system

Abstract

A system is provided.SOLUTION: A system includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data by using a natural language processing technique, means for using an AI model that digitizes taste based on an analysis result, means for integrating and analyzing visualizing data of taste and point-of-sale data, means for generating a report in a report format, and means for providing the generated report to a terminal of a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Current food development relies on the experience and intuition of those in charge, making it difficult to quickly respond to changing consumer preferences and trends. As a result, purchasing data alone is insufficient to keep up with market changes, resulting in inefficient product development and a loss of competitiveness. Furthermore, due to a lack of means to quantify and analyze specific taste information, there is a lack of a scientific, data-driven approach to new product planning and development. Furthermore, the lack of efficient data collection and analysis methods significantly increases the time and effort required for development. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting posted data from social media, a means for preprocessing the collected posted data, a means for analyzing the preprocessed data using natural language processing technology, a means for utilizing an AI model that quantifies taste based on the analysis results, a means for integrating and analyzing the visualized taste data and point-of-sale management data, a means for generating the analysis results in report format, and a means for providing the generated report to a user's device. This enables scientific, data-driven product development without relying on the experience or intuition of staff, enabling rapid response to consumer preferences and trends. Furthermore, efficient data collection and analysis can significantly reduce the time and effort required for product development and improve the productivity of food manufacturers.

[0006] "SNS" stands for Social Networking Service, an online platform for people to interact and share information over the Internet.

[0007] "Posted data" refers to information content such as articles, comments, photos, and videos created by users on SNS.

[0008] "Preprocessing" refers to the initial processing of collected data to convert it into a format suitable for analysis, and specifically includes data cleansing and filtering.

[0009] "Natural language processing technology" is a technology for processing and analyzing human language using computers, and includes language analysis, sentiment analysis, topic modeling, etc.

[0010] "Analysis results" refers to the collection of information and data extracted and analyzed using natural language processing technology.

[0011] An "AI model that quantifies taste" is an artificial intelligence model that expresses specific taste characteristics (sweetness, sourness, umami, etc.) as numbers from text and other data.

[0012] "Point of sale information management data" refers to data related to the sale of goods obtained through a POS (Point of Sale) system, including sales, inventory, price, etc.

[0013] "Integrating and analyzing" refers to a series of processes that combine and analyze different data sets (e.g., taste data and POS data) to extract insights and patterns.

[0014] "Generating in report format" means summarizing the analysis results in a visually easy-to-understand format (e.g., text, graph, dashboard).

[0015] "User terminal" refers to a device used by a user to view information, such as a computer, smartphone, or tablet. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention relates to a system for streamlining the development of new food products, and in particular aims to support the development of products based on consumer preferences by integrating and analyzing social media data and POS data. This system collects and analyzes data posted on social media, visualizes taste based on the results, and then integrates and analyzes the data with POS data, thereby realizing scientific, data-driven product development.

[0038] Explanation of program processing

[0039] 1. User requests social media data collection

[0040] Users request the collection of social media data based on specific keywords or hashtags from their device.

[0041] 2. Start collecting social media data

[0042] The server uses the API of the specified social media platform to collect post data containing the requested keywords and hashtags.

[0043] 3. Data Preprocessing

[0044] The server performs preprocessing such as cleansing (removing unnecessary characters and tags) and language filtering (excluding data in languages ​​other than the target language) on the collected SNS post data.

[0045] 4. Text analysis using natural language processing technology

[0046] The server performs morphological analysis on the preprocessed data to extract important keywords, and also analyzes the sentiment score and topics of posts using sentiment analysis and topic modeling.

[0047] 5. Quantifying taste using an AI model

[0048] The server's AI model quantifies specific taste characteristics (sweetness, sourness, umami, etc.) based on the analyzed text data. In doing so, the AI ​​extracts relevant taste information from the text and expresses it as a score.

[0049] 6. Integration and analysis of POS data

[0050] The server integrates the visualized taste data with point-of-sale (POS) data and compiles it into a single dataset, allowing for analysis of the correlation between taste scores and actual sales data.

[0051] 7. Generate Reports

[0052] The server extracts insights from the integrated data and automatically generates detailed reports including trend analysis, consumer preference predictions, and new product suggestions.

[0053] 8. Check the report

[0054] Users can check the reports generated on their devices and use them to develop new products and improve existing products based on scientific evidence.

[0055] Specific examples

[0056] For example, if a user wants to develop a new "chocolate product," the following specific example can be considered.

[0057] 1. User submits a request:

[0058] The user requests the collection of social media data by specifying the keywords "chocolate, new product, trend" on the device.

[0059] 2. Data Collection:

[0060] The server collects posts containing specified keywords from social media platforms such as Twitter and Instagram.

[0061] 3. Data Preprocessing and Analysis:

[0062] The server preprocesses the collected data, performs morphological analysis, and identifies posts with strong positive sentiment and posts with weak negative sentiment.

[0063] 4. Quantifying taste:

[0064] The server's AI model generates values ​​such as "sweetness score 80, sourness score 20, umami score 50."

[0065] 5. Integration with POS data:

[0066] Based on the integrated data, the server extracts insights such as "products with high sweetness scores record high sales in winter."

[0067] 6. Provision of Report:

[0068] The user checks the generated report on the terminal and decides on a development strategy for a new chocolate product.

[0069] This system will be a powerful tool for users to develop products efficiently and based on data. By integrating and analyzing social media data and POS data, users can quickly bring products to market that meet consumer demand.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] A user submits a request for collection of social media data related to a specific product development from their device, including keywords or hashtags of interest, target social media platforms (e.g., Twitter, Instagram, etc.), and a collection period.

[0073] Step 2:

[0074] The server calls the API of the target social media platform based on the received request and collects post data containing the specified keywords and hashtags. The data obtained from the API includes the post content, posting date and time, user ID, etc.

[0075] Step 3:

[0076] The server preprocesses the collected social media post data. Specifically, it removes unnecessary HTML tags and special characters, eliminates unnecessary spaces, and performs language filtering to exclude data in languages ​​other than the target language. It also normalizes the data to unify the data format.

[0077] Step 4:

[0078] The server analyzes the pre-processed data using natural language processing (NLP) techniques, including:

[0079] Morphological analysis: Breaks down the content of social media posts into morphemes and extracts important keywords and phrases.

[0080] Sentiment Analysis: Calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post.

[0081] Topic modeling: Grouping similar posts and extracting major topics.

[0082] Step 5:

[0083] The server's AI model quantifies taste characteristics based on the analyzed text data. The model extracts taste-related information from the text and generates scores for sweetness, sourness, umami, bitterness, saltiness, etc.

[0084] Step 6:

[0085] The server integrates the visualized taste data with point-of-sale (POS) data. Specifically, it combines taste scores and POS data (sales, inventory, price, etc.) into a single integrated data set. This allows for analysis of the correlation between taste data and actual sales data.

[0086] Step 7:

[0087] The server analyzes changes in consumer preferences and market trends based on the integrated data, extracts important insights and patterns, and creates reports for efficient and effective product development.

[0088] Step 8:

[0089] The server delivers automatically generated reports to the user's device, including trend analysis, consumer preference predictions, and new product suggestions.

[0090] Step 9:

[0091] Users can check the reports on their devices and develop products scientifically and efficiently based on the data. Based on these reports, they can plan new products and prepare to respond quickly to changes in the market.

[0092] By following the above steps, users can integrate and analyze social media data and POS data, enabling them to efficiently develop data-based products.

[0093] Example 1

[0094] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0095] In conventional new food product development, it is difficult to accurately grasp consumer preferences, and because product development is not based on data, it is difficult to quickly bring products that meet consumer needs to market. The objective of this invention is to support more efficient and effective product development by integrating and analyzing SNS data and point-of-sale management data to scientifically visualize consumer preferences.

[0096] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0097] In this invention, the server includes: means for a user to request collection of SNS data based on specific keywords or hashtags from a terminal; means for collecting posted data including the requested keywords or hashtags using the API of the SNS platform; means for cleansing and language filtering the collected posted data; means for analyzing the preprocessed data using morphological analysis, sentiment analysis, and topic modeling; means for using a generative AI model that quantifies specific taste characteristics based on text data; means for integrating and analyzing visualized taste data and point-of-sale data; means for extracting insights from the integrated data and generating reports such as trend analysis, consumer preference predictions, and new product suggestions; and means for providing the generated reports in a format that can be viewed on the user's terminal. This enables scientific understanding of consumer preferences based on data and rapid and efficient launch of new products to the market.

[0098] "SNS data" refers to information such as messages, comments, tags, images, and videos posted by users on social networking services.

[0099] "API" stands for Application Programming Interface and refers to the interface or protocol for exchanging functions and data between software programs.

[0100] "Collection method" refers to a method or system for obtaining specific information from the Internet or a database.

[0101] "Cleansing" refers to the process of removing unnecessary characters, tags, duplicate data, etc. in the data preprocessing process to improve the quality of the data.

[0102] "Language filtering" refers to the process of extracting data related to a specific language and excluding data in other languages.

[0103] "Morphological analysis" refers to a natural language processing technique that breaks down a sentence into its smallest meaningful units and extracts the parts of speech and morphemes of each word.

[0104] "Sentiment analysis" refers to the technology of analyzing trends such as positive and negative emotions and opinions from text data.

[0105] "Topic modeling" refers to a method for discovering common themes and topics from large amounts of text data.

[0106] An "AI model" refers to an algorithm or neural network that uses artificial intelligence, a system that can automatically perform specific tasks by learning from large amounts of data.

[0107] "Taste characteristics" refers to the numerical expression of specific taste characteristics of food (e.g., sweetness, sourness, umami, etc.).

[0108] "Point of sale data (POS data)" refers to data collected at the time of sale of a product, including details such as sales, inventory, and customer information.

[0109] "Integration" refers to the process of combining different data sets into one and analyzing and using them comprehensively.

[0110] "Insight" refers to insights and findings gained through data analysis.

[0111] "Trend analysis" refers to the technique of analyzing current trends and patterns based on past data and predicting future trends.

[0112] "New product proposal" refers to proposing new product development ideas and concepts based on market needs and trends.

[0113] A "report" refers to a document or material that summarizes analytical results and insights and provides information to assist users in making decisions.

[0114] This invention is a system for streamlining the development of new food products, and its purpose is to support the development of products based on consumer preferences by integrating and analyzing social media data and point-of-sale (POS) data. This system collects and analyzes data posted on social media, quantifies taste based on the results, and then integrates and analyzes the results with POS data, thereby realizing scientific, data-driven product development.

[0115] Data collection and preprocessing

[0116] A user uses a device to request the collection of social media data based on specific keywords or hashtags. The server then uses the API of the specified social media platform to collect post data containing the requested keywords or hashtags. Examples of APIs used in this collection process include the Twitter API and Instagram API.

[0117] The collected data undergoes preprocessing on the server side, including cleansing (removing unnecessary characters and tags) and language filtering (excluding data in languages ​​other than the target language). Software used for this includes the Python libraries regex and beautifulsoup.

[0118] Use of natural language processing technology

[0119] The preprocessed data is then analyzed by the server using natural language processing techniques such as morphological analysis, sentiment analysis, and topic modeling. For morphological analysis, natural language processing libraries such as NLTK and spaCy are used, and for sentiment analysis, TextBlob and VADER are used.

[0120] Quantifying taste characteristics

[0121] Based on the analyzed text data, a generative AI model on the server quantifies specific taste characteristics. This is done using deep learning frameworks such as TensorFlow and PyTorch. The model expresses taste characteristics such as sweetness, sourness, and umami as numerical values ​​based on keywords and sentiment scores extracted from the text data.

[0122] Data Integration and Reporting

[0123] The server integrates the quantified taste data and POS data into a single data set, allowing for analysis of the correlation between taste scores and sales data. This process uses MySQL or PostgreSQL as the database system.

[0124] It extracts insights from the integrated data and automatically generates detailed reports such as trend analysis, consumer preference predictions, new product suggestions, etc. Data visualization tools used include Matplotlib and Plotly, and the generated reports are exported in PDF or Excel format.

[0125] Users can check the reports generated on their devices and use them to develop new products or improve existing products based on scientific evidence. This system enables users to develop products efficiently and based on data.

[0126] Specific examples

[0127] For example, if a user wants to develop a new "chocolate product," the following is a specific example.

[0128] 1. User submits a request:

[0129] The user requests the collection of social media data by specifying the keywords "chocolate, new product, trend" on the device.

[0130] 2. Data Collection:

[0131] The server collects posts containing specified keywords from social media platforms such as Twitter and Instagram.

[0132] 3. Data Preprocessing and Analysis:

[0133] The server preprocesses the collected data, performs morphological analysis, and identifies posts with strong positive sentiment and weak negative sentiment.

[0134] 4. Quantifying taste:

[0135] The server's AI model generates values ​​such as "sweetness score 80, sourness score 20, umami score 50."

[0136] 5. Integration with POS data:

[0137] Based on the integrated data, the server extracts insights such as "products with high sweetness scores record high sales in winter."

[0138] 6. Provision of Report:

[0139] The user checks the generated report on the terminal and decides on a development strategy for a new chocolate product.

[0140] Prompt Sentence Examples

[0141] Examples of prompts to input to a generative AI model might include:

[0142] Regarding a new chocolate product, please collect data from Twitter and Instagram posts containing the keywords "chocolate, new product, trend." Also, please quantify the taste characteristics of the new product based on the collected data and integrate it with POS data to provide insights for optimal product development.

[0143] As described above, the present invention integrates SNS data and POS data, enabling scientific product development based on consumer preferences.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1:

[0146] A user requests the collection of social media data based on specific keywords or hashtags from their device.

[0147] Specific operation: The user enters keywords into the input form specified in the dedicated application on the device and clicks the "Collect data" button.

[0148] Input: User-specified keywords and hashtags.

[0149] Output: A social media data collection request is sent to the server.

[0150] Step 2:

[0151] The server uses the API of the social media platform to collect post data containing the requested keywords and hashtags.

[0152] Specific operation: The server uses the API key to send a request to the social media platform (e.g., Twitter, Instagram) and retrieves the relevant post data.

[0153] Input: User-specified keywords, hashtags, and API keys.

[0154] Output: Retrieved social media post data.

[0155] Step 3:

[0156] The server cleanses and language filters the social media post data collected.

[0157] Specific operation: A Python script on the server uses libraries such as regex and beautifulsoup to remove unnecessary characters and tags from the data and exclude data in languages ​​other than the target language.

[0158] Input: Collected social media posting data.

[0159] Output: Preprocessed SNS data.

[0160] Step 4:

[0161] The server analyzes the preprocessed data using morphological analysis, sentiment analysis, and topic modeling.

[0162] How it works: It uses NLTK and spaCy libraries for morphological analysis, TextBlob and VADER for sentiment analysis, and Gensim for topic modeling.

[0163] Input: Preprocessed SNS data.

[0164] Output: Morphological analysis results, sentiment score, topic information.

[0165] Step 5:

[0166] The server's generative AI model quantifies specific taste characteristics based on the analyzed text data.

[0167] Specific operation: Using a deep learning framework (e.g., TensorFlow, PyTorch), a trained model quantifies sweetness, sourness, umami, etc. from text data.

[0168] Input: Morphological analysis results, sentiment scores, topic information.

[0169] Output: Numerical data of taste attributes (e.g., sweetness score 80, sourness score 20, umami score 50).

[0170] Step 6:

[0171] The server integrates and analyzes the visualized taste data and point-of-sale data (POS data).

[0172] Specific operation: Executes an SQL query on a database system (e.g., MySQL, PostgreSQL) to combine taste data and POS data.

[0173] Input: Numerical data of taste characteristics, POS data.

[0174] Output: A consolidated dataset.

[0175] Step 7:

[0176] The server extracts insights from the integrated data and generates reports such as trend analysis, consumer preference predictions, and new product suggestions.

[0177] Specific behavior: Create graphs and charts using data visualization tools (e.g., Matplotlib, Plotly) and export reports in PDF and Excel formats.

[0178] Input: The integrated dataset.

[0179] Output: Detailed report (e.g. PDF, Excel file).

[0180] Step 8:

[0181] The user checks the generated report on the device.

[0182] Specific operation: The user downloads the generated report using a dedicated application on the device and reviews the contents.

[0183] Input: Detailed report (e.g. PDF, Excel file).

[0184] Output: Report information reviewed by the user.

[0185] (Application example 1)

[0186] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0187] In the past, new food product development relied mainly on sales data and survey results, as it was difficult to accurately grasp consumer preferences and market trends. As a result, planning and development of new products that quickly reflected the latest consumer preferences and trends tended to be delayed. Furthermore, it was difficult for employees to utilize this data to propose new products, which led to inefficient product deployment in physical stores.

[0188] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0189] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an AI model for quantifying taste based on the analysis results, means for integrating and analyzing the visualized taste data and point-of-sale management data, means for generating the analysis results in report format, and means for providing the generated report to a user's visual display device. This enables the planning and development of new products that quickly and accurately reflect the latest consumer preferences, and allows employees at physical stores to use this data in real time to help with sales strategies and product development.

[0190] "Means for collecting post data from social media" refers to a system for collecting post data from social media platforms based on specific keywords or hashtags.

[0191] "Means for preprocessing collected post data" refers to the process of deleting unnecessary characters and tags from the collected SNS post data and excluding data in languages ​​other than the target language.

[0192] "Means of analysis using natural language processing technology" refers to a system that uses preprocessed data to analyze it using natural language processing technology such as morphological analysis, sentiment analysis, and topic modeling.

[0193] "Means of using an AI model" refers to a mechanism that utilizes an artificial intelligence model to quantify specific taste characteristics based on analyzed text data.

[0194] "Means for integrating and analyzing visualized taste data and point-of-sale management data" is a system that integrates visualized taste data and sales data and analyzes correlations.

[0195] "Means for generating analysis results in report format" refers to a system that automatically generates reports based on insights gained from integrated data.

[0196] The "means for providing the generated report to the user's visual display device" refers to a mechanism for displaying the generated report in real time on the user's visual display device, such as smart glasses.

[0197] This invention consists of a system that can be applied to support new product development in brick-and-mortar stores. This system collects and analyzes data from social media, and integrates and analyzes it with point-of-sale (POS) data to intuitively support users in developing new products and formulating sales strategies. Specific embodiments for implementing this invention are described below.

[0198] 1. Generate the program:

[0199] This system consists of a server, a terminal, and the user's visual display device. The server runs a program that collects posted data from SNS and preprocesses the collected data. This preprocessing includes removing unnecessary characters and tags and excluding data in a language other than the target language. The data is then analyzed using natural language processing techniques (morphological analysis, sentiment analysis, topic modeling, etc.) to quantify taste characteristics (sweetness, sourness, umami, etc.). The server integrates these analysis results with the POS data, analyzes them as a single dataset, and automatically generates a report. This report is provided in real time to the user's visual display device.

[0200] 2. Natural language processing description:

[0201] Specifically, when collecting data from social media platforms, the server uses the APIs of each platform. For data preprocessing, Python libraries (e.g., NLTK, SpaCy) are used to clean and filter text. For morphological analysis and sentiment analysis, Google Cloud Natural Language API is used. Furthermore, machine learning frameworks (e.g., TensorFlow, PyTorch) are used to quantify taste using an AI model. Google Cloud BigQuery is used to integrate and analyze the analysis results and POS data, and Google Data Studio is used to generate reports. Smart glasses, such as Google Glass, are used as visual display devices. These devices allow users to manipulate data through voice commands or touch operations.

[0202] 3. Adding concrete examples:

[0203] For example, consider the case where a user develops a new "seasonal chocolate flavor." The user specifies the keywords "seasonal, flavor, chocolate" on a visual display device and requests the collection of social media data. The server collects posts containing the specified keywords from Twitter and Instagram and performs preprocessing. The analysis results generate numerical values ​​such as "sweetness score 85, sourness score 15, umami score 40." These values ​​are then integrated with POS data to extract insights such as "products with high sweetness scores record high sales in spring." Finally, these analysis results are displayed in real time on the user's visual display device, smart glasses.

[0204] Examples of prompts for a generative AI model might include:

[0205] "Please quantify the taste characteristics (sweetness, sourness, umami) from the following social media posts."

[0206] This chocolate is so sweet and delicious!

[0207] "This chocolate is too sour."

[0208] "This chocolate has an exquisite flavor."

[0209] As described above, the system embodying this invention makes it possible to efficiently plan and develop new products in physical stores that quickly and accurately reflect the latest consumer preferences.

[0210] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0211] Step 1:

[0212] A user requests social media data collection.

[0213] The user requests the collection of social media data by specifying keywords such as "seasonal, flavor, chocolate" on the visual display. The input is the specified keyword, and the output is the transmission of a collection command. The visual display is used to execute the request by voice command or touch operation.

[0214] Step 2:

[0215] The server starts collecting social media data.

[0216] The server uses the social media platform API to collect post data based on the specified keywords. The input is the requested keywords, and the output is the collected social media post data. Specifically, the data is collected from Twitter and Instagram and saved in JSON format on the server.

[0217] Step 3:

[0218] The server preprocesses the collected submission data.

[0219] The collected post data is preprocessed by the server. The input is the collected SNS post data, and the output is the preprocessed data. Specifically, Python's NLTK and SpaCy are used to remove unnecessary characters and tags, and to exclude data in languages ​​other than the target language.

[0220] Step 4:

[0221] The server analyzes the preprocessed data using natural language processing techniques.

[0222] Based on the preprocessed data, the server uses natural language processing technology to perform sentiment analysis and topic modeling. The input is the preprocessed data, and the output is the analysis results. Specifically, it uses the Google Cloud Natural Language API to extract important keywords and analyze sentiment scores.

[0223] Step 5:

[0224] The server uses an AI model to quantify the taste based on the analysis results.

[0225] Based on the analyzed text data, the server uses an AI model to quantify specific taste characteristics. The input is the analysis result, and the output is a taste score. Specifically, TensorFlow and PyTorch are used to generate scores for sweetness, sourness, and umami.

[0226] Step 6:

[0227] The server integrates and analyzes taste visualization data and point-of-sale (POS) data.

[0228] The taste scores and POS data from physical stores are integrated and analyzed as a single dataset. The inputs are taste scores and POS data, and the output is an integrated dataset. Specifically, the data is integrated using Google Cloud BigQuery and correlation analysis is performed.

[0229] Step 7:

[0230] The server generates a report from the analysis results.

[0231] Based on the insights gained from the integrated data, the server automatically generates detailed reports. The input is the integrated dataset and the output is the report. The reports are generated using Google Data Studio and visually displayed in graphs and charts.

[0232] Step 8:

[0233] The server provides the generated report to the user's visual display.

[0234] The generated report is provided in real time to the user's visual display device. The input is the generated report, and the output is the displayed report. The report is displayed on a visual display device (e.g., smart glasses) and can be confirmed by the user via voice or touch.

[0235] Above, we have described the specific processing operations and inputs / outputs for each step, and have explained in detail the processing flow of the entire system.

[0236] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0237] This invention relates to a system that supports product development by integrating and analyzing social media data and POS data, and using an emotion engine in combination. This system analyzes posted data collected from social media, quantifies the analysis results into taste, and integrates the analysis with sales data, while recognizing user emotions and providing insights.

[0238] Explanation of program processing

[0239] 1. User requests social media data collection

[0240] The user sends a request for collecting social media data related to a specific product development from their device. The request includes keywords, target platforms, and a collection period.

[0241] 2. Start collecting social media data

[0242] The server calls the API of the specified social media platform and collects post data including keywords and hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[0243] 3. Data Preprocessing

[0244] The server preprocesses the collected social media post data. Specifically, it removes unnecessary HTML tags, special characters, and unnecessary spaces, and performs language filtering. Language filtering excludes posts in languages ​​other than the target language.

[0245] 4. Text analysis using natural language processing technology

[0246] The server analyzes the preprocessed data using natural language processing techniques. The analysis operations include:

[0247] Morphological analysis: Breaks down text into morpheme units and extracts important keywords and phrases.

[0248] Sentiment Analysis: Calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post.

[0249] Topic modeling: Clustering relevant posts and extracting major topics.

[0250] 5. Quantifying taste using an AI model

[0251] The server's AI model quantifies taste characteristics based on the analyzed text data, generating taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text.

[0252] 6. Integration and analysis of POS data

[0253] The server integrates the visualized taste data with point-of-sale (POS) data, combining taste scores and POS data (sales, inventory, price, etc.) into a single dataset and analyzing the relationships between them.

[0254] 7. Emotion recognition and insights

[0255] The server utilizes an emotion engine to recognize the user's emotions and provide insights based on the analysis results, which then generates a detailed report reflecting the user's emotional state.

[0256] 8. Generate Reports

[0257] The server generates detailed reports on changing consumer preferences and market trends based on the integrated data and the output of the emotion engine, including trend analysis, consumer preference predictions, and new product suggestions.

[0258] 9. Check the report

[0259] Users can check the reports generated on their devices and develop products scientifically and efficiently based on the data. Based on these reports, they can plan new products and prepare to respond quickly to changes in the market.

[0260] Specific examples

[0261] For example, if a user wants to develop a new "ice cream product," the following specific example can be considered.

[0262] 1. User submits a request:

[0263] The user requests the collection of SNS data by specifying the keywords "ice cream, new product, summer" on the terminal.

[0264] 2. Data collection and preprocessing:

[0265] The server collects posts containing the specified keywords from the social media platform. After collection, unnecessary data is removed and preprocessed.

[0266] 3. Data analysis and taste quantification:

[0267] The server performs natural language processing on the preprocessed data and then uses an AI model to generate a taste score, such as "sweet score 90, sour score 10, salty score 5."

[0268] 4. POS data integration and analysis:

[0269] The server integrates the taste scores with POS data to extract the insight that "ice cream with a high sweetness score records high sales in the summer."

[0270] 5. Emotion Recognition and Report Generation:

[0271] The server uses an emotion engine to recognize user emotions and generates detailed reports that provide insights based on the analysis results.

[0272] 6. Report provision and review:

[0273] Users can check the reports generated on their devices and decide on new product development strategies. Insights based on emotion information can help plan products that are more likely to be accepted by consumers.

[0274] This system helps users analyze consumer preferences and market trends based on social media and POS data, and utilizes an emotion engine to respond quickly, enabling scientific and data-based product development and efficient response to market changes.

[0275] The processing flow will be explained below.

[0276] Step 1:

[0277] Users submit a request for social media data collection related to new product developments from their device by inputting keywords of interest (e.g., "chocolate," "new product," "trend"), target social media platforms (e.g., Twitter, Instagram), and the data collection period.

[0278] Step 2:

[0279] The server calls the API of the social media platform based on the received request and collects posts containing the specified keywords or hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[0280] Step 3:

[0281] The server preprocesses the collected SNS data. Specifically, it performs the following operations:

[0282] Remove unnecessary characters: Remove HTML tags, special characters, emojis, etc.

[0283] Language filtering: Filter out posts in languages ​​other than your target language (e.g., if you only target Japanese).

[0284] Text normalization: unifying full-width and half-width characters, converting uppercase and lowercase characters, etc.

[0285] Step 4:

[0286] The server analyzes the preprocessed data using natural language processing (NLP) technology. Specifically, it performs the following processes:

[0287] Morphological analysis: Breaks down the text of a post into morphemes and extracts important keywords.

[0288] Sentiment analysis: Calculates positive, negative, and neutral sentiment scores.

[0289] Topic modeling: Clustering posts and extracting major topics.

[0290] Step 5:

[0291] The server's AI model quantifies taste characteristics based on the analysis results. Specifically, it generates scores for sweetness, sourness, umami, bitterness, saltiness, etc. from the text data. This taste quantification visualizes the consumer's post as specific taste characteristics.

[0292] Step 6:

[0293] The server integrates and analyzes taste data and point-of-sale (POS) data. Specifically, it performs the following operations:

[0294] Data integration: Integrate taste scores and POS data (sales, inventory, price, etc.) into one.

[0295] Association analysis: Based on the integrated data, the relationship between taste characteristics and sales performance is analyzed (e.g., products with high sweetness scores have high sales).

[0296] Step 7:

[0297] The server uses an emotion engine to recognize the user's emotions. Specifically, it evaluates the user's emotional state in real time based on the user's operation history and input information when they access the system.

[0298] Step 8:

[0299] The server adds insights corresponding to the user's emotional state to the report based on the output of the emotion engine, thereby generating a detailed report containing insights based on the user's emotions.

[0300] Step 9:

[0301] The server provides the generated report to the user's device, where the user can check the report and develop products based on scientific evidence and data.

[0302] Step 10:

[0303] Users can use the reports provided on their devices to decide on new product plans and development policies, enabling them to quickly develop products that respond to consumer preferences and market trends.

[0304] In this way, this system integrates and analyzes SNS data and POS data, and by combining it with an emotion engine, provides product development support based on data that is useful to users.

[0305] Example 2

[0306] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0307] Conventional methods have made it difficult to efficiently integrate social media data and point-of-sale data to quickly understand consumer preferences and market trends. Furthermore, there is a lack of means to recognize user emotions using an emotion engine or generate detailed reports, which hinders the efficiency of the scientific, data-driven product development process. To solve these problems, a system is needed that can consistently analyze social media data, quantify taste perception, integrate data, recognize emotions, and generate reports.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0309] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an artificial intelligence model that quantifies taste based on the analysis results, means for integrating and analyzing the taste visualization data and point-of-sale management data, means for recognizing user emotions using an emotion engine, means for generating a detailed report based on the integrated data and the output of the emotion engine, and means for providing the generated report to the user's terminal. This enables rapid understanding of consumer preferences and market trends and enables scientific product development based on data.

[0310] "SNS data" refers to information such as user messages, comments, images, and videos posted on social media platforms.

[0311] "Preprocessing" refers to the process of removing unnecessary information from collected data and converting it into a format suitable for analysis.

[0312] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language.

[0313] An "artificial intelligence model" refers to an algorithm that learns from large amounts of data and makes predictions and analyses based on that data.

[0314] "Quantifying taste" refers to the process of extracting taste characteristics (sweetness, sourness, umami, bitterness, saltiness, etc.) from text data and expressing those characteristics numerically.

[0315] "Point of sale data" refers to data used to manage sales information in real time, including product sales, inventory, prices, etc.

[0316] "Emotion engine" refers to an algorithm or system for analyzing and recognizing a user's emotions.

[0317] "Report" means a written or digital report summarizing the results of an analysis or insights.

[0318] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0319] "User" refers to the person or company that uses the system to collect, analyze, and check reports on social media data.

[0320] This invention is a system that integrates and analyzes social media data and point-of-sale (POS) data to recognize user sentiment and support product development. The system collects, analyzes, and integrates data through multiple steps, and finally generates a report to provide to the user.

[0321] The main components of this system include a server, a terminal, and a user. The configuration of this system and a specific embodiment will be described in detail below.

[0322] Data collection and preprocessing

[0323] A user requests the collection of social media data through their device. The request includes specific keywords (e.g., "ice cream, new products, summer"), the target social media platform (e.g., Twitter, Instagram), and the data collection period (e.g., the past three months).

[0324] The server receives a request from a user and uses the API of the social media platform (e.g., Twitter API) to collect post data containing the specified keywords and hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[0325] The server then pre-processes the collected data, which includes removing unnecessary HTML tags, special characters, and unnecessary spaces, and language filtering to retain only the specified language (e.g., Japanese).

[0326] Text analysis and quantification of taste

[0327] The preprocessed data is then analyzed on the server using natural language processing (NLP) techniques. This analysis includes morphological analysis, sentiment analysis, and topic modeling. Morphological analysis breaks down text into words and extracts important keywords and phrases. Sentiment analysis calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post. Topic modeling clusters related posts and extracts major topics.

[0328] The server's AI model quantifies taste characteristics based on the analyzed text data. This model generates taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text. For example, a score such as "sweetness score 90, sourness score 10, saltiness score 5" may be generated.

[0329] Integration and analysis of POS data

[0330] The server integrates the taste scores with the POS data. The POS data includes sales-related information such as sales, inventory, and price. The integrated data is analyzed on the server to analyze the relationship between the taste scores and the POS data. For example, an insight such as "ice cream with a high sweetness score records high sales in the summer" can be extracted.

[0331] Emotion Recognition and Report Generation

[0332] The server uses an emotion engine to recognize the user's emotions and generates a detailed report based on the results, including changes in consumer preferences, market trends, insights, consumer preference predictions, and new product suggestions. The report is provided to the user's device, where the user can review it and decide on a new product development strategy.

[0333] Specific examples

[0334] For example, if a user wants to develop a new "ice cream product," here are the specific steps:

[0335] 1. User submits a request

[0336] The user requests the collection of SNS data by specifying the keywords "ice cream, new product, summer" on the terminal.

[0337] 2. Data collection and preprocessing

[0338] The server calls the Twitter API, collects posts containing the specified keywords, and preprocesses them.

[0339] 3. Data analysis and taste quantification

[0340] The server analyzes the preprocessed data using natural language processing technology and uses an AI model to generate a taste score such as "sweetness score 90, sourness score 10, saltiness score 5."

[0341] 4. POS data integration and analysis

[0342] The server integrates the taste scores and POS data, analyzes the correlations, and extracts the insight that "ice cream with a high sweetness score records high sales in the summer."

[0343] 5. Emotion Recognition and Report Generation

[0344] The server uses an emotion engine to recognize the user's emotions, and generates a detailed report that is provided to the user's terminal.

[0345] 6. Provision and review of reports

[0346] The user checks the generated report on the terminal and decides on a new product development strategy. For example, based on the report, the user may plan a "new, highly sweet ice cream flavor" for the summer season.

[0347] This system allows users to integrate social media data and POS data to quickly analyze consumer preferences and market trends, and utilize an emotion engine to develop data-driven products.

[0348] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0349] Step 1:

[0350] Sending a social media data collection request

[0351] Users use their devices to request social media data collection by specifying specific keywords (e.g., "ice cream, new product, summer"), the target social media platform (e.g., Twitter, Instagram), and the data collection period (e.g., the past three months).

[0352] Input: Keywords, target platform, collection period

[0353] Output: Social Media Data Collection Request

[0354] Step 2:

[0355] Started collecting social media data

[0356] Based on the received request, the server uses the API of the specified social media platform (e.g., Twitter API) to collect related post data, including the post content, posting date and time, and user ID.

[0357] Input: Social Media Data Collection Request

[0358] Output: Collected social media post data

[0359] Specific operations: Acquiring data through API calls and analyzing responses

[0360] Step 3:

[0361] Data Preprocessing

[0362] The server preprocesses the collected social media post data, specifically removing unnecessary HTML tags, special characters, and unnecessary spaces, and filtering the data to retain the specified language (e.g., Japanese).

[0363] Input: Collected social media post data

[0364] Output: Preprocessed data

[0365] Specific behavior: Text cleaning, language filtering

[0366] Step 4:

[0367] Text analysis using natural language processing technology

[0368] The server then analyzes the preprocessed data using natural language processing techniques. These include morphological analysis, sentiment analysis, and topic modeling. Morphological analysis breaks down text into words and extracts important keywords and phrases. Sentiment analysis calculates positive, negative, and neutral sentiment scores. Topic modeling clusters related posts and extracts key topics.

[0369] Input: Preprocessed data

[0370] Output: Analysis results (morphological analysis results, sentiment scores, topic models)

[0371] Specific operations: Applying NLP algorithms and saving analysis results

[0372] Step 5:

[0373] Quantifying taste using an AI model

[0374] The server's AI model quantifies taste characteristics based on the analysis results, generating taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text.

[0375] Input: Analysis results

[0376] Output: Taste score (e.g. sweet score 90, sour score 10, salty score 5)

[0377] Specific operation: Text analysis and quantification using AI models

[0378] Step 6:

[0379] Integration and analysis of POS data

[0380] The server integrates the taste scores and POS data, and analyzes the relationship between the taste scores and POS data (sales, inventory, price, etc.) based on the integrated data set.

[0381] Input: Taste score, POS data

[0382] Output: Integrated dataset, relationship analysis results

[0383] Specific operations: Data combination, correlation analysis

[0384] Step 7:

[0385] Emotion recognition and insights

[0386] The server uses an emotion engine to recognize user emotions, and based on the results, provides insights into consumer preferences and market trends.

[0387] Input: Integrated dataset, user emotion information

[0388] Output: Insights, detailed reports

[0389] Specific operations: Applying emotion engine, generating reports

[0390] Step 8:

[0391] Generate reports

[0392] The server generates detailed reports based on the integrated data and the output of the emotion engine, including trend analysis and new product recommendations.

[0393] Inputs: Insights, Integrated Data

[0394] Output: Report

[0395] Specific operations: Data embedding and finalization in report template

[0396] Step 9:

[0397] Providing reports

[0398] Users can check the generated reports on their devices, which allows for scientific and efficient product development based on data.

[0399] Input: Report

[0400] Output: New product development strategy

[0401] Specific actions: Downloading and viewing reports, product development decision-making

[0402] In this way, the system integrates social media data and POS data to quickly analyze consumer preferences and market trends, and utilizes an emotion engine to support data-based product development.

[0403] (Application example 2)

[0404] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0405] Conventional content distribution services lack a method for providing optimized content based on a user's individual emotional state or interests. Therefore, to increase user satisfaction, it is necessary to provide personalized content that takes into account social media data and emotional states. Furthermore, more accurate market analysis and prediction of consumer preferences are required by integrating social media data analysis and POS data.

[0406] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0407] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an AI model for quantifying taste based on the analysis results, means for integrating and analyzing the taste visualization data and point-of-sale management data, means for analyzing the user's emotional state from the integrated data and providing individually optimized content, and means for providing the generated report and content recommendation results to the user terminal. This enables the provision of personalized content based on the user's emotional state and interests, improving the accuracy of market analysis and consumer preference prediction.

[0408] "SNS" stands for Social Networking Service, a platform for users to interact and share information online.

[0409] "Posted data" refers to content such as messages, images, and videos posted by users on SNS.

[0410] "Preprocessing" refers to processes such as data cleansing and normalization that are carried out to make collected data ready for analysis.

[0411] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language.

[0412] The "AI model that quantifies taste characteristics" is an artificial intelligence model that extracts taste-related characteristics from text data and converts them into quantitative values.

[0413] "Point of sale data" refers to information collected during the course of a commercial transaction, such as sales and inventory.

[0414] "Emotional state" refers to the psychological state that a user expresses through their posted data.

[0415] "Report format" refers to documents and graphs that are formatted to clearly communicate the results of analysis.

[0416] "Content recommendation" is the act of presenting appropriate content based on a user's interests, concerns, and emotional state.

[0417] A "user terminal" is a device such as a computer, smartphone, or tablet that a user uses to use a service.

[0418] This invention relates to a system that integrates and analyzes SNS data and point-of-sale (POS) data, and uses an emotion engine to provide personalized content tailored to the user's emotional state. This system operates in the following steps:

[0419] Hardware / Software

[0420] This system is application software installed on user devices such as smartphones and tablets, and data processing and analysis are performed on a server. This server includes software for collecting data through the API of the social media platform and analyzing the data using natural language processing technology and AI models.

[0421] The specific hardware and software used are as follows:

[0422] Hardware: smartphones, tablets, servers

[0423] Software: Python (requests, json, textblob libraries), SNS platform API, AI model

[0424] Data processing / data calculation

[0425] The server first calls the API of the social media platform and collects post data based on the specified keywords. This data includes the post content, posting date and time, user ID, etc. The collected data is then preprocessed and unnecessary data is filtered out. After preprocessing, the data is analyzed using natural language processing technology.

[0426] Natural language processing technology performs morphological analysis and sentiment analysis to calculate an emotional score for posts. It also uses an AI model to quantify taste characteristics based on the analysis results. This taste characteristic data is integrated with POS data for comprehensive analysis. Finally, the integrated data is used to analyze the user's emotional state and provide individually optimized content.

[0427] Specific examples

[0428] For example, if a user wants to find new content using the keyword "ice cream," the server calls the social media platform's API to collect relevant post data from the past week. The server then preprocesses this data and uses natural language processing technology to calculate a sentiment score. Based on the sentiment score, the server determines whether the user's emotional state is positive or negative and recommends personalized content.

[0429] Example prompt sentence:

[0430] Keywords: ice cream

[0431] Social Media Platform: Twitter

[0432] Collection period: Past week

[0433] Use a content recommendation system based on sentiment scores to serve content that matches the user's emotional state.

[0434] As described above, the system based on this invention improves user satisfaction by integrating and analyzing users' SNS posting data and POS data, and providing personalized content that corresponds to their individual emotional state.

[0435] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0436] Step 1:

[0437] The server receives a request for collecting SNS data from a user, which includes keywords, target platforms, and a collection period.

[0438] Input: User-specified keywords, target platform, collection period

[0439] Output: Collection request information

[0440] Specific operation: A user sends a social media data collection request from their device by specifying a keyword such as "ice cream" and the "Twitter" platform.

[0441] Step 2:

[0442] The server calls the API of the specified SNS platform and collects post data containing keywords.

[0443] Input: Collection request information

[0444] Output: Collected posting data (post content, date and time, user ID, etc.)

[0445] Specific behavior: The server uses the Twitter API to retrieve posts related to "ice cream" from the past week.

[0446] Step 3:

[0447] The server preprocesses the collected submission data, specifically removing unnecessary HTML tags, special characters, unnecessary spaces, and performing language filtering.

[0448] Input: Collected submission data

[0449] Output: Preprocessed data

[0450] Specific operation: The server removes meaningless characters and posts in foreign languages ​​from the post data it obtains, and extracts only posts in Japanese.

[0451] Step 4:

[0452] The server then analyzes the preprocessed data using natural language processing techniques, conducting morphological analysis to extract important keywords and phrases, and sentiment analysis to calculate a positive, negative, or neutral sentiment score.

[0453] Input: Preprocessed data

[0454] Output: Analysis results (morphological analysis results, emotion scores)

[0455] Specific operation: The server breaks down the text data into morpheme units and calculates the sentiment score using an NLP model.

[0456] Step 5:

[0457] The server quantifies taste characteristics based on the analyzed text data using an AI model, which generates taste scores such as sweetness, sourness, umami, bitterness, and saltiness.

[0458] Input: Analysis results (morphological analysis results, emotion scores)

[0459] Output: Taste score

[0460] Specific operation: The server uses an AI model to quantify taste characteristics from posts about "ice cream," such as "sweetness score 90, sourness score 10."

[0461] Step 6:

[0462] The server integrates the taste scores with point-of-sale (POS) data and analyzes the relationships between them. The visualized taste data is combined with POS data such as sales, inventory, and price into a single dataset.

[0463] Input: Taste score, POS data

[0464] Output: Integrated analysis data (relationship between taste score and POS data)

[0465] Specific operation: The server combines the taste scores with POS data to extract insights such as "ice cream with a high sweetness score records high sales in the summer."

[0466] Step 7:

[0467] The server utilizes an emotion engine to analyze the user's emotional state and provide individually optimized content.

[0468] Input: Integrated analysis data, user sentiment score

[0469] Output: Content recommendation results

[0470] Specific operation: The server recommends, for example, comedy shows for positive emotions and relaxing music for negative emotions based on the user's emotional state.

[0471] Step 8:

[0472] The server provides the generated report and content recommendation results to the user terminal.

[0473] Input: Content recommendation results, report data

[0474] Output: Reports and content recommendations displayed on the user's device

[0475] Specific operation: The user checks the reports and content recommendations sent from the server via a smartphone or tablet.

[0476] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0477] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0478] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0479] [Second embodiment]

[0480] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0481] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0482] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0483] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0484] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0485] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0486] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0487] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0488] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0489] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0490] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0491] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0492] This invention relates to a system for streamlining the development of new food products, and in particular aims to support the development of products based on consumer preferences by integrating and analyzing social media data and POS data. This system collects and analyzes data posted on social media, visualizes taste based on the results, and then integrates and analyzes the data with POS data, thereby realizing scientific, data-driven product development.

[0493] Explanation of program processing

[0494] 1. User requests social media data collection

[0495] Users request the collection of social media data based on specific keywords or hashtags from their device.

[0496] 2. Start collecting social media data

[0497] The server uses the API of the specified social media platform to collect post data containing the requested keywords and hashtags.

[0498] 3. Data Preprocessing

[0499] The server performs preprocessing such as cleansing (removing unnecessary characters and tags) and language filtering (excluding data in languages ​​other than the target language) on the collected SNS post data.

[0500] 4. Text analysis using natural language processing technology

[0501] The server performs morphological analysis on the preprocessed data to extract important keywords, and also analyzes the sentiment score and topics of posts using sentiment analysis and topic modeling.

[0502] 5. Quantifying taste using an AI model

[0503] The server's AI model quantifies specific taste characteristics (sweetness, sourness, umami, etc.) based on the analyzed text data. In doing so, the AI ​​extracts relevant taste information from the text and expresses it as a score.

[0504] 6. Integration and analysis of POS data

[0505] The server integrates the visualized taste data with point-of-sale (POS) data and compiles it into a single dataset, allowing for analysis of the correlation between taste scores and actual sales data.

[0506] 7. Generate Reports

[0507] The server extracts insights from the integrated data and automatically generates detailed reports including trend analysis, consumer preference predictions, and new product suggestions.

[0508] 8. Check the report

[0509] Users can check the reports generated on their devices and use them to develop new products and improve existing products based on scientific evidence.

[0510] Specific examples

[0511] For example, if a user wants to develop a new "chocolate product," the following specific example can be considered.

[0512] 1. User submits a request:

[0513] The user requests the collection of social media data by specifying the keywords "chocolate, new product, trend" on the device.

[0514] 2. Data Collection:

[0515] The server collects posts containing specified keywords from social media platforms such as Twitter and Instagram.

[0516] 3. Data Preprocessing and Analysis:

[0517] The server preprocesses the collected data, performs morphological analysis, and identifies posts with strong positive sentiment and posts with weak negative sentiment.

[0518] 4. Quantifying taste:

[0519] The server's AI model generates values ​​such as "sweetness score 80, sourness score 20, umami score 50."

[0520] 5. Integration with POS data:

[0521] Based on the integrated data, the server extracts insights such as "products with high sweetness scores record high sales in winter."

[0522] 6. Provision of Report:

[0523] The user checks the generated report on the terminal and decides on a development strategy for a new chocolate product.

[0524] This system will be a powerful tool for users to develop products efficiently and based on data. By integrating and analyzing social media data and POS data, users can quickly bring products to market that meet consumer demand.

[0525] The processing flow will be explained below.

[0526] Step 1:

[0527] A user submits a request for collection of social media data related to a specific product development from their device, including keywords or hashtags of interest, target social media platforms (e.g., Twitter, Instagram, etc.), and a collection period.

[0528] Step 2:

[0529] The server calls the API of the target social media platform based on the received request and collects post data containing the specified keywords and hashtags. The data obtained from the API includes the post content, posting date and time, user ID, etc.

[0530] Step 3:

[0531] The server preprocesses the collected social media post data. Specifically, it removes unnecessary HTML tags and special characters, eliminates unnecessary spaces, and performs language filtering to exclude data in languages ​​other than the target language. It also normalizes the data to unify the data format.

[0532] Step 4:

[0533] The server analyzes the pre-processed data using natural language processing (NLP) techniques, including:

[0534] Morphological analysis: Breaks down the content of social media posts into morphemes and extracts important keywords and phrases.

[0535] Sentiment Analysis: Calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post.

[0536] Topic modeling: Grouping similar posts and extracting major topics.

[0537] Step 5:

[0538] The server's AI model quantifies taste characteristics based on the analyzed text data. The model extracts taste-related information from the text and generates scores for sweetness, sourness, umami, bitterness, saltiness, etc.

[0539] Step 6:

[0540] The server integrates the visualized taste data with point-of-sale (POS) data. Specifically, it combines taste scores and POS data (sales, inventory, price, etc.) into a single integrated data set. This allows for analysis of the correlation between taste data and actual sales data.

[0541] Step 7:

[0542] The server analyzes changes in consumer preferences and market trends based on the integrated data, extracts important insights and patterns, and creates reports for efficient and effective product development.

[0543] Step 8:

[0544] The server delivers automatically generated reports to the user's device, including trend analysis, consumer preference predictions, and new product suggestions.

[0545] Step 9:

[0546] Users can check the reports on their devices and develop products scientifically and efficiently based on the data. Based on these reports, they can plan new products and prepare to respond quickly to changes in the market.

[0547] By following the above steps, users can integrate and analyze social media data and POS data, enabling them to efficiently develop data-based products.

[0548] Example 1

[0549] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0550] In conventional new food product development, it is difficult to accurately grasp consumer preferences, and because product development is not based on data, it is difficult to quickly bring products that meet consumer needs to market. The objective of this invention is to support more efficient and effective product development by integrating and analyzing SNS data and point-of-sale management data to scientifically visualize consumer preferences.

[0551] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0552] In this invention, the server includes: means for a user to request collection of SNS data based on specific keywords or hashtags from a terminal; means for collecting posted data including the requested keywords or hashtags using the API of the SNS platform; means for cleansing and language filtering the collected posted data; means for analyzing the preprocessed data using morphological analysis, sentiment analysis, and topic modeling; means for using a generative AI model that quantifies specific taste characteristics based on text data; means for integrating and analyzing visualized taste data and point-of-sale data; means for extracting insights from the integrated data and generating reports such as trend analysis, consumer preference predictions, and new product suggestions; and means for providing the generated reports in a format that can be viewed on the user's terminal. This enables scientific understanding of consumer preferences based on data and rapid and efficient launch of new products to the market.

[0553] "SNS data" refers to information such as messages, comments, tags, images, and videos posted by users on social networking services.

[0554] "API" stands for Application Programming Interface and refers to the interface or protocol for exchanging functions and data between software programs.

[0555] "Collection method" refers to a method or system for obtaining specific information from the Internet or a database.

[0556] "Cleansing" refers to the process of removing unnecessary characters, tags, duplicate data, etc. in the data preprocessing process to improve the quality of the data.

[0557] "Language filtering" refers to the process of extracting data related to a specific language and excluding data in other languages.

[0558] "Morphological analysis" refers to a natural language processing technique that breaks down a sentence into its smallest meaningful units and extracts the parts of speech and morphemes of each word.

[0559] "Sentiment analysis" refers to the technology of analyzing trends such as positive and negative emotions and opinions from text data.

[0560] "Topic modeling" refers to a method for discovering common themes and topics from large amounts of text data.

[0561] An "AI model" refers to an algorithm or neural network that uses artificial intelligence, a system that can automatically perform specific tasks by learning from large amounts of data.

[0562] "Taste characteristics" refers to the numerical expression of specific taste characteristics of food (e.g., sweetness, sourness, umami, etc.).

[0563] "Point of sale data (POS data)" refers to data collected at the time of sale of a product, including details such as sales, inventory, and customer information.

[0564] "Integration" refers to the process of combining different data sets into one and analyzing and using them comprehensively.

[0565] "Insight" refers to insights and findings gained through data analysis.

[0566] "Trend analysis" refers to the technique of analyzing current trends and patterns based on past data and predicting future trends.

[0567] "New product proposal" refers to proposing new product development ideas and concepts based on market needs and trends.

[0568] A "report" refers to a document or material that summarizes analytical results and insights and provides information to assist users in making decisions.

[0569] This invention is a system for streamlining the development of new food products, and its purpose is to support the development of products based on consumer preferences by integrating and analyzing social media data and point-of-sale (POS) data. This system collects and analyzes data posted on social media, quantifies taste based on the results, and then integrates and analyzes the results with POS data, thereby realizing scientific, data-driven product development.

[0570] Data collection and preprocessing

[0571] A user uses a device to request the collection of social media data based on specific keywords or hashtags. The server then uses the API of the specified social media platform to collect post data containing the requested keywords or hashtags. Examples of APIs used in this collection process include the Twitter API and Instagram API.

[0572] The collected data undergoes preprocessing on the server side, including cleansing (removing unnecessary characters and tags) and language filtering (excluding data in languages ​​other than the target language). Software used for this includes the Python libraries regex and beautifulsoup.

[0573] Use of natural language processing technology

[0574] The preprocessed data is then analyzed by the server using natural language processing techniques such as morphological analysis, sentiment analysis, and topic modeling. For morphological analysis, natural language processing libraries such as NLTK and spaCy are used, and for sentiment analysis, TextBlob and VADER are used.

[0575] Quantifying taste characteristics

[0576] Based on the analyzed text data, a generative AI model on the server quantifies specific taste characteristics. This is done using deep learning frameworks such as TensorFlow and PyTorch. The model expresses taste characteristics such as sweetness, sourness, and umami as numerical values ​​based on keywords and sentiment scores extracted from the text data.

[0577] Data Integration and Reporting

[0578] The server integrates the quantified taste data and POS data into a single data set, allowing for analysis of the correlation between taste scores and sales data. This process uses MySQL or PostgreSQL as the database system.

[0579] It extracts insights from the integrated data and automatically generates detailed reports such as trend analysis, consumer preference predictions, new product suggestions, etc. Data visualization tools used include Matplotlib and Plotly, and the generated reports are exported in PDF or Excel format.

[0580] Users can check the reports generated on their devices and use them to develop new products or improve existing products based on scientific evidence. This system enables users to develop products efficiently and based on data.

[0581] Specific examples

[0582] For example, if a user wants to develop a new "chocolate product," the following is a specific example.

[0583] 1. User submits a request:

[0584] The user requests the collection of social media data by specifying the keywords "chocolate, new product, trend" on the device.

[0585] 2. Data Collection:

[0586] The server collects posts containing specified keywords from social media platforms such as Twitter and Instagram.

[0587] 3. Data Preprocessing and Analysis:

[0588] The server preprocesses the collected data, performs morphological analysis, and identifies posts with strong positive sentiment and weak negative sentiment.

[0589] 4. Quantifying taste:

[0590] The server's AI model generates values ​​such as "sweetness score 80, sourness score 20, umami score 50."

[0591] 5. Integration with POS data:

[0592] Based on the integrated data, the server extracts insights such as "products with high sweetness scores record high sales in winter."

[0593] 6. Provision of Report:

[0594] The user checks the generated report on the terminal and decides on a development strategy for a new chocolate product.

[0595] Prompt Sentence Examples

[0596] Examples of prompts to input to a generative AI model might include:

[0597] Regarding a new chocolate product, please collect data from Twitter and Instagram posts containing the keywords "chocolate, new product, trend." Also, please quantify the taste characteristics of the new product based on the collected data and integrate it with POS data to provide insights for optimal product development.

[0598] As described above, the present invention integrates SNS data and POS data, enabling scientific product development based on consumer preferences.

[0599] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0600] Step 1:

[0601] A user requests the collection of social media data based on specific keywords or hashtags from their device.

[0602] Specific operation: The user enters keywords into the input form specified in the dedicated application on the device and clicks the "Collect data" button.

[0603] Input: User-specified keywords and hashtags.

[0604] Output: A social media data collection request is sent to the server.

[0605] Step 2:

[0606] The server uses the API of the social media platform to collect post data containing the requested keywords and hashtags.

[0607] Specific operation: The server uses the API key to send a request to the social media platform (e.g., Twitter, Instagram) and retrieves the relevant post data.

[0608] Input: User-specified keywords, hashtags, and API keys.

[0609] Output: Retrieved social media post data.

[0610] Step 3:

[0611] The server cleanses and language filters the social media post data collected.

[0612] Specific operation: A Python script on the server uses libraries such as regex and beautifulsoup to remove unnecessary characters and tags from the data and exclude data in languages ​​other than the target language.

[0613] Input: Collected social media posting data.

[0614] Output: Preprocessed SNS data.

[0615] Step 4:

[0616] The server analyzes the preprocessed data using morphological analysis, sentiment analysis, and topic modeling.

[0617] How it works: It uses NLTK and spaCy libraries for morphological analysis, TextBlob and VADER for sentiment analysis, and Gensim for topic modeling.

[0618] Input: Preprocessed SNS data.

[0619] Output: Morphological analysis results, sentiment score, topic information.

[0620] Step 5:

[0621] The server's generative AI model quantifies specific taste characteristics based on the analyzed text data.

[0622] Specific operation: Using a deep learning framework (e.g., TensorFlow, PyTorch), a trained model quantifies sweetness, sourness, umami, etc. from text data.

[0623] Input: Morphological analysis results, sentiment scores, topic information.

[0624] Output: Numerical data of taste attributes (e.g., sweetness score 80, sourness score 20, umami score 50).

[0625] Step 6:

[0626] The server integrates and analyzes the visualized taste data and point-of-sale data (POS data).

[0627] Specific operation: Executes an SQL query on a database system (e.g., MySQL, PostgreSQL) to combine taste data and POS data.

[0628] Input: Numerical data of taste characteristics, POS data.

[0629] Output: A consolidated dataset.

[0630] Step 7:

[0631] The server extracts insights from the integrated data and generates reports such as trend analysis, consumer preference predictions, and new product suggestions.

[0632] Specific behavior: Create graphs and charts using data visualization tools (e.g., Matplotlib, Plotly) and export reports in PDF and Excel formats.

[0633] Input: The integrated dataset.

[0634] Output: Detailed report (e.g. PDF, Excel file).

[0635] Step 8:

[0636] The user checks the generated report on the device.

[0637] Specific operation: The user downloads the generated report using a dedicated application on the device and reviews the contents.

[0638] Input: Detailed report (e.g. PDF, Excel file).

[0639] Output: Report information reviewed by the user.

[0640] (Application example 1)

[0641] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0642] In the past, new food product development relied mainly on sales data and survey results, as it was difficult to accurately grasp consumer preferences and market trends. As a result, planning and development of new products that quickly reflected the latest consumer preferences and trends tended to be delayed. Furthermore, it was difficult for employees to utilize this data to propose new products, which led to inefficient product deployment in physical stores.

[0643] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0644] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an AI model for quantifying taste based on the analysis results, means for integrating and analyzing the visualized taste data and point-of-sale management data, means for generating the analysis results in report format, and means for providing the generated report to a user's visual display device. This enables the planning and development of new products that quickly and accurately reflect the latest consumer preferences, and allows employees at physical stores to use this data in real time to help with sales strategies and product development.

[0645] "Means for collecting post data from social media" refers to a system for collecting post data from social media platforms based on specific keywords or hashtags.

[0646] "Means for preprocessing collected post data" refers to the process of deleting unnecessary characters and tags from the collected SNS post data and excluding data in languages ​​other than the target language.

[0647] "Means of analysis using natural language processing technology" refers to a system that uses preprocessed data to analyze it using natural language processing technology such as morphological analysis, sentiment analysis, and topic modeling.

[0648] "Means of using an AI model" refers to a mechanism that utilizes an artificial intelligence model to quantify specific taste characteristics based on analyzed text data.

[0649] "Means for integrating and analyzing visualized taste data and point-of-sale management data" is a system that integrates visualized taste data and sales data and analyzes correlations.

[0650] "Means for generating analysis results in report format" refers to a system that automatically generates reports based on insights gained from integrated data.

[0651] The "means for providing the generated report to the user's visual display device" refers to a mechanism for displaying the generated report in real time on the user's visual display device, such as smart glasses.

[0652] This invention consists of a system that can be applied to support new product development in brick-and-mortar stores. This system collects and analyzes data from social media, and integrates and analyzes it with point-of-sale (POS) data to intuitively support users in developing new products and formulating sales strategies. Specific embodiments for implementing this invention are described below.

[0653] 1. Generate the program:

[0654] This system consists of a server, a terminal, and the user's visual display device. The server runs a program that collects posted data from SNS and preprocesses the collected data. This preprocessing includes removing unnecessary characters and tags and excluding data in a language other than the target language. The data is then analyzed using natural language processing techniques (morphological analysis, sentiment analysis, topic modeling, etc.) to quantify taste characteristics (sweetness, sourness, umami, etc.). The server integrates these analysis results with the POS data, analyzes them as a single dataset, and automatically generates a report. This report is provided in real time to the user's visual display device.

[0655] 2. Natural language processing description:

[0656] Specifically, when collecting data from social media platforms, the server uses the APIs of each platform. For data preprocessing, Python libraries (e.g., NLTK, SpaCy) are used to clean and filter text. For morphological analysis and sentiment analysis, Google Cloud Natural Language API is used. Furthermore, machine learning frameworks (e.g., TensorFlow, PyTorch) are used to quantify taste using an AI model. Google Cloud BigQuery is used to integrate and analyze the analysis results and POS data, and Google Data Studio is used to generate reports. Smart glasses, such as Google Glass, are used as visual display devices. These devices allow users to manipulate data through voice commands or touch operations.

[0657] 3. Adding concrete examples:

[0658] For example, consider the case where a user develops a new "seasonal chocolate flavor." The user specifies the keywords "seasonal, flavor, chocolate" on a visual display device and requests the collection of social media data. The server collects posts containing the specified keywords from Twitter and Instagram and performs preprocessing. The analysis results generate numerical values ​​such as "sweetness score 85, sourness score 15, umami score 40." These values ​​are then integrated with POS data to extract insights such as "products with high sweetness scores record high sales in spring." Finally, these analysis results are displayed in real time on the user's visual display device, smart glasses.

[0659] Examples of prompts for a generative AI model might include:

[0660] "Please quantify the taste characteristics (sweetness, sourness, umami) from the following social media posts."

[0661] This chocolate is so sweet and delicious!

[0662] "This chocolate is too sour."

[0663] "This chocolate has an exquisite flavor."

[0664] As described above, the system embodying this invention makes it possible to efficiently plan and develop new products in physical stores that quickly and accurately reflect the latest consumer preferences.

[0665] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0666] Step 1:

[0667] A user requests social media data collection.

[0668] The user requests the collection of social media data by specifying keywords such as "seasonal, flavor, chocolate" on the visual display. The input is the specified keyword, and the output is the transmission of a collection command. The visual display is used to execute the request by voice command or touch operation.

[0669] Step 2:

[0670] The server starts collecting social media data.

[0671] The server uses the social media platform API to collect post data based on the specified keywords. The input is the requested keywords, and the output is the collected social media post data. Specifically, the data is collected from Twitter and Instagram and saved in JSON format on the server.

[0672] Step 3:

[0673] The server preprocesses the collected submission data.

[0674] The collected post data is preprocessed by the server. The input is the collected SNS post data, and the output is the preprocessed data. Specifically, Python's NLTK and SpaCy are used to remove unnecessary characters and tags, and to exclude data in languages ​​other than the target language.

[0675] Step 4:

[0676] The server analyzes the preprocessed data using natural language processing techniques.

[0677] Based on the preprocessed data, the server uses natural language processing technology to perform sentiment analysis and topic modeling. The input is the preprocessed data, and the output is the analysis results. Specifically, it uses the Google Cloud Natural Language API to extract important keywords and analyze sentiment scores.

[0678] Step 5:

[0679] The server uses an AI model to quantify the taste based on the analysis results.

[0680] Based on the analyzed text data, the server uses an AI model to quantify specific taste characteristics. The input is the analysis result, and the output is a taste score. Specifically, TensorFlow and PyTorch are used to generate scores for sweetness, sourness, and umami.

[0681] Step 6:

[0682] The server integrates and analyzes taste visualization data and point-of-sale (POS) data.

[0683] The taste scores and POS data from physical stores are integrated and analyzed as a single dataset. The inputs are taste scores and POS data, and the output is an integrated dataset. Specifically, the data is integrated using Google Cloud BigQuery and correlation analysis is performed.

[0684] Step 7:

[0685] The server generates a report from the analysis results.

[0686] Based on the insights gained from the integrated data, the server automatically generates detailed reports. The input is the integrated dataset and the output is the report. The reports are generated using Google Data Studio and visually displayed in graphs and charts.

[0687] Step 8:

[0688] The server provides the generated report to the user's visual display.

[0689] The generated report is provided in real time to the user's visual display device. The input is the generated report, and the output is the displayed report. The report is displayed on a visual display device (e.g., smart glasses) and can be confirmed by the user via voice or touch.

[0690] Above, we have described the specific processing operations and inputs / outputs for each step, and have explained in detail the processing flow of the entire system.

[0691] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0692] This invention relates to a system that supports product development by integrating and analyzing social media data and POS data, and using an emotion engine in combination. This system analyzes posted data collected from social media, quantifies the analysis results into taste, and integrates the analysis with sales data, while recognizing user emotions and providing insights.

[0693] Explanation of program processing

[0694] 1. User requests social media data collection

[0695] The user sends a request for collecting social media data related to a specific product development from their device. The request includes keywords, target platforms, and a collection period.

[0696] 2. Start collecting social media data

[0697] The server calls the API of the specified social media platform and collects post data including keywords and hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[0698] 3. Data Preprocessing

[0699] The server preprocesses the collected social media post data. Specifically, it removes unnecessary HTML tags, special characters, and unnecessary spaces, and performs language filtering. Language filtering excludes posts in languages ​​other than the target language.

[0700] 4. Text analysis using natural language processing technology

[0701] The server analyzes the preprocessed data using natural language processing techniques. The analysis operations include:

[0702] Morphological analysis: Breaks down text into morpheme units and extracts important keywords and phrases.

[0703] Sentiment Analysis: Calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post.

[0704] Topic modeling: Clustering relevant posts and extracting major topics.

[0705] 5. Quantifying taste using an AI model

[0706] The server's AI model quantifies taste characteristics based on the analyzed text data, generating taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text.

[0707] 6. Integration and analysis of POS data

[0708] The server integrates the visualized taste data with point-of-sale (POS) data, combining taste scores and POS data (sales, inventory, price, etc.) into a single dataset and analyzing the relationships between them.

[0709] 7. Emotion recognition and insights

[0710] The server utilizes an emotion engine to recognize the user's emotions and provide insights based on the analysis results, which then generates a detailed report reflecting the user's emotional state.

[0711] 8. Generate Reports

[0712] The server generates detailed reports on changing consumer preferences and market trends based on the integrated data and the output of the emotion engine, including trend analysis, consumer preference predictions, and new product suggestions.

[0713] 9. Check the report

[0714] Users can check the reports generated on their devices and develop products scientifically and efficiently based on the data. Based on these reports, they can plan new products and prepare to respond quickly to changes in the market.

[0715] Specific examples

[0716] For example, if a user wants to develop a new "ice cream product," the following specific example can be considered.

[0717] 1. User submits a request:

[0718] The user requests the collection of SNS data by specifying the keywords "ice cream, new product, summer" on the terminal.

[0719] 2. Data collection and preprocessing:

[0720] The server collects posts containing the specified keywords from the social media platform. After collection, unnecessary data is removed and preprocessed.

[0721] 3. Data analysis and taste quantification:

[0722] The server performs natural language processing on the preprocessed data and then uses an AI model to generate a taste score, such as "sweet score 90, sour score 10, salty score 5."

[0723] 4. POS data integration and analysis:

[0724] The server integrates the taste scores with POS data to extract the insight that "ice cream with a high sweetness score records high sales in the summer."

[0725] 5. Emotion Recognition and Report Generation:

[0726] The server uses an emotion engine to recognize user emotions and generates detailed reports that provide insights based on the analysis results.

[0727] 6. Report provision and review:

[0728] Users can check the reports generated on their devices and decide on new product development strategies. Insights based on emotion information can help plan products that are more likely to be accepted by consumers.

[0729] This system helps users analyze consumer preferences and market trends based on social media and POS data, and utilizes an emotion engine to respond quickly, enabling scientific and data-based product development and efficient response to market changes.

[0730] The processing flow will be explained below.

[0731] Step 1:

[0732] Users submit a request for social media data collection related to new product developments from their device by inputting keywords of interest (e.g., "chocolate," "new product," "trend"), target social media platforms (e.g., Twitter, Instagram), and the data collection period.

[0733] Step 2:

[0734] The server calls the API of the social media platform based on the received request and collects posts containing the specified keywords or hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[0735] Step 3:

[0736] The server preprocesses the collected SNS data. Specifically, it performs the following operations:

[0737] Remove unnecessary characters: Remove HTML tags, special characters, emojis, etc.

[0738] Language filtering: Filter out posts in languages ​​other than your target language (e.g., if you only target Japanese).

[0739] Text normalization: unifying full-width and half-width characters, converting uppercase and lowercase characters, etc.

[0740] Step 4:

[0741] The server analyzes the preprocessed data using natural language processing (NLP) technology. Specifically, it performs the following processes:

[0742] Morphological analysis: Breaks down the text of a post into morphemes and extracts important keywords.

[0743] Sentiment analysis: Calculates positive, negative, and neutral sentiment scores.

[0744] Topic modeling: Clustering posts and extracting major topics.

[0745] Step 5:

[0746] The server's AI model quantifies taste characteristics based on the analysis results. Specifically, it generates scores for sweetness, sourness, umami, bitterness, saltiness, etc. from the text data. This taste quantification visualizes the consumer's post as specific taste characteristics.

[0747] Step 6:

[0748] The server integrates and analyzes taste data and point-of-sale (POS) data. Specifically, it performs the following operations:

[0749] Data integration: Integrate taste scores and POS data (sales, inventory, price, etc.) into one.

[0750] Association analysis: Based on the integrated data, the relationship between taste characteristics and sales performance is analyzed (e.g., products with high sweetness scores have high sales).

[0751] Step 7:

[0752] The server uses an emotion engine to recognize the user's emotions. Specifically, it evaluates the user's emotional state in real time based on the user's operation history and input information when they access the system.

[0753] Step 8:

[0754] The server adds insights corresponding to the user's emotional state to the report based on the output of the emotion engine, thereby generating a detailed report containing insights based on the user's emotions.

[0755] Step 9:

[0756] The server provides the generated report to the user's device, where the user can check the report and develop products based on scientific evidence and data.

[0757] Step 10:

[0758] Users can use the reports provided on their devices to decide on new product plans and development policies, enabling them to quickly develop products that respond to consumer preferences and market trends.

[0759] In this way, this system integrates and analyzes SNS data and POS data, and by combining it with an emotion engine, provides product development support based on data that is useful to users.

[0760] Example 2

[0761] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0762] Conventional methods have made it difficult to efficiently integrate social media data and point-of-sale data to quickly understand consumer preferences and market trends. Furthermore, there is a lack of means to recognize user emotions using an emotion engine or generate detailed reports, which hinders the efficiency of the scientific, data-driven product development process. To solve these problems, a system is needed that can consistently analyze social media data, quantify taste perception, integrate data, recognize emotions, and generate reports.

[0763] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0764] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an artificial intelligence model that quantifies taste based on the analysis results, means for integrating and analyzing the taste visualization data and point-of-sale management data, means for recognizing user emotions using an emotion engine, means for generating a detailed report based on the integrated data and the output of the emotion engine, and means for providing the generated report to the user's terminal. This enables rapid understanding of consumer preferences and market trends and enables scientific product development based on data.

[0765] "SNS data" refers to information such as user messages, comments, images, and videos posted on social media platforms.

[0766] "Preprocessing" refers to the process of removing unnecessary information from collected data and converting it into a format suitable for analysis.

[0767] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language.

[0768] An "artificial intelligence model" refers to an algorithm that learns from large amounts of data and makes predictions and analyses based on that data.

[0769] "Quantifying taste" refers to the process of extracting taste characteristics (sweetness, sourness, umami, bitterness, saltiness, etc.) from text data and expressing those characteristics numerically.

[0770] "Point of sale data" refers to data used to manage sales information in real time, including product sales, inventory, prices, etc.

[0771] "Emotion engine" refers to an algorithm or system for analyzing and recognizing a user's emotions.

[0772] "Report" means a written or digital report summarizing the results of an analysis or insights.

[0773] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0774] "User" refers to the person or company that uses the system to collect, analyze, and check reports on social media data.

[0775] This invention is a system that integrates and analyzes social media data and point-of-sale (POS) data to recognize user sentiment and support product development. The system collects, analyzes, and integrates data through multiple steps, and finally generates a report to provide to the user.

[0776] The main components of this system include a server, a terminal, and a user. The configuration of this system and a specific embodiment will be described in detail below.

[0777] Data collection and preprocessing

[0778] A user requests the collection of social media data through their device. The request includes specific keywords (e.g., "ice cream, new products, summer"), the target social media platform (e.g., Twitter, Instagram), and the data collection period (e.g., the past three months).

[0779] The server receives a request from a user and uses the API of the social media platform (e.g., Twitter API) to collect post data containing the specified keywords and hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[0780] The server then pre-processes the collected data, which includes removing unnecessary HTML tags, special characters, and unnecessary spaces, and language filtering to retain only the specified language (e.g., Japanese).

[0781] Text analysis and quantification of taste

[0782] The preprocessed data is then analyzed on the server using natural language processing (NLP) techniques. This analysis includes morphological analysis, sentiment analysis, and topic modeling. Morphological analysis breaks down text into words and extracts important keywords and phrases. Sentiment analysis calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post. Topic modeling clusters related posts and extracts major topics.

[0783] The server's AI model quantifies taste characteristics based on the analyzed text data. This model generates taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text. For example, a score such as "sweetness score 90, sourness score 10, saltiness score 5" may be generated.

[0784] Integration and analysis of POS data

[0785] The server integrates the taste scores with the POS data. The POS data includes sales-related information such as sales, inventory, and price. The integrated data is analyzed on the server to analyze the relationship between the taste scores and the POS data. For example, an insight such as "ice cream with a high sweetness score records high sales in the summer" can be extracted.

[0786] Emotion Recognition and Report Generation

[0787] The server uses an emotion engine to recognize the user's emotions and generates a detailed report based on the results, including changes in consumer preferences, market trends, insights, consumer preference predictions, and new product suggestions. The report is provided to the user's device, where the user can review it and decide on a new product development strategy.

[0788] Specific examples

[0789] For example, if a user wants to develop a new "ice cream product," here are the specific steps:

[0790] 1. User submits a request

[0791] The user requests the collection of SNS data by specifying the keywords "ice cream, new product, summer" on the terminal.

[0792] 2. Data collection and preprocessing

[0793] The server calls the Twitter API, collects posts containing the specified keywords, and preprocesses them.

[0794] 3. Data analysis and taste quantification

[0795] The server analyzes the preprocessed data using natural language processing technology and uses an AI model to generate a taste score such as "sweetness score 90, sourness score 10, saltiness score 5."

[0796] 4. POS data integration and analysis

[0797] The server integrates the taste scores and POS data, analyzes the correlations, and extracts the insight that "ice cream with a high sweetness score records high sales in the summer."

[0798] 5. Emotion Recognition and Report Generation

[0799] The server uses an emotion engine to recognize the user's emotions, and generates a detailed report that is provided to the user's terminal.

[0800] 6. Provision and review of reports

[0801] The user checks the generated report on the terminal and decides on a new product development strategy. For example, based on the report, the user may plan a "new, highly sweet ice cream flavor" for the summer season.

[0802] This system allows users to integrate social media data and POS data to quickly analyze consumer preferences and market trends, and utilize an emotion engine to develop data-driven products.

[0803] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0804] Step 1:

[0805] Sending a social media data collection request

[0806] Users use their devices to request social media data collection by specifying specific keywords (e.g., "ice cream, new product, summer"), the target social media platform (e.g., Twitter, Instagram), and the data collection period (e.g., the past three months).

[0807] Input: Keywords, target platform, collection period

[0808] Output: Social Media Data Collection Request

[0809] Step 2:

[0810] Started collecting social media data

[0811] Based on the received request, the server uses the API of the specified social media platform (e.g., Twitter API) to collect related post data, including the post content, posting date and time, and user ID.

[0812] Input: Social Media Data Collection Request

[0813] Output: Collected social media post data

[0814] Specific operations: Acquiring data through API calls and analyzing responses

[0815] Step 3:

[0816] Data Preprocessing

[0817] The server preprocesses the collected social media post data, specifically removing unnecessary HTML tags, special characters, and unnecessary spaces, and filtering the data to retain the specified language (e.g., Japanese).

[0818] Input: Collected social media post data

[0819] Output: Preprocessed data

[0820] Specific behavior: Text cleaning, language filtering

[0821] Step 4:

[0822] Text analysis using natural language processing technology

[0823] The server then analyzes the preprocessed data using natural language processing techniques. These include morphological analysis, sentiment analysis, and topic modeling. Morphological analysis breaks down text into words and extracts important keywords and phrases. Sentiment analysis calculates positive, negative, and neutral sentiment scores. Topic modeling clusters related posts and extracts key topics.

[0824] Input: Preprocessed data

[0825] Output: Analysis results (morphological analysis results, sentiment scores, topic models)

[0826] Specific operations: Applying NLP algorithms and saving analysis results

[0827] Step 5:

[0828] Quantifying taste using an AI model

[0829] The server's AI model quantifies taste characteristics based on the analysis results, generating taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text.

[0830] Input: Analysis results

[0831] Output: Taste score (e.g. sweet score 90, sour score 10, salty score 5)

[0832] Specific operation: Text analysis and quantification using AI models

[0833] Step 6:

[0834] Integration and analysis of POS data

[0835] The server integrates the taste scores and POS data, and analyzes the relationship between the taste scores and POS data (sales, inventory, price, etc.) based on the integrated data set.

[0836] Input: Taste score, POS data

[0837] Output: Integrated dataset, relationship analysis results

[0838] Specific operations: Data combination, correlation analysis

[0839] Step 7:

[0840] Emotion recognition and insights

[0841] The server uses an emotion engine to recognize user emotions, and based on the results, provides insights into consumer preferences and market trends.

[0842] Input: Integrated dataset, user emotion information

[0843] Output: Insights, detailed reports

[0844] Specific operations: Applying emotion engine, generating reports

[0845] Step 8:

[0846] Generate reports

[0847] The server generates detailed reports based on the integrated data and the output of the emotion engine, including trend analysis and new product recommendations.

[0848] Inputs: Insights, Integrated Data

[0849] Output: Report

[0850] Specific operations: Data embedding and finalization in report template

[0851] Step 9:

[0852] Providing reports

[0853] Users can check the generated reports on their devices, which allows for scientific and efficient product development based on data.

[0854] Input: Report

[0855] Output: New product development strategy

[0856] Specific actions: Downloading and viewing reports, product development decision-making

[0857] In this way, the system integrates social media data and POS data to quickly analyze consumer preferences and market trends, and utilizes an emotion engine to support data-based product development.

[0858] (Application example 2)

[0859] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0860] Conventional content distribution services lack a method for providing optimized content based on a user's individual emotional state or interests. Therefore, to increase user satisfaction, it is necessary to provide personalized content that takes into account social media data and emotional states. Furthermore, more accurate market analysis and prediction of consumer preferences are required by integrating social media data analysis and POS data.

[0861] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0862] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an AI model for quantifying taste based on the analysis results, means for integrating and analyzing the taste visualization data and point-of-sale management data, means for analyzing the user's emotional state from the integrated data and providing individually optimized content, and means for providing the generated report and content recommendation results to the user terminal. This enables the provision of personalized content based on the user's emotional state and interests, improving the accuracy of market analysis and consumer preference prediction.

[0863] "SNS" stands for Social Networking Service, a platform for users to interact and share information online.

[0864] "Posted data" refers to content such as messages, images, and videos posted by users on SNS.

[0865] "Preprocessing" refers to processes such as data cleansing and normalization that are carried out to make collected data ready for analysis.

[0866] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language.

[0867] The "AI model that quantifies taste characteristics" is an artificial intelligence model that extracts taste-related characteristics from text data and converts them into quantitative values.

[0868] "Point of sale data" refers to information collected during the course of a commercial transaction, such as sales and inventory.

[0869] "Emotional state" refers to the psychological state that a user expresses through their posted data.

[0870] "Report format" refers to documents and graphs that are formatted to clearly communicate the results of analysis.

[0871] "Content recommendation" is the act of presenting appropriate content based on a user's interests, concerns, and emotional state.

[0872] A "user terminal" is a device such as a computer, smartphone, or tablet that a user uses to use a service.

[0873] This invention relates to a system that integrates and analyzes SNS data and point-of-sale (POS) data, and uses an emotion engine to provide personalized content tailored to the user's emotional state. This system operates in the following steps:

[0874] Hardware / Software

[0875] This system is application software installed on user devices such as smartphones and tablets, and data processing and analysis are performed on a server. This server includes software for collecting data through the API of the social media platform and analyzing the data using natural language processing technology and AI models.

[0876] The specific hardware and software used are as follows:

[0877] Hardware: smartphones, tablets, servers

[0878] Software: Python (requests, json, textblob libraries), SNS platform API, AI model

[0879] Data processing / data calculation

[0880] The server first calls the API of the social media platform and collects post data based on the specified keywords. This data includes the post content, posting date and time, user ID, etc. The collected data is then preprocessed and unnecessary data is filtered out. After preprocessing, the data is analyzed using natural language processing technology.

[0881] Natural language processing technology performs morphological analysis and sentiment analysis to calculate an emotional score for posts. It also uses an AI model to quantify taste characteristics based on the analysis results. This taste characteristic data is integrated with POS data for comprehensive analysis. Finally, the integrated data is used to analyze the user's emotional state and provide individually optimized content.

[0882] Specific examples

[0883] For example, if a user wants to find new content using the keyword "ice cream," the server calls the social media platform's API to collect relevant post data from the past week. The server then preprocesses this data and uses natural language processing technology to calculate a sentiment score. Based on the sentiment score, the server determines whether the user's emotional state is positive or negative and recommends personalized content.

[0884] Example prompt sentence:

[0885] Keywords: ice cream

[0886] Social Media Platform: Twitter

[0887] Collection period: Past week

[0888] Use a content recommendation system based on sentiment scores to serve content that matches the user's emotional state.

[0889] As described above, the system based on this invention improves user satisfaction by integrating and analyzing users' SNS posting data and POS data, and providing personalized content that corresponds to their individual emotional state.

[0890] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0891] Step 1:

[0892] The server receives a request for collecting SNS data from a user, which includes keywords, target platforms, and a collection period.

[0893] Input: User-specified keywords, target platform, collection period

[0894] Output: Collection request information

[0895] Specific operation: A user sends a social media data collection request from their device by specifying a keyword such as "ice cream" and the "Twitter" platform.

[0896] Step 2:

[0897] The server calls the API of the specified SNS platform and collects post data containing keywords.

[0898] Input: Collection request information

[0899] Output: Collected posting data (post content, date and time, user ID, etc.)

[0900] Specific behavior: The server uses the Twitter API to retrieve posts related to "ice cream" from the past week.

[0901] Step 3:

[0902] The server preprocesses the collected submission data, specifically removing unnecessary HTML tags, special characters, unnecessary spaces, and performing language filtering.

[0903] Input: Collected submission data

[0904] Output: Preprocessed data

[0905] Specific operation: The server removes meaningless characters and posts in foreign languages ​​from the post data it obtains, and extracts only posts in Japanese.

[0906] Step 4:

[0907] The server then analyzes the preprocessed data using natural language processing techniques, conducting morphological analysis to extract important keywords and phrases, and sentiment analysis to calculate a positive, negative, or neutral sentiment score.

[0908] Input: Preprocessed data

[0909] Output: Analysis results (morphological analysis results, emotion scores)

[0910] Specific operation: The server breaks down the text data into morpheme units and calculates the sentiment score using an NLP model.

[0911] Step 5:

[0912] The server quantifies taste characteristics based on the analyzed text data using an AI model, which generates taste scores such as sweetness, sourness, umami, bitterness, and saltiness.

[0913] Input: Analysis results (morphological analysis results, emotion scores)

[0914] Output: Taste score

[0915] Specific operation: The server uses an AI model to quantify taste characteristics from posts about "ice cream," such as "sweetness score 90, sourness score 10."

[0916] Step 6:

[0917] The server integrates the taste scores with point-of-sale (POS) data and analyzes the relationships between them. The visualized taste data is combined with POS data such as sales, inventory, and price into a single dataset.

[0918] Input: Taste score, POS data

[0919] Output: Integrated analysis data (relationship between taste score and POS data)

[0920] Specific operation: The server combines the taste scores with POS data to extract insights such as "ice cream with a high sweetness score records high sales in the summer."

[0921] Step 7:

[0922] The server utilizes an emotion engine to analyze the user's emotional state and provide individually optimized content.

[0923] Input: Integrated analysis data, user sentiment score

[0924] Output: Content recommendation results

[0925] Specific operation: The server recommends, for example, comedy shows for positive emotions and relaxing music for negative emotions based on the user's emotional state.

[0926] Step 8:

[0927] The server provides the generated report and content recommendation results to the user terminal.

[0928] Input: Content recommendation results, report data

[0929] Output: Reports and content recommendations displayed on the user's device

[0930] Specific operation: The user checks the reports and content recommendations sent from the server via a smartphone or tablet.

[0931] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0932] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0933] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0934] [Third embodiment]

[0935] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0936] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0937] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0938] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0939] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0940] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0941] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0942] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0943] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0944] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0945] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0946] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0947] This invention relates to a system for streamlining the development of new food products, and in particular aims to support the development of products based on consumer preferences by integrating and analyzing social media data and POS data. This system collects and analyzes data posted on social media, visualizes taste based on the results, and then integrates and analyzes the data with POS data, thereby realizing scientific, data-driven product development.

[0948] Explanation of program processing

[0949] 1. User requests social media data collection

[0950] Users request the collection of social media data based on specific keywords or hashtags from their device.

[0951] 2. Start collecting social media data

[0952] The server uses the API of the specified social media platform to collect post data containing the requested keywords and hashtags.

[0953] 3. Data Preprocessing

[0954] The server performs preprocessing such as cleansing (removing unnecessary characters and tags) and language filtering (excluding data in languages ​​other than the target language) on the collected SNS post data.

[0955] 4. Text analysis using natural language processing technology

[0956] The server performs morphological analysis on the preprocessed data to extract important keywords, and also analyzes the sentiment score and topics of posts using sentiment analysis and topic modeling.

[0957] 5. Quantifying taste using an AI model

[0958] The server's AI model quantifies specific taste characteristics (sweetness, sourness, umami, etc.) based on the analyzed text data. In doing so, the AI ​​extracts relevant taste information from the text and expresses it as a score.

[0959] 6. Integration and analysis of POS data

[0960] The server integrates the visualized taste data with point-of-sale (POS) data and compiles it into a single dataset, allowing for analysis of the correlation between taste scores and actual sales data.

[0961] 7. Generate reports

[0962] The server extracts insights from the integrated data and automatically generates detailed reports including trend analysis, consumer preference predictions, and new product suggestions.

[0963] 8. Check the report

[0964] Users can check the reports generated on their devices and use them to develop new products and improve existing products based on scientific evidence.

[0965] Specific examples

[0966] For example, if a user wants to develop a new "chocolate product," the following specific example can be considered.

[0967] 1. User submits a request:

[0968] The user requests the collection of social media data by specifying the keywords "chocolate, new product, trend" on the device.

[0969] 2. Data Collection:

[0970] The server collects posts containing specified keywords from social media platforms such as Twitter and Instagram.

[0971] 3. Data Preprocessing and Analysis:

[0972] The server preprocesses the collected data, performs morphological analysis, and identifies posts with strong positive sentiment and posts with weak negative sentiment.

[0973] 4. Quantifying taste:

[0974] The server's AI model generates values ​​such as "sweetness score 80, sourness score 20, umami score 50."

[0975] 5. Integration with POS data:

[0976] Based on the integrated data, the server extracts insights such as "products with high sweetness scores record high sales in winter."

[0977] 6. Provision of Report:

[0978] The user checks the generated report on the terminal and decides on a development strategy for a new chocolate product.

[0979] This system will be a powerful tool for users to develop products efficiently and based on data. By integrating and analyzing social media data and POS data, users can quickly bring products to market that meet consumer demand.

[0980] The processing flow will be explained below.

[0981] Step 1:

[0982] A user submits a request for collection of social media data related to a specific product development from their device, including keywords or hashtags of interest, target social media platforms (e.g., Twitter, Instagram, etc.), and a collection period.

[0983] Step 2:

[0984] The server calls the API of the target social media platform based on the received request and collects post data containing the specified keywords and hashtags. The data obtained from the API includes the post content, posting date and time, user ID, etc.

[0985] Step 3:

[0986] The server preprocesses the collected social media post data. Specifically, it removes unnecessary HTML tags and special characters, eliminates unnecessary spaces, and performs language filtering to exclude data in languages ​​other than the target language. It also normalizes the data to unify the data format.

[0987] Step 4:

[0988] The server analyzes the pre-processed data using natural language processing (NLP) techniques, including:

[0989] Morphological analysis: Breaks down the content of social media posts into morphemes and extracts important keywords and phrases.

[0990] Sentiment Analysis: Calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post.

[0991] Topic modeling: Grouping similar posts and extracting major topics.

[0992] Step 5:

[0993] The server's AI model quantifies taste characteristics based on the analyzed text data. The model extracts taste-related information from the text and generates scores for sweetness, sourness, umami, bitterness, saltiness, etc.

[0994] Step 6:

[0995] The server integrates the visualized taste data with point-of-sale (POS) data. Specifically, it combines taste scores and POS data (sales, inventory, price, etc.) into a single integrated data set. This allows for analysis of the correlation between taste data and actual sales data.

[0996] Step 7:

[0997] The server analyzes changes in consumer preferences and market trends based on the integrated data, extracts important insights and patterns, and creates reports for efficient and effective product development.

[0998] Step 8:

[0999] The server delivers automatically generated reports to the user's device, including trend analysis, consumer preference predictions, and new product suggestions.

[1000] Step 9:

[1001] Users can check the reports on their devices and develop products scientifically and efficiently based on the data. Based on these reports, they can plan new products and prepare to respond quickly to changes in the market.

[1002] By following the above steps, users can integrate and analyze social media data and POS data, enabling them to efficiently develop data-based products.

[1003] Example 1

[1004] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1005] In conventional new food product development, it is difficult to accurately grasp consumer preferences, and because product development is not based on data, it is difficult to quickly bring products that meet consumer needs to market. The objective of this invention is to support more efficient and effective product development by integrating and analyzing SNS data and point-of-sale management data to scientifically visualize consumer preferences.

[1006] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1007] In this invention, the server includes: means for a user to request collection of SNS data based on specific keywords or hashtags from a terminal; means for collecting posted data including the requested keywords or hashtags using the API of the SNS platform; means for cleansing and language filtering the collected posted data; means for analyzing the preprocessed data using morphological analysis, sentiment analysis, and topic modeling; means for using a generative AI model that quantifies specific taste characteristics based on text data; means for integrating and analyzing visualized taste data and point-of-sale data; means for extracting insights from the integrated data and generating reports such as trend analysis, consumer preference predictions, and new product suggestions; and means for providing the generated reports in a format that can be viewed on the user's terminal. This enables scientific understanding of consumer preferences based on data and rapid and efficient launch of new products to the market.

[1008] "SNS data" refers to information such as messages, comments, tags, images, and videos posted by users on social networking services.

[1009] "API" stands for Application Programming Interface and refers to the interface or protocol for exchanging functions and data between software programs.

[1010] "Collection method" refers to a method or system for obtaining specific information from the Internet or a database.

[1011] "Cleansing" refers to the process of removing unnecessary characters, tags, duplicate data, etc. in the data preprocessing process to improve the quality of the data.

[1012] "Language filtering" refers to the process of extracting data related to a specific language and excluding data in other languages.

[1013] "Morphological analysis" refers to a natural language processing technique that breaks down a sentence into its smallest meaningful units and extracts the parts of speech and morphemes of each word.

[1014] "Sentiment analysis" refers to the technology of analyzing trends such as positive and negative emotions and opinions from text data.

[1015] "Topic modeling" refers to a method for discovering common themes and topics from large amounts of text data.

[1016] An "AI model" refers to an algorithm or neural network that uses artificial intelligence, a system that can automatically perform specific tasks by learning from large amounts of data.

[1017] "Taste characteristics" refers to the numerical expression of specific taste characteristics of food (e.g., sweetness, sourness, umami, etc.).

[1018] "Point of sale data (POS data)" refers to data collected at the time of sale of a product, including details such as sales, inventory, and customer information.

[1019] "Integration" refers to the process of combining different data sets into one and analyzing and using them comprehensively.

[1020] "Insight" refers to insights and findings gained through data analysis.

[1021] "Trend analysis" refers to the technique of analyzing current trends and patterns based on past data and predicting future trends.

[1022] "New product proposal" refers to proposing new product development ideas and concepts based on market needs and trends.

[1023] A "report" refers to a document or material that summarizes analytical results and insights and provides information to assist users in making decisions.

[1024] This invention is a system for streamlining the development of new food products, and its purpose is to support the development of products based on consumer preferences by integrating and analyzing social media data and point-of-sale (POS) data. This system collects and analyzes data posted on social media, quantifies taste based on the results, and then integrates and analyzes the results with POS data, thereby realizing scientific, data-driven product development.

[1025] Data collection and preprocessing

[1026] A user uses a device to request the collection of social media data based on specific keywords or hashtags. The server then uses the API of the specified social media platform to collect post data containing the requested keywords or hashtags. Examples of APIs used in this collection process include the Twitter API and Instagram API.

[1027] The collected data undergoes preprocessing on the server side, including cleansing (removing unnecessary characters and tags) and language filtering (excluding data in languages ​​other than the target language). Software used for this includes the Python libraries regex and beautifulsoup.

[1028] Use of natural language processing technology

[1029] The preprocessed data is then analyzed by the server using natural language processing techniques such as morphological analysis, sentiment analysis, and topic modeling. For morphological analysis, natural language processing libraries such as NLTK and spaCy are used, and for sentiment analysis, TextBlob and VADER are used.

[1030] Quantifying taste characteristics

[1031] Based on the analyzed text data, a generative AI model on the server quantifies specific taste characteristics. This is done using deep learning frameworks such as TensorFlow and PyTorch. The model expresses taste characteristics such as sweetness, sourness, and umami as numerical values ​​based on keywords and sentiment scores extracted from the text data.

[1032] Data Integration and Reporting

[1033] The server integrates the quantified taste data and POS data into a single data set, allowing for analysis of the correlation between taste scores and sales data. This process uses MySQL or PostgreSQL as the database system.

[1034] It extracts insights from the integrated data and automatically generates detailed reports such as trend analysis, consumer preference predictions, new product suggestions, etc. Data visualization tools used include Matplotlib and Plotly, and the generated reports are exported in PDF or Excel format.

[1035] Users can check the reports generated on their devices and use them to develop new products or improve existing products based on scientific evidence. This system enables users to develop products efficiently and based on data.

[1036] Specific examples

[1037] For example, if a user wants to develop a new "chocolate product," the following is a specific example.

[1038] 1. User submits a request:

[1039] The user requests the collection of social media data by specifying the keywords "chocolate, new product, trend" on the device.

[1040] 2. Data Collection:

[1041] The server collects posts containing specified keywords from social media platforms such as Twitter and Instagram.

[1042] 3. Data Preprocessing and Analysis:

[1043] The server preprocesses the collected data, performs morphological analysis, and identifies posts with strong positive sentiment and weak negative sentiment.

[1044] 4. Quantifying taste:

[1045] The server's AI model generates values ​​such as "sweetness score 80, sourness score 20, umami score 50."

[1046] 5. Integration with POS data:

[1047] Based on the integrated data, the server extracts insights such as "products with high sweetness scores record high sales in winter."

[1048] 6. Provision of Report:

[1049] The user checks the generated report on the terminal and decides on a development strategy for a new chocolate product.

[1050] Prompt Sentence Examples

[1051] Examples of prompts to input to a generative AI model might include:

[1052] Regarding a new chocolate product, please collect data from Twitter and Instagram posts containing the keywords "chocolate, new product, trend." Also, please quantify the taste characteristics of the new product based on the collected data and integrate it with POS data to provide insights for optimal product development.

[1053] As described above, the present invention integrates SNS data and POS data, enabling scientific product development based on consumer preferences.

[1054] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1055] Step 1:

[1056] A user requests the collection of social media data based on specific keywords or hashtags from their device.

[1057] Specific operation: The user enters keywords into the input form specified in the dedicated application on the device and clicks the "Collect data" button.

[1058] Input: User-specified keywords and hashtags.

[1059] Output: A social media data collection request is sent to the server.

[1060] Step 2:

[1061] The server uses the API of the social media platform to collect post data containing the requested keywords and hashtags.

[1062] Specific operation: The server uses the API key to send a request to the social media platform (e.g., Twitter, Instagram) and retrieves the relevant post data.

[1063] Input: User-specified keywords, hashtags, and API keys.

[1064] Output: Retrieved social media post data.

[1065] Step 3:

[1066] The server cleanses and language filters the social media post data collected.

[1067] Specific operation: A Python script on the server uses libraries such as regex and beautifulsoup to remove unnecessary characters and tags from the data and exclude data in languages ​​other than the target language.

[1068] Input: Collected social media posting data.

[1069] Output: Preprocessed SNS data.

[1070] Step 4:

[1071] The server analyzes the preprocessed data using morphological analysis, sentiment analysis, and topic modeling.

[1072] How it works: It uses NLTK and spaCy libraries for morphological analysis, TextBlob and VADER for sentiment analysis, and Gensim for topic modeling.

[1073] Input: Preprocessed SNS data.

[1074] Output: Morphological analysis results, sentiment score, topic information.

[1075] Step 5:

[1076] The server's generative AI model quantifies specific taste characteristics based on the analyzed text data.

[1077] Specific operation: Using a deep learning framework (e.g., TensorFlow, PyTorch), a trained model quantifies sweetness, sourness, umami, etc. from text data.

[1078] Input: Morphological analysis results, sentiment scores, topic information.

[1079] Output: Numerical data of taste attributes (e.g., sweetness score 80, sourness score 20, umami score 50).

[1080] Step 6:

[1081] The server integrates and analyzes the visualized taste data and point-of-sale data (POS data).

[1082] Specific operation: Executes an SQL query on a database system (e.g., MySQL, PostgreSQL) to combine taste data and POS data.

[1083] Input: Numerical data of taste characteristics, POS data.

[1084] Output: A consolidated dataset.

[1085] Step 7:

[1086] The server extracts insights from the integrated data and generates reports such as trend analysis, consumer preference predictions, and new product suggestions.

[1087] Specific behavior: Create graphs and charts using data visualization tools (e.g., Matplotlib, Plotly) and export reports in PDF and Excel formats.

[1088] Input: The integrated dataset.

[1089] Output: Detailed report (e.g. PDF, Excel file).

[1090] Step 8:

[1091] The user checks the generated report on the device.

[1092] Specific operation: The user downloads the generated report using a dedicated application on the device and reviews the contents.

[1093] Input: Detailed report (e.g. PDF, Excel file).

[1094] Output: Report information reviewed by the user.

[1095] (Application example 1)

[1096] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1097] In the past, new food product development relied primarily on sales data and survey results, as it was difficult to accurately grasp consumer preferences and market trends. As a result, planning and development of new products that quickly reflected the latest consumer preferences and trends tended to be delayed. Furthermore, it was difficult for employees to utilize this data to propose new products, which led to inefficient product deployment in physical stores.

[1098] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1099] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an AI model for quantifying taste based on the analysis results, means for integrating and analyzing the visualized taste data and point-of-sale management data, means for generating the analysis results in report format, and means for providing the generated report to a user's visual display device. This enables the planning and development of new products that quickly and accurately reflect the latest consumer preferences, and allows employees at physical stores to use this data in real time to help with sales strategies and product development.

[1100] "Means for collecting post data from social media" refers to a system for collecting post data from social media platforms based on specific keywords or hashtags.

[1101] "Means for preprocessing collected post data" refers to the process of deleting unnecessary characters and tags from the collected SNS post data and excluding data in languages ​​other than the target language.

[1102] "Means of analysis using natural language processing technology" refers to a system that uses preprocessed data to analyze it using natural language processing technology such as morphological analysis, sentiment analysis, and topic modeling.

[1103] "Means of using an AI model" refers to a mechanism that utilizes an artificial intelligence model to quantify specific taste characteristics based on analyzed text data.

[1104] "Means for integrating and analyzing visualized taste data and point-of-sale management data" is a system that integrates visualized taste data and sales data and analyzes correlations.

[1105] "Means for generating analysis results in report format" refers to a system that automatically generates reports based on insights gained from integrated data.

[1106] The "means for providing the generated report to the user's visual display device" refers to a mechanism for displaying the generated report in real time on the user's visual display device, such as smart glasses.

[1107] This invention consists of a system that can be applied to support new product development in brick-and-mortar stores. This system collects and analyzes data from social media, and integrates and analyzes it with point-of-sale (POS) data to intuitively support users in developing new products and formulating sales strategies. Specific embodiments for implementing this invention are described below.

[1108] 1. Generate the program:

[1109] This system consists of a server, a terminal, and the user's visual display device. The server runs a program that collects posted data from SNS and preprocesses the collected data. This preprocessing includes removing unnecessary characters and tags and excluding data in a language other than the target language. The data is then analyzed using natural language processing techniques (morphological analysis, sentiment analysis, topic modeling, etc.) to quantify taste characteristics (sweetness, sourness, umami, etc.). The server integrates these analysis results with the POS data, analyzes them as a single dataset, and automatically generates a report. This report is provided in real time to the user's visual display device.

[1110] 2. Natural language processing description:

[1111] Specifically, when collecting data from social media platforms, the server uses the APIs of each platform. For data preprocessing, Python libraries (e.g., NLTK, SpaCy) are used to clean and filter text. For morphological analysis and sentiment analysis, Google Cloud Natural Language API is used. Furthermore, machine learning frameworks (e.g., TensorFlow, PyTorch) are used to quantify taste using an AI model. Google Cloud BigQuery is used to integrate and analyze the analysis results and POS data, and Google Data Studio is used to generate reports. Smart glasses, such as Google Glass, are used as visual display devices. These devices allow users to manipulate data through voice commands or touch operations.

[1112] 3. Adding concrete examples:

[1113] For example, consider the case where a user develops a new "seasonal limited edition chocolate flavor." The user specifies the keywords "seasonal limited edition, flavor, chocolate" on a visual display device and requests the collection of social media data. The server collects posts containing the specified keywords from Twitter and Instagram and performs preprocessing. The analysis results generate numerical values ​​such as "sweetness score 85, sourness score 15, umami score 40." These values ​​are then integrated with POS data to extract insights such as "products with high sweetness scores record high sales in spring." Finally, these analysis results are displayed in real time on the user's visual display device, smart glasses.

[1114] Examples of prompts for a generative AI model might include:

[1115] "Please quantify the taste characteristics (sweetness, sourness, umami) from the following social media posts."

[1116] This chocolate is so sweet and delicious!

[1117] "This chocolate is too sour."

[1118] "This chocolate has an exquisite flavor."

[1119] As described above, the system embodying this invention makes it possible to efficiently plan and develop new products in physical stores that quickly and accurately reflect the latest consumer preferences.

[1120] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1121] Step 1:

[1122] A user requests social media data collection.

[1123] The user requests the collection of social media data by specifying keywords such as "seasonal, flavor, chocolate" on the visual display. The input is the specified keyword, and the output is the transmission of a collection command. The visual display is used to execute the request by voice command or touch operation.

[1124] Step 2:

[1125] The server starts collecting social media data.

[1126] The server collects post data using the social media platform API based on the specified keywords. The input is the requested keywords, and the output is the collected social media post data. Specifically, the data is collected from Twitter and Instagram and saved in JSON format on the server.

[1127] Step 3:

[1128] The server preprocesses the collected submission data.

[1129] The collected post data is preprocessed by the server. The input is the collected SNS post data, and the output is the preprocessed data. Specifically, Python's NLTK and SpaCy are used to remove unnecessary characters and tags and exclude data in languages ​​other than the target language.

[1130] Step 4:

[1131] The server analyzes the preprocessed data using natural language processing techniques.

[1132] Based on the preprocessed data, the server uses natural language processing technology to perform sentiment analysis and topic modeling. The input is the preprocessed data, and the output is the analysis results. Specifically, it uses the Google Cloud Natural Language API to extract important keywords and analyze sentiment scores.

[1133] Step 5:

[1134] The server uses an AI model to quantify the taste based on the analysis results.

[1135] Based on the analyzed text data, the server uses an AI model to quantify specific taste characteristics. The input is the analysis result, and the output is a taste score. Specifically, TensorFlow and PyTorch are used to generate scores for sweetness, sourness, and umami.

[1136] Step 6:

[1137] The server integrates and analyzes taste visualization data and point-of-sale (POS) data.

[1138] The taste scores and POS data from physical stores are integrated and analyzed as a single dataset. The inputs are taste scores and POS data, and the output is an integrated dataset. Specifically, the data is integrated using Google Cloud BigQuery and correlation analysis is performed.

[1139] Step 7:

[1140] The server generates a report from the analysis results.

[1141] Based on the insights gained from the integrated data, the server automatically generates detailed reports. The input is the integrated dataset and the output is the report. The reports are generated using Google Data Studio and visually displayed in graphs and charts.

[1142] Step 8:

[1143] The server provides the generated report to the user's visual display.

[1144] The generated report is provided in real time to the user's visual display device. The input is the generated report, and the output is the displayed report. The report is displayed on a visual display device (e.g., smart glasses) and can be confirmed by the user via voice or touch.

[1145] Above, we have described the specific processing operations and inputs / outputs for each step, and have explained in detail the processing flow of the entire system.

[1146] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1147] This invention relates to a system that supports product development by integrating and analyzing social media data and POS data, and using an emotion engine in combination. This system analyzes posted data collected from social media, quantifies the analysis results into taste, and performs integrated analysis with sales data, as well as recognizing user emotions and providing insights.

[1148] Explanation of program processing

[1149] 1. User requests social media data collection

[1150] The user sends a request for collection of social media data related to a specific product development from their device. The request includes keywords, target platforms, and a collection period.

[1151] 2. Start collecting social media data

[1152] The server calls the API of the specified social media platform and collects post data including keywords and hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[1153] 3. Data Preprocessing

[1154] The server preprocesses the collected social media post data. Specifically, it removes unnecessary HTML tags, special characters, and unnecessary spaces, and performs language filtering. Language filtering excludes posts in languages ​​other than the target language.

[1155] 4. Text analysis using natural language processing technology

[1156] The server analyzes the preprocessed data using natural language processing techniques. The analysis operations include:

[1157] Morphological analysis: Breaks down text into morpheme units and extracts important keywords and phrases.

[1158] Sentiment Analysis: Calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post.

[1159] Topic modeling: Clustering relevant posts and extracting major topics.

[1160] 5. Quantifying taste using an AI model

[1161] The server's AI model quantifies taste characteristics based on the analyzed text data, generating taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text.

[1162] 6. Integration and analysis of POS data

[1163] The server integrates the visualized taste data with point-of-sale (POS) data, combining taste scores and POS data (sales, inventory, price, etc.) into a single dataset and analyzing the relationships between them.

[1164] 7. Emotion recognition and insights

[1165] The server utilizes an emotion engine to recognize the user's emotions and provide insights based on the analysis results, which then generates a detailed report reflecting the user's emotional state.

[1166] 8. Generate Reports

[1167] The server generates detailed reports on changing consumer preferences and market trends based on the integrated data and the output of the emotion engine, including trend analysis, consumer preference predictions, and new product suggestions.

[1168] 9. Check the report

[1169] Users can check the reports generated on their devices and develop products scientifically and efficiently based on the data. Based on these reports, they can plan new products and prepare to respond quickly to changes in the market.

[1170] Specific examples

[1171] For example, if a user wants to develop a new "ice cream product," the following specific example can be considered.

[1172] 1. User submits a request:

[1173] The user requests the collection of SNS data by specifying the keywords "ice cream, new product, summer" on the terminal.

[1174] 2. Data collection and preprocessing:

[1175] The server collects posts containing the specified keywords from the social media platform. After collection, unnecessary data is removed and preprocessed.

[1176] 3. Data analysis and taste quantification:

[1177] The server performs natural language processing on the preprocessed data and then uses an AI model to generate a taste score, such as "sweet score 90, sour score 10, salty score 5."

[1178] 4. POS data integration and analysis:

[1179] The server integrates the taste scores with POS data to extract the insight that "ice cream with a high sweetness score records high sales in the summer."

[1180] 5. Emotion Recognition and Report Generation:

[1181] The server uses an emotion engine to recognize user emotions and generates detailed reports that provide insights based on the analysis results.

[1182] 6. Report provision and review:

[1183] Users can check the reports generated on their devices and decide on new product development strategies. Insights based on emotion information can help plan products that are more likely to be accepted by consumers.

[1184] This system helps users analyze consumer preferences and market trends based on social media and POS data, and utilizes an emotion engine to respond quickly, enabling scientific and data-based product development and efficient response to market changes.

[1185] The processing flow will be explained below.

[1186] Step 1:

[1187] Users submit a request for social media data collection related to new product developments from their device by inputting keywords of interest (e.g., "chocolate," "new product," "trend"), target social media platforms (e.g., Twitter, Instagram), and the data collection period.

[1188] Step 2:

[1189] The server calls the API of the social media platform based on the received request and collects posts containing the specified keywords or hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[1190] Step 3:

[1191] The server preprocesses the collected SNS data. Specifically, it performs the following operations:

[1192] Remove unnecessary characters: Remove HTML tags, special characters, emojis, etc.

[1193] Language filtering: Filter out posts in languages ​​other than your target language (e.g., if you only target Japanese).

[1194] Text normalization: unifying full-width and half-width characters, converting uppercase and lowercase characters, etc.

[1195] Step 4:

[1196] The server analyzes the preprocessed data using natural language processing (NLP) technology. Specifically, it performs the following processes:

[1197] Morphological analysis: Breaks down the text of a post into morphemes and extracts important keywords.

[1198] Sentiment analysis: Calculates positive, negative, and neutral sentiment scores.

[1199] Topic modeling: Clustering posts and extracting major topics.

[1200] Step 5:

[1201] The server's AI model quantifies taste characteristics based on the analysis results. Specifically, it generates scores for sweetness, sourness, umami, bitterness, saltiness, etc. from the text data. This taste quantification visualizes the consumer's posts as specific taste characteristics.

[1202] Step 6:

[1203] The server integrates and analyzes taste data and point-of-sale (POS) data. Specifically, it performs the following operations:

[1204] Data integration: Integrate taste scores and POS data (sales, inventory, price, etc.) into one.

[1205] Association analysis: Based on the integrated data, the relationship between taste characteristics and sales performance is analyzed (e.g., products with high sweetness scores have high sales).

[1206] Step 7:

[1207] The server uses an emotion engine to recognize the user's emotions. Specifically, it evaluates the user's emotional state in real time based on the user's operation history and input information when they access the system.

[1208] Step 8:

[1209] The server adds insights corresponding to the user's emotional state to the report based on the output of the emotion engine, thereby generating a detailed report containing insights based on the user's emotions.

[1210] Step 9:

[1211] The server provides the generated report to the user's device, where the user can check the report and develop products based on scientific evidence and data.

[1212] Step 10:

[1213] Users can use the reports provided on their devices to decide on new product plans and development policies, making it possible to quickly develop products that respond to consumer preferences and market trends.

[1214] In this way, this system integrates and analyzes SNS data and POS data, and by combining it with an emotion engine, provides product development support based on data that is useful to users.

[1215] Example 2

[1216] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1217] Conventional methods have made it difficult to efficiently integrate social media data and point-of-sale data to quickly understand consumer preferences and market trends. Furthermore, there is a lack of means to recognize user emotions using an emotion engine or generate detailed reports, which hinders the efficiency of the scientific, data-driven product development process. To solve these problems, a system is needed that can consistently analyze social media data, quantify taste perception, integrate data, recognize emotions, and generate reports.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1219] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an artificial intelligence model that quantifies taste based on the analysis results, means for integrating and analyzing the taste visualization data and point-of-sale management data, means for recognizing user emotions using an emotion engine, means for generating a detailed report based on the integrated data and the output of the emotion engine, and means for providing the generated report to the user's terminal. This enables rapid understanding of consumer preferences and market trends and enables scientific product development based on data.

[1220] "SNS data" refers to information such as user messages, comments, images, and videos posted on social media platforms.

[1221] "Preprocessing" refers to the process of removing unnecessary information from collected data and converting it into a format suitable for analysis.

[1222] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language.

[1223] An "artificial intelligence model" refers to an algorithm that learns from large amounts of data and makes predictions and analyses based on that data.

[1224] "Quantifying taste" refers to the process of extracting taste characteristics (sweetness, sourness, umami, bitterness, saltiness, etc.) from text data and expressing those characteristics numerically.

[1225] "Point of sale data" refers to data used to manage sales information in real time, including product sales, inventory, prices, etc.

[1226] "Emotion engine" refers to an algorithm or system for analyzing and recognizing a user's emotions.

[1227] "Report" means a written or digital report summarizing the results of an analysis or insights.

[1228] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[1229] "User" refers to the person or company that uses the system to collect, analyze, and check reports on social media data.

[1230] This invention is a system that integrates and analyzes social media data and point-of-sale (POS) data to recognize user sentiment and support product development. The system collects, analyzes, and integrates data through multiple steps, and finally generates a report to provide to the user.

[1231] The main components of this system include a server, a terminal, and a user. The configuration of this system and a specific embodiment will be described in detail below.

[1232] Data collection and preprocessing

[1233] A user requests collection of social media data through their device. The request includes specific keywords (e.g., "ice cream, new products, summer"), the target social media platform (e.g., Twitter, Instagram), and the data collection period (e.g., the past three months).

[1234] The server receives a request from a user and uses the API of the social media platform (e.g., Twitter API) to collect post data containing the specified keywords and hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[1235] The server then pre-processes the collected data, which includes removing unnecessary HTML tags, special characters, and unnecessary spaces, and language filtering to retain only the specified language (e.g., Japanese).

[1236] Text analysis and quantification of taste

[1237] The preprocessed data is then analyzed on the server using natural language processing (NLP) techniques. This analysis includes morphological analysis, sentiment analysis, and topic modeling. Morphological analysis breaks down text into words and extracts important keywords and phrases. Sentiment analysis calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post. Topic modeling clusters related posts and extracts major topics.

[1238] The server's AI model quantifies taste characteristics based on the analyzed text data. This model generates taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text. For example, a score such as "sweetness score 90, sourness score 10, saltiness score 5" may be generated.

[1239] Integration and analysis of POS data

[1240] The server integrates the taste scores with the POS data. The POS data includes sales-related information such as sales, inventory, and price. The integrated data is analyzed on the server to analyze the relationship between the taste scores and the POS data. For example, an insight such as "ice cream with a high sweetness score records high sales in the summer" can be extracted.

[1241] Emotion Recognition and Report Generation

[1242] The server uses an emotion engine to recognize the user's emotions and generates a detailed report based on the results, including changes in consumer preferences, market trends, insights, consumer preference predictions, and new product suggestions. The report is provided to the user's device, where the user can review it and decide on a new product development strategy.

[1243] Specific examples

[1244] For example, if a user wants to develop a new "ice cream product," here are the specific steps:

[1245] 1. User submits a request

[1246] The user requests the collection of SNS data by specifying the keywords "ice cream, new product, summer" on the terminal.

[1247] 2. Data collection and preprocessing

[1248] The server calls the Twitter API, collects posts containing the specified keywords, and preprocesses them.

[1249] 3. Data analysis and taste quantification

[1250] The server analyzes the preprocessed data using natural language processing technology and uses an AI model to generate a taste score such as "sweetness score 90, sourness score 10, saltiness score 5."

[1251] 4. POS data integration and analysis

[1252] The server integrates the taste scores and POS data, analyzes the correlations, and extracts the insight that "ice cream with a high sweetness score records high sales in the summer."

[1253] 5. Emotion Recognition and Report Generation

[1254] The server uses an emotion engine to recognize the user's emotions, and generates a detailed report that is provided to the user's terminal.

[1255] 6. Provision and review of reports

[1256] The user checks the generated report on the terminal and decides on a new product development strategy, for example, planning a "new, highly sweet ice cream flavor" for the summer season based on the report.

[1257] This system allows users to integrate social media data and POS data to quickly analyze consumer preferences and market trends, and utilize an emotion engine to develop data-driven products.

[1258] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1259] Step 1:

[1260] Sending a social media data collection request

[1261] Users use their devices to request social media data collection by specifying specific keywords (e.g., "ice cream, new product, summer"), the target social media platform (e.g., Twitter, Instagram), and the data collection period (e.g., the past three months).

[1262] Input: Keywords, target platform, collection period

[1263] Output: Social Media Data Collection Request

[1264] Step 2:

[1265] Started collecting social media data

[1266] Based on the received request, the server uses the API of the specified social media platform (e.g., Twitter API) to collect related post data, including the post content, posting date and time, and user ID.

[1267] Input: Social Media Data Collection Request

[1268] Output: Collected social media post data

[1269] Specific operations: Acquiring data through API calls and analyzing responses

[1270] Step 3:

[1271] Data Preprocessing

[1272] The server preprocesses the collected social media post data, specifically removing unnecessary HTML tags, special characters, and unnecessary spaces, and filtering the data to retain the specified language (e.g., Japanese).

[1273] Input: Collected social media post data

[1274] Output: Preprocessed data

[1275] Specific behavior: Text cleaning, language filtering

[1276] Step 4:

[1277] Text analysis using natural language processing technology

[1278] The server then analyzes the preprocessed data using natural language processing techniques. These include morphological analysis, sentiment analysis, and topic modeling. Morphological analysis breaks down text into words and extracts important keywords and phrases. Sentiment analysis calculates positive, negative, and neutral sentiment scores. Topic modeling clusters related posts and extracts major topics.

[1279] Input: Preprocessed data

[1280] Output: Analysis results (morphological analysis results, sentiment scores, topic models)

[1281] Specific operations: Applying NLP algorithms and saving analysis results

[1282] Step 5:

[1283] Quantifying taste using an AI model

[1284] The server's AI model quantifies taste characteristics based on the analysis results, generating taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text.

[1285] Input: Analysis results

[1286] Output: Taste score (e.g. sweet score 90, sour score 10, salty score 5)

[1287] Specific operation: Text analysis and quantification using AI models

[1288] Step 6:

[1289] Integration and analysis of POS data

[1290] The server integrates the taste scores and POS data, and analyzes the relationship between the taste scores and POS data (sales, inventory, price, etc.) based on the integrated data set.

[1291] Input: Taste score, POS data

[1292] Output: Integrated dataset, relationship analysis results

[1293] Specific operations: Data combination, correlation analysis

[1294] Step 7:

[1295] Emotion recognition and insights

[1296] The server uses an emotion engine to recognize user emotions, and based on the results, provides insights into consumer preferences and market trends.

[1297] Input: Integrated dataset, user emotion information

[1298] Output: Insights, detailed reports

[1299] Specific operations: Applying emotion engine, generating reports

[1300] Step 8:

[1301] Generate reports

[1302] The server generates detailed reports based on the integrated data and the output of the emotion engine, including trend analysis and new product recommendations.

[1303] Inputs: Insights, Integrated Data

[1304] Output: Report

[1305] Specific operations: Data embedding and finalization in report template

[1306] Step 9:

[1307] Providing reports

[1308] Users can check the generated reports on their devices, which allows for scientific and efficient product development based on data.

[1309] Input: Report

[1310] Output: New product development strategy

[1311] Specific actions: Downloading and viewing reports, product development decision-making

[1312] In this way, the system integrates social media data and POS data to quickly analyze consumer preferences and market trends, and utilizes an emotion engine to support data-based product development.

[1313] (Application example 2)

[1314] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1315] Conventional content distribution services lack a method for providing optimized content based on a user's individual emotional state or interests. Therefore, to increase user satisfaction, it is necessary to provide personalized content that takes into account social media data and emotional states. Furthermore, more accurate market analysis and prediction of consumer preferences are required by integrating social media data analysis and POS data.

[1316] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1317] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an AI model for quantifying taste based on the analysis results, means for integrating and analyzing the taste visualization data and point-of-sale management data, means for analyzing the user's emotional state from the integrated data and providing individually optimized content, and means for providing the generated report and content recommendation results to the user terminal. This enables the provision of personalized content based on the user's emotional state and interests, improving the accuracy of market analysis and consumer preference prediction.

[1318] "SNS" stands for Social Networking Service, a platform for users to interact and share information online.

[1319] "Posted data" refers to content such as messages, images, and videos posted by users on SNS.

[1320] "Preprocessing" refers to processes such as data cleansing and normalization that are carried out to make collected data ready for analysis.

[1321] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language.

[1322] The "AI model that quantifies taste characteristics" is an artificial intelligence model that extracts taste-related characteristics from text data and converts them into quantitative values.

[1323] "Point of sale data" refers to information collected during the course of a commercial transaction, such as sales and inventory.

[1324] "Emotional state" refers to the psychological state that a user expresses through their posted data.

[1325] "Report format" refers to documents and graphs that are formatted to clearly communicate the results of analysis.

[1326] "Content recommendation" is the act of presenting appropriate content based on a user's interests, concerns, and emotional state.

[1327] A "user terminal" is a device such as a computer, smartphone, or tablet that a user uses to use a service.

[1328] This invention relates to a system that integrates and analyzes SNS data and point-of-sale (POS) data, and uses an emotion engine to provide personalized content tailored to the user's emotional state. This system operates in the following steps:

[1329] Hardware / Software

[1330] This system is application software installed on user devices such as smartphones and tablets, and data processing and analysis are performed on a server. This server includes software for collecting data through the API of the social media platform and analyzing the data using natural language processing technology and AI models.

[1331] The specific hardware and software used are as follows:

[1332] Hardware: smartphones, tablets, servers

[1333] Software: Python (requests, json, textblob libraries), SNS platform API, AI model

[1334] Data processing / data calculation

[1335] The server first calls the API of the social media platform and collects post data based on the specified keywords. This data includes the post content, posting date and time, user ID, etc. The collected data is then preprocessed and unnecessary data is filtered out. After preprocessing, the data is analyzed using natural language processing technology.

[1336] Natural language processing technology performs morphological analysis and sentiment analysis to calculate an emotional score for posts. It also uses an AI model to quantify taste characteristics based on the analysis results. This taste characteristic data is integrated with POS data for comprehensive analysis. Finally, the integrated data is used to analyze the user's emotional state and provide individually optimized content.

[1337] Specific examples

[1338] For example, if a user wants to find new content using the keyword "ice cream," the server calls the social media platform's API to collect relevant post data from the past week. The server then preprocesses this data and uses natural language processing technology to calculate a sentiment score. Based on the sentiment score, the server determines whether the user's emotional state is positive or negative and recommends personalized content.

[1339] Example prompt sentence:

[1340] Keywords: ice cream

[1341] Social Media Platform: Twitter

[1342] Collection period: Past week

[1343] Use a content recommendation system based on sentiment scores to serve content that matches the user's emotional state.

[1344] As described above, the system based on this invention improves user satisfaction by integrating and analyzing users' SNS posting data and POS data, and providing personalized content that corresponds to their individual emotional state.

[1345] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1346] Step 1:

[1347] The server receives a request for collecting SNS data from a user, which includes keywords, target platforms, and a collection period.

[1348] Input: User-specified keywords, target platform, collection period

[1349] Output: Collection request information

[1350] Specific operation: A user sends a social media data collection request from their device by specifying a keyword such as "ice cream" and the "Twitter" platform.

[1351] Step 2:

[1352] The server calls the API of the specified SNS platform and collects post data containing keywords.

[1353] Input: Collection request information

[1354] Output: Collected posting data (post content, date and time, user ID, etc.)

[1355] Specific behavior: The server uses the Twitter API to retrieve posts related to "ice cream" from the past week.

[1356] Step 3:

[1357] The server preprocesses the collected submission data, specifically removing unnecessary HTML tags, special characters, unnecessary spaces, and performing language filtering.

[1358] Input: Collected submission data

[1359] Output: Preprocessed data

[1360] Specific operation: The server removes meaningless characters and posts in foreign languages ​​from the post data it obtains, and extracts only posts in Japanese.

[1361] Step 4:

[1362] The server then analyzes the preprocessed data using natural language processing techniques, conducting morphological analysis to extract important keywords and phrases, and sentiment analysis to calculate a positive, negative, or neutral sentiment score.

[1363] Input: Preprocessed data

[1364] Output: Analysis results (morphological analysis results, emotion scores)

[1365] Specific operation: The server breaks down the text data into morpheme units and calculates the sentiment score using an NLP model.

[1366] Step 5:

[1367] The server quantifies taste characteristics based on the analyzed text data using an AI model, which generates taste scores such as sweetness, sourness, umami, bitterness, and saltiness.

[1368] Input: Analysis results (morphological analysis results, emotion scores)

[1369] Output: Taste score

[1370] Specific operation: The server uses an AI model to quantify taste characteristics from posts about "ice cream," such as "sweetness score 90, sourness score 10."

[1371] Step 6:

[1372] The server integrates the taste scores with point-of-sale (POS) data and analyzes the relationships between them. The visualized taste data is combined with POS data such as sales, inventory, and price into a single dataset.

[1373] Input: Taste score, POS data

[1374] Output: Integrated analysis data (relationship between taste scores and POS data)

[1375] Specific operation: The server combines the taste scores with POS data to extract insights such as "ice cream with a high sweetness score records high sales in the summer."

[1376] Step 7:

[1377] The server utilizes an emotion engine to analyze the user's emotional state and provide individually optimized content.

[1378] Input: Integrated analysis data, user sentiment score

[1379] Output: Content recommendation results

[1380] Specific operation: The server recommends, for example, comedy shows for positive emotions and relaxing music for negative emotions based on the user's emotional state.

[1381] Step 8:

[1382] The server provides the generated report and content recommendation results to the user terminal.

[1383] Input: Content recommendation results, report data

[1384] Output: Reports and content recommendations displayed on the user's device

[1385] Specific operation: The user checks the reports and content recommendations sent from the server via a smartphone or tablet.

[1386] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1387] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1388] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1389] [Fourth embodiment]

[1390] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1391] 7, a 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.

[1392] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1393] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1394] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1395] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1396] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1397] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1398] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1399] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1400] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1401] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1402] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1403] This invention relates to a system for streamlining the development of new food products, and in particular aims to support the development of products based on consumer preferences by integrating and analyzing social media data and POS data. This system collects and analyzes data posted on social media, visualizes taste based on the results, and then integrates and analyzes the data with POS data, thereby realizing scientific, data-driven product development.

[1404] Explanation of program processing

[1405] 1. User requests social media data collection

[1406] Users request the collection of social media data based on specific keywords or hashtags from their device.

[1407] 2. Start collecting social media data

[1408] The server uses the API of the specified social media platform to collect post data containing the requested keywords and hashtags.

[1409] 3. Data Preprocessing

[1410] The server performs preprocessing such as cleansing (removing unnecessary characters and tags) and language filtering (excluding data in languages ​​other than the target language) on the collected SNS post data.

[1411] 4. Text analysis using natural language processing technology

[1412] The server performs morphological analysis on the preprocessed data to extract important keywords, and also analyzes the sentiment score and topics of posts using sentiment analysis and topic modeling.

[1413] 5. Quantifying taste using an AI model

[1414] The server's AI model quantifies specific taste characteristics (sweetness, sourness, umami, etc.) based on the analyzed text data. In doing so, the AI ​​extracts relevant taste information from the text and expresses it as a score.

[1415] 6. Integration and analysis of POS data

[1416] The server integrates the visualized taste data with point-of-sale (POS) data and compiles it into a single dataset, allowing for analysis of the correlation between taste scores and actual sales data.

[1417] 7. Generate reports

[1418] The server extracts insights from the integrated data and automatically generates detailed reports including trend analysis, consumer preference predictions, and new product suggestions.

[1419] 8. Check the report

[1420] Users can check the reports generated on their devices and use them to develop new products and improve existing products based on scientific evidence.

[1421] Specific examples

[1422] For example, if a user wants to develop a new "chocolate product," the following specific example can be considered.

[1423] 1. User submits a request:

[1424] The user requests the collection of social media data by specifying the keywords "chocolate, new product, trend" on the device.

[1425] 2. Data Collection:

[1426] The server collects posts containing specified keywords from social media platforms such as Twitter and Instagram.

[1427] 3. Data Preprocessing and Analysis:

[1428] The server preprocesses the collected data, performs morphological analysis, and identifies posts with strong positive sentiment and posts with weak negative sentiment.

[1429] 4. Quantifying taste:

[1430] The server's AI model generates values ​​such as "sweetness score 80, sourness score 20, umami score 50."

[1431] 5. Integration with POS data:

[1432] Based on the integrated data, the server extracts insights such as "products with high sweetness scores record high sales in winter."

[1433] 6. Provision of Report:

[1434] The user checks the generated report on the terminal and decides on a development strategy for a new chocolate product.

[1435] This system will be a powerful tool for users to develop products efficiently and based on data. By integrating and analyzing social media data and POS data, users can quickly bring products to market that meet consumer demand.

[1436] The processing flow will be explained below.

[1437] Step 1:

[1438] A user submits a request for collection of social media data related to a specific product development from their device, including keywords or hashtags of interest, target social media platforms (e.g., Twitter, Instagram, etc.), and a collection period.

[1439] Step 2:

[1440] The server calls the API of the target social media platform based on the received request and collects post data containing the specified keywords and hashtags. The data obtained from the API includes the post content, posting date and time, user ID, etc.

[1441] Step 3:

[1442] The server preprocesses the collected social media post data. Specifically, it removes unnecessary HTML tags and special characters, eliminates unnecessary spaces, and performs language filtering to exclude data in languages ​​other than the target language. It also normalizes the data to unify the data format.

[1443] Step 4:

[1444] The server analyzes the pre-processed data using natural language processing (NLP) techniques, including:

[1445] Morphological analysis: Breaks down the content of social media posts into morphemes and extracts important keywords and phrases.

[1446] Sentiment Analysis: Calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post.

[1447] Topic modeling: Grouping similar posts and extracting major topics.

[1448] Step 5:

[1449] The server's AI model quantifies taste characteristics based on the analyzed text data. The model extracts taste-related information from the text and generates scores for sweetness, sourness, umami, bitterness, saltiness, etc.

[1450] Step 6:

[1451] The server integrates the visualized taste data with point-of-sale (POS) data. Specifically, it combines taste scores and POS data (sales, inventory, price, etc.) into a single integrated data set. This allows for analysis of the correlation between taste data and actual sales data.

[1452] Step 7:

[1453] The server analyzes changes in consumer preferences and market trends based on the integrated data, extracts important insights and patterns, and creates reports for efficient and effective product development.

[1454] Step 8:

[1455] The server delivers automatically generated reports to the user's device, including trend analysis, consumer preference predictions, and new product suggestions.

[1456] Step 9:

[1457] Users can check the reports on their devices and develop products scientifically and efficiently based on the data. Based on these reports, they can plan new products and prepare to respond quickly to changes in the market.

[1458] By following the above steps, users can integrate and analyze social media data and POS data, enabling them to efficiently develop data-based products.

[1459] Example 1

[1460] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1461] In conventional new food product development, it is difficult to accurately grasp consumer preferences, and because product development is not based on data, it is difficult to quickly bring products that meet consumer needs to market. The objective of this invention is to support more efficient and effective product development by integrating and analyzing SNS data and point-of-sale management data to scientifically visualize consumer preferences.

[1462] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1463] In this invention, the server includes: means for a user to request collection of SNS data based on specific keywords or hashtags from a terminal; means for collecting posted data including the requested keywords or hashtags using the API of the SNS platform; means for cleansing and language filtering the collected posted data; means for analyzing the preprocessed data using morphological analysis, sentiment analysis, and topic modeling; means for using a generative AI model that quantifies specific taste characteristics based on text data; means for integrating and analyzing visualized taste data and point-of-sale data; means for extracting insights from the integrated data and generating reports such as trend analysis, consumer preference predictions, and new product suggestions; and means for providing the generated reports in a format that can be viewed on the user's terminal. This enables scientific understanding of consumer preferences based on data and rapid and efficient launch of new products to the market.

[1464] "SNS data" refers to information such as messages, comments, tags, images, and videos posted by users on social networking services.

[1465] "API" stands for Application Programming Interface and refers to the interface or protocol for exchanging functions and data between software programs.

[1466] "Collection method" refers to a method or system for obtaining specific information from the Internet or a database.

[1467] "Cleansing" refers to the process of removing unnecessary characters, tags, duplicate data, etc. in the data preprocessing process to improve the quality of the data.

[1468] "Language filtering" refers to the process of extracting data related to a specific language and excluding data in other languages.

[1469] "Morphological analysis" refers to a natural language processing technique that breaks down a sentence into its smallest meaningful units and extracts the parts of speech and morphemes of each word.

[1470] "Sentiment analysis" refers to the technology of analyzing trends such as positive and negative emotions and opinions from text data.

[1471] "Topic modeling" refers to a method for discovering common themes and topics from large amounts of text data.

[1472] An "AI model" refers to an algorithm or neural network that uses artificial intelligence, a system that can automatically perform specific tasks by learning from large amounts of data.

[1473] "Taste characteristics" refers to the numerical expression of specific taste characteristics of food (e.g., sweetness, sourness, umami, etc.).

[1474] "Point of sale data (POS data)" refers to data collected at the time of sale of a product, including details such as sales, inventory, and customer information.

[1475] "Integration" refers to the process of combining different data sets into one and analyzing and using them comprehensively.

[1476] "Insight" refers to insights and findings gained through data analysis.

[1477] "Trend analysis" refers to the technique of analyzing current trends and patterns based on past data and predicting future trends.

[1478] "New product proposal" refers to proposing new product development ideas and concepts based on market needs and trends.

[1479] A "report" refers to a document or material that summarizes analytical results and insights and provides information to assist users in making decisions.

[1480] This invention is a system for streamlining the development of new food products, and its purpose is to support the development of products based on consumer preferences by integrating and analyzing social media data and point-of-sale (POS) data. This system collects and analyzes data posted on social media, quantifies taste based on the results, and then integrates and analyzes the results with POS data, thereby realizing scientific, data-driven product development.

[1481] Data collection and preprocessing

[1482] A user uses a device to request the collection of social media data based on specific keywords or hashtags. The server then uses the API of the specified social media platform to collect post data containing the requested keywords or hashtags. Examples of APIs used in this collection process include the Twitter API and Instagram API.

[1483] The collected data undergoes preprocessing on the server side, including cleansing (removing unnecessary characters and tags) and language filtering (excluding data in languages ​​other than the target language). Software used for this includes the Python libraries regex and beautifulsoup.

[1484] Use of natural language processing technology

[1485] The preprocessed data is then analyzed by the server using natural language processing techniques such as morphological analysis, sentiment analysis, and topic modeling. For morphological analysis, natural language processing libraries such as NLTK and spaCy are used, and for sentiment analysis, TextBlob and VADER are used.

[1486] Quantifying taste characteristics

[1487] Based on the analyzed text data, a generative AI model on the server quantifies specific taste characteristics. This is done using deep learning frameworks such as TensorFlow and PyTorch. The model expresses taste characteristics such as sweetness, sourness, and umami as numerical values ​​based on keywords and sentiment scores extracted from the text data.

[1488] Data Integration and Reporting

[1489] The server integrates the quantified taste data and POS data into a single data set, allowing for analysis of the correlation between taste scores and sales data. This process uses MySQL or PostgreSQL as the database system.

[1490] It extracts insights from the integrated data and automatically generates detailed reports such as trend analysis, consumer preference predictions, new product suggestions, etc. Data visualization tools used include Matplotlib and Plotly, and the generated reports are exported in PDF or Excel format.

[1491] Users can check the reports generated on their devices and use them to develop new products or improve existing products based on scientific evidence. This system enables users to develop products efficiently and based on data.

[1492] Specific examples

[1493] For example, if a user wants to develop a new "chocolate product," the following is a specific example.

[1494] 1. User submits a request:

[1495] The user requests the collection of social media data by specifying the keywords "chocolate, new product, trend" on the device.

[1496] 2. Data Collection:

[1497] The server collects posts containing specified keywords from social media platforms such as Twitter and Instagram.

[1498] 3. Data Preprocessing and Analysis:

[1499] The server preprocesses the collected data, performs morphological analysis, and identifies posts with strong positive sentiment and weak negative sentiment.

[1500] 4. Quantifying taste:

[1501] The server's AI model generates values ​​such as "sweetness score 80, sourness score 20, umami score 50."

[1502] 5. Integration with POS data:

[1503] Based on the integrated data, the server extracts insights such as "products with high sweetness scores record high sales in winter."

[1504] 6. Provision of Report:

[1505] The user checks the generated report on the terminal and decides on a development strategy for a new chocolate product.

[1506] Prompt Sentence Examples

[1507] Examples of prompts to input to a generative AI model might include:

[1508] Regarding a new chocolate product, please collect data from Twitter and Instagram posts containing the keywords "chocolate, new product, trend." Also, please quantify the taste characteristics of the new product based on the collected data and integrate it with POS data to provide insights for optimal product development.

[1509] As described above, the present invention integrates SNS data and POS data, enabling scientific product development based on consumer preferences.

[1510] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1511] Step 1:

[1512] A user requests the collection of social media data based on specific keywords or hashtags from their device.

[1513] Specific operation: The user enters keywords into the input form specified in the dedicated application on the device and clicks the "Collect data" button.

[1514] Input: User-specified keywords and hashtags.

[1515] Output: A social media data collection request is sent to the server.

[1516] Step 2:

[1517] The server uses the API of the social media platform to collect post data containing the requested keywords and hashtags.

[1518] Specific operation: The server uses the API key to send a request to the social media platform (e.g., Twitter, Instagram) and retrieves the relevant post data.

[1519] Input: User-specified keywords, hashtags, and API keys.

[1520] Output: Retrieved social media post data.

[1521] Step 3:

[1522] The server cleanses and language filters the social media post data collected.

[1523] Specific operation: A Python script on the server uses libraries such as regex and beautifulsoup to remove unnecessary characters and tags from the data and exclude data in languages ​​other than the target language.

[1524] Input: Collected social media posting data.

[1525] Output: Preprocessed SNS data.

[1526] Step 4:

[1527] The server analyzes the preprocessed data using morphological analysis, sentiment analysis, and topic modeling.

[1528] How it works: It uses NLTK and spaCy libraries for morphological analysis, TextBlob and VADER for sentiment analysis, and Gensim for topic modeling.

[1529] Input: Preprocessed SNS data.

[1530] Output: Morphological analysis results, sentiment score, topic information.

[1531] Step 5:

[1532] The server's generative AI model quantifies specific taste characteristics based on the analyzed text data.

[1533] Specific operation: Using a deep learning framework (e.g., TensorFlow, PyTorch), a trained model quantifies sweetness, sourness, umami, etc. from text data.

[1534] Input: Morphological analysis results, sentiment scores, topic information.

[1535] Output: Numerical data of taste attributes (e.g., sweetness score 80, sourness score 20, umami score 50).

[1536] Step 6:

[1537] The server integrates and analyzes the visualized taste data and point-of-sale data (POS data).

[1538] Specific operation: Executes an SQL query on a database system (e.g., MySQL, PostgreSQL) to combine taste data and POS data.

[1539] Input: Numerical data of taste characteristics, POS data.

[1540] Output: A consolidated dataset.

[1541] Step 7:

[1542] The server extracts insights from the integrated data and generates reports such as trend analysis, consumer preference predictions, and new product suggestions.

[1543] Specific behavior: Create graphs and charts using data visualization tools (e.g., Matplotlib, Plotly) and export reports in PDF and Excel formats.

[1544] Input: The integrated dataset.

[1545] Output: Detailed report (e.g. PDF, Excel file).

[1546] Step 8:

[1547] The user checks the generated report on the device.

[1548] Specific operation: The user downloads the generated report using a dedicated application on the device and reviews the contents.

[1549] Input: Detailed report (e.g. PDF, Excel file).

[1550] Output: Report information reviewed by the user.

[1551] (Application example 1)

[1552] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1553] In the past, new food product development relied primarily on sales data and survey results, as it was difficult to accurately grasp consumer preferences and market trends. As a result, planning and development of new products that quickly reflected the latest consumer preferences and trends tended to be delayed. Furthermore, it was difficult for employees to utilize this data to propose new products, which led to inefficient product deployment in physical stores.

[1554] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1555] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an AI model for quantifying taste based on the analysis results, means for integrating and analyzing the visualized taste data and point-of-sale management data, means for generating the analysis results in report format, and means for providing the generated report to a user's visual display device. This enables the planning and development of new products that quickly and accurately reflect the latest consumer preferences, and allows employees at physical stores to use this data in real time to help with sales strategies and product development.

[1556] "Means for collecting post data from social media" refers to a system for collecting post data from social media platforms based on specific keywords or hashtags.

[1557] "Means for preprocessing collected post data" refers to the process of deleting unnecessary characters and tags from the collected SNS post data and excluding data in languages ​​other than the target language.

[1558] "Means of analysis using natural language processing technology" refers to a system that uses preprocessed data to analyze it using natural language processing technology such as morphological analysis, sentiment analysis, and topic modeling.

[1559] "Means of using an AI model" refers to a mechanism that utilizes an artificial intelligence model to quantify specific taste characteristics based on analyzed text data.

[1560] "Means for integrating and analyzing visualized taste data and point-of-sale management data" is a system that integrates visualized taste data and sales data and analyzes correlations.

[1561] "Means for generating analysis results in report format" refers to a system that automatically generates reports based on insights gained from integrated data.

[1562] The "means for providing the generated report to the user's visual display device" refers to a mechanism for displaying the generated report in real time on the user's visual display device, such as smart glasses.

[1563] This invention consists of a system that can be applied to support new product development in brick-and-mortar stores. This system collects and analyzes data from social media, and integrates and analyzes it with point-of-sale (POS) data to intuitively support users in developing new products and formulating sales strategies. Specific embodiments for implementing this invention are described below.

[1564] 1. Generate the program:

[1565] This system consists of a server, a terminal, and the user's visual display device. The server runs a program that collects posted data from SNS and preprocesses the collected data. This preprocessing includes removing unnecessary characters and tags and excluding data in a language other than the target language. The data is then analyzed using natural language processing techniques (morphological analysis, sentiment analysis, topic modeling, etc.) to quantify taste characteristics (sweetness, sourness, umami, etc.). The server integrates these analysis results with the POS data, analyzes them as a single dataset, and automatically generates a report. This report is provided in real time to the user's visual display device.

[1566] 2. Natural language processing description:

[1567] Specifically, when collecting data from social media platforms, the server uses the APIs of each platform. For data preprocessing, Python libraries (e.g., NLTK, SpaCy) are used to clean and filter text. For morphological analysis and sentiment analysis, Google Cloud Natural Language API is used. Furthermore, machine learning frameworks (e.g., TensorFlow, PyTorch) are used to quantify taste using an AI model. Google Cloud BigQuery is used to integrate and analyze the analysis results and POS data, and Google Data Studio is used to generate reports. Smart glasses, such as Google Glass, are used as visual display devices. These devices allow users to manipulate data through voice commands or touch operations.

[1568] 3. Adding concrete examples:

[1569] For example, consider the case where a user develops a new "seasonal limited edition chocolate flavor." The user specifies the keywords "seasonal limited edition, flavor, chocolate" on a visual display device and requests the collection of social media data. The server collects posts containing the specified keywords from Twitter and Instagram and performs preprocessing. The analysis results generate numerical values ​​such as "sweetness score 85, sourness score 15, umami score 40." These values ​​are then integrated with POS data to extract insights such as "products with high sweetness scores record high sales in spring." Finally, these analysis results are displayed in real time on the user's visual display device, smart glasses.

[1570] Examples of prompts for a generative AI model might include:

[1571] "Please quantify the taste characteristics (sweetness, sourness, umami) from the following social media posts."

[1572] This chocolate is so sweet and delicious!

[1573] "This chocolate is too sour."

[1574] "This chocolate has an exquisite flavor."

[1575] As described above, the system embodying this invention makes it possible to efficiently plan and develop new products in physical stores that quickly and accurately reflect the latest consumer preferences.

[1576] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1577] Step 1:

[1578] A user requests social media data collection.

[1579] The user requests the collection of social media data by specifying keywords such as "seasonal, flavor, chocolate" on the visual display. The input is the specified keyword, and the output is the transmission of a collection command. The visual display is used to execute the request by voice command or touch operation.

[1580] Step 2:

[1581] The server starts collecting social media data.

[1582] The server collects post data using the social media platform API based on the specified keywords. The input is the requested keywords, and the output is the collected social media post data. Specifically, the data is collected from Twitter and Instagram and saved in JSON format on the server.

[1583] Step 3:

[1584] The server preprocesses the collected submission data.

[1585] The collected post data is preprocessed by the server. The input is the collected SNS post data, and the output is the preprocessed data. Specifically, Python's NLTK and SpaCy are used to remove unnecessary characters and tags and exclude data in languages ​​other than the target language.

[1586] Step 4:

[1587] The server analyzes the preprocessed data using natural language processing techniques.

[1588] Based on the preprocessed data, the server uses natural language processing technology to perform sentiment analysis and topic modeling. The input is the preprocessed data, and the output is the analysis results. Specifically, it uses the Google Cloud Natural Language API to extract important keywords and analyze sentiment scores.

[1589] Step 5:

[1590] The server uses an AI model to quantify the taste based on the analysis results.

[1591] Based on the analyzed text data, the server uses an AI model to quantify specific taste characteristics. The input is the analysis result, and the output is a taste score. Specifically, TensorFlow and PyTorch are used to generate scores for sweetness, sourness, and umami.

[1592] Step 6:

[1593] The server integrates and analyzes taste visualization data and point-of-sale (POS) data.

[1594] The taste scores and POS data from physical stores are integrated and analyzed as a single dataset. The inputs are taste scores and POS data, and the output is an integrated dataset. Specifically, the data is integrated using Google Cloud BigQuery and correlation analysis is performed.

[1595] Step 7:

[1596] The server generates a report from the analysis results.

[1597] Based on the insights gained from the integrated data, the server automatically generates detailed reports. The input is the integrated dataset and the output is the report. The reports are generated using Google Data Studio and visually displayed in graphs and charts.

[1598] Step 8:

[1599] The server provides the generated report to the user's visual display.

[1600] The generated report is provided in real time to the user's visual display device. The input is the generated report, and the output is the displayed report. The report is displayed on a visual display device (e.g., smart glasses) and can be confirmed by the user via voice or touch.

[1601] Above, we have described the specific processing operations and inputs / outputs for each step, and have explained in detail the processing flow of the entire system.

[1602] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1603] This invention relates to a system that supports product development by integrating and analyzing social media data and POS data, and using an emotion engine in combination. This system analyzes posted data collected from social media, quantifies the analysis results into taste, and performs integrated analysis with sales data, as well as recognizing user emotions and providing insights.

[1604] Explanation of program processing

[1605] 1. User requests social media data collection

[1606] The user sends a request for collection of social media data related to a specific product development from their device. The request includes keywords, target platforms, and a collection period.

[1607] 2. Start collecting social media data

[1608] The server calls the API of the specified social media platform and collects post data including keywords and hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[1609] 3. Data Preprocessing

[1610] The server preprocesses the collected social media post data. Specifically, it removes unnecessary HTML tags, special characters, and unnecessary spaces, and performs language filtering. Language filtering excludes posts in languages ​​other than the target language.

[1611] 4. Text analysis using natural language processing technology

[1612] The server analyzes the preprocessed data using natural language processing techniques. The analysis operations include:

[1613] Morphological analysis: Breaks down text into morpheme units and extracts important keywords and phrases.

[1614] Sentiment Analysis: Calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post.

[1615] Topic modeling: Clustering relevant posts and extracting major topics.

[1616] 5. Quantifying taste using an AI model

[1617] The server's AI model quantifies taste characteristics based on the analyzed text data, generating taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text.

[1618] 6. Integration and analysis of POS data

[1619] The server integrates the visualized taste data with point-of-sale (POS) data, combining taste scores and POS data (sales, inventory, price, etc.) into a single dataset and analyzing the relationships between them.

[1620] 7. Emotion recognition and insights

[1621] The server utilizes an emotion engine to recognize the user's emotions and provide insights based on the analysis results, which then generates a detailed report reflecting the user's emotional state.

[1622] 8. Generate Reports

[1623] The server generates detailed reports on changing consumer preferences and market trends based on the integrated data and the output of the emotion engine, including trend analysis, consumer preference predictions, and new product suggestions.

[1624] 9. Check the report

[1625] Users can check the reports generated on their devices and develop products scientifically and efficiently based on the data. Based on these reports, they can plan new products and prepare to respond quickly to changes in the market.

[1626] Specific examples

[1627] For example, if a user wants to develop a new "ice cream product," the following specific example can be considered.

[1628] 1. User submits a request:

[1629] The user requests the collection of SNS data by specifying the keywords "ice cream, new product, summer" on the terminal.

[1630] 2. Data collection and preprocessing:

[1631] The server collects posts containing the specified keywords from the social media platform. After collection, unnecessary data is removed and preprocessed.

[1632] 3. Data analysis and taste quantification:

[1633] The server performs natural language processing on the preprocessed data and then uses an AI model to generate a taste score, such as "sweet score 90, sour score 10, salty score 5."

[1634] 4. POS data integration and analysis:

[1635] The server integrates the taste scores with POS data to extract the insight that "ice cream with a high sweetness score records high sales in the summer."

[1636] 5. Emotion Recognition and Report Generation:

[1637] The server uses an emotion engine to recognize user emotions and generates detailed reports that provide insights based on the analysis results.

[1638] 6. Report provision and review:

[1639] Users can check the reports generated on their devices and decide on new product development strategies. Insights based on emotion information can help plan products that are more likely to be accepted by consumers.

[1640] This system helps users analyze consumer preferences and market trends based on social media and POS data, and utilizes an emotion engine to respond quickly, enabling scientific and data-based product development and efficient response to market changes.

[1641] The processing flow will be explained below.

[1642] Step 1:

[1643] Users submit a request for social media data collection related to new product developments from their device by inputting keywords of interest (e.g., "chocolate," "new product," "trend"), target social media platforms (e.g., Twitter, Instagram), and the data collection period.

[1644] Step 2:

[1645] The server calls the API of the social media platform based on the received request and collects posts containing the specified keywords or hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[1646] Step 3:

[1647] The server preprocesses the collected SNS data. Specifically, it performs the following operations:

[1648] Remove unnecessary characters: Remove HTML tags, special characters, emojis, etc.

[1649] Language filtering: Filter out posts in languages ​​other than your target language (e.g., if you only target Japanese).

[1650] Text normalization: unifying full-width and half-width characters, converting uppercase and lowercase characters, etc.

[1651] Step 4:

[1652] The server analyzes the preprocessed data using natural language processing (NLP) technology. Specifically, it performs the following processes:

[1653] Morphological analysis: Breaks down the text of a post into morphemes and extracts important keywords.

[1654] Sentiment analysis: Calculates positive, negative, and neutral sentiment scores.

[1655] Topic modeling: Clustering posts and extracting major topics.

[1656] Step 5:

[1657] The server's AI model quantifies taste characteristics based on the analysis results. Specifically, it generates scores for sweetness, sourness, umami, bitterness, saltiness, etc. from the text data. This taste quantification visualizes the consumer's posts as specific taste characteristics.

[1658] Step 6:

[1659] The server integrates and analyzes taste data and point-of-sale (POS) data. Specifically, it performs the following operations:

[1660] Data integration: Integrate taste scores and POS data (sales, inventory, price, etc.) into one.

[1661] Association analysis: Based on the integrated data, the relationship between taste characteristics and sales performance is analyzed (e.g., products with high sweetness scores have high sales).

[1662] Step 7:

[1663] The server uses an emotion engine to recognize the user's emotions. Specifically, it evaluates the user's emotional state in real time based on the user's operation history and input information when they access the system.

[1664] Step 8:

[1665] The server adds insights corresponding to the user's emotional state to the report based on the output of the emotion engine, thereby generating a detailed report containing insights based on the user's emotions.

[1666] Step 9:

[1667] The server provides the generated report to the user's device, where the user can check the report and develop products based on scientific evidence and data.

[1668] Step 10:

[1669] Users can use the reports provided on their devices to decide on new product plans and development policies, making it possible to quickly develop products that respond to consumer preferences and market trends.

[1670] In this way, this system integrates and analyzes SNS data and POS data, and by combining it with an emotion engine, provides product development support based on data that is useful to users.

[1671] Example 2

[1672] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1673] Conventional methods have made it difficult to efficiently integrate social media data and point-of-sale data to quickly understand consumer preferences and market trends. Furthermore, there is a lack of means to recognize user emotions using an emotion engine or generate detailed reports, which hinders the efficiency of the scientific, data-driven product development process. To solve these problems, a system is needed that can consistently analyze social media data, quantify taste perception, integrate data, recognize emotions, and generate reports.

[1674] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1675] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an artificial intelligence model that quantifies taste based on the analysis results, means for integrating and analyzing the taste visualization data and point-of-sale management data, means for recognizing user emotions using an emotion engine, means for generating a detailed report based on the integrated data and the output of the emotion engine, and means for providing the generated report to the user's terminal. This enables rapid understanding of consumer preferences and market trends and enables scientific product development based on data.

[1676] "SNS data" refers to information such as user messages, comments, images, and videos posted on social media platforms.

[1677] "Preprocessing" refers to the process of removing unnecessary information from collected data and converting it into a format suitable for analysis.

[1678] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and generate human language.

[1679] An "artificial intelligence model" refers to an algorithm that learns from large amounts of data and makes predictions and analyses based on that data.

[1680] "Quantifying taste" refers to the process of extracting taste characteristics (sweetness, sourness, umami, bitterness, saltiness, etc.) from text data and expressing those characteristics numerically.

[1681] "Point of sale data" refers to data used to manage sales information in real time, including product sales, inventory, prices, etc.

[1682] "Emotion engine" refers to an algorithm or system for analyzing and recognizing a user's emotions.

[1683] "Report" means a written or digital report summarizing the results of an analysis or insights.

[1684] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[1685] "User" refers to the person or company that uses the system to collect, analyze, and check reports on social media data.

[1686] This invention is a system that integrates and analyzes social media data and point-of-sale (POS) data to recognize user sentiment and support product development. The system collects, analyzes, and integrates data through multiple steps, and finally generates a report to provide to the user.

[1687] The main components of this system include a server, a terminal, and a user. The configuration of this system and a specific embodiment will be described in detail below.

[1688] Data collection and preprocessing

[1689] A user requests collection of social media data through their device. The request includes specific keywords (e.g., "ice cream, new products, summer"), the target social media platform (e.g., Twitter, Instagram), and the data collection period (e.g., the past three months).

[1690] The server receives a request from a user and uses the API of the social media platform (e.g., Twitter API) to collect post data containing the specified keywords and hashtags. The collected data includes the post content, posting date and time, user ID, etc.

[1691] The server then pre-processes the collected data, which includes removing unnecessary HTML tags, special characters, and unnecessary spaces, and language filtering to retain only the specified language (e.g., Japanese).

[1692] Text analysis and quantification of taste

[1693] The preprocessed data is then analyzed on the server using natural language processing (NLP) techniques. This analysis includes morphological analysis, sentiment analysis, and topic modeling. Morphological analysis breaks down text into words and extracts important keywords and phrases. Sentiment analysis calculates a positive, negative, or neutral sentiment score to identify the emotional tone of a post. Topic modeling clusters related posts and extracts major topics.

[1694] The server's AI model quantifies taste characteristics based on the analyzed text data. This model generates taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text. For example, a score such as "sweetness score 90, sourness score 10, saltiness score 5" may be generated.

[1695] Integration and analysis of POS data

[1696] The server integrates the taste scores with the POS data. The POS data includes sales-related information such as sales, inventory, and price. The integrated data is analyzed on the server to analyze the relationship between the taste scores and the POS data. For example, an insight such as "ice cream with a high sweetness score records high sales in the summer" can be extracted.

[1697] Emotion Recognition and Report Generation

[1698] The server uses an emotion engine to recognize the user's emotions and generates a detailed report based on the results, including changes in consumer preferences, market trends, insights, consumer preference predictions, and new product suggestions. The report is provided to the user's device, where the user can review it and decide on a new product development strategy.

[1699] Specific examples

[1700] For example, if a user wants to develop a new "ice cream product," here are the specific steps:

[1701] 1. User submits a request

[1702] The user requests the collection of SNS data by specifying the keywords "ice cream, new product, summer" on the terminal.

[1703] 2. Data collection and preprocessing

[1704] The server calls the Twitter API, collects posts containing the specified keywords, and preprocesses them.

[1705] 3. Data analysis and taste quantification

[1706] The server analyzes the preprocessed data using natural language processing technology and uses an AI model to generate a taste score such as "sweetness score 90, sourness score 10, saltiness score 5."

[1707] 4. POS data integration and analysis

[1708] The server integrates the taste scores and POS data, analyzes the correlations, and extracts the insight that "ice cream with a high sweetness score records high sales in the summer."

[1709] 5. Emotion Recognition and Report Generation

[1710] The server uses an emotion engine to recognize the user's emotions, and generates a detailed report that is provided to the user's terminal.

[1711] 6. Provision and review of reports

[1712] The user checks the generated report on the terminal and decides on a new product development strategy, for example, planning a "new, highly sweet ice cream flavor" for the summer season based on the report.

[1713] This system allows users to integrate social media data and POS data to quickly analyze consumer preferences and market trends, and utilize an emotion engine to develop data-driven products.

[1714] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1715] Step 1:

[1716] Sending a social media data collection request

[1717] Users use their devices to request social media data collection by specifying specific keywords (e.g., "ice cream, new product, summer"), the target social media platform (e.g., Twitter, Instagram), and the data collection period (e.g., the past three months).

[1718] Input: Keywords, target platform, collection period

[1719] Output: Social Media Data Collection Request

[1720] Step 2:

[1721] Started collecting social media data

[1722] Based on the received request, the server uses the API of the specified social media platform (e.g., Twitter API) to collect related post data, including the post content, posting date and time, and user ID.

[1723] Input: Social Media Data Collection Request

[1724] Output: Collected social media post data

[1725] Specific operations: Acquiring data through API calls and analyzing responses

[1726] Step 3:

[1727] Data Preprocessing

[1728] The server preprocesses the collected social media post data, specifically removing unnecessary HTML tags, special characters, and unnecessary spaces, and filtering the data to retain the specified language (e.g., Japanese).

[1729] Input: Collected social media post data

[1730] Output: Preprocessed data

[1731] Specific behavior: Text cleaning, language filtering

[1732] Step 4:

[1733] Text analysis using natural language processing technology

[1734] The server then analyzes the preprocessed data using natural language processing techniques. These include morphological analysis, sentiment analysis, and topic modeling. Morphological analysis breaks down text into words and extracts important keywords and phrases. Sentiment analysis calculates positive, negative, and neutral sentiment scores. Topic modeling clusters related posts and extracts major topics.

[1735] Input: Preprocessed data

[1736] Output: Analysis results (morphological analysis results, sentiment scores, topic models)

[1737] Specific operations: Applying NLP algorithms and saving analysis results

[1738] Step 5:

[1739] Quantifying taste using an AI model

[1740] The server's AI model quantifies taste characteristics based on the analysis results, generating taste scores such as sweetness, sourness, umami, bitterness, and saltiness from the text.

[1741] Input: Analysis results

[1742] Output: Taste score (e.g. sweet score 90, sour score 10, salty score 5)

[1743] Specific operation: Text analysis and quantification using AI models

[1744] Step 6:

[1745] Integration and analysis of POS data

[1746] The server integrates the taste scores and POS data, and analyzes the relationship between the taste scores and POS data (sales, inventory, price, etc.) based on the integrated data set.

[1747] Input: Taste score, POS data

[1748] Output: Integrated dataset, relationship analysis results

[1749] Specific operations: Data combination, correlation analysis

[1750] Step 7:

[1751] Emotion recognition and insights

[1752] The server uses an emotion engine to recognize user emotions, and based on the results, provides insights into consumer preferences and market trends.

[1753] Input: Integrated dataset, user emotion information

[1754] Output: Insights, detailed reports

[1755] Specific operations: Applying emotion engine, generating reports

[1756] Step 8:

[1757] Generate reports

[1758] The server generates detailed reports based on the integrated data and the output of the emotion engine, including trend analysis and new product recommendations.

[1759] Inputs: Insights, Integrated Data

[1760] Output: Report

[1761] Specific operations: Data embedding and finalization in report template

[1762] Step 9:

[1763] Providing reports

[1764] Users can check the generated reports on their devices, which allows for scientific and efficient product development based on data.

[1765] Input: Report

[1766] Output: New product development strategy

[1767] Specific actions: Downloading and viewing reports, product development decision-making

[1768] In this way, the system integrates social media data and POS data to quickly analyze consumer preferences and market trends, and utilizes an emotion engine to support data-based product development.

[1769] (Application example 2)

[1770] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1771] Conventional content distribution services lack a method for providing optimized content based on a user's individual emotional state or interests. Therefore, to increase user satisfaction, it is necessary to provide personalized content that takes into account social media data and emotional states. Furthermore, more accurate market analysis and prediction of consumer preferences are required by integrating social media data analysis and POS data.

[1772] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1773] In this invention, the server includes means for collecting posted data from SNS, means for preprocessing the collected posted data, means for analyzing the preprocessed data using natural language processing technology, means for utilizing an AI model for quantifying taste based on the analysis results, means for integrating and analyzing the taste visualization data and point-of-sale management data, means for analyzing the user's emotional state from the integrated data and providing individually optimized content, and means for providing the generated report and content recommendation results to the user terminal. This enables the provision of personalized content based on the user's emotional state and interests, improving the accuracy of market analysis and consumer preference prediction.

[1774] "SNS" stands for Social Networking Service, a platform for users to interact and share information online.

[1775] "Posted data" refers to content such as messages, images, and videos posted by users on SNS.

[1776] "Preprocessing" refers to processes such as data cleansing and normalization that are carried out to make collected data ready for analysis.

[1777] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language.

[1778] The "AI model that quantifies taste characteristics" is an artificial intelligence model that extracts taste-related characteristics from text data and converts them into quantitative values.

[1779] "Point of sale data" refers to information collected during the course of a commercial transaction, such as sales and inventory.

[1780] "Emotional state" refers to the psychological state that a user expresses through their posted data.

[1781] "Report format" refers to documents and graphs that are formatted to clearly communicate the results of analysis.

[1782] "Content recommendation" is the act of presenting appropriate content based on a user's interests, concerns, and emotional state.

[1783] A "user terminal" is a device such as a computer, smartphone, or tablet that a user uses to use a service.

[1784] This invention relates to a system that integrates and analyzes SNS data and point-of-sale (POS) data, and uses an emotion engine to provide personalized content tailored to the user's emotional state. This system operates in the following steps:

[1785] Hardware / Software

[1786] This system is application software installed on user devices such as smartphones and tablets, and data processing and analysis are performed on a server. This server includes software for collecting data through the API of the social media platform and analyzing the data using natural language processing technology and AI models.

[1787] The specific hardware and software used are as follows:

[1788] Hardware: smartphones, tablets, servers

[1789] Software: Python (requests, json, textblob libraries), SNS platform API, AI model

[1790] Data processing / data calculation

[1791] The server first calls the API of the social media platform and collects post data based on the specified keywords. This data includes the post content, posting date and time, user ID, etc. The collected data is then preprocessed and unnecessary data is filtered out. After preprocessing, the data is analyzed using natural language processing technology.

[1792] Natural language processing technology performs morphological analysis and sentiment analysis to calculate an emotional score for posts. It also uses an AI model to quantify taste characteristics based on the analysis results. This taste characteristic data is integrated with POS data for comprehensive analysis. Finally, the integrated data is used to analyze the user's emotional state and provide individually optimized content.

[1793] Specific examples

[1794] For example, if a user wants to find new content using the keyword "ice cream," the server calls the social media platform's API to collect relevant post data from the past week. The server then preprocesses this data and uses natural language processing technology to calculate a sentiment score. Based on the sentiment score, the server determines whether the user's emotional state is positive or negative and recommends personalized content.

[1795] Example prompt sentence:

[1796] Keywords: ice cream

[1797] Social Media Platform: Twitter

[1798] Collection period: Past week

[1799] Use a content recommendation system based on sentiment scores to serve content that matches the user's emotional state.

[1800] As described above, the system based on this invention improves user satisfaction by integrating and analyzing users' SNS posting data and POS data, and providing personalized content that corresponds to their individual emotional state.

[1801] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1802] Step 1:

[1803] The server receives a request for collecting SNS data from a user, which includes keywords, target platforms, and a collection period.

[1804] Input: User-specified keywords, target platform, collection period

[1805] Output: Collection request information

[1806] Specific operation: A user sends a social media data collection request from their device by specifying a keyword such as "ice cream" and the "Twitter" platform.

[1807] Step 2:

[1808] The server calls the API of the specified SNS platform and collects post data containing keywords.

[1809] Input: Collection request information

[1810] Output: Collected posting data (post content, date and time, user ID, etc.)

[1811] Specific behavior: The server uses the Twitter API to retrieve posts related to "ice cream" from the past week.

[1812] Step 3:

[1813] The server preprocesses the collected submission data, specifically removing unnecessary HTML tags, special characters, unnecessary spaces, and performing language filtering.

[1814] Input: Collected submission data

[1815] Output: Preprocessed data

[1816] Specific operation: The server removes meaningless characters and posts in foreign languages ​​from the post data it obtains, and extracts only posts in Japanese.

[1817] Step 4:

[1818] The server then analyzes the preprocessed data using natural language processing techniques, conducting morphological analysis to extract important keywords and phrases, and sentiment analysis to calculate a positive, negative, or neutral sentiment score.

[1819] Input: Preprocessed data

[1820] Output: Analysis results (morphological analysis results, emotion scores)

[1821] Specific operation: The server breaks down the text data into morpheme units and calculates the sentiment score using an NLP model.

[1822] Step 5:

[1823] The server quantifies taste characteristics based on the analyzed text data using an AI model, which generates taste scores such as sweetness, sourness, umami, bitterness, and saltiness.

[1824] Input: Analysis results (morphological analysis results, emotion scores)

[1825] Output: Taste score

[1826] Specific operation: The server uses an AI model to quantify taste characteristics from posts about "ice cream," such as "sweetness score 90, sourness score 10."

[1827] Step 6:

[1828] The server integrates the taste scores with point-of-sale (POS) data and analyzes the relationships between them. The visualized taste data is combined with POS data such as sales, inventory, and price into a single dataset.

[1829] Input: Taste score, POS data

[1830] Output: Integrated analysis data (relationship between taste scores and POS data)

[1831] Specific operation: The server combines the taste scores with POS data to extract insights such as "ice cream with a high sweetness score records high sales in the summer."

[1832] Step 7:

[1833] The server utilizes an emotion engine to analyze the user's emotional state and provide individually optimized content.

[1834] Input: Integrated analysis data, user sentiment score

[1835] Output: Content recommendation results

[1836] Specific operation: The server recommends, for example, comedy shows for positive emotions and relaxing music for negative emotions based on the user's emotional state.

[1837] Step 8:

[1838] The server provides the generated report and content recommendation results to the user terminal.

[1839] Input: Content recommendation results, report data

[1840] Output: Reports and content recommendations displayed on the user's device

[1841] Specific operation: The user checks the reports and content recommendations sent from the server via a smartphone or tablet.

[1842] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1843] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1844] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1845] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1846] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1847] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1848] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1849] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1850] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1851] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1852] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1853] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1854] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1855] 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.

[1856] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1857] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1858] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1859] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1860] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1861] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1862] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1863] The following is further disclosed regarding the above embodiment.

[1864] (Claim 1)

[1865] A means of collecting posting data from SNS,

[1866] a means for preprocessing the collected submission data;

[1867] means for analyzing the preprocessed data using natural language processing techniques;

[1868] Using an AI model that quantifies taste based on the analysis results,

[1869] A means of integrating and analyzing taste visualization data and point-of-sale data;

[1870] a means for generating the results of the analysis in the form of a report;

[1871] means for providing the generated report to a user's terminal;

[1872] A system including:

[1873] (Claim 2)

[1874] 10. The system of claim 1, further comprising means for performing morphological analysis from the preprocessed data.

[1875] (Claim 3)

[1876] 10. The system of claim 1, further comprising means for performing sentiment analysis using natural language processing techniques.

[1877] "Example 1"

[1878] (Claim 1)

[1879] A means for users to request the collection of social media data based on specific keywords or hashtags from their device;

[1880] A means of collecting post data including requested keywords and hashtags using the API of a social media platform;

[1881] a means for cleansing and language filtering the collected submission data;

[1882] means for analyzing the preprocessed data using morphological analysis, sentiment analysis, and topic modeling;

[1883] By using a generative AI model that quantifies specific taste characteristics based on text data;

[1884] A means of integrating and analyzing visualized taste data and point-of-sale data;

[1885] A means to extract insights from integrated data and generate reports such as trend analysis, consumer preference predictions, and new product suggestions.

[1886] A means for providing the generated report in a format that can be viewed on the user's terminal;

[1887] A system including:

[1888] (Claim 2)

[1889] 10. The system of claim 1, further comprising means for performing morphological analysis from the preprocessed data.

[1890] (Claim 3)

[1891] 10. The system of claim 1, further comprising means for performing sentiment analysis and topic modeling using natural language processing techniques.

[1892] "Application Example 1"

[1893] (Claim 1)

[1894] A means of collecting posting data from SNS,

[1895] a means for preprocessing the collected submission data;

[1896] means for analyzing the preprocessed data using natural language processing techniques;

[1897] Using an AI model that quantifies taste based on the analysis results,

[1898] A means of integrating and analyzing taste visualization data and point-of-sale data;

[1899] a means for generating the results of the analysis in the form of a report;

[1900] means for providing the generated report to a user's visual display;

[1901] A system including:

[1902] (Claim 2)

[1903] 10. The system of claim 1, further comprising means for performing morphological analysis from the preprocessed data.

[1904] (Claim 3)

[1905] 10. The system of claim 1, further comprising means for performing sentiment analysis using natural language processing techniques.

[1906] "Example 2: Combining Emotion Engines"

[1907] (Claim 1)

[1908] A means of collecting posting data from SNS,

[1909] a means for preprocessing the collected submission data;

[1910] means for analyzing the preprocessed data using natural language processing techniques;

[1911] A method that uses an artificial intelligence model to quantify taste based on the analysis results, and

[1912] A means of integrating and analyzing taste visualization data and point-of-sale data;

[1913] means for recognizing a user's emotion using an emotion engine;

[1914] A means to generate detailed reports based on the integrated data and the output of the sentiment engine;

[1915] means for providing the generated report to a user's terminal;

[1916] A system including:

[1917] (Claim 2)

[1918] 10. The system of claim 1, further comprising means for performing morphological analysis from the preprocessed data.

[1919] (Claim 3)

[1920] 10. The system of claim 1, further comprising means for performing sentiment analysis using natural language processing techniques.

[1921] "Application example 2 when combining emotion engines"

[1922] (Claim 1)

[1923] A means of collecting posting data from SNS,

[1924] a means for preprocessing the collected submission data;

[1925] means for analyzing the preprocessed data using natural language processing techniques;

[1926] Using an AI model that quantifies taste based on the analysis results,

[1927] A means of integrating and analyzing taste visualization data and point-of-sale data;

[1928] A means for analyzing the emotional state of a user from the integrated data and providing individually optimized content;

[1929] a means for providing the generated report and content recommendation results to a user terminal;

[1930] A system including:

[1931] (Claim 2)

[1932] 10. The system of claim 1, further comprising means for performing morphological analysis from the preprocessed data.

[1933] (Claim 3)

[1934] 10. The system of claim 1, further comprising means for performing sentiment analysis using natural language processing techniques. [Explanation of symbols]

[1935] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting posting data from SNS, a means for preprocessing the collected submission data; means for analyzing the preprocessed data using natural language processing techniques; Using an AI model that quantifies taste based on the analysis results, A means of integrating and analyzing taste visualization data and point-of-sale data; a means for generating the results of the analysis in the form of a report; means for providing the generated report to a user's terminal; A system including:

2. 2. The system of claim 1, further comprising means for performing morphological analysis from the preprocessed data.

3. The system of claim 1 further comprising means for performing sentiment analysis using natural language processing techniques.

Images