports. The input is the generated trend information, and the output is the analysis report sent to the partner company.

[0296] Step 7:

[0297] Partner companies formulate product development strategies based on the provided trend information. Product development meetings are held within the company, and specific product development projects are launched. The input is the provided trend information, and the output is the formulated product development strategy.

[0298] Step 8:

[0299] The server provides an application that recommends relevant products to users in real time based on trend information. This application is installed on smartphones. The input is trend information, and the output is recommended product information provided to the user.

[0300] Step 9:

[0301] The terminal displays links to recommended products for the user, allowing the user to purchase them directly by clicking the links. The input is recommended product information sent from the server, and the output is the product links displayed to the user.

[0302] Step 10:

[0303] Users purchase products using the provided links. Based on the user's purchase behavior, the overall system's effectiveness is evaluated, and feedback is sent to the server as needed. The input is the user's purchasing behavior, and the output is the post-purchase feedback.

[0304] Examples of prompts to input into a generative AI model:

[0305] User message: I want a new pistachio-colored sweater.

[0306] Extract trending keywords from this message and recommend related products.

[0307] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion specific model 59 and perform specific processing using the user's emotions.

[0308] The present invention relates to a system that collects message data of a user from a communication terminal, analyzes emotions using an emotion engine, extracts trends based on this, and utilizes them for product development. This system is composed of a user's communication terminal, a server that collects and analyzes data, and a partner company that conducts product development.

[0309] The operation of this system proceeds as follows.

[0310] Collection of Message Data

[0311] User

[0312] The user uses their communication terminal to exchange daily messages on LINE or other messaging apps. The user gives prior consent to participate in the system and permits the collection of message data.

[0313] Terminal

[0314] The terminal collects the message data generated by the user in the background. Data containing specific keywords or phrases is prioritized as the collection target. The collected data is encrypted and prepared to be sent to the server.

[0315] Server

[0316] The server receives the message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, and personal information is protected.

[0317] Analysis by Emotion Engine

[0318] Next, we will perform emotion analysis using an emotion engine.

[0319] server

[0320] The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. This allows the server to understand the meaning and sentiment of the text data.

[0321] Emotional Engine

[0322] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[0323] Trend Analysis

[0324] Based on the sentiment analysis results, we will further analyze the trends in detail.

[0325] server

[0326] Based on the results of the emotion engine, the server extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, they will be recognized as a trend.

[0327] server

[0328] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0329] Formulating a product development strategy

[0330] Based on the analysis results, we will develop specific products.

[0331] server

[0332] The server provides trend and sentiment information to partner companies, including detailed analysis reports and proposals.

[0333] Partner companies

[0334] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[0335] Revenue sharing settings

[0336] We will establish a sales revenue sharing agreement for the jointly developed product.

[0337] server

[0338] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[0339] Prototype testing and feedback gathering

[0340] Partner companies

[0341] The partner company will create a prototype of the developed product and prepare it for market launch.

[0342] User

[0343] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[0344] terminal

[0345] The device collects feedback messages from users and sends them back to the server.

[0346] server

[0347] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes.

[0348] Through the steps described above, the present invention utilizes LINE message data to grasp consumers' real-time opinions and trends, and enables rapid and effective product development based on this information. Furthermore, by including user sentiment information, it becomes possible to formulate more accurate product development and marketing strategies.

[0349] The following describes the processing flow.

[0350] Step 1:

[0351] User

[0352] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[0353] Step 2:

[0354] terminal

[0355] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[0356] Step 3:

[0357] server

[0358] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[0359] Step 4:

[0360] server

[0361] The server performs natural language processing (NLP) techniques on the stored message data. This includes morphological analysis, entity recognition, and sentiment analysis. Through this analysis, it understands the meaning and sentiment of the text data.

[0362] Step 5:

[0363] Emotional Engine

[0364] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[0365] Step 6:

[0366] server

[0367] Based on the results of the emotion engine, the server extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, they will be recognized as a trend.

[0368] Step 7:

[0369] server

[0370] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0371] Step 8:

[0372] server

[0373] The server provides trend and sentiment information to partner companies. This includes detailed analysis reports and proposals. For example, it might provide information such as, "Users feel very happy with Basque cheesecake."

[0374] Step 9:

[0375] Partner companies

[0376] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[0377] Step 10:

[0378] server

[0379] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[0380] Step 11:

[0381] Partner companies

[0382] The partner company will create a prototype of the developed product and prepare it for market launch.

[0383] Step 12:

[0384] User

[0385] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[0386] Step 13:

[0387] terminal

[0388] The device collects feedback messages from users and sends them back to the server.

[0389] Step 14:

[0390] server

[0391] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes. For example, they might improve their product based on information that "soft fabrics are preferred."

[0392] Through the steps described above, the present invention utilizes LINE message data to grasp consumers' real-time opinions, trends, and emotional information, and enables rapid and effective product development based on this information. Furthermore, by including user emotional information, it becomes possible to formulate more accurate product development and marketing strategies.

[0393] (Example 2)

[0394] 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".

[0395] In recent years, there has been a growing demand to accurately capture consumer behavior and emotions and immediately reflect them in product development. However, traditional methods have fragmented the processes from data collection and sentiment analysis to trend extraction, product development strategy formulation, and market feedback collection, making real-time product development difficult. This has made it difficult to respond quickly to market needs and maintain competitiveness.

[0396] 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.

[0397] In this invention, the server includes means for encrypting collected message data and transmitting it to the server, means for storing and anonymizing the transmitted message data, and means for analyzing the stored message data using natural language processing technology to recognize emotions. This enables product development based on users' real-time emotions and trends, and the rapid reflection of feedback.

[0398] A "communication terminal" is a device used by a user to generate and send message data, and includes smartphones, tablets, personal computers, etc.

[0399] "Message data" refers to data such as text, images, audio, and video that users send and receive through their communication devices.

[0400] "Encryption" is the process of transforming message data using specific algorithms to protect it and prevent third parties from accessing it.

[0401] A "server" refers to a central system that receives, stores, analyzes, and manages data sent from users' communication terminals.

[0402] "Anonymization" is the process of removing personally identifiable information from message data so that personal information cannot be identified.

[0403] "Natural language processing technology" refers to the techniques that enable computers to understand, analyze, and generate human language, and includes morphological analysis, entity recognition, and sentiment analysis.

[0404] "Emotions" refer to psychological states such as "joy," "anger," "sadness," and "surprise" contained in the user's message data.

[0405] A "trend" refers to a specific tendency or fashion that is recognized based on the frequent appearance of certain keywords or phrases in a large number of messages, as determined by analyzed message data.

[0406] "Partner companies" refer to companies that develop products based on trend and sentiment information obtained using this system.

[0407] "Joint development costs" refer to a certain percentage of sales generated from the developed product, and are development costs shared with partner companies.

[0408] "Feedback" refers to specific opinions and evaluations, such as user experience and areas for improvement, provided by users after using a prototype.

[0409] This invention relates to a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, extracts trends based on that analysis, and utilizes them for product development. This system consists of a user's communication terminal, a server that collects and analyzes data, and a partner company that develops products.

[0410] Users use their communication devices to exchange messages daily using LINE and other messaging apps. Users consent in advance to participate in this system and allow the collection of message data. The communication device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is encrypted and prepared for transmission to the server. Protocols such as SSL / TLS are used for encryption.

[0411] The server receives message data sent from each communication terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information. The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. This allows for an understanding of the meaning and sentiment of the text data.

[0412] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[0413] As part of trend analysis, the server extracts frequently occurring apparel-related words and keywords related to food ingredients and cooking based on the results of the sentiment engine. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in numerous messages, it is recognized as a trend. The server improves data accuracy by filtering out noise data (meaningless information) and retaining only highly reliable keywords. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0414] In formulating product development strategies, the server provides partner companies with trend and sentiment information. This includes detailed analysis reports and proposals. Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. The partner companies then proceed with specific design and manufacturing processes.

[0415] When setting up revenue sharing, the server can set a percentage of joint development costs based on sales (for example, 10%) and reflect this in the contract with the partner company, allowing both parties to share the profits.

[0416] In prototype testing and feedback gathering, partner companies create prototypes of the developed products and prepare them for market launch. Users use the prototypes and send feedback via LINE messages about their experience and areas for improvement. For example, specific opinions such as "the fabric should be a little softer" may be given. Communication terminals collect feedback messages from users and send them back to the server. The server analyzes the collected feedback again and provides the results to the partner companies. This allows the partner companies to obtain specific guidance for improving the prototypes.

[0417] This system utilizes LINE message data to grasp real-time consumer opinions and trends, enabling rapid and effective product development based on that information. Furthermore, by including user sentiment data, it allows for more accurate product development and marketing strategy formulation.

[0418] Example of a prompt:

[0419] "Please describe in natural language in detail a system that analyzes user sentiment towards fashion items on social media, identifies trends, and uses this information for product development."

[0420] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0421] Step 1:

[0422] Collection of message data

[0423] User: Users send and receive everyday messages using messaging apps such as LINE. In this process, users have given prior consent to data collection.

[0424] Input: The message that the user sends to the messaging app.

[0425] Output: The generated message is passed to the terminal.

[0426] Terminal operation: The terminal collects messages in a background process. Messages containing specific keywords or phrases are collected preferentially and prepared for encryption.

[0427] Step 2:

[0428] Data encryption and transmission

[0429] Terminal: The terminal encrypts the collected message data. The SSL / TLS protocol is used for this purpose.

[0430] Input: Collected message data.

[0431] Output: Encrypted message data is sent to the server.

[0432] Terminal operation: The terminal applies an encryption algorithm and prepares to encrypt the data and send it to the server. Specifically, it encrypts the data using the SSL / TLS protocol and sends it to the server through a secure communication circuit.

[0433] Step 3:

[0434] Data storage and anonymization

[0435] Server: The server stores the received encrypted data in a database and performs an anonymization process.

[0436] Input: Encrypted message data.

[0437] Output: Anonymized message data is stored in the database.

[0438] Server operation: The server extracts personally identifiable information and anonymizes the data through hashing and substitution operations. The data is stored in the database in a format that does not identify individuals.

[0439] Step 4:

[0440] Analysis using an emotion engine

[0441] Server: The server analyzes stored data using natural language processing (NLP) techniques.

[0442] Input: Anonymized message data.

[0443] Output: Analysis results related to the sentiment of the message.

[0444] Server operation: The server performs morphological analysis and extracts important information from messages through entity recognition. Then, it performs sentiment analysis and classifies the emotions expressed in the messages into categories such as "joy," "anger," and "sadness."

[0445] Step 5:

[0446] Trend Analysis

[0447] Server: The server extracts trends from the sentiment engine's results. It particularly identifies frequently occurring words related to apparel and keywords related to cooking and ingredients.

[0448] Input: Sentiment analysis results.

[0449] Output: Keywords and statistics related to the trend.

[0450] Server operation: The server extracts frequently occurring keywords from the analysis results and filters out noise data (irrelevant information). Then, it performs statistical analysis to evaluate the frequency and importance of each keyword and creates a trend report.

[0451] Step 6:

[0452] Formulating a product development strategy

[0453] Server: The server provides trend information and sentiment information to partner companies.

[0454] Input: Keywords and statistics related to the trend.

[0455] Output: Detailed analysis report and proposal.

[0456] Server operation: Based on the analysis results, the server generates detailed reports and proposals, which are then provided to partner companies via APIs and secure communication methods.

[0457] Step 7:

[0458] Revenue sharing settings

[0459] Server: Server sets the percentage of joint development costs based on sales and reflects this in contracts with partner companies.

[0460] Input: Sales information.

[0461] Output: Joint development cost setting information.

[0462] Server operation: Analyzes sales information, calculates joint development costs based on pre-set percentages, and reflects the results in the contract.

[0463] Step 8:

[0464] Prototype testing and feedback gathering

[0465] Partner companies: Partner companies create prototypes and prepare them for market launch.

[0466] User: Users use the prototype and submit feedback on their experience and areas for improvement.

[0467] Input: User feedback message.

[0468] Output: Collected feedback data.

[0469] Terminal operation: The terminal collects feedback messages sent by the user, encrypts them, and sends them to the server.

[0470] Server operation: The server analyzes the collected feedback and provides the results to partner companies to help improve the prototype.

[0471] (Application Example 2)

[0472] 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".

[0473] In recent years, there has been a growing demand for technologies that utilize the vast amount of message data generated via communication devices to accurately understand consumer sentiment and trends, and to use this information for product development. However, existing methods lack sufficient data analysis capabilities, making it difficult to respond quickly and accurately to consumer needs. Furthermore, there is a lack of means to improve the accuracy of personalized product recommendations. As a result, it is difficult to improve consumer satisfaction and achieve business growth.

[0474] 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.

[0475] In this invention, the server includes means for collecting message data generated by users from communication terminals, means for storing and analyzing the collected message data, means for analyzing the stored message data using natural language processing technology and extracting trends, means for providing the extracted trends to partner companies, means for formulating product development strategies in collaboration with partner companies, means for setting a certain percentage of sales obtained from the developed products as joint development costs, means for collecting user feedback and improving products based on that feedback, and means for generating and presenting personalized product suggestions to users based on the analysis results. This makes it possible to accurately grasp consumers' real-time emotions and trends, make product suggestions optimized for consumers, and achieve rapid and effective product development.

[0476] A "communication terminal" is a device used by users to generate message data and communicate.

[0477] "Message data" refers to data that includes text information and media content generated by users using communication devices.

[0478] "Storage" refers to the process of retaining collected data for a long period of time.

[0479] "Analysis" refers to the process of understanding the meaning and emotions of stored data using natural language processing techniques.

[0480] "Natural language processing technology" is a technique that uses computers to analyze human language and extract meaning and emotions.

[0481] A "trend" is a keyword or concept that indicates something or something that is supported by many users within a certain period of time.

[0482] A "partner company" is an external company that cooperates in product development based on data analysis results.

[0483] A "product development strategy" is a plan for effectively developing and providing products based on market needs and trends.

[0484] "A certain percentage of sales" refers to a predetermined percentage set out to distribute sales among the companies involved in the joint development project.

[0485] "Feedback" refers to opinions and requests regarding products and services provided by users.

[0486] "Personalized product recommendations" refer to products suggested based on the sentiment analysis results and trend data of individual users.

[0487] This invention is a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, and extracts trends based on that analysis to aid in product development. The main components of this system include a communication terminal, a server, and partner companies.

[0488] Collection of message data

[0489] User

[0490] Users routinely communicate through messaging apps using their own communication devices. Message data is collected only from users who have given prior consent to the system.

[0491] terminal

[0492] The device collects user message data in the background. Messages containing specific keywords or sentiments are prioritized for collection. The collected data is encrypted and sent to the server.

[0493] server

[0494] The server receives message data sent from communication terminals and stores it in a secure database. This data is anonymized, ensuring user privacy.

[0495] Analysis using an emotion engine

[0496] server

[0497] The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. Examples of NLP libraries used include spaCy and NLTK.

[0498] Emotional Engine

[0499] The emotion engine analyzes the user's emotions based on the analysis results and classifies each message into emotional categories such as "joy," "anger," and "sadness." For example, IBM Watson® Tone Analyzer is used as the emotion engine.

[0500] Trend analysis and personalized product recommendations

[0501] server

[0502] The server extracts frequently occurring trending words based on the results of the sentiment engine. Keywords related to fashion, food, and lifestyle goods are particularly extracted.

[0503] Next, the server matches the extracted trending words with related product data to generate product suggestions optimized for the user. This results in personalized product recommendations being presented to the user.

[0504] Specific example

[0505] If a user sends a LINE message saying, "I've been really stressed lately," the emotion engine classifies this message as a "negative emotion." The server then extracts products based on trending words related to "stress reduction" and "relaxation," and suggests items such as "stress-reducing aroma diffusers" and "relaxation massage machines" to the user.

[0506] Example of a prompt

[0507] If a friend mentions feeling stressed lately during a conversation, recommend related relaxation products or stress-reducing items based on this message. Also, consider that the user is experiencing the emotion of "stress."

[0508] In this way, the present invention provides a system for acquiring real-time consumer opinions and trends and suggesting products suitable for users. This enables rapid and effective product development and the formulation of marketing strategies.

[0509] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0510] Step 1:

[0511] Collecting message data from users

[0512] The user uses a communication terminal to engage in everyday conversations and generate message data. The terminal collects this message data in the background. It receives the generated message data as input and encrypts it. The encrypted message data is obtained as output.

[0513] Step 2:

[0514] Encrypted data sent to the server

[0515] The terminal sends encrypted message data to the server. It takes encrypted message data as input and executes a process to send that data to the server. The output is the encrypted data stored on the server.

[0516] Step 3:

[0517] Data storage and preparation for analysis

[0518] The server stores the received encrypted message data in a database and prepares it for analysis. It takes the received encrypted data as input and stores it in the database. The stored data is then output.

[0519] Step 4:

[0520] Data analysis using Natural Language Processing (NLP)

[0521] The server retrieves message data stored in the database and performs analysis using natural language processing (NLP) techniques. It uses the message data retrieved from the database as input and performs NLP processing (morphological analysis, entity recognition, sentiment analysis). The output is the analyzed text data.

[0522] Step 5:

[0523] Emotional analysis using an emotion engine

[0524] The server uses NLP analysis results to run an emotion engine and classify the user's emotions. It uses NLP-analyzed data as input and runs it through an emotion engine (e.g., IBM Watson Tone Analyzer). The output is data categorized into emotion categories.

[0525] Step 6:

[0526] Extraction of trending words

[0527] The server extracts trending words based on sentiment analysis results. It uses sentiment-analyzed data as input to extract frequently occurring keywords and trending words. The output is a list of the extracted trending words.

[0528] Step 7:

[0529] Matching with the product database

[0530] The server matches the extracted trending keywords with the product database and selects relevant products. It uses the trending keyword list and the product database as input to search for products that match the keywords. The output is a personalized product list.

[0531] Step 8:

[0532] Generating and presenting personalized product suggestions

[0533] The server generates personalized product suggestions based on the selected products and presents them to the user's communication device. It uses a product list as input to generate recommended product messages. The output is the product suggestion message presented to the user.

[0534] This series of steps makes it possible to accurately grasp emotions and trends from user message data and provide product recommendations based on that.

[0535] 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.

[0536] 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.

[0537] 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.

[0538] [Second Embodiment]

[0539] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0540] 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.

[0541] 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).

[0542] 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.

[0543] 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.

[0544] 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).

[0545] 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.

[0546] 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.

[0547] 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.

[0548] 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.

[0549] 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.

[0550] 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".

[0551] This invention is a system that collects user message data from communication terminals, extracts trends based on that data, and uses them to aid in product development. This system consists of the user's communication terminal, a server that collects and analyzes the data, and a partner company that develops the product.

[0552] The system operates as follows:

[0553] Collection of message data

[0554] User

[0555] Users use their communication devices (smartphones and tablets) to conduct daily communication using LINE and other messaging apps. Users give prior consent to participate in the system and grant permission for data collection.

[0556] terminal

[0557] The device collects user-generated message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases.

[0558] server

[0559] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[0560] Trend Analysis

[0561] Next, we will perform a trend analysis.

[0562] server

[0563] The server applies natural language processing (NLP) techniques to the stored message data. This analyzes the meaning of the text data and extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, this will be recognized as a trend.

[0564] Data filtering and aggregation

[0565] The extracted data is further refined and analyzed.

[0566] server

[0567] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Next, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0568] Formulating a product development strategy

[0569] Based on the analysis results, we will develop specific products.

[0570] server

[0571] The server provides trend information to partner companies, including detailed analysis reports and proposals.

[0572] Partner companies

[0573] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[0574] Revenue sharing settings

[0575] We will establish a sales revenue sharing agreement for the jointly developed product.

[0576] server

[0577] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[0578] Prototype testing and feedback gathering

[0579] Partner companies

[0580] The partner company will create a prototype of the developed product and prepare it for market launch.

[0581] User

[0582] Users use the prototype and provide feedback via a communication device. For example, they might offer specific suggestions such as, "The fabric could be a little softer."

[0583] server

[0584] The server collects and analyzes feedback. The results are then provided back to partner companies to help improve the product.

[0585] This invention makes it possible to capture consumer preferences in real time and proceed with product development quickly and accurately, thereby enhancing market competitiveness.

[0586] The following describes the processing flow.

[0587] Step 1:

[0588] User

[0589] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[0590] Step 2:

[0591] terminal

[0592] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[0593] Step 3:

[0594] server

[0595] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[0596] Step 4:

[0597] server

[0598] The server analyzes the stored message data using natural language processing (NLP) techniques. Specifically, it utilizes techniques such as morphological analysis, entity recognition, and sentiment analysis to understand the meaning and sentiment of each data point.

[0599] Step 5:

[0600] server

[0601] The server extracts frequently occurring apparel-related words and keywords related to sweets and cooking from the analysis results. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, it will be recognized as a trend.

[0602] Step 6:

[0603] server

[0604] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0605] Step 7:

[0606] server

[0607] The server provides trend information to partner companies, including detailed analysis reports and proposals.

[0608] Step 8:

[0609] Partner companies

[0610] Partner companies hold internal product development meetings based on the trend information they receive. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, product design and manufacturing processes proceed.

[0611] Step 9:

[0612] server

[0613] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[0614] Step 10:

[0615] Partner companies

[0616] The partner company will create a prototype of the developed product and prepare it for market launch.

[0617] Step 11:

[0618] User

[0619] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[0620] Step 12:

[0621] terminal

[0622] The device collects feedback messages from users and sends them back to the server.

[0623] Step 13:

[0624] server

[0625] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes.

[0626] In this way, through a series of steps, LINE message data is utilized to grasp real-time consumer opinions and trends, enabling rapid and effective product development based on that information.

[0627] (Example 1)

[0628] 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."

[0629] In today's world, quickly and accurately understanding consumer preferences and trends is crucial for maintaining a competitive advantage. However, traditional systems have struggled to collect and analyze consumer interests and trends in real time and incorporate them into product development. Furthermore, there has been a lack of mechanisms to effectively collect feedback from consumers and utilize it for product improvement. As a result, companies have found it difficult to respond quickly to market trends, which could lead to a decline in competitiveness.

[0630] 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.

[0631] In this invention, the server includes means for collecting text message data generated by users from a communication device, means for storing and anonymizing the collected message data, means for analyzing the stored message data using natural language processing technology and extracting trends, means for filtering the recognized trends and retaining only highly reliable data, means for providing the extracted trends to partner companies, means for formulating product development strategies in collaboration with partner companies, means for setting a percentage of sales obtained from the developed product as joint development costs, and means for collecting user feedback and improving the product based on that feedback. This makes it possible to grasp user preferences and trends in real time and reflect them in product development quickly and accurately.

[0632] A "communication device" is a device used by users to generate and send text messages. This includes smartphones, tablets, and personal computers.

[0633] "User" refers to a person or individual who uses a communication device to generate text messages.

[0634] "Text message data" refers to character-based information generated and transmitted by users using communication devices. This includes the content sent in text messaging applications.

[0635] "Collection" refers to the process of obtaining text message data from a communication device and sending that data to a server.

[0636] "Saving" refers to the process of accumulating collected text message data in a database.

[0637] "Anonymization" is the process of removing personal information from collected text message data and transforming the data into a form that cannot be linked to an individual.

[0638] "Natural language processing technology" refers to the techniques that enable computers to understand and analyze human language. This includes algorithms for analyzing the meaning of text and performing syntactic and grammatical analysis.

[0639] "Trends" refer to frequently occurring keywords and phrases related to specific products or themes that emerge from the analysis of collected text message data.

[0640] "Filtering" is the process of removing noise from recognized trend data and selecting only meaningful data.

[0641] A "partner company" refers to a company or organization that collaborates with this system to develop products.

[0642] A "product development strategy" refers to the product development plan and policies formulated jointly with partner companies. This strategy is formulated based on analyzed trend information.

[0643] "Joint development costs" refer to expenses set as a certain percentage of the sales generated from the developed product. This is part of the compensation for the product developed through the collaboration between the system and partner companies.

[0644] "Feedback" refers to the opinions and impressions that users provide after using a developed product. This includes specific comments on areas for improvement and the user experience.

[0645] This invention is a system that collects text message data generated from users' communication devices, analyzes it to extract trends, and uses them for product development. This system consists of the user's communication device, a server that collects and analyzes the data, and partner companies that develop products.

[0646] Data collection

[0647] User actions

[0648] Users use their own communication devices (smartphones and tablets) to exchange text messages on a daily basis. Users themselves must consent to the handling of the collected data.

[0649] Terminal operation

[0650] The device collects user-generated text message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases, and the data is sent to the server in real time. For example, collection may be based on keyword lists such as "pistachio color" or "oversize."

[0651] Data storage and anonymization

[0652] Server Operations

[0653] The server receives message data sent from each terminal and stores it in a secure database. During this process, the collected data is anonymized to protect personal information. Data anonymity is ensured by replacing user IDs with random identifiers.

[0654] Trend Analysis

[0655] Server Operations

[0656] The semantic analysis of text is performed by applying natural language processing (NLP) techniques to the stored data. Techniques such as BERT (Bidirectional Encoder Representations from Transformers) are used in this process. Frequently occurring words are extracted and recognized as trends.

[0657] Data filtering and aggregation

[0658] Server Operations

[0659] From the analyzed trend data, noise is filtered out, and only meaningful data is retained. Statistical information is generated based on reliable trend data, and the frequency and importance of occurrences are evaluated.

[0660] Formulating a product development strategy

[0661] Server and partner company operations

[0662] The server provides trend information to partner companies, and together they formulate product development strategies. For example, a development project for a "pistachio-colored oversized sweater" might be launched.

[0663] Revenue sharing settings

[0664] Server Operations

[0665] The percentage of joint development costs will be determined based on the product's sales. For example, 10% of sales will be allocated as development costs and reflected in the contract.

[0666] Prototype testing and feedback gathering

[0667] Operation by partner companies

[0668] The partner company will create a prototype of the developed product and prepare it for market launch.

[0669] User actions

[0670] Users provide feedback via their devices using the prototypes. Specific feedback, such as "The fabric could be a little softer," is provided.

[0671] Server Operations

[0672] The server collects and analyzes user feedback. The results of the feedback are then provided back to partner companies to help improve the product.

[0673] Examples of specific cases and prompts for generative AI models.

[0674] Specific example

[0675] A message sent by a user to a friend on LINE, saying "Apparently pistachio-colored clothes are popular lately," is collected. This message is analyzed by a server, and the trending keyword "pistachio color" is extracted. Partner companies then proceed with product development based on this information.

[0676] Example of a prompt

[0677] "Please analyze recent trends regarding popular colors from messages sent by users on LINE."

[0678] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0679] Step 1: Prepare for data collection

[0680] User actions

[0681] Users use their communication devices to exchange text messages on a daily basis. Prior to this, they are prompted to grant permission for data collection, and they give their consent.

[0682] input

[0683] User permission and consent.

[0684] output

[0685] Data collection is ready.

[0686] Step 2: Collect message connections

[0687] Terminal operation

[0688] The device begins collecting user-generated text message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases (e.g., "pistachio color," "oversize"). The collected data is sent to the server in real time.

[0689] input

[0690] Text message data generated by the device.

[0691] Data processing

[0692] Filtering based on a keyword list.

[0693] output

[0694] Filtered message data is sent to the server.

[0695] Step 3: Data storage and anonymization

[0696] Server Operations

[0697] The server receives message data sent from each terminal and stores it in a secure database. Before storage, the data is anonymized and user IDs are replaced with random identifiers.

[0698] input

[0699] Message data sent from the device.

[0700] Data processing

[0701] Anonymization process (replacement of user IDs with random identifiers).

[0702] output

[0703] Anonymized message data is stored in a database.

[0704] Step 4: Trend Analysis

[0705] Server Operations

[0706] The server applies natural language processing (NLP) techniques to the stored message data to analyze the meaning of the text. Specifically, it uses methods such as BERT (Bidirectional Encoder Representations from Transformers). It extracts frequently occurring keywords and recognizes them as trends.

[0707] input

[0708] Anonymized message data.

[0709] Data processing

[0710] Text semantic analysis and keyword extraction using natural language processing technology.

[0711] output

[0712] Recognized trending keywords.

[0713] Step 5: Filtering and Aggregating Data

[0714] Server Operations

[0715] The server filters out noise data (irrelevant information) from the analyzed trend data, retaining only meaningful data. Next, it evaluates the frequency and importance of each keyword based on the aggregated results.

[0716] input

[0717] Recognized trending keywords.

[0718] Data processing

[0719] Filtering of noise data and aggregation of occurrence frequencies.

[0720] output

[0721] A list of trending keywords that have been evaluated.

[0722] Step 6: Formulate a product development strategy

[0723] Server and partner company operations

[0724] The server generates trend information as an analysis report and provides it to partner companies. Based on this information, partner companies hold product development meetings and formulate product development strategies. For example, a development project for a "pistachio-colored oversized sweater" might be launched.

[0725] input

[0726] A list of trending keywords that have been evaluated.

[0727] Data processing

[0728] Generation of analysis reports and proposals.

[0729] output

[0730] Formulating product development strategies and launching projects.

[0731] Step 7: Setting up revenue sharing

[0732] Server Operations

[0733] The server sets the percentage of joint development costs based on the sales of the developed product. For example, it might enter into an agreement with a partner company to distribute 10% of sales as development costs.

[0734] input

[0735] Product sales data.

[0736] Data processing

[0737] Calculation of the joint development cost ratio and its inclusion in the contract.

[0738] output

[0739] Revenue sharing setup complete.

[0740] Step 8: Test the prototype and gather feedback

[0741] Operation by partner companies

[0742] The partner company will create a prototype of the developed product and prepare it for market launch.

[0743] input

[0744] Product development strategy and design data.

[0745] Data processing

[0746] Prototype creation and test scenario development.

[0747] output

[0748] Prototype completed and testing begins.

[0749] User actions

[0750] Users use the prototype and provide feedback via a communication device. For example, they can send specific opinions such as, "The fabric could be a little softer."

[0751] input

[0752] Impressions of using the prototype.

[0753] Data processing

[0754] Gathering feedback and classifying specific opinions.

[0755] output

[0756] User feedback data.

[0757] Server Operations

[0758] The server collects and analyzes user feedback. The results are then provided back to partner companies to help improve the product.

[0759] input

[0760] User feedback data.

[0761] Data processing

[0762] Feedback analysis and identification of areas for improvement.

[0763] output

[0764] Feedback report for product improvement.

[0765] The above outlines the specific processing steps of this system. This system makes it possible to grasp user preferences and trends in real time and reflect them quickly and accurately in product development.

[0766] (Application Example 1)

[0767] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0768] Conventional trend extraction systems have difficulty reflecting user preferences in real time and are unable to respond to consumers' rapid purchasing intentions. Furthermore, they lack a mechanism to actively utilize the extracted trend information for product recommendations, making it difficult for end users to quickly and easily find specific products.

[0769] 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.

[0770] In this invention, the server includes means for collecting message data generated by users from communication terminals; means for storing and analyzing the collected message data; means for analyzing the stored message data using natural language processing technology and extracting trends; means for providing the extracted trends to partner companies; means for formulating product development strategies in collaboration with partner companies; means for setting a certain percentage of the sales obtained from the developed products as joint development costs; means for collecting user feedback and improving products based on that feedback; means for providing an application that recommends related products to users in real time based on trends; and means for providing users with links to purchase the recommended products. This enables product recommendations that quickly reflect user preferences, allowing consumers to intuitively and quickly discover and purchase related products.

[0771] A "communication terminal" is a device used to collect message data generated by users, and refers to smartphones, tablets, and other similar devices.

[0772] "Message data" refers to data such as text messages and chat content entered by users on their communication devices.

[0773] "Means of collection" refers to the technical means of capturing and storing message data from communication terminals.

[0774] "Means of preservation" refers to technical means for retaining collected message data over a long period of time.

[0775] "Means of analysis" refers to data processing techniques used to extract trends from stored message data.

[0776] "Natural language processing technology" refers to artificial intelligence and text analysis technologies used to analyze meaning from collected message data and extract trends.

[0777] "Trends" refer to keywords and phrases that frequently appear in message data, indicating tendencies that reflect consumer preferences.

[0778] "Partner companies" refer to companies that cooperate in product development based on collected trend information.

[0779] A "product development strategy" refers to a specific plan or policy for developing new products based on trend information.

[0780] "Joint development costs" refer to expenses that are shared between partner companies based on the sales of the developed product.

[0781] "Feedback" refers to the opinions and evaluations that users provide about prototypes or products.

[0782] "Improvement" refers to the act of enhancing the quality and functionality of a product based on collected feedback.

[0783] "Related products" refer to products suggested to users based on extracted trends.

[0784] "Real-time" refers to processing that occurs instantly without delay.

[0785] An "application" refers to software installed on a communication device that provides a specific function.

[0786] "To recommend" refers to the act of selecting and presenting products that match the user's preferences.

[0787] A "link" refers to a URL or button that a user can click to purchase a recommended product.

[0788] This invention relates to a system that collects message data from a user's communication terminal, performs analysis and trend extraction, and provides product recommendations based on those trends. This system is implemented using the following hardware and software.

[0789] The server first collects message data from the communication terminal. Users use messaging applications (e.g., LINE or WhatsApp) on their communication terminals to exchange messages on a daily basis. During the collection process, users must grant permission for data collection in advance.

[0790] Next, the collected message data is sent to a server and stored in a database. The data is anonymized to ensure the protection of personal information.

[0791] The server uses natural language processing (NLP) techniques to analyze the stored message data. For example, the Google Cloud Natural Language API can be used to perform semantic analysis on text data.

[0792] The analysis extracts frequently occurring keywords and phrases as trends. This trend information is further filtered to remove noise data. Only highly reliable trend keywords are retained during this process.

[0793] The server provides extracted trend information to partner companies, supporting them in formulating product development strategies. Based on the provided trends, partner companies hold product development meetings, and for example, a development project for a "pistachio-colored oversized sweater" might be launched.

[0794] Furthermore, the server provides an application that recommends relevant products to users in real time based on trend information. This application is installed on smartphones and presents recommended products based on trends extracted from the user's message data. Recommended products also include links that users can use to purchase them directly, enabling quick purchases.

[0795] For example, if a user sends a message saying, "I want a new pistachio-colored sweater," "pistachio color" will be extracted as a trending keyword from that message. Then, sweaters related to "pistachio color" will be searched for via the product recommendation API and recommended to the user. The user can then purchase the product directly by clicking on the recommended product link.

[0796] Examples of prompts to input into a generative AI model include the following:

[0797] User message: I want a new pistachio-colored sweater.

[0798] Extract trending keywords from this message and recommend related products.

[0799] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0800] Step 1:

[0801] The device collects message data generated by the user. During this process, the device retrieves message data from the user in the background, prioritizing the collection of data containing specific keywords or phrases. The input is the user's message data, and the output is the collected raw message data.

[0802] Step 2:

[0803] The device sends the collected message data to the server. During transmission, the data is protected by end-to-end encryption and anonymized to protect personal information. The input is the message data collected by the device, and the output is the encrypted and anonymized message data.

[0804] Step 3:

[0805] The server stores received message data in a secure database. During this process, the data is anonymized, protecting the user's personal information. The input is encrypted and anonymized message data, and the output is the message data stored in the database.

[0806] Step 4:

[0807] The server performs natural language processing (NLP) techniques on the stored message data. Specifically, it uses the Google Cloud Natural Language API to perform semantic analysis of the text data. The input is message data stored in the database, and the output is extracted keywords and trending words.

[0808] Step 5:

[0809] The server generates trend information based on keywords extracted using natural language processing. Trends are identified by counting the frequency of the extracted keywords and evaluating their importance. The input is the extracted keywords, and the output is the generated trend information.

[0810] Step 6:

[0811] The server provides the generated trend information to partner companies. The information provided includes the frequency of trending words and detailed analysis reports. The input is the generated trend information, and the output is the analysis report sent to the partner company.

[0812] Step 7:

[0813] Partner companies formulate product development strategies based on the provided trend information. Product development meetings are held within the company, and specific product development projects are launched. The input is the provided trend information, and the output is the formulated product development strategy.

[0814] Step 8:

[0815] The server provides an application that recommends relevant products to users in real time based on trend information. This application is installed on smartphones. The input is trend information, and the output is recommended product information provided to the user.

[0816] Step 9:

[0817] The terminal displays links to recommended products for the user, allowing the user to purchase them directly by clicking the links. The input is recommended product information sent from the server, and the output is the product links displayed to the user.

[0818] Step 10:

[0819] Users purchase products using the provided links. Based on the user's purchase behavior, the overall system's effectiveness is evaluated, and feedback is sent to the server as needed. The input is the user's purchasing behavior, and the output is the post-purchase feedback.

[0820] Examples of prompts to input into a generative AI model:

[0821] User message: I want a new pistachio-colored sweater.

[0822] Extract trending keywords from this message and recommend related products.

[0823] 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.

[0824] This invention relates to a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, extracts trends based on that analysis, and utilizes them for product development. This system consists of a user's communication terminal, a server that collects and analyzes data, and a partner company that develops products.

[0825] The system operates as follows:

[0826] Collection of message data

[0827] User

[0828] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[0829] terminal

[0830] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[0831] server

[0832] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[0833] Analysis using an emotion engine

[0834] Next, we will perform emotion analysis using an emotion engine.

[0835] server

[0836] The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. This allows the server to understand the meaning and sentiment of the text data.

[0837] Emotional Engine

[0838] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[0839] Trend Analysis

[0840] Based on the sentiment analysis results, we will further analyze the trends in detail.

[0841] server

[0842] Based on the results of the emotion engine, the server extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, they will be recognized as a trend.

[0843] server

[0844] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0845] Formulating a product development strategy

[0846] Based on the analysis results, we will develop specific products.

[0847] server

[0848] The server provides trend and sentiment information to partner companies, including detailed analysis reports and proposals.

[0849] Partner companies

[0850] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[0851] Revenue sharing settings

[0852] We will establish a sales revenue sharing agreement for the jointly developed product.

[0853] server

[0854] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[0855] Prototype testing and feedback gathering

[0856] Partner companies

[0857] The partner company will create a prototype of the developed product and prepare it for market launch.

[0858] User

[0859] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[0860] terminal

[0861] The device collects feedback messages from users and sends them back to the server.

[0862] server

[0863] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes.

[0864] Through the steps described above, the present invention utilizes LINE message data to grasp consumers' real-time opinions and trends, and enables rapid and effective product development based on this information. Furthermore, by including user sentiment information, it becomes possible to formulate more accurate product development and marketing strategies.

[0865] The following describes the processing flow.

[0866] Step 1:

[0867] User

[0868] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[0869] Step 2:

[0870] terminal

[0871] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[0872] Step 3:

[0873] server

[0874] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[0875] Step 4:

[0876] server

[0877] The server performs natural language processing (NLP) techniques on the stored message data. This includes morphological analysis, entity recognition, and sentiment analysis. Through this analysis, it understands the meaning and sentiment of the text data.

[0878] Step 5:

[0879] Emotional Engine

[0880] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[0881] Step 6:

[0882] server

[0883] Based on the results of the emotion engine, the server extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, they will be recognized as a trend.

[0884] Step 7:

[0885] server

[0886] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0887] Step 8:

[0888] server

[0889] The server provides trend and sentiment information to partner companies. This includes detailed analysis reports and proposals. For example, it might provide information such as, "Users feel very happy with Basque cheesecake."

[0890] Step 9:

[0891] Partner companies

[0892] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[0893] Step 10:

[0894] server

[0895] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[0896] Step 11:

[0897] Partner companies

[0898] The partner company will create a prototype of the developed product and prepare it for market launch.

[0899] Step 12:

[0900] User

[0901] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[0902] Step 13:

[0903] terminal

[0904] The device collects feedback messages from users and sends them back to the server.

[0905] Step 14:

[0906] server

[0907] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes. For example, they might improve their product based on information that "soft fabrics are preferred."

[0908] Through the steps described above, the present invention utilizes LINE message data to grasp consumers' real-time opinions, trends, and emotional information, and enables rapid and effective product development based on this information. Furthermore, by including user emotional information, it becomes possible to formulate more accurate product development and marketing strategies.

[0909] (Example 2)

[0910] 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".

[0911] In recent years, there has been a growing demand to accurately capture consumer behavior and emotions and immediately reflect them in product development. However, traditional methods have fragmented the processes from data collection and sentiment analysis to trend extraction, product development strategy formulation, and market feedback collection, making real-time product development difficult. This has made it difficult to respond quickly to market needs and maintain competitiveness.

[0912] 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.

[0913] In this invention, the server includes means for encrypting collected message data and transmitting it to the server, means for storing and anonymizing the transmitted message data, and means for analyzing the stored message data using natural language processing technology to recognize emotions. This enables product development based on users' real-time emotions and trends, and the rapid reflection of feedback.

[0914] A "communication terminal" is a device used by a user to generate and send message data, and includes smartphones, tablets, personal computers, etc.

[0915] "Message data" refers to data such as text, images, audio, and video that users send and receive through their communication devices.

[0916] "Encryption" is the process of transforming message data using specific algorithms to protect it and prevent third parties from accessing it.

[0917] A "server" refers to a central system that receives, stores, analyzes, and manages data sent from users' communication terminals.

[0918] "Anonymization" is the process of removing personally identifiable information from message data so that personal information cannot be identified.

[0919] "Natural language processing technology" refers to the techniques that enable computers to understand, analyze, and generate human language, and includes morphological analysis, entity recognition, and sentiment analysis.

[0920] "Emotions" refer to psychological states such as "joy," "anger," "sadness," and "surprise" contained in the user's message data.

[0921] A "trend" refers to a specific tendency or fashion that is recognized based on the frequent appearance of certain keywords or phrases in a large number of messages, as determined by analyzed message data.

[0922] "Partner companies" refer to companies that develop products based on trend and sentiment information obtained using this system.

[0923] "Joint development costs" refer to a certain percentage of sales generated from the developed product, and are development costs shared with partner companies.

[0924] "Feedback" refers to specific opinions and evaluations, such as user experience and areas for improvement, provided by users after using a prototype.

[0925] This invention relates to a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, extracts trends based on that analysis, and utilizes them for product development. This system consists of a user's communication terminal, a server that collects and analyzes data, and a partner company that develops products.

[0926] Users use their communication devices to exchange messages daily using LINE and other messaging apps. Users consent in advance to participate in this system and allow the collection of message data. The communication device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is encrypted and prepared for transmission to the server. Protocols such as SSL / TLS are used for encryption.

[0927] The server receives message data sent from each communication terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information. The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. This allows for an understanding of the meaning and sentiment of the text data.

[0928] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[0929] As part of trend analysis, the server extracts frequently occurring apparel-related words and keywords related to food ingredients and cooking based on the results of the sentiment engine. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in numerous messages, it is recognized as a trend. The server improves data accuracy by filtering out noise data (meaningless information) and retaining only highly reliable keywords. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[0930] In formulating product development strategies, the server provides partner companies with trend and sentiment information. This includes detailed analysis reports and proposals. Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. The partner companies then proceed with specific design and manufacturing processes.

[0931] When setting up revenue sharing, the server can set a percentage of joint development costs based on sales (for example, 10%) and reflect this in the contract with the partner company, allowing both parties to share the profits.

[0932] In prototype testing and feedback gathering, partner companies create prototypes of the developed products and prepare them for market launch. Users use the prototypes and send feedback via LINE messages about their experience and areas for improvement. For example, specific opinions such as "the fabric should be a little softer" may be given. Communication terminals collect feedback messages from users and send them back to the server. The server analyzes the collected feedback again and provides the results to the partner companies. This allows the partner companies to obtain specific guidance for improving the prototypes.

[0933] This system utilizes LINE message data to grasp real-time consumer opinions and trends, enabling rapid and effective product development based on that information. Furthermore, by including user sentiment data, it allows for more accurate product development and marketing strategy formulation.

[0934] Example of a prompt:

[0935] "Please describe in natural language in detail a system that analyzes user sentiment towards fashion items on social media, identifies trends, and uses this information for product development."

[0936] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0937] Step 1:

[0938] Collection of message data

[0939] User: Users send and receive everyday messages using messaging apps such as LINE. In this process, users have given prior consent to data collection.

[0940] Input: The message that the user sends to the messaging app.

[0941] Output: The generated message is passed to the terminal.

[0942] Terminal operation: The terminal collects messages in a background process. Messages containing specific keywords or phrases are collected preferentially and prepared for encryption.

[0943] Step 2:

[0944] Data encryption and transmission

[0945] Terminal: The terminal encrypts the collected message data. The SSL / TLS protocol is used for this purpose.

[0946] Input: Collected message data.

[0947] Output: Encrypted message data is sent to the server.

[0948] Terminal operation: The terminal applies an encryption algorithm and prepares to encrypt the data and send it to the server. Specifically, it encrypts the data using the SSL / TLS protocol and sends it to the server through a secure communication circuit.

[0949] Step 3:

[0950] Data storage and anonymization

[0951] Server: The server stores the received encrypted data in a database and performs an anonymization process.

[0952] Input: Encrypted message data.

[0953] Output: Anonymized message data is stored in the database.

[0954] Server operation: The server extracts personally identifiable information and anonymizes the data through hashing and substitution operations. The data is stored in the database in a format that does not identify individuals.

[0955] Step 4:

[0956] Analysis using an emotion engine

[0957] Server: The server analyzes stored data using natural language processing (NLP) techniques.

[0958] Input: Anonymized message data.

[0959] Output: Analysis results related to the sentiment of the message.

[0960] Server operation: The server performs morphological analysis and extracts important information from messages through entity recognition. Then, it performs sentiment analysis and classifies the emotions expressed in the messages into categories such as "joy," "anger," and "sadness."

[0961] Step 5:

[0962] Trend Analysis

[0963] Server: The server extracts trends from the sentiment engine's results. It particularly identifies frequently occurring words related to apparel and keywords related to cooking and ingredients.

[0964] Input: Sentiment analysis results.

[0965] Output: Keywords and statistics related to the trend.

[0966] Server operation: The server extracts frequently occurring keywords from the analysis results and filters out noise data (irrelevant information). Then, it performs statistical analysis to evaluate the frequency and importance of each keyword and creates a trend report.

[0967] Step 6:

[0968] Formulating a product development strategy

[0969] Server: The server provides trend information and sentiment information to partner companies.

[0970] Input: Keywords and statistics related to the trend.

[0971] Output: Detailed analysis report and proposal.

[0972] Server operation: Based on the analysis results, the server generates detailed reports and proposals, which are then provided to partner companies via APIs and secure communication methods.

[0973] Step 7:

[0974] Revenue sharing settings

[0975] Server: Server sets the percentage of joint development costs based on sales and reflects this in contracts with partner companies.

[0976] Input: Sales information.

[0977] Output: Joint development cost setting information.

[0978] Server operation: Analyzes sales information, calculates joint development costs based on pre-set percentages, and reflects the results in the contract.

[0979] Step 8:

[0980] Prototype testing and feedback gathering

[0981] Partner companies: Partner companies create prototypes and prepare them for market launch.

[0982] User: Users use the prototype and submit feedback on their experience and areas for improvement.

[0983] Input: User feedback message.

[0984] Output: Collected feedback data.

[0985] Terminal operation: The terminal collects feedback messages sent by the user, encrypts them, and sends them to the server.

[0986] Server operation: The server analyzes the collected feedback and provides the results to partner companies to help improve the prototype.

[0987] (Application Example 2)

[0988] 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."

[0989] In recent years, there has been a growing demand for technologies that utilize the vast amount of message data generated via communication devices to accurately understand consumer sentiment and trends, and to use this information for product development. However, existing methods lack sufficient data analysis capabilities, making it difficult to respond quickly and accurately to consumer needs. Furthermore, there is a lack of means to improve the accuracy of personalized product recommendations. As a result, it is difficult to improve consumer satisfaction and achieve business growth.

[0990] 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.

[0991] In this invention, the server includes means for collecting message data generated by users from communication terminals, means for storing and analyzing the collected message data, means for analyzing the stored message data using natural language processing technology and extracting trends, means for providing the extracted trends to partner companies, means for formulating product development strategies in collaboration with partner companies, means for setting a certain percentage of sales obtained from the developed products as joint development costs, means for collecting user feedback and improving products based on that feedback, and means for generating and presenting personalized product suggestions to users based on the analysis results. This makes it possible to accurately grasp consumers' real-time emotions and trends, make product suggestions optimized for consumers, and achieve rapid and effective product development.

[0992] A "communication terminal" is a device used by users to generate message data and communicate.

[0993] "Message data" refers to data that includes text information and media content generated by users using communication devices.

[0994] "Storage" refers to the process of retaining collected data for a long period of time.

[0995] "Analysis" refers to the process of understanding the meaning and emotions of stored data using natural language processing techniques.

[0996] "Natural language processing technology" is a technique that uses computers to analyze human language and extract meaning and emotions.

[0997] A "trend" is a keyword or concept that indicates something or something that is supported by many users within a certain period of time.

[0998] A "partner company" is an external company that cooperates in product development based on data analysis results.

[0999] A "product development strategy" is a plan for effectively developing and providing products based on market needs and trends.

[1000] "A certain percentage of sales" refers to a predetermined percentage set out to distribute sales among the companies involved in the joint development project.

[1001] "Feedback" refers to opinions and requests regarding products and services provided by users.

[1002] "Personalized product recommendations" refer to products suggested based on the sentiment analysis results and trend data of individual users.

[1003] This invention is a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, and extracts trends based on that analysis to aid in product development. The main components of this system include a communication terminal, a server, and partner companies.

[1004] Collection of message data

[1005] User

[1006] Users routinely communicate through messaging apps using their own communication devices. Message data is collected only from users who have given prior consent to the system.

[1007] terminal

[1008] The device collects user message data in the background. Messages containing specific keywords or sentiments are prioritized for collection. The collected data is encrypted and sent to the server.

[1009] server

[1010] The server receives message data sent from communication terminals and stores it in a secure database. This data is anonymized, ensuring user privacy.

[1011] Analysis using an emotion engine

[1012] server

[1013] The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. Examples of NLP libraries used include spaCy and NLTK.

[1014] Emotional Engine

[1015] The emotion engine analyzes the user's emotions based on the analysis results and classifies each message into emotional categories such as "joy," "anger," and "sadness." For example, IBM Watson Tone Analyzer is used as an emotion engine.

[1016] Trend analysis and personalized product recommendations

[1017] server

[1018] The server extracts frequently occurring trending words based on the results of the sentiment engine. Keywords related to fashion, food, and lifestyle goods are particularly extracted.

[1019] Next, the server matches the extracted trending words with related product data to generate product suggestions optimized for the user. This results in personalized product recommendations being presented to the user.

[1020] Specific example

[1021] If a user sends a LINE message saying, "I've been really stressed lately," the emotion engine classifies this message as a "negative emotion." The server then extracts products based on trending words related to "stress reduction" and "relaxation," and suggests items such as "stress-reducing aroma diffusers" and "relaxation massage machines" to the user.

[1022] Example of a prompt

[1023] If a friend mentions feeling stressed lately during a conversation, recommend related relaxation products or stress-reducing items based on this message. Also, consider that the user is experiencing the emotion of "stress."

[1024] In this way, the present invention provides a system for acquiring real-time consumer opinions and trends and suggesting products suitable for users. This enables rapid and effective product development and the formulation of marketing strategies.

[1025] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1026] Step 1:

[1027] Collecting message data from users

[1028] The user uses a communication terminal to engage in everyday conversations and generate message data. The terminal collects this message data in the background. It receives the generated message data as input and encrypts it. The encrypted message data is obtained as output.

[1029] Step 2:

[1030] Encrypted data sent to the server

[1031] The terminal sends encrypted message data to the server. It takes encrypted message data as input and executes a process to send that data to the server. The output is the encrypted data stored on the server.

[1032] Step 3:

[1033] Data storage and preparation for analysis

[1034] The server stores the received encrypted message data in a database and prepares it for analysis. It takes the received encrypted data as input and stores it in the database. The stored data is then output.

[1035] Step 4:

[1036] Data analysis using Natural Language Processing (NLP)

[1037] The server retrieves message data stored in the database and performs analysis using natural language processing (NLP) techniques. It uses the message data retrieved from the database as input and performs NLP processing (morphological analysis, entity recognition, sentiment analysis). The output is the analyzed text data.

[1038] Step 5:

[1039] Emotional analysis using an emotion engine

[1040] The server uses NLP analysis results to run an emotion engine and classify the user's emotions. It uses NLP-analyzed data as input and runs it through an emotion engine (e.g., IBM Watson Tone Analyzer). The output is data categorized into emotion categories.

[1041] Step 6:

[1042] Extraction of trending words

[1043] The server extracts trending words based on sentiment analysis results. It uses sentiment-analyzed data as input to extract frequently occurring keywords and trending words. The output is a list of the extracted trending words.

[1044] Step 7:

[1045] Matching with the product database

[1046] The server matches the extracted trending keywords with the product database and selects relevant products. It uses the trending keyword list and the product database as input to search for products that match the keywords. The output is a personalized product list.

[1047] Step 8:

[1048] Generating and presenting personalized product suggestions

[1049] The server generates personalized product suggestions based on the selected products and presents them to the user's communication device. It uses a product list as input to generate recommended product messages. The output is the product suggestion message presented to the user.

[1050] This series of steps makes it possible to accurately grasp emotions and trends from user message data and provide product recommendations based on that.

[1051] 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.

[1052] 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.

[1053] 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.

[1054] [Third Embodiment]

[1055] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1056] 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.

[1057] 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).

[1058] 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.

[1059] 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.

[1060] 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).

[1061] 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.

[1062] 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.

[1063] 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.

[1064] 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.

[1065] 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.

[1066] 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".

[1067] This invention is a system that collects user message data from communication terminals, extracts trends based on that data, and uses them to aid in product development. This system consists of the user's communication terminal, a server that collects and analyzes the data, and a partner company that develops the product.

[1068] The system operates as follows:

[1069] Collection of message data

[1070] User

[1071] Users use their communication devices (smartphones and tablets) to conduct daily communication using LINE and other messaging apps. Users give prior consent to participate in the system and grant permission for data collection.

[1072] terminal

[1073] The device collects user-generated message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases.

[1074] server

[1075] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[1076] Trend Analysis

[1077] Next, we will perform a trend analysis.

[1078] server

[1079] The server applies natural language processing (NLP) techniques to the stored message data. This analyzes the meaning of the text data and extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, this will be recognized as a trend.

[1080] Data filtering and aggregation

[1081] The extracted data is further refined and analyzed.

[1082] server

[1083] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Next, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1084] Formulating a product development strategy

[1085] Based on the analysis results, we will develop specific products.

[1086] server

[1087] The server provides trend information to partner companies, including detailed analysis reports and proposals.

[1088] Partner companies

[1089] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[1090] Revenue sharing settings

[1091] We will establish a sales revenue sharing agreement for the jointly developed product.

[1092] server

[1093] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[1094] Prototype testing and feedback gathering

[1095] Partner companies

[1096] The partner company will create a prototype of the developed product and prepare it for market launch.

[1097] User

[1098] Users use the prototype and provide feedback via a communication device. For example, they might offer specific suggestions such as, "The fabric could be a little softer."

[1099] server

[1100] The server collects and analyzes feedback. The results are then provided back to partner companies to help improve the product.

[1101] This invention makes it possible to capture consumer preferences in real time and proceed with product development quickly and accurately, thereby enhancing market competitiveness.

[1102] The following describes the processing flow.

[1103] Step 1:

[1104] User

[1105] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[1106] Step 2:

[1107] terminal

[1108] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[1109] Step 3:

[1110] server

[1111] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[1112] Step 4:

[1113] server

[1114] The server analyzes the stored message data using natural language processing (NLP) techniques. Specifically, it utilizes techniques such as morphological analysis, entity recognition, and sentiment analysis to understand the meaning and sentiment of each data point.

[1115] Step 5:

[1116] server

[1117] The server extracts frequently occurring apparel-related words and keywords related to sweets and cooking from the analysis results. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, it will be recognized as a trend.

[1118] Step 6:

[1119] server

[1120] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1121] Step 7:

[1122] server

[1123] The server provides trend information to partner companies, including detailed analysis reports and proposals.

[1124] Step 8:

[1125] Partner companies

[1126] Partner companies hold internal product development meetings based on the trend information they receive. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, product design and manufacturing processes proceed.

[1127] Step 9:

[1128] server

[1129] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[1130] Step 10:

[1131] Partner companies

[1132] The partner company will create a prototype of the developed product and prepare it for market launch.

[1133] Step 11:

[1134] User

[1135] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[1136] Step 12:

[1137] terminal

[1138] The device collects feedback messages from users and sends them back to the server.

[1139] Step 13:

[1140] server

[1141] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes.

[1142] In this way, through a series of steps, LINE message data is utilized to grasp real-time consumer opinions and trends, enabling rapid and effective product development based on that information.

[1143] (Example 1)

[1144] 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."

[1145] In today's world, quickly and accurately understanding consumer preferences and trends is crucial for maintaining a competitive advantage. However, traditional systems have struggled to collect and analyze consumer interests and trends in real time and incorporate them into product development. Furthermore, there has been a lack of mechanisms to effectively collect feedback from consumers and utilize it for product improvement. As a result, companies have found it difficult to respond quickly to market trends, which could lead to a decline in competitiveness.

[1146] 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.

[1147] In this invention, the server includes means for collecting text message data generated by users from a communication device, means for storing and anonymizing the collected message data, means for analyzing the stored message data using natural language processing technology and extracting trends, means for filtering the recognized trends and retaining only highly reliable data, means for providing the extracted trends to partner companies, means for formulating product development strategies in collaboration with partner companies, means for setting a percentage of sales obtained from the developed product as joint development costs, and means for collecting user feedback and improving the product based on that feedback. This makes it possible to grasp user preferences and trends in real time and reflect them in product development quickly and accurately.

[1148] A "communication device" is a device used by users to generate and send text messages. This includes smartphones, tablets, and personal computers.

[1149] "User" refers to a person or individual who uses a communication device to generate text messages.

[1150] "Text message data" refers to character-based information generated and transmitted by users using communication devices. This includes the content sent in text messaging applications.

[1151] "Collection" refers to the process of obtaining text message data from a communication device and sending that data to a server.

[1152] "Saving" refers to the process of accumulating collected text message data in a database.

[1153] "Anonymization" is the process of removing personal information from collected text message data and transforming the data into a form that cannot be linked to an individual.

[1154] "Natural language processing technology" refers to the techniques that enable computers to understand and analyze human language. This includes algorithms for analyzing the meaning of text and performing syntactic and grammatical analysis.

[1155] "Trends" refer to frequently occurring keywords and phrases related to specific products or themes that emerge from the analysis of collected text message data.

[1156] "Filtering" is the process of removing noise from recognized trend data and selecting only meaningful data.

[1157] A "partner company" refers to a company or organization that collaborates with this system to develop products.

[1158] A "product development strategy" refers to the product development plan and policies formulated jointly with partner companies. This strategy is formulated based on analyzed trend information.

[1159] "Joint development costs" refer to expenses set as a certain percentage of the sales generated from the developed product. This is part of the compensation for the product developed through the collaboration between the system and partner companies.

[1160] "Feedback" refers to the opinions and impressions that users provide after using a developed product. This includes specific comments on areas for improvement and the user experience.

[1161] This invention is a system that collects text message data generated from users' communication devices, analyzes it to extract trends, and uses them for product development. This system consists of the user's communication device, a server that collects and analyzes the data, and partner companies that develop products.

[1162] Data collection

[1163] User actions

[1164] Users use their own communication devices (smartphones and tablets) to exchange text messages on a daily basis. Users themselves must consent to the handling of the collected data.

[1165] Terminal operation

[1166] The device collects user-generated text message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases, and the data is sent to the server in real time. For example, collection may be based on keyword lists such as "pistachio color" or "oversize."

[1167] Data storage and anonymization

[1168] Server Operations

[1169] The server receives message data sent from each terminal and stores it in a secure database. During this process, the collected data is anonymized to protect personal information. Data anonymity is ensured by replacing user IDs with random identifiers.

[1170] Trend Analysis

[1171] Server Operations

[1172] The semantic analysis of text is performed by applying natural language processing (NLP) techniques to the stored data. Techniques such as BERT (Bidirectional Encoder Representations from Transformers) are used in this process. Frequently occurring words are extracted and recognized as trends.

[1173] Data filtering and aggregation

[1174] Server Operations

[1175] From the analyzed trend data, noise is filtered out, and only meaningful data is retained. Statistical information is generated based on reliable trend data, and the frequency and importance of occurrences are evaluated.

[1176] Formulating a product development strategy

[1177] Server and partner company operations

[1178] The server provides trend information to partner companies, and together they formulate product development strategies. For example, a development project for a "pistachio-colored oversized sweater" might be launched.

[1179] Revenue sharing settings

[1180] Server Operations

[1181] The percentage of joint development costs will be determined based on the product's sales. For example, 10% of sales will be allocated as development costs and reflected in the contract.

[1182] Prototype testing and feedback gathering

[1183] Operation by partner companies

[1184] The partner company will create a prototype of the developed product and prepare it for market launch.

[1185] User actions

[1186] Users provide feedback via their devices using the prototypes. Specific feedback, such as "The fabric could be a little softer," is provided.

[1187] Server Operations

[1188] The server collects and analyzes user feedback. The results of the feedback are then provided back to partner companies to help improve the product.

[1189] Examples of specific cases and prompts for generative AI models.

[1190] Specific example

[1191] A message sent by a user to a friend on LINE, saying "Apparently pistachio-colored clothes are popular lately," is collected. This message is analyzed by a server, and the trending keyword "pistachio color" is extracted. Partner companies then proceed with product development based on this information.

[1192] Example of a prompt

[1193] "Please analyze recent trends regarding popular colors from messages sent by users on LINE."

[1194] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1195] Step 1: Prepare for data collection

[1196] User actions

[1197] Users use their communication devices to exchange text messages on a daily basis. Prior to this, they are prompted to grant permission for data collection, and they give their consent.

[1198] input

[1199] User permission and consent.

[1200] output

[1201] Data collection is ready.

[1202] Step 2: Collect message connections

[1203] Terminal operation

[1204] The device begins collecting user-generated text message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases (e.g., "pistachio color," "oversize"). The collected data is sent to the server in real time.

[1205] input

[1206] Text message data generated by the device.

[1207] Data processing

[1208] Filtering based on a keyword list.

[1209] output

[1210] Filtered message data is sent to the server.

[1211] Step 3: Data storage and anonymization

[1212] Server Operations

[1213] The server receives message data sent from each terminal and stores it in a secure database. Before storage, the data is anonymized and user IDs are replaced with random identifiers.

[1214] input

[1215] Message data sent from the device.

[1216] Data processing

[1217] Anonymization process (replacement of user IDs with random identifiers).

[1218] output

[1219] Anonymized message data is stored in a database.

[1220] Step 4: Trend Analysis

[1221] Server Operations

[1222] The server applies natural language processing (NLP) techniques to the stored message data to analyze the meaning of the text. Specifically, it uses methods such as BERT (Bidirectional Encoder Representations from Transformers). It extracts frequently occurring keywords and recognizes them as trends.

[1223] input

[1224] Anonymized message data.

[1225] Data processing

[1226] Text semantic analysis and keyword extraction using natural language processing technology.

[1227] output

[1228] Recognized trending keywords.

[1229] Step 5: Filtering and Aggregating Data

[1230] Server Operations

[1231] The server filters out noise data (irrelevant information) from the analyzed trend data, retaining only meaningful data. Next, it evaluates the frequency and importance of each keyword based on the aggregated results.

[1232] input

[1233] Recognized trending keywords.

[1234] Data processing

[1235] Filtering of noise data and aggregation of occurrence frequencies.

[1236] output

[1237] A list of trending keywords that have been evaluated.

[1238] Step 6: Formulate a product development strategy

[1239] Server and partner company operations

[1240] The server generates trend information as an analysis report and provides it to partner companies. Based on this information, partner companies hold product development meetings and formulate product development strategies. For example, a development project for a "pistachio-colored oversized sweater" might be launched.

[1241] input

[1242] A list of trending keywords that have been evaluated.

[1243] Data processing

[1244] Generation of analysis reports and proposals.

[1245] output

[1246] Formulating product development strategies and launching projects.

[1247] Step 7: Setting up revenue sharing

[1248] Server Operations

[1249] The server sets the percentage of joint development costs based on the sales of the developed product. For example, it might enter into an agreement with a partner company to distribute 10% of sales as development costs.

[1250] input

[1251] Product sales data.

[1252] Data processing

[1253] Calculation of the joint development cost ratio and its inclusion in the contract.

[1254] output

[1255] Revenue sharing setup complete.

[1256] Step 8: Test the prototype and gather feedback

[1257] Operation by partner companies

[1258] The partner company will create a prototype of the developed product and prepare it for market launch.

[1259] input

[1260] Product development strategy and design data.

[1261] Data processing

[1262] Prototype creation and test scenario development.

[1263] output

[1264] Prototype completed and testing begins.

[1265] User actions

[1266] Users use the prototype and provide feedback via a communication device. For example, they can send specific opinions such as, "The fabric could be a little softer."

[1267] input

[1268] Impressions of using the prototype.

[1269] Data processing

[1270] Gathering feedback and classifying specific opinions.

[1271] output

[1272] User feedback data.

[1273] Server Operations

[1274] The server collects and analyzes user feedback. The results are then provided back to partner companies to help improve the product.

[1275] input

[1276] User feedback data.

[1277] Data processing

[1278] Feedback analysis and identification of areas for improvement.

[1279] output

[1280] Feedback report for product improvement.

[1281] The above outlines the specific processing steps of this system. This system makes it possible to grasp user preferences and trends in real time and reflect them quickly and accurately in product development.

[1282] (Application Example 1)

[1283] 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."

[1284] Conventional trend extraction systems have difficulty reflecting user preferences in real time and are unable to respond to consumers' rapid purchasing intentions. Furthermore, they lack a mechanism to actively utilize the extracted trend information for product recommendations, making it difficult for end users to quickly and easily find specific products.

[1285] 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.

[1286] In this invention, the server includes means for collecting message data generated by users from communication terminals; means for storing and analyzing the collected message data; means for analyzing the stored message data using natural language processing technology and extracting trends; means for providing the extracted trends to partner companies; means for formulating product development strategies in collaboration with partner companies; means for setting a certain percentage of the sales obtained from the developed products as joint development costs; means for collecting user feedback and improving products based on that feedback; means for providing an application that recommends related products to users in real time based on trends; and means for providing users with links to purchase the recommended products. This enables product recommendations that quickly reflect user preferences, allowing consumers to intuitively and quickly discover and purchase related products.

[1287] A "communication terminal" is a device used to collect message data generated by users, and refers to smartphones, tablets, and other similar devices.

[1288] "Message data" refers to data such as text messages and chat content entered by users on their communication devices.

[1289] "Means of collection" refers to the technical means of capturing and storing message data from communication terminals.

[1290] "Means of preservation" refers to technical means for retaining collected message data over a long period of time.

[1291] "Means of analysis" refers to data processing techniques used to extract trends from stored message data.

[1292] "Natural language processing technology" refers to artificial intelligence and text analysis technologies used to analyze meaning from collected message data and extract trends.

[1293] "Trends" refer to keywords and phrases that frequently appear in message data, indicating tendencies that reflect consumer preferences.

[1294] "Partner companies" refer to companies that cooperate in product development based on collected trend information.

[1295] A "product development strategy" refers to a specific plan or policy for developing new products based on trend information.

[1296] "Joint development costs" refer to expenses that are shared between partner companies based on the sales of the developed product.

[1297] "Feedback" refers to the opinions and evaluations that users provide about prototypes or products.

[1298] "Improvement" refers to the act of enhancing the quality and functionality of a product based on collected feedback.

[1299] "Related products" refer to products suggested to users based on extracted trends.

[1300] "Real-time" refers to processing that occurs instantly without delay.

[1301] An "application" refers to software installed on a communication device that provides a specific function.

[1302] "To recommend" refers to the act of selecting and presenting products that match the user's preferences.

[1303] A "link" refers to a URL or button that a user can click to purchase a recommended product.

[1304] This invention relates to a system that collects message data from a user's communication terminal, performs analysis and trend extraction, and provides product recommendations based on those trends. This system is implemented using the following hardware and software.

[1305] The server first collects message data from the communication terminal. Users use messaging applications (e.g., LINE or WhatsApp) on their communication terminals to exchange messages on a daily basis. During the collection process, users must grant permission for data collection in advance.

[1306] Next, the collected message data is sent to a server and stored in a database. The data is anonymized to ensure the protection of personal information.

[1307] The server uses natural language processing (NLP) techniques to analyze the stored message data. For example, the Google Cloud Natural Language API can be used to perform semantic analysis on text data.

[1308] The analysis extracts frequently occurring keywords and phrases as trends. This trend information is further filtered to remove noise data. Only highly reliable trend keywords are retained during this process.

[1309] The server provides extracted trend information to partner companies, supporting them in formulating product development strategies. Based on the provided trends, partner companies hold product development meetings, and for example, a development project for a "pistachio-colored oversized sweater" might be launched.

[1310] Furthermore, the server provides an application that recommends relevant products to users in real time based on trend information. This application is installed on smartphones and presents recommended products based on trends extracted from the user's message data. Recommended products also include links that users can use to purchase them directly, enabling quick purchases.

[1311] For example, if a user sends a message saying, "I want a new pistachio-colored sweater," "pistachio color" will be extracted as a trending keyword from that message. Then, sweaters related to "pistachio color" will be searched for via the product recommendation API and recommended to the user. The user can then purchase the product directly by clicking on the recommended product link.

[1312] Examples of prompts to input into a generative AI model include the following:

[1313] User message: I want a new pistachio-colored sweater.

[1314] Extract trending keywords from this message and recommend related products.

[1315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1316] Step 1:

[1317] The device collects message data generated by the user. During this process, the device retrieves message data from the user in the background, prioritizing the collection of data containing specific keywords or phrases. The input is the user's message data, and the output is the collected raw message data.

[1318] Step 2:

[1319] The device sends the collected message data to the server. During transmission, the data is protected by end-to-end encryption and anonymized to protect personal information. The input is the message data collected by the device, and the output is the encrypted and anonymized message data.

[1320] Step 3:

[1321] The server stores received message data in a secure database. During this process, the data is anonymized, protecting the user's personal information. The input is encrypted and anonymized message data, and the output is the message data stored in the database.

[1322] Step 4:

[1323] The server performs natural language processing (NLP) techniques on the stored message data. Specifically, it uses the Google Cloud Natural Language API to perform semantic analysis of the text data. The input is message data stored in the database, and the output is extracted keywords and trending words.

[1324] Step 5:

[1325] The server generates trend information based on keywords extracted using natural language processing. Trends are identified by counting the frequency of the extracted keywords and evaluating their importance. The input is the extracted keywords, and the output is the generated trend information.

[1326] Step 6:

[1327] The server provides the generated trend information to partner companies. The information provided includes the frequency of trending words and detailed analysis reports. The input is the generated trend information, and the output is the analysis report sent to the partner company.

[1328] Step 7:

[1329] Partner companies formulate product development strategies based on the provided trend information. Product development meetings are held within the company, and specific product development projects are launched. The input is the provided trend information, and the output is the formulated product development strategy.

[1330] Step 8:

[1331] The server provides an application that recommends relevant products to users in real time based on trend information. This application is installed on smartphones. The input is trend information, and the output is recommended product information provided to the user.

[1332] Step 9:

[1333] The terminal displays links to recommended products for the user, allowing the user to purchase them directly by clicking the links. The input is recommended product information sent from the server, and the output is the product links displayed to the user.

[1334] Step 10:

[1335] Users purchase products using the provided links. Based on the user's purchase behavior, the overall system's effectiveness is evaluated, and feedback is sent to the server as needed. The input is the user's purchasing behavior, and the output is the post-purchase feedback.

[1336] Examples of prompts to input into a generative AI model:

[1337] User message: I want a new pistachio-colored sweater.

[1338] Extract trending keywords from this message and recommend related products.

[1339] 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.

[1340] This invention relates to a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, extracts trends based on that analysis, and utilizes them for product development. This system consists of a user's communication terminal, a server that collects and analyzes data, and a partner company that develops products.

[1341] The system operates as follows:

[1342] Collection of message data

[1343] User

[1344] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[1345] terminal

[1346] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[1347] server

[1348] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[1349] Analysis using an emotion engine

[1350] Next, we will perform emotion analysis using an emotion engine.

[1351] server

[1352] The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. This allows the server to understand the meaning and sentiment of the text data.

[1353] Emotional Engine

[1354] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[1355] Trend Analysis

[1356] Based on the sentiment analysis results, we will further analyze the trends in detail.

[1357] server

[1358] Based on the results of the emotion engine, the server extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, they will be recognized as a trend.

[1359] server

[1360] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1361] Formulating a product development strategy

[1362] Based on the analysis results, we will develop specific products.

[1363] server

[1364] The server provides trend and sentiment information to partner companies, including detailed analysis reports and proposals.

[1365] Partner companies

[1366] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[1367] Revenue sharing settings

[1368] We will establish a sales revenue sharing agreement for the jointly developed product.

[1369] server

[1370] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[1371] Prototype testing and feedback gathering

[1372] Partner companies

[1373] The partner company will create a prototype of the developed product and prepare it for market launch.

[1374] User

[1375] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[1376] terminal

[1377] The device collects feedback messages from users and sends them back to the server.

[1378] server

[1379] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes.

[1380] Through the steps described above, the present invention utilizes LINE message data to grasp consumers' real-time opinions and trends, and enables rapid and effective product development based on this information. Furthermore, by including user sentiment information, it becomes possible to formulate more accurate product development and marketing strategies.

[1381] The following describes the processing flow.

[1382] Step 1:

[1383] User

[1384] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[1385] Step 2:

[1386] terminal

[1387] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[1388] Step 3:

[1389] server

[1390] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[1391] Step 4:

[1392] server

[1393] The server performs natural language processing (NLP) techniques on the stored message data. This includes morphological analysis, entity recognition, and sentiment analysis. Through this analysis, it understands the meaning and sentiment of the text data.

[1394] Step 5:

[1395] Emotional Engine

[1396] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[1397] Step 6:

[1398] server

[1399] Based on the results of the emotion engine, the server extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, they will be recognized as a trend.

[1400] Step 7:

[1401] server

[1402] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1403] Step 8:

[1404] server

[1405] The server provides trend and sentiment information to partner companies. This includes detailed analysis reports and proposals. For example, it might provide information such as, "Users feel very happy with Basque cheesecake."

[1406] Step 9:

[1407] Partner companies

[1408] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[1409] Step 10:

[1410] server

[1411] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[1412] Step 11:

[1413] Partner companies

[1414] The partner company will create a prototype of the developed product and prepare it for market launch.

[1415] Step 12:

[1416] User

[1417] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[1418] Step 13:

[1419] terminal

[1420] The device collects feedback messages from users and sends them back to the server.

[1421] Step 14:

[1422] server

[1423] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes. For example, they might improve their product based on information that "soft fabrics are preferred."

[1424] Through the steps described above, the present invention utilizes LINE message data to grasp consumers' real-time opinions, trends, and emotional information, and enables rapid and effective product development based on this information. Furthermore, by including user emotional information, it becomes possible to formulate more accurate product development and marketing strategies.

[1425] (Example 2)

[1426] 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."

[1427] In recent years, there has been a growing demand to accurately capture consumer behavior and emotions and immediately reflect them in product development. However, traditional methods have fragmented the processes from data collection and sentiment analysis to trend extraction, product development strategy formulation, and market feedback collection, making real-time product development difficult. This has made it difficult to respond quickly to market needs and maintain competitiveness.

[1428] 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.

[1429] In this invention, the server includes means for encrypting collected message data and transmitting it to the server, means for storing and anonymizing the transmitted message data, and means for analyzing the stored message data using natural language processing technology to recognize emotions. This enables product development based on users' real-time emotions and trends, and the rapid reflection of feedback.

[1430] A "communication terminal" is a device used by a user to generate and send message data, and includes smartphones, tablets, personal computers, etc.

[1431] "Message data" refers to data such as text, images, audio, and video that users send and receive through their communication devices.

[1432] "Encryption" is the process of transforming message data using specific algorithms to protect it and prevent third parties from accessing it.

[1433] A "server" refers to a central system that receives, stores, analyzes, and manages data sent from users' communication terminals.

[1434] "Anonymization" is the process of removing personally identifiable information from message data so that personal information cannot be identified.

[1435] "Natural language processing technology" refers to the techniques that enable computers to understand, analyze, and generate human language, and includes morphological analysis, entity recognition, and sentiment analysis.

[1436] "Emotions" refer to psychological states such as "joy," "anger," "sadness," and "surprise" contained in the user's message data.

[1437] A "trend" refers to a specific tendency or fashion that is recognized based on the frequent appearance of certain keywords or phrases in a large number of messages, as determined by analyzed message data.

[1438] "Partner companies" refer to companies that develop products based on trend and sentiment information obtained using this system.

[1439] "Joint development costs" refer to a certain percentage of sales generated from the developed product, and are development costs shared with partner companies.

[1440] "Feedback" refers to specific opinions and evaluations, such as user experience and areas for improvement, provided by users after using a prototype.

[1441] This invention relates to a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, extracts trends based on that analysis, and utilizes them for product development. This system consists of a user's communication terminal, a server that collects and analyzes data, and a partner company that develops products.

[1442] Users use their communication devices to exchange messages daily using LINE and other messaging apps. Users consent in advance to participate in this system and allow the collection of message data. The communication device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is encrypted and prepared for transmission to the server. Protocols such as SSL / TLS are used for encryption.

[1443] The server receives message data sent from each communication terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information. The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. This allows for an understanding of the meaning and sentiment of the text data.

[1444] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[1445] As part of trend analysis, the server extracts frequently occurring apparel-related words and keywords related to food ingredients and cooking based on the results of the sentiment engine. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in numerous messages, it is recognized as a trend. The server improves data accuracy by filtering out noise data (meaningless information) and retaining only highly reliable keywords. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1446] In formulating product development strategies, the server provides partner companies with trend and sentiment information. This includes detailed analysis reports and proposals. Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. The partner companies then proceed with specific design and manufacturing processes.

[1447] When setting up revenue sharing, the server can set a percentage of joint development costs based on sales (for example, 10%) and reflect this in the contract with the partner company, allowing both parties to share the profits.

[1448] In prototype testing and feedback gathering, partner companies create prototypes of the developed products and prepare them for market launch. Users use the prototypes and send feedback via LINE messages about their experience and areas for improvement. For example, specific opinions such as "the fabric should be a little softer" may be given. Communication terminals collect feedback messages from users and send them back to the server. The server analyzes the collected feedback again and provides the results to the partner companies. This allows the partner companies to obtain specific guidance for improving the prototypes.

[1449] This system utilizes LINE message data to grasp real-time consumer opinions and trends, enabling rapid and effective product development based on that information. Furthermore, by including user sentiment data, it allows for more accurate product development and marketing strategy formulation.

[1450] Example of a prompt:

[1451] "Please describe in natural language in detail a system that analyzes user sentiment towards fashion items on social media, identifies trends, and uses this information for product development."

[1452] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1453] Step 1:

[1454] Collection of message data

[1455] User: Users send and receive everyday messages using messaging apps such as LINE. In this process, users have given prior consent to data collection.

[1456] Input: The message that the user sends to the messaging app.

[1457] Output: The generated message is passed to the terminal.

[1458] Terminal operation: The terminal collects messages in a background process. Messages containing specific keywords or phrases are collected preferentially and prepared for encryption.

[1459] Step 2:

[1460] Data encryption and transmission

[1461] Terminal: The terminal encrypts the collected message data. The SSL / TLS protocol is used for this purpose.

[1462] Input: Collected message data.

[1463] Output: Encrypted message data is sent to the server.

[1464] Terminal operation: The terminal applies an encryption algorithm and prepares to encrypt the data and send it to the server. Specifically, it encrypts the data using the SSL / TLS protocol and sends it to the server through a secure communication circuit.

[1465] Step 3:

[1466] Data storage and anonymization

[1467] Server: The server stores the received encrypted data in a database and performs an anonymization process.

[1468] Input: Encrypted message data.

[1469] Output: Anonymized message data is stored in the database.

[1470] Server operation: The server extracts personally identifiable information and anonymizes the data through hashing and substitution operations. The data is stored in the database in a format that does not identify individuals.

[1471] Step 4:

[1472] Analysis using an emotion engine

[1473] Server: The server analyzes stored data using natural language processing (NLP) techniques.

[1474] Input: Anonymized message data.

[1475] Output: Analysis results related to the sentiment of the message.

[1476] Server operation: The server performs morphological analysis and extracts important information from messages through entity recognition. Then, it performs sentiment analysis and classifies the emotions expressed in the messages into categories such as "joy," "anger," and "sadness."

[1477] Step 5:

[1478] Trend Analysis

[1479] Server: The server extracts trends from the sentiment engine's results. It particularly identifies frequently occurring words related to apparel and keywords related to cooking and ingredients.

[1480] Input: Sentiment analysis results.

[1481] Output: Keywords and statistics related to the trend.

[1482] Server operation: The server extracts frequently occurring keywords from the analysis results and filters out noise data (irrelevant information). Then, it performs statistical analysis to evaluate the frequency and importance of each keyword and creates a trend report.

[1483] Step 6:

[1484] Formulating a product development strategy

[1485] Server: The server provides trend information and sentiment information to partner companies.

[1486] Input: Keywords and statistics related to the trend.

[1487] Output: Detailed analysis report and proposal.

[1488] Server operation: Based on the analysis results, the server generates detailed reports and proposals, which are then provided to partner companies via APIs and secure communication methods.

[1489] Step 7:

[1490] Revenue sharing settings

[1491] Server: Server sets the percentage of joint development costs based on sales and reflects this in contracts with partner companies.

[1492] Input: Sales information.

[1493] Output: Joint development cost setting information.

[1494] Server operation: Analyzes sales information, calculates joint development costs based on pre-set percentages, and reflects the results in the contract.

[1495] Step 8:

[1496] Prototype testing and feedback gathering

[1497] Partner companies: Partner companies create prototypes and prepare them for market launch.

[1498] User: Users use the prototype and submit feedback on their experience and areas for improvement.

[1499] Input: User feedback message.

[1500] Output: Collected feedback data.

[1501] Terminal operation: The terminal collects feedback messages sent by the user, encrypts them, and sends them to the server.

[1502] Server operation: The server analyzes the collected feedback and provides the results to partner companies to help improve the prototype.

[1503] (Application Example 2)

[1504] 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."

[1505] In recent years, there has been a growing demand for technologies that utilize the vast amount of message data generated via communication devices to accurately understand consumer sentiment and trends, and to use this information for product development. However, existing methods lack sufficient data analysis capabilities, making it difficult to respond quickly and accurately to consumer needs. Furthermore, there is a lack of means to improve the accuracy of personalized product recommendations. As a result, it is difficult to improve consumer satisfaction and achieve business growth.

[1506] 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.

[1507] In this invention, the server includes means for collecting message data generated by users from communication terminals, means for storing and analyzing the collected message data, means for analyzing the stored message data using natural language processing technology and extracting trends, means for providing the extracted trends to partner companies, means for formulating product development strategies in collaboration with partner companies, means for setting a certain percentage of sales obtained from the developed products as joint development costs, means for collecting user feedback and improving products based on that feedback, and means for generating and presenting personalized product suggestions to users based on the analysis results. This makes it possible to accurately grasp consumers' real-time emotions and trends, make product suggestions optimized for consumers, and achieve rapid and effective product development.

[1508] A "communication terminal" is a device used by users to generate message data and communicate.

[1509] "Message data" refers to data that includes text information and media content generated by users using communication devices.

[1510] "Storage" refers to the process of retaining collected data for a long period of time.

[1511] "Analysis" refers to the process of understanding the meaning and emotions of stored data using natural language processing techniques.

[1512] "Natural language processing technology" is a technique that uses computers to analyze human language and extract meaning and emotions.

[1513] A "trend" is a keyword or concept that indicates something or something that is supported by many users within a certain period of time.

[1514] A "partner company" is an external company that cooperates in product development based on data analysis results.

[1515] A "product development strategy" is a plan for effectively developing and providing products based on market needs and trends.

[1516] "A certain percentage of sales" refers to a predetermined percentage set out to distribute sales among the companies involved in the joint development project.

[1517] "Feedback" refers to opinions and requests regarding products and services provided by users.

[1518] "Personalized product recommendations" refer to products suggested based on the sentiment analysis results and trend data of individual users.

[1519] This invention is a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, and extracts trends based on that analysis to aid in product development. The main components of this system include a communication terminal, a server, and partner companies.

[1520] Collection of message data

[1521] User

[1522] Users routinely communicate through messaging apps using their own communication devices. Message data is collected only from users who have given prior consent to the system.

[1523] terminal

[1524] The device collects user message data in the background. Messages containing specific keywords or sentiments are prioritized for collection. The collected data is encrypted and sent to the server.

[1525] server

[1526] The server receives message data sent from communication terminals and stores it in a secure database. This data is anonymized, ensuring user privacy.

[1527] Analysis using an emotion engine

[1528] server

[1529] The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. Examples of NLP libraries used include spaCy and NLTK.

[1530] Emotional Engine

[1531] The emotion engine analyzes the user's emotions based on the analysis results and classifies each message into emotional categories such as "joy," "anger," and "sadness." For example, IBM Watson Tone Analyzer is used as an emotion engine.

[1532] Trend analysis and personalized product recommendations

[1533] server

[1534] The server extracts frequently occurring trending words based on the results of the sentiment engine. Keywords related to fashion, food, and lifestyle goods are particularly extracted.

[1535] Next, the server matches the extracted trending words with related product data to generate product suggestions optimized for the user. This results in personalized product recommendations being presented to the user.

[1536] Specific example

[1537] If a user sends a LINE message saying, "I've been really stressed lately," the emotion engine classifies this message as a "negative emotion." The server then extracts products based on trending words related to "stress reduction" and "relaxation," and suggests items such as "stress-reducing aroma diffusers" and "relaxation massage machines" to the user.

[1538] Example of a prompt

[1539] If a friend mentions feeling stressed lately during a conversation, recommend related relaxation products or stress-reducing items based on this message. Also, consider that the user is experiencing the emotion of "stress."

[1540] In this way, the present invention provides a system for acquiring real-time consumer opinions and trends and suggesting products suitable for users. This enables rapid and effective product development and the formulation of marketing strategies.

[1541] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1542] Step 1:

[1543] Collecting message data from users

[1544] The user uses a communication terminal to engage in everyday conversations and generate message data. The terminal collects this message data in the background. It receives the generated message data as input and encrypts it. The encrypted message data is obtained as output.

[1545] Step 2:

[1546] Encrypted data sent to the server

[1547] The terminal sends encrypted message data to the server. It takes encrypted message data as input and executes a process to send that data to the server. The output is the encrypted data stored on the server.

[1548] Step 3:

[1549] Data storage and preparation for analysis

[1550] The server stores the received encrypted message data in a database and prepares it for analysis. It takes the received encrypted data as input and stores it in the database. The stored data is then output.

[1551] Step 4:

[1552] Data analysis using Natural Language Processing (NLP)

[1553] The server retrieves message data stored in the database and performs analysis using natural language processing (NLP) techniques. It uses the message data retrieved from the database as input and performs NLP processing (morphological analysis, entity recognition, sentiment analysis). The output is the analyzed text data.

[1554] Step 5:

[1555] Emotional analysis using an emotion engine

[1556] The server uses NLP analysis results to run an emotion engine and classify the user's emotions. It uses NLP-analyzed data as input and runs it through an emotion engine (e.g., IBM Watson Tone Analyzer). The output is data categorized into emotion categories.

[1557] Step 6:

[1558] Extraction of trending words

[1559] The server extracts trending words based on sentiment analysis results. It uses sentiment-analyzed data as input to extract frequently occurring keywords and trending words. The output is a list of the extracted trending words.

[1560] Step 7:

[1561] Matching with the product database

[1562] The server matches the extracted trending keywords with the product database and selects relevant products. It uses the trending keyword list and the product database as input to search for products that match the keywords. The output is a personalized product list.

[1563] Step 8:

[1564] Generating and presenting personalized product suggestions

[1565] The server generates personalized product suggestions based on the selected products and presents them to the user's communication device. It uses a product list as input to generate recommended product messages. The output is the product suggestion message presented to the user.

[1566] This series of steps makes it possible to accurately grasp emotions and trends from user message data and provide product recommendations based on that.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] [Fourth Embodiment]

[1571] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1572] 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.

[1573] 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).

[1574] 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.

[1575] 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.

[1576] 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).

[1577] 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.

[1578] 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.

[1579] 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.

[1580] 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.

[1581] 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.

[1582] 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.

[1583] 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".

[1584] This invention is a system that collects user message data from communication terminals, extracts trends based on that data, and uses them to aid in product development. This system consists of the user's communication terminal, a server that collects and analyzes the data, and a partner company that develops the product.

[1585] The system operates as follows:

[1586] Collection of message data

[1587] User

[1588] Users use their communication devices (smartphones and tablets) to conduct daily communication using LINE and other messaging apps. Users give prior consent to participate in the system and grant permission for data collection.

[1589] terminal

[1590] The device collects user-generated message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases.

[1591] server

[1592] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[1593] Trend Analysis

[1594] Next, we will perform a trend analysis.

[1595] server

[1596] The server applies natural language processing (NLP) techniques to the stored message data. This analyzes the meaning of the text data and extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, this will be recognized as a trend.

[1597] Data filtering and aggregation

[1598] The extracted data is further refined and analyzed.

[1599] server

[1600] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Next, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1601] Formulating a product development strategy

[1602] Based on the analysis results, we will develop specific products.

[1603] server

[1604] The server provides trend information to partner companies, including detailed analysis reports and proposals.

[1605] Partner companies

[1606] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[1607] Revenue sharing settings

[1608] We will establish a sales revenue sharing agreement for the jointly developed product.

[1609] server

[1610] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[1611] Prototype testing and feedback gathering

[1612] Partner companies

[1613] The partner company will create a prototype of the developed product and prepare it for market launch.

[1614] User

[1615] Users use the prototype and provide feedback via a communication device. For example, they might offer specific suggestions such as, "The fabric could be a little softer."

[1616] server

[1617] The server collects and analyzes feedback. The results are then provided back to partner companies to help improve the product.

[1618] This invention makes it possible to capture consumer preferences in real time and proceed with product development quickly and accurately, thereby enhancing market competitiveness.

[1619] The following describes the processing flow.

[1620] Step 1:

[1621] User

[1622] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[1623] Step 2:

[1624] terminal

[1625] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[1626] Step 3:

[1627] server

[1628] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[1629] Step 4:

[1630] server

[1631] The server analyzes the stored message data using natural language processing (NLP) techniques. Specifically, it utilizes techniques such as morphological analysis, entity recognition, and sentiment analysis to understand the meaning and sentiment of each data point.

[1632] Step 5:

[1633] server

[1634] The server extracts frequently occurring apparel-related words and keywords related to sweets and cooking from the analysis results. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, it will be recognized as a trend.

[1635] Step 6:

[1636] server

[1637] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1638] Step 7:

[1639] server

[1640] The server provides trend information to partner companies, including detailed analysis reports and proposals.

[1641] Step 8:

[1642] Partner companies

[1643] Partner companies hold internal product development meetings based on the trend information they receive. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, product design and manufacturing processes proceed.

[1644] Step 9:

[1645] server

[1646] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[1647] Step 10:

[1648] Partner companies

[1649] The partner company will create a prototype of the developed product and prepare it for market launch.

[1650] Step 11:

[1651] User

[1652] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[1653] Step 12:

[1654] terminal

[1655] The device collects feedback messages from users and sends them back to the server.

[1656] Step 13:

[1657] server

[1658] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes.

[1659] In this way, through a series of steps, LINE message data is utilized to grasp real-time consumer opinions and trends, enabling rapid and effective product development based on that information.

[1660] (Example 1)

[1661] 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".

[1662] In today's world, quickly and accurately understanding consumer preferences and trends is crucial for maintaining a competitive advantage. However, traditional systems have struggled to collect and analyze consumer interests and trends in real time and incorporate them into product development. Furthermore, there has been a lack of mechanisms to effectively collect feedback from consumers and utilize it for product improvement. As a result, companies have found it difficult to respond quickly to market trends, which could lead to a decline in competitiveness.

[1663] 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.

[1664] In this invention, the server includes means for collecting text message data generated by users from a communication device, means for storing and anonymizing the collected message data, means for analyzing the stored message data using natural language processing technology and extracting trends, means for filtering the recognized trends and retaining only highly reliable data, means for providing the extracted trends to partner companies, means for formulating product development strategies in collaboration with partner companies, means for setting a percentage of sales obtained from the developed product as joint development costs, and means for collecting user feedback and improving the product based on that feedback. This makes it possible to grasp user preferences and trends in real time and reflect them in product development quickly and accurately.

[1665] A "communication device" is a device used by users to generate and send text messages. This includes smartphones, tablets, and personal computers.

[1666] "User" refers to a person or individual who uses a communication device to generate text messages.

[1667] "Text message data" refers to character-based information generated and transmitted by users using communication devices. This includes the content sent in text messaging applications.

[1668] "Collection" refers to the process of obtaining text message data from a communication device and sending that data to a server.

[1669] "Saving" refers to the process of accumulating collected text message data in a database.

[1670] "Anonymization" is the process of removing personal information from collected text message data and transforming the data into a form that cannot be linked to an individual.

[1671] "Natural language processing technology" refers to the techniques that enable computers to understand and analyze human language. This includes algorithms for analyzing the meaning of text and performing syntactic and grammatical analysis.

[1672] "Trends" refer to frequently occurring keywords and phrases related to specific products or themes that emerge from the analysis of collected text message data.

[1673] "Filtering" is the process of removing noise from recognized trend data and selecting only meaningful data.

[1674] A "partner company" refers to a company or organization that collaborates with this system to develop products.

[1675] A "product development strategy" refers to the product development plan and policies formulated jointly with partner companies. This strategy is formulated based on analyzed trend information.

[1676] "Joint development costs" refer to expenses set as a certain percentage of the sales generated from the developed product. This is part of the compensation for the product developed through the collaboration between the system and partner companies.

[1677] "Feedback" refers to the opinions and impressions that users provide after using a developed product. This includes specific comments on areas for improvement and the user experience.

[1678] This invention is a system that collects text message data generated from users' communication devices, analyzes it to extract trends, and uses them for product development. This system consists of the user's communication device, a server that collects and analyzes the data, and partner companies that develop products.

[1679] Data collection

[1680] User actions

[1681] Users use their own communication devices (smartphones and tablets) to exchange text messages on a daily basis. Users themselves must consent to the handling of the collected data.

[1682] Terminal operation

[1683] The device collects user-generated text message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases, and the data is sent to the server in real time. For example, collection may be based on keyword lists such as "pistachio color" or "oversize."

[1684] Data storage and anonymization

[1685] Server Operations

[1686] The server receives message data sent from each terminal and stores it in a secure database. During this process, the collected data is anonymized to protect personal information. Data anonymity is ensured by replacing user IDs with random identifiers.

[1687] Trend Analysis

[1688] Server Operations

[1689] The semantic analysis of text is performed by applying natural language processing (NLP) techniques to the stored data. Techniques such as BERT (Bidirectional Encoder Representations from Transformers) are used in this process. Frequently occurring words are extracted and recognized as trends.

[1690] Data filtering and aggregation

[1691] Server Operations

[1692] From the analyzed trend data, noise is filtered out, and only meaningful data is retained. Statistical information is generated based on reliable trend data, and the frequency and importance of occurrences are evaluated.

[1693] Formulating a product development strategy

[1694] Server and partner company operations

[1695] The server provides trend information to partner companies, and together they formulate product development strategies. For example, a development project for a "pistachio-colored oversized sweater" might be launched.

[1696] Revenue sharing settings

[1697] Server Operations

[1698] The percentage of joint development costs will be determined based on the product's sales. For example, 10% of sales will be allocated as development costs and reflected in the contract.

[1699] Prototype testing and feedback gathering

[1700] Operation by partner companies

[1701] The partner company will create a prototype of the developed product and prepare it for market launch.

[1702] User actions

[1703] Users provide feedback via their devices using the prototypes. Specific feedback, such as "The fabric could be a little softer," is provided.

[1704] Server Operations

[1705] The server collects and analyzes user feedback. The results of the feedback are then provided back to partner companies to help improve the product.

[1706] Examples of specific cases and prompts for generative AI models.

[1707] Specific example

[1708] A message sent by a user to a friend on LINE, saying "Apparently pistachio-colored clothes are popular lately," is collected. This message is analyzed by a server, and the trending keyword "pistachio color" is extracted. Partner companies then proceed with product development based on this information.

[1709] Example of a prompt

[1710] "Please analyze recent trends regarding popular colors from messages sent by users on LINE."

[1711] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1712] Step 1: Prepare for data collection

[1713] User actions

[1714] Users use their communication devices to exchange text messages on a daily basis. Prior to this, they are prompted to grant permission for data collection, and they give their consent.

[1715] input

[1716] User permission and consent.

[1717] output

[1718] Data collection is ready.

[1719] Step 2: Collect message connections

[1720] Terminal operation

[1721] The device begins collecting user-generated text message data in the background. It is configured to prioritize the collection of data containing specific keywords or phrases (e.g., "pistachio color," "oversize"). The collected data is sent to the server in real time.

[1722] input

[1723] Text message data generated by the device.

[1724] Data processing

[1725] Filtering based on a keyword list.

[1726] output

[1727] Filtered message data is sent to the server.

[1728] Step 3: Data storage and anonymization

[1729] Server Operations

[1730] The server receives message data sent from each terminal and stores it in a secure database. Before storage, the data is anonymized and user IDs are replaced with random identifiers.

[1731] input

[1732] Message data sent from the device.

[1733] Data processing

[1734] Anonymization process (replacement of user IDs with random identifiers).

[1735] output

[1736] Anonymized message data is stored in a database.

[1737] Step 4: Trend Analysis

[1738] Server Operations

[1739] The server applies natural language processing (NLP) techniques to the stored message data to analyze the meaning of the text. Specifically, it uses methods such as BERT (Bidirectional Encoder Representations from Transformers). It extracts frequently occurring keywords and recognizes them as trends.

[1740] input

[1741] Anonymized message data.

[1742] Data processing

[1743] Text semantic analysis and keyword extraction using natural language processing technology.

[1744] output

[1745] Recognized trending keywords.

[1746] Step 5: Filtering and Aggregating Data

[1747] Server Operations

[1748] The server filters out noise data (irrelevant information) from the analyzed trend data, retaining only meaningful data. Next, it evaluates the frequency and importance of each keyword based on the aggregated results.

[1749] input

[1750] Recognized trending keywords.

[1751] Data processing

[1752] Filtering of noise data and aggregation of occurrence frequencies.

[1753] output

[1754] A list of trending keywords that have been evaluated.

[1755] Step 6: Formulate a product development strategy

[1756] Server and partner company operations

[1757] The server generates trend information as an analysis report and provides it to partner companies. Based on this information, partner companies hold product development meetings and formulate product development strategies. For example, a development project for a "pistachio-colored oversized sweater" might be launched.

[1758] input

[1759] A list of trending keywords that have been evaluated.

[1760] Data processing

[1761] Generation of analysis reports and proposals.

[1762] output

[1763] Formulating product development strategies and launching projects.

[1764] Step 7: Setting up revenue sharing

[1765] Server Operations

[1766] The server sets the percentage of joint development costs based on the sales of the developed product. For example, it might enter into an agreement with a partner company to distribute 10% of sales as development costs.

[1767] input

[1768] Product sales data.

[1769] Data processing

[1770] Calculation of the joint development cost ratio and its inclusion in the contract.

[1771] output

[1772] Revenue sharing setup complete.

[1773] Step 8: Test the prototype and gather feedback

[1774] Operation by partner companies

[1775] The partner company will create a prototype of the developed product and prepare it for market launch.

[1776] input

[1777] Product development strategy and design data.

[1778] Data processing

[1779] Prototype creation and test scenario development.

[1780] output

[1781] Prototype completed and testing begins.

[1782] User actions

[1783] Users use the prototype and provide feedback via a communication device. For example, they can send specific opinions such as, "The fabric could be a little softer."

[1784] input

[1785] Impressions of using the prototype.

[1786] Data processing

[1787] Gathering feedback and classifying specific opinions.

[1788] output

[1789] User feedback data.

[1790] Server Operations

[1791] The server collects and analyzes user feedback. The results are then provided back to partner companies to help improve the product.

[1792] input

[1793] User feedback data.

[1794] Data processing

[1795] Feedback analysis and identification of areas for improvement.

[1796] output

[1797] Feedback report for product improvement.

[1798] The above outlines the specific processing steps of this system. This system makes it possible to grasp user preferences and trends in real time and reflect them quickly and accurately in product development.

[1799] (Application Example 1)

[1800] 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".

[1801] Conventional trend extraction systems have difficulty reflecting user preferences in real time and are unable to respond to consumers' rapid purchasing intentions. Furthermore, they lack a mechanism to actively utilize the extracted trend information for product recommendations, making it difficult for end users to quickly and easily find specific products.

[1802] 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.

[1803] In this invention, the server includes means for collecting message data generated by users from communication terminals; means for storing and analyzing the collected message data; means for analyzing the stored message data using natural language processing technology and extracting trends; means for providing the extracted trends to partner companies; means for formulating product development strategies in collaboration with partner companies; means for setting a certain percentage of the sales obtained from the developed products as joint development costs; means for collecting user feedback and improving products based on that feedback; means for providing an application that recommends related products to users in real time based on trends; and means for providing users with links to purchase the recommended products. This enables product recommendations that quickly reflect user preferences, allowing consumers to intuitively and quickly discover and purchase related products.

[1804] A "communication terminal" is a device used to collect message data generated by users, and refers to smartphones, tablets, and other similar devices.

[1805] "Message data" refers to data such as text messages and chat content entered by users on their communication devices.

[1806] "Means of collection" refers to the technical means of capturing and storing message data from communication terminals.

[1807] "Means of preservation" refers to technical means for retaining collected message data over a long period of time.

[1808] "Means of analysis" refers to data processing techniques used to extract trends from stored message data.

[1809] "Natural language processing technology" refers to artificial intelligence and text analysis technologies used to analyze meaning from collected message data and extract trends.

[1810] "Trends" refer to keywords and phrases that frequently appear in message data, indicating tendencies that reflect consumer preferences.

[1811] "Partner companies" refer to companies that cooperate in product development based on collected trend information.

[1812] A "product development strategy" refers to a specific plan or policy for developing new products based on trend information.

[1813] "Joint development costs" refer to expenses that are shared between partner companies based on the sales of the developed product.

[1814] "Feedback" refers to the opinions and evaluations that users provide about prototypes or products.

[1815] "Improvement" refers to the act of enhancing the quality and functionality of a product based on collected feedback.

[1816] "Related products" refer to products suggested to users based on extracted trends.

[1817] "Real-time" refers to processing that occurs instantly without delay.

[1818] An "application" refers to software installed on a communication device that provides a specific function.

[1819] "To recommend" refers to the act of selecting and presenting products that match the user's preferences.

[1820] A "link" refers to a URL or button that a user can click to purchase a recommended product.

[1821] This invention relates to a system that collects message data from a user's communication terminal, performs analysis and trend extraction, and provides product recommendations based on those trends. This system is implemented using the following hardware and software.

[1822] The server first collects message data from the communication terminal. Users use messaging applications (e.g., LINE or WhatsApp) on their communication terminals to exchange messages on a daily basis. During the collection process, users must grant permission for data collection in advance.

[1823] Next, the collected message data is sent to a server and stored in a database. The data is anonymized to ensure the protection of personal information.

[1824] The server uses natural language processing (NLP) techniques to analyze the stored message data. For example, the Google Cloud Natural Language API can be used to perform semantic analysis on text data.

[1825] The analysis extracts frequently occurring keywords and phrases as trends. This trend information is further filtered to remove noise data. Only highly reliable trend keywords are retained during this process.

[1826] The server provides extracted trend information to partner companies, supporting them in formulating product development strategies. Based on the provided trends, partner companies hold product development meetings, and for example, a development project for a "pistachio-colored oversized sweater" might be launched.

[1827] Furthermore, the server provides an application that recommends relevant products to users in real time based on trend information. This application is installed on smartphones and presents recommended products based on trends extracted from the user's message data. Recommended products also include links that users can use to purchase them directly, enabling quick purchases.

[1828] For example, if a user sends a message saying, "I want a new pistachio-colored sweater," "pistachio color" will be extracted as a trending keyword from that message. Then, sweaters related to "pistachio color" will be searched for via the product recommendation API and recommended to the user. The user can then purchase the product directly by clicking on the recommended product link.

[1829] Examples of prompts to input into a generative AI model include the following:

[1830] User message: I want a new pistachio-colored sweater.

[1831] Extract trending keywords from this message and recommend related products.

[1832] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1833] Step 1:

[1834] The device collects message data generated by the user. During this process, the device retrieves message data from the user in the background, prioritizing the collection of data containing specific keywords or phrases. The input is the user's message data, and the output is the collected raw message data.

[1835] Step 2:

[1836] The device sends the collected message data to the server. During transmission, the data is protected by end-to-end encryption and anonymized to protect personal information. The input is the message data collected by the device, and the output is the encrypted and anonymized message data.

[1837] Step 3:

[1838] The server stores received message data in a secure database. During this process, the data is anonymized, protecting the user's personal information. The input is encrypted and anonymized message data, and the output is the message data stored in the database.

[1839] Step 4:

[1840] The server performs natural language processing (NLP) techniques on the stored message data. Specifically, it uses the Google Cloud Natural Language API to perform semantic analysis of the text data. The input is message data stored in the database, and the output is extracted keywords and trending words.

[1841] Step 5:

[1842] The server generates trend information based on keywords extracted using natural language processing. Trends are identified by counting the frequency of the extracted keywords and evaluating their importance. The input is the extracted keywords, and the output is the generated trend information.

[1843] Step 6:

[1844] The server provides the generated trend information to partner companies. The information provided includes the frequency of trending words and detailed analysis reports. The input is the generated trend information, and the output is the analysis report sent to the partner company.

[1845] Step 7:

[1846] Partner companies formulate product development strategies based on the provided trend information. Product development meetings are held within the company, and specific product development projects are launched. The input is the provided trend information, and the output is the formulated product development strategy.

[1847] Step 8:

[1848] The server provides an application that recommends relevant products to users in real time based on trend information. This application is installed on smartphones. The input is trend information, and the output is recommended product information provided to the user.

[1849] Step 9:

[1850] The terminal displays links to recommended products for the user, allowing the user to purchase them directly by clicking the links. The input is recommended product information sent from the server, and the output is the product links displayed to the user.

[1851] Step 10:

[1852] Users purchase products using the provided links. Based on the user's purchase behavior, the overall system's effectiveness is evaluated, and feedback is sent to the server as needed. The input is the user's purchasing behavior, and the output is the post-purchase feedback.

[1853] Examples of prompts to input into a generative AI model:

[1854] User message: I want a new pistachio-colored sweater.

[1855] Extract trending keywords from this message and recommend related products.

[1856] 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.

[1857] This invention relates to a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, extracts trends based on that analysis, and utilizes them for product development. This system consists of a user's communication terminal, a server that collects and analyzes data, and a partner company that develops products.

[1858] The system operates as follows:

[1859] Collection of message data

[1860] User

[1861] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[1862] terminal

[1863] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[1864] server

[1865] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[1866] Analysis using an emotion engine

[1867] Next, we will perform emotion analysis using an emotion engine.

[1868] server

[1869] The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. This allows the server to understand the meaning and sentiment of the text data.

[1870] Emotional Engine

[1871] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[1872] Trend Analysis

[1873] Based on the sentiment analysis results, we will further analyze the trends in detail.

[1874] server

[1875] Based on the results of the emotion engine, the server extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, they will be recognized as a trend.

[1876] server

[1877] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1878] Formulating a product development strategy

[1879] Based on the analysis results, we will develop specific products.

[1880] server

[1881] The server provides trend and sentiment information to partner companies, including detailed analysis reports and proposals.

[1882] Partner companies

[1883] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[1884] Revenue sharing settings

[1885] We will establish a sales revenue sharing agreement for the jointly developed product.

[1886] server

[1887] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[1888] Prototype testing and feedback gathering

[1889] Partner companies

[1890] The partner company will create a prototype of the developed product and prepare it for market launch.

[1891] User

[1892] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[1893] terminal

[1894] The device collects feedback messages from users and sends them back to the server.

[1895] server

[1896] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes.

[1897] Through the steps described above, the present invention utilizes LINE message data to grasp consumers' real-time opinions and trends, and enables rapid and effective product development based on this information. Furthermore, by including user sentiment information, it becomes possible to formulate more accurate product development and marketing strategies.

[1898] The following describes the processing flow.

[1899] Step 1:

[1900] User

[1901] Users use their communication devices to exchange messages on a daily basis using LINE and other messaging apps. Users give prior consent to participate in the system and allow the collection of message data.

[1902] Step 2:

[1903] terminal

[1904] The device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is then encrypted and prepared for transmission to the server.

[1905] Step 3:

[1906] server

[1907] The server receives message data sent from each terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information.

[1908] Step 4:

[1909] server

[1910] The server performs natural language processing (NLP) techniques on the stored message data. This includes morphological analysis, entity recognition, and sentiment analysis. Through this analysis, it understands the meaning and sentiment of the text data.

[1911] Step 5:

[1912] Emotional Engine

[1913] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[1914] Step 6:

[1915] server

[1916] Based on the results of the emotion engine, the server extracts frequently occurring apparel-related words and keywords related to sweets and cooking. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in many messages, they will be recognized as a trend.

[1917] Step 7:

[1918] server

[1919] The server filters out noise data (meaningless information) and retains only highly reliable keywords. This improves the accuracy of the data. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1920] Step 8:

[1921] server

[1922] The server provides trend and sentiment information to partner companies. This includes detailed analysis reports and proposals. For example, it might provide information such as, "Users feel very happy with Basque cheesecake."

[1923] Step 9:

[1924] Partner companies

[1925] Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. Subsequently, specific design and manufacturing processes are developed.

[1926] Step 10:

[1927] server

[1928] The server sets a percentage of joint development costs based on sales (e.g., 10%) and reflects this in the contract with the partner company. This allows both parties to share the profits.

[1929] Step 11:

[1930] Partner companies

[1931] The partner company will create a prototype of the developed product and prepare it for market launch.

[1932] Step 12:

[1933] User

[1934] Users use the prototype and send feedback via LINE message about their experience and areas for improvement. For example, they might give specific feedback such as, "The fabric could be a little softer."

[1935] Step 13:

[1936] terminal

[1937] The device collects feedback messages from users and sends them back to the server.

[1938] Step 14:

[1939] server

[1940] The server then re-analyzes the collected feedback and provides the results to partner companies. This gives partner companies specific guidance for improving their prototypes. For example, they might improve their product based on information that "soft fabrics are preferred."

[1941] Through the steps described above, the present invention utilizes LINE message data to grasp consumers' real-time opinions, trends, and emotional information, and enables rapid and effective product development based on this information. Furthermore, by including user emotional information, it becomes possible to formulate more accurate product development and marketing strategies.

[1942] (Example 2)

[1943] 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".

[1944] In recent years, there has been a growing demand to accurately capture consumer behavior and emotions and immediately reflect them in product development. However, traditional methods have fragmented the processes from data collection and sentiment analysis to trend extraction, product development strategy formulation, and market feedback collection, making real-time product development difficult. This has made it difficult to respond quickly to market needs and maintain competitiveness.

[1945] 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.

[1946] In this invention, the server includes means for encrypting collected message data and transmitting it to the server, means for storing and anonymizing the transmitted message data, and means for analyzing the stored message data using natural language processing technology to recognize emotions. This enables product development based on users' real-time emotions and trends, and the rapid reflection of feedback.

[1947] A "communication terminal" is a device used by a user to generate and send message data, and includes smartphones, tablets, personal computers, etc.

[1948] "Message data" refers to data such as text, images, audio, and video that users send and receive through their communication devices.

[1949] "Encryption" is the process of transforming message data using specific algorithms to protect it and prevent third parties from accessing it.

[1950] A "server" refers to a central system that receives, stores, analyzes, and manages data sent from users' communication terminals.

[1951] "Anonymization" is the process of removing personally identifiable information from message data so that personal information cannot be identified.

[1952] "Natural language processing technology" refers to the techniques that enable computers to understand, analyze, and generate human language, and includes morphological analysis, entity recognition, and sentiment analysis.

[1953] "Emotions" refer to psychological states such as "joy," "anger," "sadness," and "surprise" contained in the user's message data.

[1954] A "trend" refers to a specific tendency or fashion that is recognized based on the frequent appearance of certain keywords or phrases in a large number of messages, as determined by analyzed message data.

[1955] "Partner companies" refer to companies that develop products based on trend and sentiment information obtained using this system.

[1956] "Joint development costs" refer to a certain percentage of sales generated from the developed product, and are development costs shared with partner companies.

[1957] "Feedback" refers to specific opinions and evaluations, such as user experience and areas for improvement, provided by users after using a prototype.

[1958] This invention relates to a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, extracts trends based on that analysis, and utilizes them for product development. This system consists of a user's communication terminal, a server that collects and analyzes data, and a partner company that develops products.

[1959] Users use their communication devices to exchange messages daily using LINE and other messaging apps. Users consent in advance to participate in this system and allow the collection of message data. The communication device collects user-generated message data in the background. Priority is given to data containing specific keywords or phrases. The collected data is encrypted and prepared for transmission to the server. Protocols such as SSL / TLS are used for encryption.

[1960] The server receives message data sent from each communication terminal and stores it in a secure database. The data is anonymized at the time of collection, protecting personal information. The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. This allows for an understanding of the meaning and sentiment of the text data.

[1961] The emotion engine recognizes the user's emotions from the analysis results. Specifically, it analyzes the wording, context, and emotional expressions in the message and classifies them into emotional categories such as "joy," "anger," "sadness," and "surprise."

[1962] As part of trend analysis, the server extracts frequently occurring apparel-related words and keywords related to food ingredients and cooking based on the results of the sentiment engine. For example, if related words such as "pistachio color," "oversized," and "Basque cheesecake" are mentioned in numerous messages, it is recognized as a trend. The server improves data accuracy by filtering out noise data (meaningless information) and retaining only highly reliable keywords. Subsequently, statistical information is generated based on the aggregated results, and the frequency and importance of each keyword are evaluated.

[1963] In formulating product development strategies, the server provides partner companies with trend and sentiment information. This includes detailed analysis reports and proposals. Based on the information received, partner companies hold internal product development meetings. For example, a development project for a "pistachio-colored oversized sweater" might be launched. The partner companies then proceed with specific design and manufacturing processes.

[1964] When setting up revenue sharing, the server can set a percentage of joint development costs based on sales (for example, 10%) and reflect this in the contract with the partner company, allowing both parties to share the profits.

[1965] In prototype testing and feedback gathering, partner companies create prototypes of the developed products and prepare them for market launch. Users use the prototypes and send feedback via LINE messages about their experience and areas for improvement. For example, specific opinions such as "the fabric should be a little softer" may be given. Communication terminals collect feedback messages from users and send them back to the server. The server analyzes the collected feedback again and provides the results to the partner companies. This allows the partner companies to obtain specific guidance for improving the prototypes.

[1966] This system utilizes LINE message data to grasp real-time consumer opinions and trends, enabling rapid and effective product development based on that information. Furthermore, by including user sentiment data, it allows for more accurate product development and marketing strategy formulation.

[1967] Example of a prompt:

[1968] "Please describe in natural language in detail a system that analyzes user sentiment towards fashion items on social media, identifies trends, and uses this information for product development."

[1969] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1970] Step 1:

[1971] Collection of message data

[1972] User: Users send and receive everyday messages using messaging apps such as LINE. In this process, users have given prior consent to data collection.

[1973] Input: The message that the user sends to the messaging app.

[1974] Output: The generated message is passed to the terminal.

[1975] Terminal operation: The terminal collects messages in a background process. Messages containing specific keywords or phrases are collected preferentially and prepared for encryption.

[1976] Step 2:

[1977] Data encryption and transmission

[1978] Terminal: The terminal encrypts the collected message data. The SSL / TLS protocol is used for this purpose.

[1979] Input: Collected message data.

[1980] Output: Encrypted message data is sent to the server.

[1981] Terminal operation: The terminal applies an encryption algorithm and prepares to encrypt the data and send it to the server. Specifically, it encrypts the data using the SSL / TLS protocol and sends it to the server through a secure communication circuit.

[1982] Step 3:

[1983] Data storage and anonymization

[1984] Server: The server stores the received encrypted data in a database and performs an anonymization process.

[1985] Input: Encrypted message data.

[1986] Output: Anonymized message data is stored in the database.

[1987] Server operation: The server extracts personally identifiable information and anonymizes the data through hashing and substitution operations. The data is stored in the database in a format that does not identify individuals.

[1988] Step 4:

[1989] Analysis using an emotion engine

[1990] Server: The server analyzes stored data using natural language processing (NLP) techniques.

[1991] Input: Anonymized message data.

[1992] Output: Analysis results related to the sentiment of the message.

[1993] Server operation: The server performs morphological analysis and extracts important information from messages through entity recognition. Then, it performs sentiment analysis and classifies the emotions expressed in the messages into categories such as "joy," "anger," and "sadness."

[1994] Step 5:

[1995] Trend Analysis

[1996] Server: The server extracts trends from the sentiment engine's results. It particularly identifies frequently occurring words related to apparel and keywords related to cooking and ingredients.

[1997] Input: Sentiment analysis results.

[1998] Output: Keywords and statistics related to the trend.

[1999] Server operation: The server extracts frequently occurring keywords from the analysis results and filters out noise data (irrelevant information). Then, it performs statistical analysis to evaluate the frequency and importance of each keyword and creates a trend report.

[2000] Step 6:

[2001] Formulating a product development strategy

[2002] Server: The server provides trend information and sentiment information to partner companies.

[2003] Input: Keywords and statistics related to the trend.

[2004] Output: Detailed analysis report and proposal.

[2005] Server operation: Based on the analysis results, the server generates detailed reports and proposals, which are then provided to partner companies via APIs and secure communication methods.

[2006] Step 7:

[2007] Revenue sharing settings

[2008] Server: Server sets the percentage of joint development costs based on sales and reflects this in contracts with partner companies.

[2009] Input: Sales information.

[2010] Output: Joint development cost setting information.

[2011] Server operation: Analyzes sales information, calculates joint development costs based on pre-set percentages, and reflects the results in the contract.

[2012] Step 8:

[2013] Prototype testing and feedback gathering

[2014] Partner companies: Partner companies create prototypes and prepare them for market launch.

[2015] User: Users use the prototype and submit feedback on their experience and areas for improvement.

[2016] Input: User feedback message.

[2017] Output: Collected feedback data.

[2018] Terminal operation: The terminal collects feedback messages sent by the user, encrypts them, and sends them to the server.

[2019] Server operation: The server analyzes the collected feedback and provides the results to partner companies to help improve the prototype.

[2020] (Application Example 2)

[2021] 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".

[2022] In recent years, there has been a growing demand for technologies that utilize the vast amount of message data generated via communication devices to accurately understand consumer sentiment and trends, and to use this information for product development. However, existing methods lack sufficient data analysis capabilities, making it difficult to respond quickly and accurately to consumer needs. Furthermore, there is a lack of means to improve the accuracy of personalized product recommendations. As a result, it is difficult to improve consumer satisfaction and achieve business growth.

[2023] 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.

[2024] In this invention, the server includes means for collecting message data generated by users from communication terminals, means for storing and analyzing the collected message data, means for analyzing the stored message data using natural language processing technology and extracting trends, means for providing the extracted trends to partner companies, means for formulating product development strategies in collaboration with partner companies, means for setting a certain percentage of sales obtained from the developed products as joint development costs, means for collecting user feedback and improving products based on that feedback, and means for generating and presenting personalized product suggestions to users based on the analysis results. This makes it possible to accurately grasp consumers' real-time emotions and trends, make product suggestions optimized for consumers, and achieve rapid and effective product development.

[2025] A "communication terminal" is a device used by users to generate message data and communicate.

[2026] "Message data" refers to data that includes text information and media content generated by users using communication devices.

[2027] "Storage" refers to the process of retaining collected data for a long period of time.

[2028] "Analysis" refers to the process of understanding the meaning and emotions of stored data using natural language processing techniques.

[2029] "Natural language processing technology" is a technique that uses computers to analyze human language and extract meaning and emotions.

[2030] A "trend" is a keyword or concept that indicates something or something that is supported by many users within a certain period of time.

[2031] A "partner company" is an external company that cooperates in product development based on data analysis results.

[2032] A "product development strategy" is a plan for effectively developing and providing products based on market needs and trends.

[2033] "A certain percentage of sales" refers to a predetermined percentage set out to distribute sales among the companies involved in the joint development project.

[2034] "Feedback" refers to opinions and requests regarding products and services provided by users.

[2035] "Personalized product recommendations" refer to products suggested based on the sentiment analysis results and trend data of individual users.

[2036] This invention is a system that collects user message data from a communication terminal, analyzes emotions using an emotion engine, and extracts trends based on that analysis to aid in product development. The main components of this system include a communication terminal, a server, and partner companies.

[2037] Collection of message data

[2038] User

[2039] Users routinely communicate through messaging apps using their own communication devices. Message data is collected only from users who have given prior consent to the system.

[2040] terminal

[2041] The device collects user message data in the background. Messages containing specific keywords or sentiments are prioritized for collection. The collected data is encrypted and sent to the server.

[2042] server

[2043] The server receives message data sent from communication terminals and stores it in a secure database. This data is anonymized, ensuring user privacy.

[2044] Analysis using an emotion engine

[2045] server

[2046] The server performs natural language processing (NLP) techniques on the stored message data. This processing includes morphological analysis, entity recognition, and sentiment analysis. Examples of NLP libraries used include spaCy and NLTK.

[2047] Emotional Engine

[2048] The emotion engine analyzes the user's emotions based on the analysis results and classifies each message into emotional categories such as "joy," "anger," and "sadness." For example, IBM Watson Tone Analyzer is used as an emotion engine.

[2049] Trend analysis and personalized product recommendations

[2050] server

[2051] The server extracts frequently occurring trending words based on the results of the sentiment engine. Keywords related to fashion, food, and lifestyle goods are particularly extracted.

[2052] Next, the server matches the extracted trending words with related product data to generate product suggestions optimized for the user. This results in personalized product recommendations being presented to the user.

[2053] Specific example

[2054] If a user sends a LINE message saying, "I've been really stressed lately," the emotion engine classifies this message as a "negative emotion." The server then extracts products based on trending words related to "stress reduction" and "relaxation," and suggests items such as "stress-reducing aroma diffusers" and "relaxation massage machines" to the user.

[2055] Example of a prompt

[2056] If a friend mentions feeling stressed lately during a conversation, recommend related relaxation products or stress-reducing items based on this message. Also, consider that the user is experiencing the emotion of "stress."

[2057] In this way, the present invention provides a system for acquiring real-time consumer opinions and trends and suggesting products suitable for users. This enables rapid and effective product development and the formulation of marketing strategies.

[2058] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2059] Step 1:

[2060] Collecting message data from users

[2061] The user uses a communication terminal to engage in everyday conversations and generate message data. The terminal collects this message data in the background. It receives the generated message data as input and encrypts it. The encrypted message data is obtained as output.

[2062] Step 2:

[2063] Encrypted data sent to the server

[2064] The terminal sends encrypted message data to the server. It takes encrypted message data as input and executes a process to send that data to the server. The output is the encrypted data stored on the server.

[2065] Step 3:

[2066] Data storage and preparation for analysis

[2067] The server stores the received encrypted message data in a database and prepares it for analysis. It takes the received encrypted data as input and stores it in the database. The stored data is then output.

[2068] Step 4:

[2069] Data analysis using Natural Language Processing (NLP)

[2070] The server retrieves message data stored in the database and performs analysis using natural language processing (NLP) techniques. It uses the message data retrieved from the database as input and performs NLP processing (morphological analysis, entity recognition, sentiment analysis). The output is the analyzed text data.

[2071] Step 5:

[2072] Emotional analysis using an emotion engine

[2073] The server uses NLP analysis results to run an emotion engine and classify the user's emotions. It uses NLP-analyzed data as input and runs it through an emotion engine (e.g., IBM Watson Tone Analyzer). The output is data categorized into emotion categories.

[2074] Step 6:

[2075] Extraction of trending words

[2076] The server extracts trending words based on sentiment analysis results. It uses sentiment-analyzed data as input to extract frequently occurring keywords and trending words. The output is a list of the extracted trending words.

[2077] Step 7:

[2078] Matching with the product database

[2079] The server matches the extracted trending keywords with the product database and selects relevant products. It uses the trending keyword list and the product database as input to search for products that match the keywords. The output is a personalized product list.

[2080] Step 8:

[2081] Generating and presenting personalized product suggestions

[2082] The server generates personalized product suggestions based on the selected products and presents them to the user's communication device. It uses a product list as input to generate recommended product messages. The output is the product suggestion message presented to the user.

[2083] This series of steps makes it possible to accurately grasp emotions and trends from user message data and provide product recommendations based on that.

[2084] 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.

[2085] 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.

[2086] 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 robot 414.

[2087] 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.

[2088] 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.

[2089] 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.

[2090] 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.

[2091] 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.

[2092] 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."

[2093] 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.

[2094] 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.

[2095] 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.

[2096] 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.

[2097] 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.

[2098] 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.

[2099] 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.

[2100] 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.

[2101] 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.

[2102] 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.

[2103] 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.

[2104] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[2105] The following is further disclosed regarding the embodiments described above.

[2106] (Claim 1)

[2107] A means of collecting user-generated message data from a communication terminal,

[2108] A means for storing and analyzing the collected message data,

[2109] A method for analyzing stored message data using natural language processing techniques and extracting trends,

[2110] A means of providing extracted trends to partner companies,

[2111] A means of formulating a product development strategy in collaboration with partner companies,

[2112] One method is to set a certain percentage of the sales generated from the developed product as a joint development fee,

[2113] A system that includes means for collecting user feedback and improving products based on that feedback.

[2114] (Claim 2)

[2115] The system according to claim 1, wherein the extracted trends are apparel-related words such as color, design, and size, and are related to sweets and cooking.

[2116] (Claim 3)

[2117] The system according to claim 1, which obtains user permission when collecting user-generated message data from a communication terminal.

[2118] "Example 1"

[2119] (Claim 1)

[2120] A means for collecting user-generated text message data from a communication device,

[2121] A means of storing and anonymizing the collected message data,

[2122] A method for analyzing stored message data using natural language processing techniques and extracting trends,

[2123] A means of filtering out recognized trends and retaining only reliable data,

[2124] A means of providing extracted trends to partner companies,

[2125] A means of formulating a product development strategy in collaboration with partner companies,

[2126] One method is to set the percentage of sales generated from the developed product as the joint development cost,

[2127] A system that includes means for collecting user feedback and improving the product based on that feedback.

[2128] (Claim 2)

[2129] The system according to claim 1, which uses bidirectional encoder representation as a natural language processing technique for extracting trends.

[2130] (Claim 3)

[2131] The system according to claim 1, which obtains prior consent from the user for collection before anonymizing the collected message data.

[2132] "Application Example 1"

[2133] (Claim 1)

[2134] A means of collecting user-generated message data from a communication terminal,

[2135] A means for storing and analyzing the collected message data,

[2136] A method for analyzing stored message data using natural language processing techniques and extracting trends,

[2137] A means of providing extracted trends to partner companies,

[2138] A means of formulating a product development strategy in collaboration with partner companies,

[2139] One method is to set a certain percentage of the sales generated from the developed product as a joint development fee,

[2140] A means of collecting user feedback and improving products based on that feedback,

[2141] A means of providing an application that recommends relevant products to users in real time based on trends,

[2142] A system that includes means of providing users with links to purchase recommended products.

[2143] (Claim 2)

[2144] The system according to claim 1, wherein the extracted trends are apparel-related words such as color, design, and size, as well as words related to sweets and cooking, and a generating AI model uses prompt sentences to recommend products.

[2145] (Claim 3)

[2146] The system according to claim 1, which obtains user permission when collecting user-generated message data from a communication terminal.

[2147] "Example 2 of combining an emotion engine"

[2148] (Claim 1)

[2149] A means of collecting user-generated message data from a communication terminal,

[2150] A means of encrypting the collected message data and sending it to the server,

[2151] A means of saving and anonymizing sent message data,

[2152] A means of analyzing stored message data using natural language processing technology to recognize emotions,

[2153] A method for extracting trends based on recognized emotions,

[2154] A means of providing extracted trends to partner companies,

[2155] A means of formulating a product development strategy in collaboration with partner companies,

[2156] One method is to set a certain percentage of the sales generated from the developed product as a joint development fee,

[2157] A system that includes means for collecting user feedback and improving products based on that feedback.

[2158] (Claim 2)

[2159] The system according to claim 1, wherein the extracted trends are apparel-related words such as color, design, and size, and are related to ingredients and cooking.

[2160] (Claim 3)

[2161] The system according to claim 1, which obtains user permission when collecting user-generated message data from a communication terminal.

[2162] "Application example 2 when combining with an emotional engine"

[2163] (Claim 1)

[2164] A means of collecting user-generated message data from a communication terminal,

[2165] A means for storing and analyzing the collected message data,

[2166] A method for analyzing stored message data using natural language processing techniques and extracting trends,

[2167] A means of providing extracted trends to partner companies,

[2168] A means of formulating a product development strategy in collaboration with partner companies,

[2169] One method is to set a certain percentage of the sales generated from the developed product as a joint development fee,

[2170] A means of collecting user feedback and improving products based on that feedback,

[2171] A system that includes means for generating and presenting personalized product suggestions to users based on analysis results.

[2172] (Claim 2)

[2173] The system according to claim 1, wherein the extracted trends relate to fashion, food, and lifestyle goods.

[2174] (Claim 3)

[2175] The system according to claim 1, which obtains user permission when collecting user-generated message data from a communication terminal. [Explanation of symbols]

[2176] 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 collecting user-generated message data from a communication terminal, A means for storing and analyzing the collected message data, A method for analyzing stored message data using natural language processing techniques and extracting trends, A means of providing extracted trends to partner companies, A means of formulating a product development strategy in collaboration with partner companies, One method is to set a certain percentage of the sales generated from the developed product as a joint development fee, A system that includes means for collecting user feedback and improving products based on that feedback.

2. The system according to claim 1, wherein the extracted trends are apparel-related words such as color, design, and size, and are related to sweets and cooking.

3. The system according to claim 1, which obtains user permission when collecting user-generated message data from a communication terminal.

Images