System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting data about an industry specified by a user; means for pre-processing the collected data; means for executing an artificial intelligence model to analyze the pre-processed data; means for suggesting a marketing strategy to the user based on the analysis; and means for performing additional analysis and suggestions in real-time in response to a user query.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] In marketing, analyzing industry trends and consumer behavior in real time is essential for formulating effective strategies. However, many marketing professionals spend a great deal of time and effort manually collecting and analyzing vast amounts of data, making it difficult to respond quickly. This also requires specialized knowledge to apply appropriate purchasing process models. The present invention aims to solve these problems and provide a system for streamlining and optimizing the formulation of marketing strategies. [Means for solving the problem]

[0005] The present invention provides a system including a means for collecting data related to an industry specified by a user, a means for preprocessing the collected data, a means for running an artificial intelligence model to analyze the preprocessed data, a means for proposing a marketing strategy to the user based on the analysis results, and a means for performing additional analysis and proposing in real time in response to a user query. The system further includes a means for generating a proposed marketing strategy based on a purchasing process model and a means for visualizing the collected data and displaying it to the user. In this way, marketing professionals can develop effective strategies in a shorter time, thereby improving overall business efficiency and performance.

[0006] "Data collection methods" are technologies and methods for collecting real-time trend data and consumer behavior data related to a particular industry.

[0007] "Means for preprocessing data" refers to techniques and methods for converting collected data into a format suitable for analysis using methods such as cleansing, normalization, and format conversion.

[0008] "Means for implementing artificial intelligence models" means technologies or methods for running AI algorithms using pre-processed data to analyze consumer behavior and market trends.

[0009] "Means for proposing marketing strategies" refers to technologies and methods for recommending specific marketing measures and campaigns to users based on the analysis results of the AI ​​model.

[0010] "Means for providing additional analysis and suggestions in real time in response to user queries" refers to technologies and methods for responding to user questions and requests and instantly proposing additional data analysis and marketing measures.

[0011] The "purchasing process model" is a theoretical model that systematically captures the steps consumers take to purchase a product or service, and formulates marketing strategies accordingly.

[0012] "Means of visualizing and displaying to users" refers to techniques and methods for displaying analysis results and marketing strategy proposals using graphs, charts, etc., to make them easier for users to understand. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention is a digital assistant service designed for marketing professionals. This service uses AI technology to analyze real-time industry trends and consumer behavior and propose effective marketing strategies. Users can receive support for a wide range of projects, from short-term campaigns to long-term brand strategies.

[0035] System Overview

[0036] The system consists of the following main components:

[0037] 1. Data Collection Methods

[0038] The server collects data related to the industry specified by the user. For example, in the case of the fashion industry, the server collects the latest fashion trends, social media posting data, and e-commerce site purchase data.

[0039] 2. Data preprocessing methods

[0040] The server preprocesses the collected data and converts it into a format suitable for analysis by the AI ​​model, specifically by cleansing text data and normalizing numerical data.

[0041] 3. AI model execution means

[0042] The server inputs the pre-processed data into the AI ​​model to analyze consumer behavior and market trends, and the results of this analysis are presented to the user in visualizations such as graphs and charts.

[0043] 4. Marketing strategy proposal methods

[0044] The server proposes specific marketing strategies to users based on the analysis results of the AI ​​model. These proposals are generated using the AISAS and AIDMA models.

[0045] 5. User Interaction Methods

[0046] Users can receive suggestions through their devices and enter queries in real time, and the server will then perform additional analysis and provide suggestions accordingly.

[0047] Program processing

[0048] The program flow is as follows:

[0049] First, the user specifies the industry for which they want to develop a marketing strategy. Next, the server collects data related to the specified industry and preprocesses the collected data. The server then inputs the preprocessed data into an AI model to obtain analysis results. Based on the analysis results, the server proposes an optimal marketing strategy. The proposal is visualized and displayed to the user via their device. The user can review the proposal and enter a query. The server then performs additional analysis based on the query and provides the proposal to the user again.

[0050] Specific examples

[0051] For example, consider the case of a fashion industry campaigning for a new summer collection.

[0052] 1. A user requests suggestions for a summer campaign strategy for the fashion industry.

[0053] 2. The server collects the latest fashion trends, social media posts, and e-commerce site purchasing data.

[0054] 3. The server preprocesses the collected data by performing text cleansing and normalizing numeric data.

[0055] 4. The server inputs the preprocessed data into an AI model to analyze consumer purchasing patterns and popular items.

[0056] 5. Based on the AISAS model, the server will propose marketing strategies such as sharing campaigns on social media and limited-time sales on e-commerce sites.

[0057] 6. The device displays a visualization of these suggestions to the user.

[0058] 7. The user reviews the displayed suggestions and enters any follow-up questions.

[0059] 8. The server performs further analysis in response to the user's query and provides updated suggestions.

[0060] In this way, the present invention improves the efficiency of formulating marketing strategies and provides specific support for quickly implementing effective measures.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user specifies the industry for which they want to develop a marketing strategy through the terminal, for example, requesting the collection of data on new collections in the fashion industry.

[0064] Step 2:

[0065] The server collects data related to the industry specified by the user, using web scraping technology and APIs to obtain the latest fashion industry trends, social media posts, and e-commerce site purchase data.

[0066] Step 3:

[0067] The server pre-processes the collected data.

[0068] Cleanse text data to remove unnecessary information and noise.

[0069] Normalize numeric data and convert it into a uniform format.

[0070] Step 4:

[0071] The server inputs the preprocessed data into the AI ​​model, which analyzes consumer behavior and market trends and obtains analytical results.

[0072] Step 5:

[0073] The server visualizes the analysis results in a form that is easy for the user to understand, for example by creating graphs or charts.

[0074] Step 6:

[0075] Based on the analysis results, the server proposes specific marketing strategies to the user, using the AISAS and AIDMA models to generate optimal strategies for social media sharing campaigns and e-commerce site exclusive sales.

[0076] Step 7:

[0077] The device displays the marketing strategy proposals received from the server to the user, allowing them to view visualized data on a dashboard or on the screen of a dedicated app.

[0078] Step 8:

[0079] The user can review the suggestions presented and enter additional questions or queries, such as "Who is the target audience for this campaign?"

[0080] Step 9:

[0081] The terminal sends the user's query to the server.

[0082] Step 10:

[0083] The server performs additional data analysis in response to user queries, collects and analyzes new information, and updates the marketing strategy again.

[0084] Step 11:

[0085] The server sends the updated proposal to the terminal, which displays the proposal to the user.

[0086] This series of processing steps allows users to quickly develop effective marketing strategies in real time.

[0087] Example 1

[0088] 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."

[0089] Conventional marketing strategy formulation systems have struggled to perform rapid and accurate data analysis and proposals. Furthermore, they lacked a means for users to quickly obtain additional analysis results by inputting specific queries, preventing the maximum effectiveness of marketing strategies. Furthermore, they had limited means for visually grasping the analysis results, making it difficult for users to receive proposals in a format that is easy for them to understand. Therefore, the present invention aims to solve these problems and provide a system that proposes efficient and effective marketing strategies in real time.

[0090] 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.

[0091] In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for executing an artificial intelligence model that analyzes the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means for performing additional analysis and proposals in real time in response to user queries, and means for visualizing and displaying the proposed marketing strategy. This allows the user to receive marketing strategy proposals based on rapid and accurate data analysis, and further allows the user to obtain analysis results in real time for additional queries. Furthermore, by visually grasping the analysis results, the user can receive proposals in a format that is easy for the user to understand.

[0092] The "means for collecting data" is a function for collecting information about an industry specified by the user.

[0093] "Means for pre-processing data" refers to processing functions for converting collected raw data into an analyzable format.

[0094] The "means for implementing an artificial intelligence model" is a computational function that uses AI techniques to analyze the pre-processed data.

[0095] The "means for proposing marketing strategies" is a function for presenting specific marketing measures to users based on the analysis results of the artificial intelligence model.

[0096] "Means for real-time analysis and proposals in response to queries" refers to a function that instantly provides more detailed analysis results and strategic proposals in response to additional questions entered by the user.

[0097] The "means for visualizing and displaying the proposed marketing strategy" is a function for visually expressing the analysis results and proposals in the form of graphs, charts, etc., and presenting them to the user in an easy-to-understand manner.

[0098] A "purchasing process model" is a model that shows the series of behavioral patterns that consumers follow when purchasing products or services, and is a basic framework used in building marketing strategies.

[0099] This is a digital assistant service designed for marketing professionals. It uses AI technology to analyze real-time industry trends and consumer behavior and propose effective marketing strategies. Users can receive support for a wide range of projects, from short-term campaigns to long-term brand strategies.

[0100] The system consists of the following main components:

[0101] 1. Data Collection Methods

[0102] The server collects data related to the industry specified by the user. For example, in the fashion industry, the server collects the latest fashion trends, social media posting data, and e-commerce site purchase data. Specifically, it uses web scraping tools (e.g., BeautifulSoup) and API access (e.g., Twitter API).

[0103] 2. Data preprocessing methods

[0104] The server preprocesses the collected data and converts it into a format suitable for analysis by the AI ​​model. Specifically, it uses Python and pandas to cleanse text data and normalize numerical data.

[0105] 3. AI model execution means

[0106] The server then uses the preprocessed data to run AI models, such as deep learning models built using TensorFlow and PyTorch, to analyze consumer behavior and market trends.

[0107] 4. Marketing strategy proposal methods

[0108] The server then proposes specific marketing strategies to the user based on the analysis results of the AI ​​model. These proposals are generated using the AISAS and AIDMA models. For example, sharing campaigns on social media or limited-time sales on e-commerce sites may be suggested.

[0109] 5. User Interaction Methods

[0110] Users can receive suggestions via their device and input queries in real time, and the server will then perform additional analysis and provide suggestions accordingly. For example, it can instantly answer questions such as, "Are there any other social media campaigns that are effective?"

[0111] 6. Visualization Tools

[0112] The device visually displays the proposed marketing strategy to the user, using tools such as Matplotlib and Tableau to display the analysis results in graphs and charts, allowing the user to intuitively understand the proposed content.

[0113] Specific examples

[0114] For example, consider the case of a fashion industry campaigning for a new summer collection.

[0115] 1. The user is looking for suggestions for a summer campaign strategy for the fashion industry. An example of a prompt sentence is, "Please suggest a marketing strategy for the fashion industry for next summer."

[0116] 2. The server collects the latest fashion trends, social media posts, and purchase data from e-commerce sites. It uses the Twitter API to collect posts containing relevant keywords and extracts sales data from e-commerce sites using BeautifulSoup.

[0117] 3. The server preprocesses the collected data, specifically cleansing text data and normalizing numeric data using Python and pandas.

[0118] 4. The server inputs the preprocessed data into a TensorFlow model to analyze consumer purchasing patterns and popular items.

[0119] 5. Based on the AISAS model, the server will propose marketing strategies such as sharing campaigns on social media and limited-time sales on e-commerce sites.

[0120] 6. The device displays these suggestions to the user in a visual format, such as a chart showing purchasing trends or an overview of recommended campaigns.

[0121] 7. The user reviews the suggestions and enters a follow-up question, such as, "What other social media campaigns have you seen that have worked?"

[0122] 8. The server performs further analysis in response to the user's query and provides updated suggestions.

[0123] In this way, the present invention provides specific support for making the formulation of marketing strategies more efficient and for quickly implementing effective measures.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] User specifies industry

[0127] Through the system interface, users input the industry related to their business and the campaign information they wish to analyze. An example of a prompt sentence is, "Please suggest a marketing strategy for the fashion industry for next summer." This input is sent to the server as an instruction to the system.

[0128] Input: Industry and campaign information prompt text

[0129] Output: Instruction to start analysis on the server

[0130] Step 2:

[0131] The server collects the data

[0132] The server collects data related to the industry selected by the user. Specifically, it uses web scraping tools and APIs to obtain the following data:

[0133] Social Media Data: Use the Twitter API to collect posts with relevant keywords and hashtags.

[0134] E-commerce website data: Use web scraping tools to extract up-to-date sales data and product reviews.

[0135] Market Report Data: Gather the required data from published market research reports.

[0136] Input: Industry designation, campaign information

[0137] Output: Collected social media data, e-commerce site data, and other market data

[0138] Step 3:

[0139] The server preprocesses the data

[0140] The server preprocesses the collected raw data into a format suitable for analysis by the AI ​​model. The specific operations are as follows:

[0141] Text data cleansing: Use Python and pandas to remove unnecessary HTML tags, special characters, and noise data.

[0142] Normalization of numerical data: To standardize data with different scales, numerical data is normalized with z-scores.

[0143] Input: Collected social media data, e-commerce site data, and other market data

[0144] Output: Preprocessed data

[0145] Step 4:

[0146] The server runs the artificial intelligence model

[0147] The server runs an AI model (e.g., built with TensorFlow or PyTorch) on the preprocessed data. Specifically, it performs the following operations:

[0148] Data input: Input the preprocessed data into the AI ​​model.

[0149] Performing analytics: Models can analyze consumer behavior and market trends, such as the popularity of certain products and purchasing patterns.

[0150] Input: Preprocessed data

[0151] Output: Analysis results

[0152] Step 5:

[0153] The server proposes a marketing strategy

[0154] The server generates a marketing strategy to propose to the user based on the analysis results of the AI ​​model. This proposal is based on a purchasing process model such as the AISAS or AIDMA model. Specific proposals include:

[0155] Social media campaigns: Propose campaigns that utilize popular posts and hashtags.

[0156] Limited-time offer: Offering a discount or special offer on a specific product for a limited time.

[0157] Input: Analysis results

[0158] Output: Marketing strategy proposal

[0159] Step 6:

[0160] The device will visualize the suggestions and display them.

[0161] The terminal visually displays the marketing strategy proposals provided by the server to the user. The visualization uses the following tools:

[0162] Graphs and Charts: Use Matplotlib and Tableau to create graphs and charts that show consumer behavior and trends.

[0163] Dashboard: The proposed strategies are presented in a dashboard format that is easy for users to understand.

[0164] Input: Marketing strategy proposal

[0165] Output: Visualized proposal

[0166] Step 7:

[0167] The user enters a query

[0168] Users enter queries into the interface to ask follow-up questions or explore the suggestions presented, such as "What other social media campaigns are effective?"

[0169] Input: User query

[0170] Output: Request for further analysis to the server

[0171] Step 8:

[0172] The server performs additional analysis and offers suggestions

[0173] The server then analyzes the data again in response to user queries, providing additional strategies and insights. It does the following:

[0174] Additional data analysis: Reanalyze the required data based on the query.

[0175] Generate new proposals: Update your marketing strategy based on new insights.

[0176] Input: User query

[0177] Output: Additional analysis results and updated recommendations

[0178] In this way, the system provides users with real-time, data-driven marketing strategies tailored to their needs.

[0179] (Application example 1)

[0180] 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."

[0181] Traditional marketing strategies lack real-time monitoring and analysis of advertising trends and consumer behavior, making it difficult to develop fast and effective advertising strategies. In particular, the manual process of collecting, preprocessing, and analyzing complex data is time-consuming and inefficient. Another issue is that the proposed strategies are static, making them unable to adequately respond to changes in consumer behavior.

[0182] 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.

[0183] In this invention, the server includes means for collecting data related to a user-specified industry, means for pre-processing the collected data, and means for executing an artificial intelligence model that analyzes the pre-processed data, thereby enabling visualization and collection of advertising trends and campaign success stories in real time, and generating advertising strategies based on consumer purchasing patterns and popular items.

[0184] "Means for collecting data related to an industry specified by a user" refers to a system or method for obtaining necessary data related to a specific industry specified by a user from various sources (such as social media posts or purchase data from an e-commerce site).

[0185] "Means for preprocessing collected data" refers to processes or methods for converting collected data into a format suitable for analysis, such as by performing text cleansing or normalizing numerical data.

[0186] A "means for executing an artificial intelligence model that analyzes preprocessed data" is a system or method that uses preprocessed data as input and executes an artificial intelligence algorithm or model to perform data analysis.

[0187] "Means for proposing marketing strategies to users based on analysis results" refers to the process or method of presenting effective marketing measures to users based on the analysis results of an artificial intelligence model.

[0188] "Means for providing additional analysis and suggestions in real time in response to user queries" refers to a function that responds to user inquiries and questions, immediately performs additional data analysis, and re-proposes updated marketing strategies.

[0189] "A means of visualizing collected data as advertising trends and campaign success stories" is a function that displays acquired data in a visually easy-to-understand manner and visualizes the analysis results of advertising strategies and campaigns.

[0190] "Means for generating advertising strategies based on consumer purchasing patterns and popular items" refers to a system or method that automatically generates optimal advertising strategies based on analyzed consumer behavior data and trending product information.

[0191] This invention is a digital assistant service designed for marketing professionals and advertising managers. It is a system that uses AI technology to analyze real-time industry trends and consumer behavior and propose effective advertising strategies.

[0192] System configuration

[0193] The system consists of the following main components:

[0194] 1. A means of collecting data about a user-specified industry

[0195] The server collects data about a specified industry from multiple sources (e.g., social media posts, purchase data from an e-commerce site). The data is obtained via an API.

[0196] 2. Means of preprocessing the collected data

[0197] The server cleanses the collected data into a format suitable for analysis (e.g., removing noise from text data and normalizing numerical data).

[0198] 3. A means to run an artificial intelligence model that analyzes the preprocessed data

[0199] The server uses the preprocessed data as input and uses artificial intelligence models (e.g., Transformer-based models) for sentiment analysis and pattern recognition, such as the Transformers library from Hugging Face.

[0200] 4. A means of proposing marketing strategies to users based on the analysis results

[0201] Based on the analysis results of the AI ​​model, the server visualizes consumer purchasing patterns and popular items and proposes effective advertising strategies, which are generated based on the AISAS and AIDMA models.

[0202] 5. A means of providing additional analysis and suggestions in real time in response to user queries

[0203] The server receives queries from users, performs additional data analysis in real time, and generates and provides new suggestions.

[0204] Hardware and Software Used

[0205] Hardware

[0206] Server: A server with a high-performance CPU and GPU (e.g., NVIDIA GPU)

[0207] User devices: Display devices such as smartphones, tablets, and PCs

[0208] software

[0209] Data collection tools: API clients (e.g., Requests library)

[0210] Data preprocessing tools: Data frame manipulation tools (e.g., Pandas library), data normalization tools (e.g., Scikit-learn)

[0211] Artificial intelligence models: Sentiment analysis and pattern recognition tools (e.g., Hugging Face Transformers)

[0212] Visualization tools: Graphing tools (e.g., Matplotlib, Seaborn)

[0213] Specific use cases

[0214] For example, when planning a campaign for a new summer collection in the fashion industry, the following prompt might be used:

[0215] Prompt Sentence Examples

[0216] Please analyze the latest trends in the fashion industry and consumer behavior. Please provide specific suggestions to help us decide whether we should increase the volume of our next campaign.

[0217] Based on this prompt, the server collects, cleans, and analyzes the latest fashion trends, social media posts, and purchasing data from e-commerce sites. The analysis results visualize what items consumers are interested in and what purchasing patterns can be observed, and propose specific marketing strategies.

[0218] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0219] Program processing flow

[0220] Step 1:

[0221] The user inputs the specified prompt text into the server. The prompt text includes instructions on the industry to be analyzed and specific questions to ask. For example, the user inputs the prompt text, "Please analyze the latest trends and consumer behavior in the fashion industry. Please provide specific suggestions to help us decide whether we should increase the volume of our next campaign." The output of this step is the specified prompt text.

[0222] Step 2:

[0223] The server collects data related to a specified industry. Specifically, it obtains data such as social media posting data and e-commerce site purchase data from multiple APIs. The API tool used is, for example, the Requests library. The input for this step is a prompt statement and API endpoint information, and the output is the collected raw data.

[0224] Step 3:

[0225] The server preprocesses the collected data. For example, it cleanses text data and normalizes numerical data using the Pandas library or Scikit-learn. The input of this step is raw data, and the output is preprocessed, clean data.

[0226] Step 4:

[0227] The server runs an artificial intelligence model to analyze the preprocessed data. For example, it uses the Hugging Face Transformers library to perform sentiment analysis on text data. For numerical data analysis, it uses techniques such as regression analysis. The input for this step is the preprocessed data, and the output is the analysis results.

[0228] Step 5:

[0229] Based on the analysis results, the server proposes effective advertising strategies to the user. For example, using the AISAS model, it suggests "SNS sharing campaigns" or "limited sales on e-commerce sites." The input to this step is the analysis results, and the output is a specific marketing strategy proposal.

[0230] Step 6:

[0231] The server visualizes the proposed marketing strategy. Matplotlib and Seaborn are used to generate diagrams and charts and display them on the user's terminal. The input of this step is the proposed marketing strategy, and the output is the visualized graphs and charts.

[0232] Step 7:

[0233] The user inputs an additional query to the server, for example asking a specific question such as "Should we increase the budget for this campaign?" The input to this step is the user query, and the output is the query content.

[0234] Step 8:

[0235] The server performs additional analysis and new proposals in real time in response to the user's query. In this step, the data is analyzed again to generate new strategies and proposals in response to the user's query. The inputs to this step are the user query and existing data, and the output is new analysis results and proposals.

[0236] These steps allow marketing professionals to analyze data in real time and quickly develop effective advertising strategies.

[0237] 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.

[0238] This invention relates to an advanced digital assistant service designed for marketing professionals. This service utilizes AI technology to analyze real-time industry trends and consumer behavior, and then proposes effective marketing strategies based on this analysis. In addition, by incorporating an emotion engine that recognizes user emotions, more personalized strategy proposals are possible.

[0239] System Overview

[0240] The system consists of the following main components:

[0241] 1. Data Collection Methods

[0242] The server collects data related to the industry specified by the user. For example, in the case of the fashion industry, it obtains the latest trend data, social media posting data, and e-commerce site purchase data.

[0243] 2. Data preprocessing methods

[0244] The server preprocesses the collected data by cleansing, normalizing, format conversion, etc.

[0245] 3. AI model execution means

[0246] The server inputs the pre-processed data into an artificial intelligence model to analyze consumer behavior and market trends.

[0247] 4. Marketing strategy proposal methods

[0248] The server proposes specific marketing strategies to users based on the analysis results of the AI ​​model, and generates optimal strategies and campaigns using purchasing process models such as AISAS and AIDMA.

[0249] 5. User Interaction Methods

[0250] The device displays the suggestions received from the server to the user and accepts user queries in real time, and the server performs additional analysis and offers in response to the queries.

[0251] 6. Emotion Engine

[0252] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts the content of the suggestions based on the user's emotions.The server analyzes the emotions shown by the user in response to the displayed suggestions and provides real-time feedback accordingly, thereby providing a more appropriate marketing strategy.

[0253] Program processing

[0254] The program flow is as follows:

[0255] First, the user selects the industry for which they wish to develop a marketing strategy. The server then collects data related to the selected industry and preprocesses the collected data. The server then inputs the preprocessed data into an artificial intelligence model to obtain analysis results. Based on the analysis results, the server proposes specific marketing strategies to the user. The proposals are visualized and displayed to the user via the device.

[0256] At this point, an emotion engine is activated to recognize emotions from the user's facial expressions, tone of voice, etc. For example, if the user expresses dissatisfaction with the proposal, the emotion engine analyzes that information and provides feedback to the server. Based on this feedback, the server adjusts the proposal and presents it to the user again.

[0257] Specific examples

[0258] For example, consider a campaign in the fashion industry for a new summer collection.

[0259] 1. A user requests to create a summer campaign strategy for the fashion industry.

[0260] 2. The server collects the latest fashion trends, social media posts, and e-commerce site purchasing data.

[0261] 3. The server cleanses and normalizes the collected data.

[0262] 4. The server inputs the preprocessed data into an AI model to analyze consumer trends and popular items.

[0263] 5. The server generates strategies for social media sharing campaigns and limited-time sales on e-commerce sites based on the AISAS model.

[0264] 6. The device visualizes these suggestions and displays them to the user.

[0265] 7. The user confirms the displayed suggestions, and the emotion engine analyzes the user's facial expressions and tone of voice.

[0266] 8. The server receives feedback from the emotion engine and adjusts the suggestions.

[0267] 9. The server displays the adjusted proposal to the user again.

[0268] In this way, the present invention makes it possible to efficiently formulate marketing strategies and provides personalized strategies that correspond to the user's emotions, thereby supporting the implementation of more effective marketing measures.

[0269] The processing flow will be explained below.

[0270] Step 1:

[0271] The user specifies a specific industry for which a marketing strategy is to be developed through the terminal, for example, by requesting that a campaign strategy for a new summer collection in the fashion industry be developed.

[0272] Step 2:

[0273] The server collects data related to the industry specified by the user. Specifically, it uses web scraping technology and APIs to obtain the latest fashion-related trend data, social media post data, and e-commerce site purchase data.

[0274] Step 3:

[0275] The server pre-processes the collected data, which includes:

[0276] Cleansing text data (removing unnecessary data, normalizing non-standard characters, etc.).

[0277] Normalization of numeric data (standardization of units, removal of outliers, etc.).

[0278] Step 4:

[0279] The server inputs the pre-processed data into an AI model for analysis, which analyzes consumer behavior and market trends to extract insights such as popular items and purchasing patterns.

[0280] Step 5:

[0281] The server generates visualized data based on the analysis results, specifically by creating graphs and charts and converting the data into a format that is easily understandable to users.

[0282] Step 6:

[0283] The server proposes specific marketing strategies based on the analysis results, using the AISAS and AIDMA models to create optimal strategies such as social media sharing campaigns and limited-time sales on e-commerce sites.

[0284] Step 7:

[0285] The device visualizes the marketing strategy proposals received from the server and displays them to the user, who can view the proposals on a dashboard or a dedicated app screen.

[0286] Step 8:

[0287] The device runs an emotion engine that recognizes the user's emotions in real time by analyzing the user's facial expressions and tone of voice using a camera and microphone, and evaluating the user's emotions regarding the suggestions.

[0288] Step 9:

[0289] The server receives feedback from the emotion engine, for example, if the user expresses dissatisfaction with a displayed suggestion, and incorporates that information into the analysis.

[0290] Step 10:

[0291] The server adjusts the content of the proposals based on the emotional feedback, specifically fine-tuning the marketing strategy according to the user's emotions and generating more appropriate proposals.

[0292] Step 11:

[0293] The terminal revisits and displays the adjusted new proposal to the user, who can then review the proposal again.

[0294] As a result, the present invention provides a personalized marketing strategy that corresponds to the user's emotions, and supports the implementation of more effective measures.

[0295] Example 2

[0296] 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."

[0297] In today's marketing industry, there is a need to quickly analyze industry trends and consumer behavior in real time and develop effective strategies. However, traditional methods require a significant amount of time and effort to collect, preprocess, and analyze the necessary data, making it difficult to respond quickly. Furthermore, there is a lack of personalized strategy proposals based on user sentiment and feedback, making it difficult to maximize marketing effectiveness.

[0298] 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.

[0299] In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for running an artificial intelligence model to analyze the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means having an emotion engine for recognizing the user's emotions and adjusting the content of the proposal, and means for performing additional analysis and proposals in real time in response to user queries, thereby enabling real-time data analysis and personalized strategy proposals.

[0300] "User" refers to an individual or corporation that uses this system to develop a marketing strategy.

[0301] "Server" refers to a computer system that processes collected data, runs artificial intelligence models, and provides analytical results to users.

[0302] "Data collection means" refers to a function for obtaining data related to the industry specified by the user from the Internet or other databases.

[0303] "Preprocessing means" refers to a function that processes collected data, such as cleansing, normalization, and format conversion.

[0304] "Means for running artificial intelligence models" refers to the capability to run artificial intelligence techniques, such as deep learning models, to analyze the pre-processed data.

[0305] "Means for proposing marketing strategies" refers to a function that proposes specific marketing strategies to users based on the analysis results of the artificial intelligence model.

[0306] "Means with an emotion engine" refers to a function that analyzes the user's facial expressions, tone of voice, etc., and adjusts the content of suggestions based on the user's emotions.

[0307] "Means for real-time additional analysis and suggestions" refers to the ability to provide additional analysis and suggestions on the fly in response to queries and feedback from users.

[0308] "Purchasing process model" refers to theories that model consumer purchasing behavior, such as AISAS and AIDMA.

[0309] "Visualization means" refers to the function of visually displaying analysis results and proposed marketing strategies using graphs, charts, etc.

[0310] This invention relates to an advanced digital assistant service designed for marketing professionals. This service utilizes AI technology to analyze real-time industry trends and consumer behavior, and then proposes effective marketing strategies based on this analysis. In addition, by incorporating an emotion engine that recognizes user emotions, more personalized strategy proposals can be made.

[0311] The system of the present invention is composed of multiple elements such as a server, a terminal, a user, etc. How this system functions will be described below in detail.

[0312] The server collects data related to the industry specified by the user from the Internet and databases, using services such as Twitter API and Instagram Graph API to obtain the latest social media post data.

[0313] The server then pre-processes the collected data, which includes data cleansing, normalization, and format conversion, removing duplicate data and filtering out noisy data.

[0314] The pre-processed data is then analyzed using deep learning models such as TensorFlow and PyTorch, which can analyze consumer and market trends to identify, for example, this summer's trending colors and popular items.

[0315] Based on the analysis results, the server generates specific marketing strategies using purchasing process models such as AISAS (Attention, Interest, Search, Action, Share) and AIDMA (Attention, Interest, Desire, Memory, Action). For example, strategies such as social media sharing campaigns and e-commerce site-exclusive sales are proposed.

[0316] The device then visualizes the marketing strategies received from the server using graphs and charts, such as a dashboard displaying trending color charts and rankings of products that are attracting consumer interest.

[0317] The user checks the displayed suggestions on the device. At this time, the emotion engine analyzes the user's facial expressions and tone of voice. The emotion engine uses the camera and microphone to determine the user's facial expressions and tone of voice in real time.

[0318] The server receives feedback from the emotion engine and adjusts the content of the suggestions based on the user's emotions, for example, changing the content of the suggested campaign if the user expresses dissatisfaction with the suggestions.

[0319] Finally, the server generates the adjusted proposal again and displays it to the user through the terminal, and this process is repeated until the user is satisfied.

[0320] As a concrete example, consider a campaign for a new summer collection in the fashion industry. The user requests, "I want to create a campaign strategy for the fashion industry this summer." The server uses the Twitter API and Instagram Graph API to collect the latest social media post data, cleansing and preprocessing the collected data. It runs an AI model using TensorFlow and obtains analysis results such as "yellow is this summer's trend color" and "beachwear is a popular item." Based on the AISAS model, a strategy for "a campaign that offers discount coupons for posts shared on social media" is generated and displayed on the device. The user provides feedback such as "This campaign is good, but I would like a more unique proposal," so a readjusted strategy is proposed again, and the process is repeated until the user is satisfied.

[0321] An example of a prompt might be, "How do you feel about this proposal?"

[0322] In this way, the present invention makes it possible to efficiently formulate marketing strategies and provides personalized strategies that correspond to the user's emotions, thereby supporting the implementation of more effective marketing measures.

[0323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0324] Step 1:

[0325] The user specifies the industry for which they want to develop a marketing strategy from their terminal. The input includes the name of the industry and specific campaign content. The request is "I want to create a summer campaign strategy for the fashion industry." The output is that this request is sent to the server.

[0326] Step 2:

[0327] The server collects data related to the industry specified by the user from the internet and databases. The input is the specified industry name, and the output is the acquired social media post data, trend data, and purchase data. Specifically, the data is collected using the Twitter API, Instagram Graph API, etc.

[0328] Step 3:

[0329] The server preprocesses the collected data. The input is the collected raw data, and the output is the cleansed and normalized data. Specific operations include removing duplicate data, filtering out noisy data, and standardizing date formats.

[0330] Step 4:

[0331] The server inputs the preprocessed data into a deep learning model for analysis. The input is cleansed and normalized data, and the output is the analysis results. Specifically, TensorFlow and PyTorch are used to analyze market trends and consumer behavior, and to obtain specific insights such as "yellow is the trend color this summer."

[0332] Step 5:

[0333] The server generates a marketing strategy based on the analysis results. The input is the analysis results of the AI ​​model, and the output is a proposed marketing strategy. Specifically, it uses purchasing process models such as AISAS and AIDMA to generate strategies such as "a campaign that offers discount coupons for posts shared on social media."

[0334] Step 6:

[0335] The terminal visualizes the proposed marketing strategy and displays it to the user. The input is the proposed marketing strategy, and the output is visualized graphs and charts. For example, a dashboard displays a graph of trend colors and a ranking of products that attract consumer interest.

[0336] Step 7:

[0337] The user can review the proposals and provide feedback through the device. The input is the visualized marketing strategy, and the output is feedback and queries from the user. The user can provide comments such as, "This campaign is good, but I'd like a more unique proposal."

[0338] Step 8:

[0339] The server uses an emotion engine to recognize the user's emotions and adjust the content of the suggestions. The input is emotional data obtained from the user's facial expressions and tone of voice, and the output is an adjusted marketing strategy. For example, the server uses a camera and microphone to analyze the user's emotions, and if dissatisfaction is expressed, the content of the suggestions is changed.

[0340] Step 9:

[0341] The server again generates an adjusted proposal and displays it to the user through the terminal. The input is the adjusted marketing strategy, and the output is the re-proposed visualization. This process is repeated until the user is satisfied.

[0342] (Application example 2)

[0343] 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."

[0344] Traditional marketing strategy planning tools placed emphasis on data analysis, but were unable to provide personalized suggestions based on user sentiment. Real-time data updates and immediate responses to queries were also lacking, leaving marketing professionals with a lack of support for quickly and accurately formulating strategies. There is a need to address these shortcomings and provide more effective marketing strategies.

[0345] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for executing an artificial intelligence model that analyzes the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means for performing additional analysis and proposals in real time in response to user queries, and emotion recognition means for detecting the user's emotions and reflecting them in the proposal content. This makes it possible to propose a personalized marketing strategy based on the user's emotions, enabling more effective and rapid implementation of marketing measures.

[0346] The "data collection means" is a device or system for automatically acquiring data relating to an industry specified by a user from the Internet or various databases.

[0347] A "data pre-processing means" is a device or method for cleansing, normalizing, and converting collected raw data into a form suitable for analysis.

[0348] An "artificial intelligence model execution means" is a device or system that uses preprocessed data as input and executes artificial intelligence algorithms such as machine learning and deep learning to analyze consumer behavior and market trends.

[0349] The "marketing strategy proposal means" is a device or system for generating and proposing specific marketing strategies and campaigns to users based on the analysis results of the artificial intelligence model.

[0350] A "real-time analytics means" is a device or system that provides additional data analysis and suggestions in real time in response to user queries.

[0351] An "emotion recognition means" is a device or system that automatically detects emotions from a user's facial expressions, tone of voice, text feedback, etc., and adjusts marketing strategy suggestions based on those emotions.

[0352] A "visualization means" is a device or system for presenting analysis results and proposed marketing strategies to a user in a visual format such as graphs or charts.

[0353] System Overview

[0354] This invention is an advanced digital assistant system for optimizing effective advertising campaigns in real time. This system combines AI technology to analyze industry trends and consumer behavior with emotion recognition technology to detect user emotions and reflect them in recommendations. The main components of the system and their respective processing steps are described below.

[0355] Key Components

[0356] 1. Data Collection Methods

[0357] Data related to the industry specified by the user is automatically collected from social media, e-commerce sites, trend databases, etc. This allows for accurate and timely acquisition of the latest industry trends and consumer behavior.

[0358] 2. Data preprocessing methods

[0359] The collected raw data is first cleansed to remove noise and extract necessary data. The data is then normalized and converted into a format that is easy for AI models to process. These processes are the prerequisite for achieving highly efficient data analysis.

[0360] 3. AI model execution means

[0361] The pre-processed data is then fed into an AI model, which runs on a machine learning framework such as TensorFlow. The AI ​​model analyzes the collected data and predicts consumer behavior and market trends. The analysis results are then used to generate subsequent marketing strategies.

[0362] 4. Marketing strategy proposal methods

[0363] Based on the analysis results obtained from the AI ​​model, a marketing strategy is proposed. This proposal is generated using a purchasing process model such as the AISAS model or the AIDMA model, and is presented as the most effective advertising strategy for the user.

[0364] 5. Real-time analysis tools

[0365] In response to user queries, additional data analysis and suggestions are provided in real time, allowing users to instantly obtain the data and analysis results they need and quickly adjust their marketing strategies.

[0366] 6. Emotion recognition means

[0367] A sentiment analysis engine analyzes the user's facial expressions, tone of voice, and text feedback to detect their emotional state. This emotional data is used to adjust marketing proposals. If the user expresses dissatisfaction with a proposal, the system will readjust the proposal based on that feedback.

[0368] 7. Visualization Tools

[0369] The analysis results and proposed marketing strategies are presented to the user in visual formats such as graphs and charts, making it easier for users to intuitively understand the analysis results.

[0370] Explanation of program processing

[0371] 1. Data Collection

[0372] The server automatically collects data on the industry specified by the user from social media, e-commerce sites, and trend databases.

[0373] 2. Data Preprocessing

[0374] The server cleanses, denoises, and normalizes the collected data, resulting in a dataset suitable for analysis.

[0375] 3. AI analysis

[0376] The pre-processed data is then fed into an artificial intelligence model, which uses machine learning frameworks such as TensorFlow to analyze the data and predict consumer behavior and market trends.

[0377] 4. Strategic proposals

[0378] Based on the results of the AI ​​analysis, a marketing strategy is generated. This proposal is based on the AISAS and AIDMA models and is presented to the user as a specific advertising strategy.

[0379] 5. Real-time analytics

[0380] In response to user queries, the server performs additional data analysis and offers suggestions in real time, allowing users to quickly obtain the information they need.

[0381] 6. Emotion recognition

[0382] The emotion recognition engine analyzes users' facial expressions, tone of voice, and text feedback to detect their emotional state. This emotional data is used to tailor marketing recommendations.

[0383] 7. Visualization

[0384] The analysis results and proposed strategies are displayed to the user in visual formats such as graphs and charts, allowing for intuitive understanding.

[0385] Specific examples

[0386] For example, when a marketing expert is planning a new summer product campaign, the system collects and analyzes the latest trend data and social media post data to propose optimal social media advertising campaigns and e-commerce site promotion strategies. Users can provide feedback using their smartphone's camera and microphone, and the emotion recognition engine analyzes their reactions and adjusts the proposals as necessary.

[0387] Example prompt sentence:

[0388] "For our new summer product campaign, please collect and analyze the latest consumer trend data and social media post data, and propose an effective advertising strategy based on the AISAS model. Also, please adjust your proposal based on my emotional feedback."

[0389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0390] Step 1:

[0391] Data collection

[0392] The server collects data related to the industry specified by the user. As input, it obtains the latest posts and purchase data from social media, e-commerce sites, and trend databases. The output is a collection of collected raw data. Specific operations include obtaining post data using the API of a social media site and collecting purchase history from the API of an e-commerce site.

[0393] Step 2:

[0394] Data Preprocessing

[0395] The server cleanses and normalizes the collected data. The input is the raw data collected in step 1. Data processing includes noise removal, standardization of data formats, and handling of missing data. The output is a clean, normalized dataset suitable for analysis. Specific operations include filtering out inappropriate data and standardizing timestamps.

[0396] Step 3:

[0397] AI analysis

[0398] The server inputs the preprocessed data into the artificial intelligence model. The input is the preprocessed clean data. For AI analysis, a machine learning model such as TensorFlow is used to perform data calculations to predict consumer behavior and market trends. The output is the analysis results that show consumer preferences and market trends. Specifically, the data is passed to the AI ​​model and prediction results are obtained from the trained model.

[0399] Step 4:

[0400] Strategic proposal

[0401] The server proposes a marketing strategy based on the analysis results of the AI ​​model. The input is the analysis results obtained in step 3. An optimal advertising strategy is generated using a purchasing process model such as the AISAS model or AIDMA model. The output is a proposal of a specific marketing strategy. Specific operations include designing campaign content and promotion methods in accordance with the analysis results.

[0402] Step 5:

[0403] Real-time analytics

[0404] The server performs additional data analysis in real time in response to user queries. The input is the user query. Data processing involves reanalyzing the dataset based on the query. The output is additional marketing suggestions in line with the query. Specifically, the server accesses the database in response to the user's request, and retrieves and analyzes the required information.

[0405] Step 6:

[0406] emotion recognition

[0407] The server recognizes the user's facial expressions and tone of voice and analyzes their emotional state. The input is the user's feedback (facial expression data and voice data). An emotion recognition engine (for example, a Transformers emotion analysis model) is used for data calculation. The output is the user's emotional state. Specifically, the system captures the user's reactions with a camera or microphone, inputs them into the emotion recognition model, and obtains the results.

[0408] Step 7:

[0409] Adjusting the proposal

[0410] The server readjusts the marketing strategy based on the emotion recognition results. The input is the emotional state obtained in step 6 and the marketing strategy proposed in step 4. Data processing involves changing the proposed content according to the emotional state. The output is the adjusted marketing strategy. Specifically, if the user expresses dissatisfaction, the proposed content is changed and presented to the user again.

[0411] Step 8:

[0412] Visualization

[0413] The server visualizes the analysis results and proposals and displays them to the user. The input is the marketing strategies obtained in steps 4 and 7. The data is then visualized in graphs and charts. The output is the visualized proposals. Specifically, the analysis results are displayed graphically using a data visualization tool.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] [Second embodiment]

[0418] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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."

[0430] This invention is a digital assistant service designed for marketing professionals. This service uses AI technology to analyze real-time industry trends and consumer behavior and propose effective marketing strategies. Users can receive support for a wide range of projects, from short-term campaigns to long-term brand strategies.

[0431] System Overview

[0432] The system consists of the following main components:

[0433] 1. Data Collection Methods

[0434] The server collects data related to the industry specified by the user. For example, in the case of the fashion industry, the server collects the latest fashion trends, social media posting data, and e-commerce site purchase data.

[0435] 2. Data preprocessing methods

[0436] The server preprocesses the collected data and converts it into a format suitable for analysis by the AI ​​model, specifically by cleansing text data and normalizing numerical data.

[0437] 3. AI model execution means

[0438] The server inputs the pre-processed data into the AI ​​model to analyze consumer behavior and market trends, and the results of this analysis are presented to the user in visualizations such as graphs and charts.

[0439] 4. Marketing strategy proposal methods

[0440] The server proposes specific marketing strategies to users based on the analysis results of the AI ​​model. These proposals are generated using the AISAS and AIDMA models.

[0441] 5. User Interaction Methods

[0442] Users can receive suggestions through their devices and enter queries in real time, and the server will then perform additional analysis and provide suggestions accordingly.

[0443] Program processing

[0444] The program flow is as follows:

[0445] First, the user specifies the industry for which they want to develop a marketing strategy. Next, the server collects data related to the specified industry and preprocesses the collected data. The server then inputs the preprocessed data into an AI model to obtain analysis results. Based on the analysis results, the server proposes an optimal marketing strategy. The proposal is visualized and displayed to the user via their device. The user can review the proposal and enter a query. The server then performs additional analysis based on the query and provides the proposal to the user again.

[0446] Specific examples

[0447] For example, consider the case of a fashion industry campaigning for a new summer collection.

[0448] 1. A user requests suggestions for a summer campaign strategy for the fashion industry.

[0449] 2. The server collects the latest fashion trends, social media posts, and e-commerce site purchasing data.

[0450] 3. The server preprocesses the collected data by performing text cleansing and normalizing numeric data.

[0451] 4. The server inputs the preprocessed data into an AI model to analyze consumer purchasing patterns and popular items.

[0452] 5. Based on the AISAS model, the server will propose marketing strategies such as sharing campaigns on social media and limited-time sales on e-commerce sites.

[0453] 6. The device displays a visualization of these suggestions to the user.

[0454] 7. The user reviews the displayed suggestions and enters any follow-up questions.

[0455] 8. The server performs further analysis in response to the user's query and provides updated suggestions.

[0456] In this way, the present invention improves the efficiency of formulating marketing strategies and provides specific support for quickly implementing effective measures.

[0457] The processing flow will be explained below.

[0458] Step 1:

[0459] The user specifies the industry for which they want to develop a marketing strategy through the terminal, for example, requesting the collection of data on new collections in the fashion industry.

[0460] Step 2:

[0461] The server collects data related to the industry specified by the user, using web scraping technology and APIs to obtain the latest fashion industry trends, social media posts, and e-commerce site purchase data.

[0462] Step 3:

[0463] The server pre-processes the collected data.

[0464] Cleanse text data to remove unnecessary information and noise.

[0465] Normalize numeric data and convert it into a uniform format.

[0466] Step 4:

[0467] The server inputs the preprocessed data into the AI ​​model, which analyzes consumer behavior and market trends and obtains analytical results.

[0468] Step 5:

[0469] The server visualizes the analysis results in a form that is easy for the user to understand, for example by creating graphs or charts.

[0470] Step 6:

[0471] Based on the analysis results, the server proposes specific marketing strategies to the user, using the AISAS and AIDMA models to generate optimal strategies for social media sharing campaigns and e-commerce site exclusive sales.

[0472] Step 7:

[0473] The device displays the marketing strategy proposals received from the server to the user, allowing them to view visualized data on a dashboard or on the screen of a dedicated app.

[0474] Step 8:

[0475] The user can review the suggestions presented and enter additional questions or queries, such as "Who is the target audience for this campaign?"

[0476] Step 9:

[0477] The terminal sends the user's query to the server.

[0478] Step 10:

[0479] The server performs additional data analysis in response to user queries, collects and analyzes new information, and updates the marketing strategy again.

[0480] Step 11:

[0481] The server sends the updated proposal to the terminal, which displays the proposal to the user.

[0482] This series of processing steps allows users to quickly develop effective marketing strategies in real time.

[0483] Example 1

[0484] 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."

[0485] Conventional marketing strategy formulation systems have struggled to perform rapid and accurate data analysis and proposals. Furthermore, they lacked a means for users to quickly obtain additional analysis results by inputting specific queries, preventing the maximum effectiveness of marketing strategies. Furthermore, they had limited means for visually grasping the analysis results, making it difficult for users to receive proposals in a format that is easy for them to understand. Therefore, the present invention aims to solve these problems and provide a system that proposes efficient and effective marketing strategies in real time.

[0486] 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.

[0487] In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for executing an artificial intelligence model that analyzes the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means for performing additional analysis and proposals in real time in response to user queries, and means for visualizing and displaying the proposed marketing strategy. This allows the user to receive marketing strategy proposals based on rapid and accurate data analysis, and further allows the user to obtain analysis results in real time for additional queries. Furthermore, by visually grasping the analysis results, the user can receive proposals in a format that is easy for the user to understand.

[0488] The "means for collecting data" is a function for collecting information about an industry specified by the user.

[0489] "Means for pre-processing data" refers to processing functions for converting collected raw data into an analyzable format.

[0490] The "means for implementing an artificial intelligence model" is a computational function that uses AI techniques to analyze the pre-processed data.

[0491] The "means for proposing marketing strategies" is a function for presenting specific marketing measures to users based on the analysis results of the artificial intelligence model.

[0492] "Means for real-time analysis and proposals in response to queries" refers to a function that instantly provides more detailed analysis results and strategic proposals in response to additional questions entered by the user.

[0493] The "means for visualizing and displaying the proposed marketing strategy" is a function for visually expressing the analysis results and proposals in the form of graphs, charts, etc., and presenting them to the user in an easy-to-understand manner.

[0494] A "purchasing process model" is a model that shows the series of behavioral patterns that consumers follow when purchasing products or services, and is a basic framework used in building marketing strategies.

[0495] This is a digital assistant service designed for marketing professionals. It uses AI technology to analyze real-time industry trends and consumer behavior and propose effective marketing strategies. Users can receive support for a wide range of projects, from short-term campaigns to long-term brand strategies.

[0496] The system consists of the following main components:

[0497] 1. Data Collection Methods

[0498] The server collects data related to the industry specified by the user. For example, in the fashion industry, the server collects the latest fashion trends, social media posting data, and e-commerce site purchase data. Specifically, it uses web scraping tools (e.g., BeautifulSoup) and API access (e.g., Twitter API).

[0499] 2. Data preprocessing methods

[0500] The server preprocesses the collected data and converts it into a format suitable for analysis by the AI ​​model. Specifically, it uses Python and pandas to cleanse text data and normalize numerical data.

[0501] 3. AI model execution means

[0502] The server then uses the preprocessed data to run AI models, such as deep learning models built using TensorFlow and PyTorch, to analyze consumer behavior and market trends.

[0503] 4. Marketing strategy proposal methods

[0504] The server then proposes specific marketing strategies to the user based on the analysis results of the AI ​​model. These proposals are generated using the AISAS and AIDMA models. For example, sharing campaigns on social media or limited-time sales on e-commerce sites may be suggested.

[0505] 5. User Interaction Methods

[0506] Users can receive suggestions via their device and input queries in real time, and the server will then perform additional analysis and provide suggestions accordingly. For example, it can instantly answer questions such as, "Are there any other social media campaigns that are effective?"

[0507] 6. Visualization Tools

[0508] The device visually displays the proposed marketing strategy to the user, using tools such as Matplotlib and Tableau to display the analysis results in graphs and charts, allowing the user to intuitively understand the proposed content.

[0509] Specific examples

[0510] For example, consider the case of a fashion industry campaigning for a new summer collection.

[0511] 1. The user is looking for suggestions for a summer campaign strategy for the fashion industry. An example of a prompt sentence is, "Please suggest a marketing strategy for the fashion industry for next summer."

[0512] 2. The server collects the latest fashion trends, social media posts, and purchase data from e-commerce sites. It uses the Twitter API to collect posts containing relevant keywords and extracts sales data from e-commerce sites using BeautifulSoup.

[0513] 3. The server preprocesses the collected data, specifically cleansing text data and normalizing numeric data using Python and pandas.

[0514] 4. The server inputs the preprocessed data into a TensorFlow model to analyze consumer purchasing patterns and popular items.

[0515] 5. Based on the AISAS model, the server will propose marketing strategies such as sharing campaigns on social media and limited-time sales on e-commerce sites.

[0516] 6. The device displays these suggestions to the user in a visual format, such as a chart showing purchasing trends or an overview of recommended campaigns.

[0517] 7. The user reviews the suggestions and enters a follow-up question, such as, "What other social media campaigns have you seen that have worked?"

[0518] 8. The server performs further analysis in response to the user's query and provides updated suggestions.

[0519] In this way, the present invention provides specific support for making the formulation of marketing strategies more efficient and for quickly implementing effective measures.

[0520] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0521] Step 1:

[0522] User specifies industry

[0523] Through the system interface, users input the industry related to their business and the campaign information they wish to analyze. An example of a prompt sentence is, "Please suggest a marketing strategy for the fashion industry for next summer." This input is sent to the server as an instruction to the system.

[0524] Input: Industry and campaign information prompt text

[0525] Output: Instruction to start analysis on the server

[0526] Step 2:

[0527] The server collects the data

[0528] The server collects data related to the industry selected by the user. Specifically, it uses web scraping tools and APIs to obtain the following data:

[0529] Social Media Data: Use the Twitter API to collect posts with relevant keywords and hashtags.

[0530] E-commerce website data: Use web scraping tools to extract up-to-date sales data and product reviews.

[0531] Market Report Data: Gather the required data from published market research reports.

[0532] Input: Industry designation, campaign information

[0533] Output: Collected social media data, e-commerce site data, and other market data

[0534] Step 3:

[0535] The server preprocesses the data

[0536] The server preprocesses the collected raw data into a format suitable for analysis by the AI ​​model. The specific operations are as follows:

[0537] Text data cleansing: Use Python and pandas to remove unnecessary HTML tags, special characters, and noise data.

[0538] Normalization of numerical data: To standardize data with different scales, numerical data is normalized with z-scores.

[0539] Input: Collected social media data, e-commerce site data, and other market data

[0540] Output: Preprocessed data

[0541] Step 4:

[0542] The server runs the artificial intelligence model

[0543] The server runs an AI model (e.g., built with TensorFlow or PyTorch) on the preprocessed data. Specifically, it performs the following operations:

[0544] Data input: Input the preprocessed data into the AI ​​model.

[0545] Performing analytics: Models can analyze consumer behavior and market trends, such as the popularity of certain products and purchasing patterns.

[0546] Input: Preprocessed data

[0547] Output: Analysis results

[0548] Step 5:

[0549] The server proposes a marketing strategy

[0550] The server generates a marketing strategy to propose to the user based on the analysis results of the AI ​​model. This proposal is based on a purchasing process model such as the AISAS or AIDMA model. Specific proposals include:

[0551] Social media campaigns: Propose campaigns that utilize popular posts and hashtags.

[0552] Limited-time offer: Offering a discount or special offer on a specific product for a limited time.

[0553] Input: Analysis results

[0554] Output: Marketing strategy proposal

[0555] Step 6:

[0556] The device will visualize the suggestions and display them.

[0557] The terminal visually displays the marketing strategy proposals provided by the server to the user. The visualization uses the following tools:

[0558] Graphs and Charts: Use Matplotlib and Tableau to create graphs and charts that show consumer behavior and trends.

[0559] Dashboard: The proposed strategies are presented in a dashboard format that is easy for users to understand.

[0560] Input: Marketing strategy proposal

[0561] Output: Visualized proposal

[0562] Step 7:

[0563] The user enters a query

[0564] Users enter queries into the interface to ask follow-up questions or explore the suggestions presented, such as "What other social media campaigns are effective?"

[0565] Input: User query

[0566] Output: Request for further analysis to the server

[0567] Step 8:

[0568] The server performs additional analysis and offers suggestions

[0569] The server then analyzes the data again in response to user queries, providing additional strategies and insights. It does the following:

[0570] Additional data analysis: Reanalyze the required data based on the query.

[0571] Generate new proposals: Update your marketing strategy based on new insights.

[0572] Input: User query

[0573] Output: Additional analysis results and updated recommendations

[0574] In this way, the system provides users with real-time, data-driven marketing strategies tailored to their needs.

[0575] (Application example 1)

[0576] 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."

[0577] Traditional marketing strategies lack real-time monitoring and analysis of advertising trends and consumer behavior, making it difficult to develop fast and effective advertising strategies. In particular, the manual process of collecting, preprocessing, and analyzing complex data is time-consuming and inefficient. Another issue is that the proposed strategies are static, making them unable to adequately respond to changes in consumer behavior.

[0578] 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.

[0579] In this invention, the server includes means for collecting data related to a user-specified industry, means for pre-processing the collected data, and means for executing an artificial intelligence model that analyzes the pre-processed data, thereby enabling visualization and collection of advertising trends and campaign success stories in real time, and generating advertising strategies based on consumer purchasing patterns and popular items.

[0580] "Means for collecting data related to an industry specified by a user" refers to a system or method for obtaining necessary data related to a specific industry specified by a user from various sources (such as social media posts or purchase data from an e-commerce site).

[0581] "Means for preprocessing collected data" refers to processes or methods for converting collected data into a format suitable for analysis, such as by performing text cleansing or normalizing numerical data.

[0582] A "means for executing an artificial intelligence model that analyzes preprocessed data" is a system or method that uses preprocessed data as input and executes an artificial intelligence algorithm or model to perform data analysis.

[0583] "Means for proposing marketing strategies to users based on analysis results" refers to the process or method of presenting effective marketing measures to users based on the analysis results of an artificial intelligence model.

[0584] "Means for providing additional analysis and suggestions in real time in response to user queries" refers to a function that responds to user inquiries and questions, immediately performs additional data analysis, and re-proposes updated marketing strategies.

[0585] "A means of visualizing collected data as advertising trends and campaign success stories" is a function that displays acquired data in a visually easy-to-understand manner and visualizes the analysis results of advertising strategies and campaigns.

[0586] "Means for generating advertising strategies based on consumer purchasing patterns and popular items" refers to a system or method that automatically generates optimal advertising strategies based on analyzed consumer behavior data and trending product information.

[0587] This invention is a digital assistant service designed for marketing professionals and advertising managers. It is a system that uses AI technology to analyze real-time industry trends and consumer behavior and propose effective advertising strategies.

[0588] System configuration

[0589] The system consists of the following main components:

[0590] 1. A means of collecting data about a user-specified industry

[0591] The server collects data about a specified industry from multiple sources (e.g., social media posts, purchase data from an e-commerce site). The data is obtained via an API.

[0592] 2. Means of preprocessing the collected data

[0593] The server cleanses the collected data into a format suitable for analysis (e.g., removing noise from text data and normalizing numerical data).

[0594] 3. A means to run an artificial intelligence model that analyzes the preprocessed data

[0595] The server uses the preprocessed data as input and uses artificial intelligence models (e.g., Transformer-based models) for sentiment analysis and pattern recognition, such as the Transformers library from Hugging Face.

[0596] 4. A means of proposing marketing strategies to users based on the analysis results

[0597] Based on the analysis results of the AI ​​model, the server visualizes consumer purchasing patterns and popular items and proposes effective advertising strategies, which are generated based on the AISAS and AIDMA models.

[0598] 5. A means of providing additional analysis and suggestions in real time in response to user queries

[0599] The server receives queries from users, performs additional data analysis in real time, and generates and provides new suggestions.

[0600] Hardware and Software Used

[0601] Hardware

[0602] Server: A server with a high-performance CPU and GPU (e.g., NVIDIA GPU)

[0603] User devices: Display devices such as smartphones, tablets, and PCs

[0604] software

[0605] Data collection tools: API clients (e.g., Requests library)

[0606] Data preprocessing tools: Data frame manipulation tools (e.g., Pandas library), data normalization tools (e.g., Scikit-learn)

[0607] Artificial intelligence models: Sentiment analysis and pattern recognition tools (e.g., Hugging Face Transformers)

[0608] Visualization tools: Graphing tools (e.g., Matplotlib, Seaborn)

[0609] Specific use cases

[0610] For example, when planning a campaign for a new summer collection in the fashion industry, the following prompt might be used:

[0611] Prompt Sentence Examples

[0612] Please analyze the latest trends in the fashion industry and consumer behavior. Please provide specific suggestions to help us decide whether we should increase the volume of our next campaign.

[0613] Based on this prompt, the server collects, cleans, and analyzes the latest fashion trends, social media posts, and purchasing data from e-commerce sites. The analysis results visualize what items consumers are interested in and what purchasing patterns can be observed, and propose specific marketing strategies.

[0614] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0615] Program processing flow

[0616] Step 1:

[0617] The user inputs the specified prompt text into the server. The prompt text includes instructions on the industry to be analyzed and specific questions to ask. For example, the user inputs the prompt text, "Please analyze the latest trends and consumer behavior in the fashion industry. Please provide specific suggestions to help us decide whether we should increase the volume of our next campaign." The output of this step is the specified prompt text.

[0618] Step 2:

[0619] The server collects data related to a specified industry. Specifically, it obtains data such as social media posting data and e-commerce site purchase data from multiple APIs. The API tool used is, for example, the Requests library. The input for this step is a prompt statement and API endpoint information, and the output is the collected raw data.

[0620] Step 3:

[0621] The server preprocesses the collected data. For example, it cleanses text data and normalizes numerical data using the Pandas library or Scikit-learn. The input of this step is raw data, and the output is preprocessed, clean data.

[0622] Step 4:

[0623] The server runs an artificial intelligence model to analyze the preprocessed data. For example, it uses the Hugging Face Transformers library to perform sentiment analysis on text data. For numerical data analysis, it uses techniques such as regression analysis. The input for this step is the preprocessed data, and the output is the analysis results.

[0624] Step 5:

[0625] Based on the analysis results, the server proposes effective advertising strategies to the user. For example, using the AISAS model, it suggests "SNS sharing campaigns" or "limited sales on e-commerce sites." The input to this step is the analysis results, and the output is a specific marketing strategy proposal.

[0626] Step 6:

[0627] The server visualizes the proposed marketing strategy. Matplotlib and Seaborn are used to generate diagrams and charts and display them on the user's terminal. The input of this step is the proposed marketing strategy, and the output is the visualized graphs and charts.

[0628] Step 7:

[0629] The user inputs an additional query to the server, for example asking a specific question such as "Should we increase the budget for this campaign?" The input to this step is the user query, and the output is the query content.

[0630] Step 8:

[0631] The server performs additional analysis and new proposals in real time in response to the user's query. In this step, the data is analyzed again to generate new strategies and proposals in response to the user's query. The inputs to this step are the user query and existing data, and the output is new analysis results and proposals.

[0632] These steps allow marketing professionals to analyze data in real time and quickly develop effective advertising strategies.

[0633] 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.

[0634] This invention relates to an advanced digital assistant service designed for marketing professionals. This service utilizes AI technology to analyze real-time industry trends and consumer behavior, and then proposes effective marketing strategies based on this analysis. In addition, by incorporating an emotion engine that recognizes user emotions, more personalized strategy proposals are possible.

[0635] System Overview

[0636] The system consists of the following main components:

[0637] 1. Data Collection Methods

[0638] The server collects data related to the industry specified by the user. For example, in the case of the fashion industry, it obtains the latest trend data, social media posting data, and e-commerce site purchase data.

[0639] 2. Data preprocessing methods

[0640] The server preprocesses the collected data by cleansing, normalizing, format conversion, etc.

[0641] 3. AI model execution means

[0642] The server inputs the pre-processed data into an artificial intelligence model to analyze consumer behavior and market trends.

[0643] 4. Marketing strategy proposal methods

[0644] The server proposes specific marketing strategies to users based on the analysis results of the AI ​​model, and generates optimal strategies and campaigns using purchasing process models such as AISAS and AIDMA.

[0645] 5. User Interaction Methods

[0646] The device displays the suggestions received from the server to the user and accepts user queries in real time, and the server performs additional analysis and offers in response to the queries.

[0647] 6. Emotion Engine

[0648] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts the content of the suggestions based on the user's emotions.The server analyzes the emotions shown by the user in response to the displayed suggestions and provides real-time feedback accordingly, thereby providing a more appropriate marketing strategy.

[0649] Program processing

[0650] The program flow is as follows:

[0651] First, the user selects the industry for which they wish to develop a marketing strategy. The server then collects data related to the selected industry and preprocesses the collected data. The server then inputs the preprocessed data into an artificial intelligence model to obtain analysis results. Based on the analysis results, the server proposes specific marketing strategies to the user. The proposals are visualized and displayed to the user via the device.

[0652] At this point, an emotion engine is activated to recognize emotions from the user's facial expressions, tone of voice, etc. For example, if the user expresses dissatisfaction with the proposal, the emotion engine analyzes that information and provides feedback to the server. Based on this feedback, the server adjusts the proposal and presents it to the user again.

[0653] Specific examples

[0654] For example, consider a campaign in the fashion industry for a new summer collection.

[0655] 1. A user requests to create a summer campaign strategy for the fashion industry.

[0656] 2. The server collects the latest fashion trends, social media posts, and e-commerce site purchasing data.

[0657] 3. The server cleanses and normalizes the collected data.

[0658] 4. The server inputs the preprocessed data into an AI model to analyze consumer trends and popular items.

[0659] 5. The server generates strategies for social media sharing campaigns and limited-time sales on e-commerce sites based on the AISAS model.

[0660] 6. The device visualizes these suggestions and displays them to the user.

[0661] 7. The user confirms the displayed suggestions, and the emotion engine analyzes the user's facial expressions and tone of voice.

[0662] 8. The server receives feedback from the emotion engine and adjusts the suggestions.

[0663] 9. The server displays the adjusted proposal to the user again.

[0664] In this way, the present invention makes it possible to efficiently formulate marketing strategies and provides personalized strategies that correspond to the user's emotions, thereby supporting the implementation of more effective marketing measures.

[0665] The processing flow will be explained below.

[0666] Step 1:

[0667] The user specifies a specific industry for which a marketing strategy is to be developed through the terminal, for example, by requesting that a campaign strategy for a new summer collection in the fashion industry be developed.

[0668] Step 2:

[0669] The server collects data related to the industry specified by the user. Specifically, it uses web scraping technology and APIs to obtain the latest fashion-related trend data, social media post data, and e-commerce site purchase data.

[0670] Step 3:

[0671] The server pre-processes the collected data, which includes:

[0672] Cleansing text data (removing unnecessary data, normalizing non-standard characters, etc.).

[0673] Normalization of numeric data (standardization of units, removal of outliers, etc.).

[0674] Step 4:

[0675] The server inputs the pre-processed data into an AI model for analysis, which analyzes consumer behavior and market trends to extract insights such as popular items and purchasing patterns.

[0676] Step 5:

[0677] The server generates visualized data based on the analysis results, specifically by creating graphs and charts and converting the data into a format that is easily understandable to users.

[0678] Step 6:

[0679] The server proposes specific marketing strategies based on the analysis results, using the AISAS and AIDMA models to create optimal strategies such as social media sharing campaigns and limited-time sales on e-commerce sites.

[0680] Step 7:

[0681] The device visualizes the marketing strategy proposals received from the server and displays them to the user, who can view the proposals on a dashboard or a dedicated app screen.

[0682] Step 8:

[0683] The device runs an emotion engine that recognizes the user's emotions in real time by analyzing the user's facial expressions and tone of voice using a camera and microphone, and evaluating the user's emotions regarding the suggestions.

[0684] Step 9:

[0685] The server receives feedback from the emotion engine, for example, if the user expresses dissatisfaction with a displayed suggestion, and incorporates that information into the analysis.

[0686] Step 10:

[0687] The server adjusts the content of the proposals based on the emotional feedback, specifically fine-tuning the marketing strategy according to the user's emotions and generating more appropriate proposals.

[0688] Step 11:

[0689] The terminal revisits and displays the adjusted new proposal to the user, who can then review the proposal again.

[0690] As a result, the present invention provides a personalized marketing strategy that corresponds to the user's emotions, and supports the implementation of more effective measures.

[0691] Example 2

[0692] 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."

[0693] In today's marketing industry, there is a need to quickly analyze industry trends and consumer behavior in real time and develop effective strategies. However, traditional methods require a significant amount of time and effort to collect, preprocess, and analyze the necessary data, making it difficult to respond quickly. Furthermore, there is a lack of personalized strategy proposals based on user sentiment and feedback, making it difficult to maximize marketing effectiveness.

[0694] 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.

[0695] In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for running an artificial intelligence model to analyze the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means having an emotion engine for recognizing the user's emotions and adjusting the content of the proposal, and means for performing additional analysis and proposals in real time in response to user queries, thereby enabling real-time data analysis and personalized strategy proposals.

[0696] "User" refers to an individual or corporation that uses this system to develop a marketing strategy.

[0697] "Server" refers to a computer system that processes collected data, runs artificial intelligence models, and provides analytical results to users.

[0698] "Data collection means" refers to a function for obtaining data related to the industry specified by the user from the Internet or other databases.

[0699] "Preprocessing means" refers to a function that processes collected data, such as cleansing, normalization, and format conversion.

[0700] "Means for running artificial intelligence models" refers to the capability to run artificial intelligence techniques, such as deep learning models, to analyze the pre-processed data.

[0701] "Means for proposing marketing strategies" refers to a function that proposes specific marketing strategies to users based on the analysis results of the artificial intelligence model.

[0702] "Means with an emotion engine" refers to a function that analyzes the user's facial expressions, tone of voice, etc., and adjusts the content of suggestions based on the user's emotions.

[0703] "Means for real-time additional analysis and suggestions" refers to the ability to provide additional analysis and suggestions on the fly in response to queries and feedback from users.

[0704] "Purchasing process model" refers to theories that model consumer purchasing behavior, such as AISAS and AIDMA.

[0705] "Visualization means" refers to the function of visually displaying analysis results and proposed marketing strategies using graphs, charts, etc.

[0706] This invention relates to an advanced digital assistant service designed for marketing professionals. This service utilizes AI technology to analyze real-time industry trends and consumer behavior, and then proposes effective marketing strategies based on this analysis. In addition, by incorporating an emotion engine that recognizes user emotions, more personalized strategy proposals can be made.

[0707] The system of the present invention is composed of multiple elements such as a server, a terminal, a user, etc. How this system functions will be described below in detail.

[0708] The server collects data related to the industry specified by the user from the Internet and databases, using services such as Twitter API and Instagram Graph API to obtain the latest social media post data.

[0709] The server then pre-processes the collected data, which includes data cleansing, normalization, and format conversion, removing duplicate data and filtering out noisy data.

[0710] The pre-processed data is then analyzed using deep learning models such as TensorFlow and PyTorch, which can analyze consumer and market trends to identify, for example, this summer's trending colors and popular items.

[0711] Based on the analysis results, the server generates specific marketing strategies using purchasing process models such as AISAS (Attention, Interest, Search, Action, Share) and AIDMA (Attention, Interest, Desire, Memory, Action). For example, strategies such as social media sharing campaigns and e-commerce site-exclusive sales are proposed.

[0712] The device then visualizes the marketing strategies received from the server using graphs and charts, such as a dashboard displaying trending color charts and rankings of products that are attracting consumer interest.

[0713] The user checks the displayed suggestions on the device. At this time, the emotion engine analyzes the user's facial expressions and tone of voice. The emotion engine uses the camera and microphone to determine the user's facial expressions and tone of voice in real time.

[0714] The server receives feedback from the emotion engine and adjusts the content of the suggestions based on the user's emotions, for example, changing the content of the suggested campaign if the user expresses dissatisfaction with the suggestions.

[0715] Finally, the server generates the adjusted proposal again and displays it to the user through the terminal, and this process is repeated until the user is satisfied.

[0716] As a concrete example, consider a campaign for a new summer collection in the fashion industry. The user requests, "I want to create a campaign strategy for the fashion industry this summer." The server uses the Twitter API and Instagram Graph API to collect the latest social media post data, cleansing and preprocessing the collected data. It runs an AI model using TensorFlow and obtains analysis results such as "yellow is this summer's trend color" and "beachwear is a popular item." Based on the AISAS model, a strategy for "a campaign that offers discount coupons for posts shared on social media" is generated and displayed on the device. The user provides feedback such as "This campaign is good, but I would like a more unique proposal," so a readjusted strategy is proposed again, and the process is repeated until the user is satisfied.

[0717] An example of a prompt might be, "How do you feel about this proposal?"

[0718] In this way, the present invention makes it possible to efficiently formulate marketing strategies and provides personalized strategies that correspond to the user's emotions, thereby supporting the implementation of more effective marketing measures.

[0719] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0720] Step 1:

[0721] The user specifies the industry for which they want to develop a marketing strategy from their terminal. The input includes the name of the industry and specific campaign content. The request is "I want to create a summer campaign strategy for the fashion industry." The output is that this request is sent to the server.

[0722] Step 2:

[0723] The server collects data related to the industry specified by the user from the internet and databases. The input is the specified industry name, and the output is the acquired social media post data, trend data, and purchase data. Specifically, the data is collected using the Twitter API, Instagram Graph API, etc.

[0724] Step 3:

[0725] The server preprocesses the collected data. The input is the collected raw data, and the output is the cleansed and normalized data. Specific operations include removing duplicate data, filtering out noisy data, and standardizing date formats.

[0726] Step 4:

[0727] The server inputs the preprocessed data into a deep learning model for analysis. The input is cleansed and normalized data, and the output is the analysis results. Specifically, TensorFlow and PyTorch are used to analyze market trends and consumer behavior, and to obtain specific insights such as "yellow is the trend color this summer."

[0728] Step 5:

[0729] The server generates a marketing strategy based on the analysis results. The input is the analysis results of the AI ​​model, and the output is a proposed marketing strategy. Specifically, it uses purchasing process models such as AISAS and AIDMA to generate strategies such as "a campaign that offers discount coupons for posts shared on social media."

[0730] Step 6:

[0731] The terminal visualizes the proposed marketing strategy and displays it to the user. The input is the proposed marketing strategy, and the output is visualized graphs and charts. For example, a dashboard displays a graph of trend colors and a ranking of products that attract consumer interest.

[0732] Step 7:

[0733] The user can review the proposals and provide feedback through the device. The input is the visualized marketing strategy, and the output is feedback and queries from the user. The user can provide comments such as, "This campaign is good, but I'd like a more unique proposal."

[0734] Step 8:

[0735] The server uses an emotion engine to recognize the user's emotions and adjust the content of the suggestions. The input is emotional data obtained from the user's facial expressions and tone of voice, and the output is an adjusted marketing strategy. For example, the server uses a camera and microphone to analyze the user's emotions, and if dissatisfaction is expressed, the content of the suggestions is changed.

[0736] Step 9:

[0737] The server again generates an adjusted proposal and displays it to the user through the terminal. The input is the adjusted marketing strategy, and the output is the re-proposed visualization. This process is repeated until the user is satisfied.

[0738] (Application example 2)

[0739] 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."

[0740] Traditional marketing strategy planning tools placed emphasis on data analysis, but were unable to provide personalized suggestions based on user sentiment. Real-time data updates and immediate responses to queries were also lacking, leaving marketing professionals with a lack of support for quickly and accurately formulating strategies. There is a need to address these shortcomings and provide more effective marketing strategies.

[0741] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for executing an artificial intelligence model that analyzes the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means for performing additional analysis and proposals in real time in response to user queries, and emotion recognition means for detecting the user's emotions and reflecting them in the proposal content. This makes it possible to propose a personalized marketing strategy based on the user's emotions, enabling more effective and rapid implementation of marketing measures.

[0742] The "data collection means" is a device or system for automatically acquiring data relating to an industry specified by a user from the Internet or various databases.

[0743] A "data pre-processing means" is a device or method for cleansing, normalizing, and converting collected raw data into a form suitable for analysis.

[0744] An "artificial intelligence model execution means" is a device or system that uses preprocessed data as input and executes artificial intelligence algorithms such as machine learning and deep learning to analyze consumer behavior and market trends.

[0745] The "marketing strategy proposal means" is a device or system for generating and proposing specific marketing strategies and campaigns to users based on the analysis results of the artificial intelligence model.

[0746] A "real-time analytics means" is a device or system that provides additional data analysis and suggestions in real time in response to user queries.

[0747] An "emotion recognition means" is a device or system that automatically detects emotions from a user's facial expressions, tone of voice, text feedback, etc., and adjusts marketing strategy suggestions based on those emotions.

[0748] A "visualization means" is a device or system for presenting analysis results and proposed marketing strategies to a user in a visual format such as graphs or charts.

[0749] System Overview

[0750] This invention is an advanced digital assistant system for optimizing effective advertising campaigns in real time. This system combines AI technology to analyze industry trends and consumer behavior with emotion recognition technology to detect user emotions and reflect them in recommendations. The main components of the system and their respective processing steps are described below.

[0751] Key Components

[0752] 1. Data Collection Methods

[0753] Data related to the industry specified by the user is automatically collected from social media, e-commerce sites, trend databases, etc. This allows for accurate and timely acquisition of the latest industry trends and consumer behavior.

[0754] 2. Data preprocessing methods

[0755] The collected raw data is first cleansed to remove noise and extract necessary data. The data is then normalized and converted into a format that is easy for AI models to process. These processes are the prerequisite for achieving highly efficient data analysis.

[0756] 3. AI model execution means

[0757] The pre-processed data is then fed into an AI model, which runs on a machine learning framework such as TensorFlow. The AI ​​model analyzes the collected data and predicts consumer behavior and market trends. The analysis results are then used to generate subsequent marketing strategies.

[0758] 4. Marketing strategy proposal methods

[0759] Based on the analysis results obtained from the AI ​​model, a marketing strategy is proposed. This proposal is generated using a purchasing process model such as the AISAS model or the AIDMA model, and is presented as the most effective advertising strategy for the user.

[0760] 5. Real-time analysis tools

[0761] In response to user queries, additional data analysis and suggestions are provided in real time, allowing users to instantly obtain the data and analysis results they need and quickly adjust their marketing strategies.

[0762] 6. Emotion recognition means

[0763] A sentiment analysis engine analyzes the user's facial expressions, tone of voice, and text feedback to detect their emotional state. This emotional data is used to adjust marketing proposals. If the user expresses dissatisfaction with a proposal, the system will readjust the proposal based on that feedback.

[0764] 7. Visualization Tools

[0765] The analysis results and proposed marketing strategies are presented to the user in visual formats such as graphs and charts, making it easier for users to intuitively understand the analysis results.

[0766] Explanation of program processing

[0767] 1. Data Collection

[0768] The server automatically collects data on the industry specified by the user from social media, e-commerce sites, and trend databases.

[0769] 2. Data Preprocessing

[0770] The server cleanses, denoises, and normalizes the collected data, resulting in a dataset suitable for analysis.

[0771] 3. AI analysis

[0772] The pre-processed data is then fed into an artificial intelligence model, which uses machine learning frameworks such as TensorFlow to analyze the data and predict consumer behavior and market trends.

[0773] 4. Strategic proposals

[0774] Based on the results of the AI ​​analysis, a marketing strategy is generated. This proposal is based on the AISAS and AIDMA models and is presented to the user as a specific advertising strategy.

[0775] 5. Real-time analytics

[0776] In response to user queries, the server performs additional data analysis and offers suggestions in real time, allowing users to quickly obtain the information they need.

[0777] 6. Emotion recognition

[0778] The emotion recognition engine analyzes users' facial expressions, tone of voice, and text feedback to detect their emotional state. This emotional data is used to tailor marketing recommendations.

[0779] 7. Visualization

[0780] The analysis results and proposed strategies are displayed to the user in visual formats such as graphs and charts, allowing for intuitive understanding.

[0781] Specific examples

[0782] For example, when a marketing expert is planning a new summer product campaign, the system collects and analyzes the latest trend data and social media post data to propose optimal social media advertising campaigns and e-commerce site promotion strategies. Users can provide feedback using their smartphone's camera and microphone, and the emotion recognition engine analyzes their reactions and adjusts the proposals as necessary.

[0783] Example prompt sentence:

[0784] "For our new summer product campaign, please collect and analyze the latest consumer trend data and social media post data, and propose an effective advertising strategy based on the AISAS model. Also, please adjust your proposal based on my emotional feedback."

[0785] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0786] Step 1:

[0787] Data collection

[0788] The server collects data related to the industry specified by the user. As input, it obtains the latest posts and purchase data from social media, e-commerce sites, and trend databases. The output is a collection of collected raw data. Specific operations include obtaining post data using the API of a social media site and collecting purchase history from the API of an e-commerce site.

[0789] Step 2:

[0790] Data Preprocessing

[0791] The server cleanses and normalizes the collected data. The input is the raw data collected in step 1. Data processing includes noise removal, standardization of data formats, and handling of missing data. The output is a clean, normalized dataset suitable for analysis. Specific operations include filtering out inappropriate data and standardizing timestamps.

[0792] Step 3:

[0793] AI analysis

[0794] The server inputs the preprocessed data into the artificial intelligence model. The input is the preprocessed clean data. For AI analysis, a machine learning model such as TensorFlow is used to perform data calculations to predict consumer behavior and market trends. The output is the analysis results that show consumer preferences and market trends. Specifically, the data is passed to the AI ​​model and prediction results are obtained from the trained model.

[0795] Step 4:

[0796] Strategic proposal

[0797] The server proposes a marketing strategy based on the analysis results of the AI ​​model. The input is the analysis results obtained in step 3. An optimal advertising strategy is generated using a purchasing process model such as the AISAS model or AIDMA model. The output is a proposal of a specific marketing strategy. Specific operations include designing campaign content and promotion methods in accordance with the analysis results.

[0798] Step 5:

[0799] Real-time analytics

[0800] The server performs additional data analysis in real time in response to user queries. The input is the user query. Data processing involves reanalyzing the dataset based on the query. The output is additional marketing suggestions in line with the query. Specifically, the server accesses the database in response to the user's request, and retrieves and analyzes the required information.

[0801] Step 6:

[0802] emotion recognition

[0803] The server recognizes the user's facial expressions and tone of voice and analyzes their emotional state. The input is the user's feedback (facial expression data and voice data). An emotion recognition engine (for example, a Transformers emotion analysis model) is used for data calculation. The output is the user's emotional state. Specifically, the system captures the user's reactions with a camera or microphone, inputs them into the emotion recognition model, and obtains the results.

[0804] Step 7:

[0805] Adjusting the proposal

[0806] The server readjusts the marketing strategy based on the emotion recognition results. The input is the emotional state obtained in step 6 and the marketing strategy proposed in step 4. Data processing involves changing the proposed content according to the emotional state. The output is the adjusted marketing strategy. Specifically, if the user expresses dissatisfaction, the proposed content is changed and presented to the user again.

[0807] Step 8:

[0808] Visualization

[0809] The server visualizes the analysis results and proposals and displays them to the user. The input is the marketing strategies obtained in steps 4 and 7. The data is then visualized in graphs and charts. The output is the visualized proposals. Specifically, the analysis results are displayed graphically using a data visualization tool.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] [Third embodiment]

[0814] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0815] 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.

[0816] 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).

[0817] 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.

[0818] 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.

[0819] 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).

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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."

[0826] This invention is a digital assistant service designed for marketing professionals. This service uses AI technology to analyze real-time industry trends and consumer behavior and propose effective marketing strategies. Users can receive support for a wide range of projects, from short-term campaigns to long-term brand strategies.

[0827] System Overview

[0828] The system consists of the following main components:

[0829] 1. Data Collection Methods

[0830] The server collects data related to the industry specified by the user. For example, in the case of the fashion industry, the server collects the latest fashion trends, social media posting data, and e-commerce site purchase data.

[0831] 2. Data preprocessing methods

[0832] The server preprocesses the collected data and converts it into a format suitable for analysis by the AI ​​model, specifically by cleansing text data and normalizing numerical data.

[0833] 3. AI model execution means

[0834] The server inputs the pre-processed data into the AI ​​model to analyze consumer behavior and market trends, and the results of this analysis are presented to the user in visualizations such as graphs and charts.

[0835] 4. Marketing strategy proposal methods

[0836] The server proposes specific marketing strategies to users based on the analysis results of the AI ​​model. These proposals are generated using the AISAS and AIDMA models.

[0837] 5. User Interaction Methods

[0838] Users can receive suggestions through their devices and enter queries in real time, and the server will then perform additional analysis and provide suggestions accordingly.

[0839] Program processing

[0840] The program flow is as follows:

[0841] First, the user specifies the industry for which they want to develop a marketing strategy. Next, the server collects data related to the specified industry and preprocesses the collected data. The server then inputs the preprocessed data into an AI model to obtain analysis results. Based on the analysis results, the server proposes an optimal marketing strategy. The proposal is visualized and displayed to the user via their device. The user can review the proposal and enter a query. The server then performs additional analysis based on the query and provides the proposal to the user again.

[0842] Specific examples

[0843] For example, consider the case of a fashion industry campaigning for a new summer collection.

[0844] 1. A user requests suggestions for a summer campaign strategy for the fashion industry.

[0845] 2. The server collects the latest fashion trends, social media posts, and e-commerce site purchasing data.

[0846] 3. The server preprocesses the collected data by performing text cleansing and normalizing numeric data.

[0847] 4. The server inputs the preprocessed data into an AI model to analyze consumer purchasing patterns and popular items.

[0848] 5. Based on the AISAS model, the server will propose marketing strategies such as sharing campaigns on social media and limited-time sales on e-commerce sites.

[0849] 6. The device displays a visualization of these suggestions to the user.

[0850] 7. The user reviews the displayed suggestions and enters any follow-up questions.

[0851] 8. The server performs further analysis in response to the user's query and provides updated suggestions.

[0852] In this way, the present invention improves the efficiency of formulating marketing strategies and provides specific support for quickly implementing effective measures.

[0853] The processing flow will be explained below.

[0854] Step 1:

[0855] The user specifies the industry for which they want to develop a marketing strategy through the terminal, for example, requesting the collection of data on new collections in the fashion industry.

[0856] Step 2:

[0857] The server collects data related to the industry specified by the user, using web scraping technology and APIs to obtain the latest fashion industry trends, social media posts, and e-commerce site purchase data.

[0858] Step 3:

[0859] The server pre-processes the collected data.

[0860] Cleanse text data to remove unnecessary information and noise.

[0861] Normalize numeric data and convert it into a uniform format.

[0862] Step 4:

[0863] The server inputs the preprocessed data into the AI ​​model, which analyzes consumer behavior and market trends and obtains analytical results.

[0864] Step 5:

[0865] The server visualizes the analysis results in a form that is easy for the user to understand, for example by creating graphs or charts.

[0866] Step 6:

[0867] Based on the analysis results, the server proposes specific marketing strategies to the user, using the AISAS and AIDMA models to generate optimal strategies for social media sharing campaigns and e-commerce site exclusive sales.

[0868] Step 7:

[0869] The device displays the marketing strategy proposals received from the server to the user, allowing them to view visualized data on a dashboard or on the screen of a dedicated app.

[0870] Step 8:

[0871] The user can review the suggestions presented and enter additional questions or queries, such as "Who is the target audience for this campaign?"

[0872] Step 9:

[0873] The terminal sends the user's query to the server.

[0874] Step 10:

[0875] The server performs additional data analysis in response to user queries, collects and analyzes new information, and updates the marketing strategy again.

[0876] Step 11:

[0877] The server sends the updated proposal to the terminal, which displays the proposal to the user.

[0878] This series of processing steps allows users to quickly develop effective marketing strategies in real time.

[0879] Example 1

[0880] 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."

[0881] Conventional marketing strategy formulation systems have struggled to perform rapid and accurate data analysis and proposals. Furthermore, they lacked a means for users to quickly obtain additional analysis results by inputting specific queries, preventing the maximum effectiveness of marketing strategies. Furthermore, they had limited means for visually grasping the analysis results, making it difficult for users to receive proposals in a format that is easy for them to understand. Therefore, the present invention aims to solve these problems and provide a system that proposes efficient and effective marketing strategies in real time.

[0882] 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.

[0883] In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for executing an artificial intelligence model that analyzes the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means for performing additional analysis and proposals in real time in response to user queries, and means for visualizing and displaying the proposed marketing strategy. This allows the user to receive marketing strategy proposals based on rapid and accurate data analysis, and further allows the user to obtain analysis results in real time for additional queries. Furthermore, by visually grasping the analysis results, the user can receive proposals in a format that is easy for the user to understand.

[0884] The "means for collecting data" is a function for collecting information about an industry specified by the user.

[0885] "Means for pre-processing data" refers to processing functions for converting collected raw data into an analyzable format.

[0886] The "means for implementing an artificial intelligence model" is a computational function that uses AI techniques to analyze the pre-processed data.

[0887] The "means for proposing marketing strategies" is a function for presenting specific marketing measures to users based on the analysis results of the artificial intelligence model.

[0888] "Means for real-time analysis and proposals in response to queries" refers to a function that instantly provides more detailed analysis results and strategic proposals in response to additional questions entered by the user.

[0889] The "means for visualizing and displaying the proposed marketing strategy" is a function for visually expressing the analysis results and proposals in the form of graphs, charts, etc., and presenting them to the user in an easy-to-understand manner.

[0890] A "purchasing process model" is a model that shows the series of behavioral patterns that consumers follow when purchasing products or services, and is a basic framework used in building marketing strategies.

[0891] This is a digital assistant service designed for marketing professionals. It uses AI technology to analyze real-time industry trends and consumer behavior and propose effective marketing strategies. Users can receive support for a wide range of projects, from short-term campaigns to long-term brand strategies.

[0892] The system consists of the following main components:

[0893] 1. Data Collection Methods

[0894] The server collects data related to the industry specified by the user. For example, in the fashion industry, the server collects the latest fashion trends, social media posting data, and e-commerce site purchase data. Specifically, it uses web scraping tools (e.g., BeautifulSoup) and API access (e.g., Twitter API).

[0895] 2. Data preprocessing methods

[0896] The server preprocesses the collected data and converts it into a format suitable for analysis by the AI ​​model. Specifically, it uses Python and pandas to cleanse text data and normalize numerical data.

[0897] 3. AI model execution means

[0898] The server then uses the preprocessed data to run AI models, such as deep learning models built using TensorFlow and PyTorch, to analyze consumer behavior and market trends.

[0899] 4. Marketing strategy proposal methods

[0900] The server then proposes specific marketing strategies to the user based on the analysis results of the AI ​​model. These proposals are generated using the AISAS and AIDMA models. For example, sharing campaigns on social media or limited-time sales on e-commerce sites may be suggested.

[0901] 5. User Interaction Methods

[0902] Users can receive suggestions via their device and input queries in real time, and the server will then perform additional analysis and provide suggestions accordingly. For example, it can instantly answer questions such as, "Are there any other social media campaigns that are effective?"

[0903] 6. Visualization Tools

[0904] The device visually displays the proposed marketing strategy to the user, using tools such as Matplotlib and Tableau to display the analysis results in graphs and charts, allowing the user to intuitively understand the proposed content.

[0905] Specific examples

[0906] For example, consider the case of a fashion industry campaigning for a new summer collection.

[0907] 1. The user is looking for suggestions for a summer campaign strategy for the fashion industry. An example of a prompt sentence is, "Please suggest a marketing strategy for the fashion industry for next summer."

[0908] 2. The server collects the latest fashion trends, social media posts, and purchase data from e-commerce sites. It uses the Twitter API to collect posts containing relevant keywords and extracts sales data from e-commerce sites using BeautifulSoup.

[0909] 3. The server preprocesses the collected data, specifically cleansing text data and normalizing numeric data using Python and pandas.

[0910] 4. The server inputs the preprocessed data into a TensorFlow model to analyze consumer purchasing patterns and popular items.

[0911] 5. Based on the AISAS model, the server will propose marketing strategies such as sharing campaigns on social media and limited-time sales on e-commerce sites.

[0912] 6. The device displays these suggestions to the user in a visual format, such as a chart showing purchasing trends or an overview of recommended campaigns.

[0913] 7. The user reviews the suggestions and enters a follow-up question, such as, "What other social media campaigns have you seen that have worked?"

[0914] 8. The server performs further analysis in response to the user's query and provides updated suggestions.

[0915] In this way, the present invention provides specific support for making the formulation of marketing strategies more efficient and for quickly implementing effective measures.

[0916] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0917] Step 1:

[0918] User specifies industry

[0919] Through the system interface, users input the industry related to their business and the campaign information they wish to analyze. An example of a prompt sentence is, "Please suggest a marketing strategy for the fashion industry for next summer." This input is sent to the server as an instruction to the system.

[0920] Input: Industry and campaign information prompt text

[0921] Output: Instruction to start analysis on the server

[0922] Step 2:

[0923] The server collects the data

[0924] The server collects data related to the industry selected by the user. Specifically, it uses web scraping tools and APIs to obtain the following data:

[0925] Social Media Data: Use the Twitter API to collect posts with relevant keywords and hashtags.

[0926] E-commerce website data: Use web scraping tools to extract up-to-date sales data and product reviews.

[0927] Market Report Data: Gather the required data from published market research reports.

[0928] Input: Industry designation, campaign information

[0929] Output: Collected social media data, e-commerce site data, and other market data

[0930] Step 3:

[0931] The server preprocesses the data

[0932] The server preprocesses the collected raw data into a format suitable for analysis by the AI ​​model. The specific operations are as follows:

[0933] Text data cleansing: Use Python and pandas to remove unnecessary HTML tags, special characters, and noise data.

[0934] Normalization of numerical data: To standardize data with different scales, numerical data is normalized with z-scores.

[0935] Input: Collected social media data, e-commerce site data, and other market data

[0936] Output: Preprocessed data

[0937] Step 4:

[0938] The server runs the artificial intelligence model

[0939] The server runs an AI model (e.g., built with TensorFlow or PyTorch) on the preprocessed data. Specifically, it performs the following operations:

[0940] Data input: Input the preprocessed data into the AI ​​model.

[0941] Performing analytics: Models can analyze consumer behavior and market trends, such as the popularity of certain products and purchasing patterns.

[0942] Input: Preprocessed data

[0943] Output: Analysis results

[0944] Step 5:

[0945] The server proposes a marketing strategy

[0946] The server generates a marketing strategy to propose to the user based on the analysis results of the AI ​​model. This proposal is based on a purchasing process model such as the AISAS or AIDMA model. Specific proposals include:

[0947] Social media campaigns: Propose campaigns that utilize popular posts and hashtags.

[0948] Limited-time offer: Offering a discount or special offer on a specific product for a limited time.

[0949] Input: Analysis results

[0950] Output: Marketing strategy proposal

[0951] Step 6:

[0952] The device will visualize the suggestions and display them.

[0953] The terminal visually displays the marketing strategy proposals provided by the server to the user. The visualization uses the following tools:

[0954] Graphs and Charts: Use Matplotlib and Tableau to create graphs and charts that show consumer behavior and trends.

[0955] Dashboard: The proposed strategies are presented in a dashboard format that is easy for users to understand.

[0956] Input: Marketing strategy proposal

[0957] Output: Visualized proposal

[0958] Step 7:

[0959] The user enters a query

[0960] Users enter queries into the interface to ask follow-up questions or explore the suggestions presented, such as "What other social media campaigns are effective?"

[0961] Input: User query

[0962] Output: Request for further analysis to the server

[0963] Step 8:

[0964] The server performs additional analysis and offers suggestions

[0965] The server then analyzes the data again in response to user queries, providing additional strategies and insights. It does the following:

[0966] Additional data analysis: Reanalyze the required data based on the query.

[0967] Generate new proposals: Update your marketing strategy based on new insights.

[0968] Input: User query

[0969] Output: Additional analysis results and updated recommendations

[0970] In this way, the system provides users with real-time, data-driven marketing strategies tailored to their needs.

[0971] (Application example 1)

[0972] 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."

[0973] Traditional marketing strategies lack real-time monitoring and analysis of advertising trends and consumer behavior, making it difficult to develop fast and effective advertising strategies. In particular, the manual process of collecting, preprocessing, and analyzing complex data is time-consuming and inefficient. Another issue is that the proposed strategies are static, making them unable to adequately respond to changes in consumer behavior.

[0974] 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.

[0975] In this invention, the server includes means for collecting data related to a user-specified industry, means for pre-processing the collected data, and means for executing an artificial intelligence model that analyzes the pre-processed data, thereby enabling visualization and collection of advertising trends and campaign success stories in real time, and generating advertising strategies based on consumer purchasing patterns and popular items.

[0976] "Means for collecting data related to an industry specified by a user" refers to a system or method for obtaining necessary data related to a specific industry specified by a user from various sources (such as social media posts or purchase data from an e-commerce site).

[0977] "Means for preprocessing collected data" refers to processes or methods for converting collected data into a format suitable for analysis, such as by performing text cleansing or normalizing numerical data.

[0978] A "means for executing an artificial intelligence model that analyzes preprocessed data" is a system or method that uses preprocessed data as input and executes an artificial intelligence algorithm or model to perform data analysis.

[0979] "Means for proposing marketing strategies to users based on analysis results" refers to the process or method of presenting effective marketing measures to users based on the analysis results of an artificial intelligence model.

[0980] "Means for providing additional analysis and suggestions in real time in response to user queries" refers to a function that responds to user inquiries and questions, immediately performs additional data analysis, and re-proposes updated marketing strategies.

[0981] "A means of visualizing collected data as advertising trends and campaign success stories" is a function that displays acquired data in a visually easy-to-understand manner and visualizes the analysis results of advertising strategies and campaigns.

[0982] "Means for generating advertising strategies based on consumer purchasing patterns and popular items" refers to a system or method that automatically generates optimal advertising strategies based on analyzed consumer behavior data and trending product information.

[0983] This invention is a digital assistant service designed for marketing professionals and advertising managers. It is a system that uses AI technology to analyze real-time industry trends and consumer behavior and propose effective advertising strategies.

[0984] System configuration

[0985] The system consists of the following main components:

[0986] 1. A means of collecting data about a user-specified industry

[0987] The server collects data about a specified industry from multiple sources (e.g., social media posts, purchase data from an e-commerce site). The data is obtained via an API.

[0988] 2. Means of preprocessing the collected data

[0989] The server cleanses the collected data into a format suitable for analysis (e.g., removing noise from text data and normalizing numerical data).

[0990] 3. A means to run an artificial intelligence model that analyzes the preprocessed data

[0991] The server uses the preprocessed data as input and uses artificial intelligence models (e.g., Transformer-based models) for sentiment analysis and pattern recognition, such as the Transformers library from Hugging Face.

[0992] 4. A means of proposing marketing strategies to users based on the analysis results

[0993] Based on the analysis results of the AI ​​model, the server visualizes consumer purchasing patterns and popular items and proposes effective advertising strategies, which are generated based on the AISAS and AIDMA models.

[0994] 5. A means of providing additional analysis and suggestions in real time in response to user queries

[0995] The server receives queries from users, performs additional data analysis in real time, and generates and provides new suggestions.

[0996] Hardware and Software Used

[0997] Hardware

[0998] Server: A server with a high-performance CPU and GPU (e.g., NVIDIA GPU)

[0999] User devices: Display devices such as smartphones, tablets, and PCs

[1000] software

[1001] Data collection tools: API clients (e.g., Requests library)

[1002] Data preprocessing tools: Data frame manipulation tools (e.g., Pandas library), data normalization tools (e.g., Scikit-learn)

[1003] Artificial intelligence models: Sentiment analysis and pattern recognition tools (e.g., Hugging Face Transformers)

[1004] Visualization tools: Graphing tools (e.g., Matplotlib, Seaborn)

[1005] Specific use cases

[1006] For example, when planning a campaign for a new summer collection in the fashion industry, the following prompt might be used:

[1007] Prompt Sentence Examples

[1008] Please analyze the latest trends in the fashion industry and consumer behavior. Please provide specific suggestions to help us decide whether we should increase the volume of our next campaign.

[1009] Based on this prompt, the server collects, cleans, and analyzes the latest fashion trends, social media posts, and purchasing data from e-commerce sites. The analysis results visualize what items consumers are interested in and what purchasing patterns can be observed, and propose specific marketing strategies.

[1010] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1011] Program processing flow

[1012] Step 1:

[1013] The user inputs the specified prompt text into the server. The prompt text includes instructions on the industry to be analyzed and specific questions to ask. For example, the user inputs the prompt text, "Please analyze the latest trends and consumer behavior in the fashion industry. Please provide specific suggestions to help us decide whether we should increase the volume of our next campaign." The output of this step is the specified prompt text.

[1014] Step 2:

[1015] The server collects data related to a specified industry. Specifically, it obtains data such as social media posting data and e-commerce site purchase data from multiple APIs. The API tool used is, for example, the Requests library. The input for this step is a prompt statement and API endpoint information, and the output is the collected raw data.

[1016] Step 3:

[1017] The server preprocesses the collected data. For example, it cleanses text data and normalizes numerical data using the Pandas library or Scikit-learn. The input of this step is raw data, and the output is preprocessed, clean data.

[1018] Step 4:

[1019] The server runs an artificial intelligence model to analyze the preprocessed data. For example, it uses the Hugging Face Transformers library to perform sentiment analysis on text data. For numerical data analysis, it uses techniques such as regression analysis. The input for this step is the preprocessed data, and the output is the analysis results.

[1020] Step 5:

[1021] Based on the analysis results, the server proposes effective advertising strategies to the user. For example, using the AISAS model, it suggests "SNS sharing campaigns" or "limited sales on e-commerce sites." The input to this step is the analysis results, and the output is a specific marketing strategy proposal.

[1022] Step 6:

[1023] The server visualizes the proposed marketing strategy. Matplotlib and Seaborn are used to generate diagrams and charts and display them on the user's terminal. The input of this step is the proposed marketing strategy, and the output is the visualized graphs and charts.

[1024] Step 7:

[1025] The user inputs an additional query to the server, for example asking a specific question such as "Should we increase the budget for this campaign?" The input to this step is the user query, and the output is the query content.

[1026] Step 8:

[1027] The server performs additional analysis and new proposals in real time in response to the user's query. In this step, the data is analyzed again to generate new strategies and proposals in response to the user's query. The inputs to this step are the user query and existing data, and the output is new analysis results and proposals.

[1028] These steps allow marketing professionals to analyze data in real time and quickly develop effective advertising strategies.

[1029] 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.

[1030] This invention relates to an advanced digital assistant service designed for marketing professionals. This service utilizes AI technology to analyze real-time industry trends and consumer behavior, and then proposes effective marketing strategies based on this analysis. In addition, by incorporating an emotion engine that recognizes user emotions, more personalized strategy proposals are possible.

[1031] System Overview

[1032] The system consists of the following main components:

[1033] 1. Data Collection Methods

[1034] The server collects data related to the industry specified by the user. For example, in the case of the fashion industry, it obtains the latest trend data, social media posting data, and e-commerce site purchase data.

[1035] 2. Data preprocessing methods

[1036] The server preprocesses the collected data by cleansing, normalizing, format conversion, etc.

[1037] 3. AI model execution means

[1038] The server inputs the pre-processed data into an artificial intelligence model to analyze consumer behavior and market trends.

[1039] 4. Marketing strategy proposal methods

[1040] The server proposes specific marketing strategies to users based on the analysis results of the AI ​​model, and generates optimal strategies and campaigns using purchasing process models such as AISAS and AIDMA.

[1041] 5. User Interaction Methods

[1042] The device displays the suggestions received from the server to the user and accepts user queries in real time, and the server performs additional analysis and offers in response to the queries.

[1043] 6. Emotion Engine

[1044] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts the content of the suggestions based on the user's emotions.The server analyzes the emotions shown by the user in response to the displayed suggestions and provides real-time feedback accordingly, thereby providing a more appropriate marketing strategy.

[1045] Program processing

[1046] The program flow is as follows:

[1047] First, the user selects the industry for which they wish to develop a marketing strategy. The server then collects data related to the selected industry and preprocesses the collected data. The server then inputs the preprocessed data into an artificial intelligence model to obtain analysis results. Based on the analysis results, the server proposes specific marketing strategies to the user. The proposals are visualized and displayed to the user via the device.

[1048] At this point, an emotion engine is activated to recognize emotions from the user's facial expressions, tone of voice, etc. For example, if the user expresses dissatisfaction with the proposal, the emotion engine analyzes that information and provides feedback to the server. Based on this feedback, the server adjusts the proposal and presents it to the user again.

[1049] Specific examples

[1050] For example, consider a campaign in the fashion industry for a new summer collection.

[1051] 1. A user requests to create a summer campaign strategy for the fashion industry.

[1052] 2. The server collects the latest fashion trends, social media posts, and e-commerce site purchasing data.

[1053] 3. The server cleanses and normalizes the collected data.

[1054] 4. The server inputs the preprocessed data into an AI model to analyze consumer trends and popular items.

[1055] 5. The server generates strategies for social media sharing campaigns and limited-time sales on e-commerce sites based on the AISAS model.

[1056] 6. The device visualizes these suggestions and displays them to the user.

[1057] 7. The user confirms the displayed suggestions, and the emotion engine analyzes the user's facial expressions and tone of voice.

[1058] 8. The server receives feedback from the emotion engine and adjusts the suggestions.

[1059] 9. The server displays the adjusted proposal to the user again.

[1060] In this way, the present invention makes it possible to efficiently formulate marketing strategies and provides personalized strategies that correspond to the user's emotions, thereby supporting the implementation of more effective marketing measures.

[1061] The processing flow will be explained below.

[1062] Step 1:

[1063] The user specifies a specific industry for which a marketing strategy is to be developed through the terminal, for example, by requesting that a campaign strategy for a new summer collection in the fashion industry be developed.

[1064] Step 2:

[1065] The server collects data related to the industry specified by the user. Specifically, it uses web scraping technology and APIs to obtain the latest fashion-related trend data, social media post data, and e-commerce site purchase data.

[1066] Step 3:

[1067] The server pre-processes the collected data, which includes:

[1068] Cleansing text data (removing unnecessary data, normalizing non-standard characters, etc.).

[1069] Normalization of numeric data (standardization of units, removal of outliers, etc.).

[1070] Step 4:

[1071] The server inputs the pre-processed data into an AI model for analysis, which analyzes consumer behavior and market trends to extract insights such as popular items and purchasing patterns.

[1072] Step 5:

[1073] The server generates visualized data based on the analysis results, specifically by creating graphs and charts and converting the data into a format that is easily understandable to users.

[1074] Step 6:

[1075] The server proposes specific marketing strategies based on the analysis results, using the AISAS and AIDMA models to create optimal strategies such as social media sharing campaigns and limited-time sales on e-commerce sites.

[1076] Step 7:

[1077] The device visualizes the marketing strategy proposals received from the server and displays them to the user, who can view the proposals on a dashboard or a dedicated app screen.

[1078] Step 8:

[1079] The device runs an emotion engine that recognizes the user's emotions in real time by analyzing the user's facial expressions and tone of voice using a camera and microphone, and evaluating the user's emotions regarding the suggestions.

[1080] Step 9:

[1081] The server receives feedback from the emotion engine, for example, if the user expresses dissatisfaction with a displayed suggestion, and incorporates that information into the analysis.

[1082] Step 10:

[1083] The server adjusts the content of the proposals based on the emotional feedback, specifically fine-tuning the marketing strategy according to the user's emotions and generating more appropriate proposals.

[1084] Step 11:

[1085] The terminal revisits and displays the adjusted new proposal to the user, who can then review the proposal again.

[1086] As a result, the present invention provides a personalized marketing strategy that corresponds to the user's emotions, and supports the implementation of more effective measures.

[1087] Example 2

[1088] 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."

[1089] In today's marketing industry, there is a need to quickly analyze industry trends and consumer behavior in real time and develop effective strategies. However, traditional methods require a significant amount of time and effort to collect, preprocess, and analyze the necessary data, making it difficult to respond quickly. Furthermore, there is a lack of personalized strategy proposals based on user sentiment and feedback, making it difficult to maximize marketing effectiveness.

[1090] 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.

[1091] In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for running an artificial intelligence model to analyze the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means having an emotion engine for recognizing the user's emotions and adjusting the content of the proposal, and means for performing additional analysis and proposals in real time in response to user queries, thereby enabling real-time data analysis and personalized strategy proposals.

[1092] "User" refers to an individual or corporation that uses this system to develop a marketing strategy.

[1093] "Server" refers to a computer system that processes collected data, runs artificial intelligence models, and provides analytical results to users.

[1094] "Data collection means" refers to a function for obtaining data related to the industry specified by the user from the Internet or other databases.

[1095] "Preprocessing means" refers to a function that processes collected data, such as cleansing, normalization, and format conversion.

[1096] "Means for running artificial intelligence models" refers to the capability to run artificial intelligence techniques, such as deep learning models, to analyze the pre-processed data.

[1097] "Means for proposing marketing strategies" refers to a function that proposes specific marketing strategies to users based on the analysis results of the artificial intelligence model.

[1098] "Means with an emotion engine" refers to a function that analyzes the user's facial expressions, tone of voice, etc., and adjusts the content of suggestions based on the user's emotions.

[1099] "Means for real-time additional analysis and suggestions" refers to the ability to provide additional analysis and suggestions on the fly in response to queries and feedback from users.

[1100] "Purchasing process model" refers to theories that model consumer purchasing behavior, such as AISAS and AIDMA.

[1101] "Visualization means" refers to the function of visually displaying analysis results and proposed marketing strategies using graphs, charts, etc.

[1102] This invention relates to an advanced digital assistant service designed for marketing professionals. This service utilizes AI technology to analyze real-time industry trends and consumer behavior, and then proposes effective marketing strategies based on this analysis. In addition, by incorporating an emotion engine that recognizes user emotions, more personalized strategy proposals can be made.

[1103] The system of the present invention is composed of multiple elements such as a server, a terminal, a user, etc. How this system functions will be described below in detail.

[1104] The server collects data related to the industry specified by the user from the Internet and databases, using services such as Twitter API and Instagram Graph API to obtain the latest social media post data.

[1105] The server then pre-processes the collected data, which includes data cleansing, normalization, and format conversion, removing duplicate data and filtering out noisy data.

[1106] The pre-processed data is then analyzed using deep learning models such as TensorFlow and PyTorch, which can analyze consumer and market trends to identify, for example, this summer's trending colors and popular items.

[1107] Based on the analysis results, the server generates specific marketing strategies using purchasing process models such as AISAS (Attention, Interest, Search, Action, Share) and AIDMA (Attention, Interest, Desire, Memory, Action). For example, strategies such as social media sharing campaigns and e-commerce site-exclusive sales are proposed.

[1108] The device then visualizes the marketing strategies received from the server using graphs and charts, such as a dashboard displaying trending color charts and rankings of products that are attracting consumer interest.

[1109] The user checks the displayed suggestions on the device. At this time, the emotion engine analyzes the user's facial expressions and tone of voice. The emotion engine uses the camera and microphone to determine the user's facial expressions and tone of voice in real time.

[1110] The server receives feedback from the emotion engine and adjusts the content of the suggestions based on the user's emotions, for example, changing the content of the suggested campaign if the user expresses dissatisfaction with the suggestions.

[1111] Finally, the server generates the adjusted proposal again and displays it to the user through the terminal, and this process is repeated until the user is satisfied.

[1112] As a concrete example, consider a campaign for a new summer collection in the fashion industry. The user requests, "I want to create a campaign strategy for the fashion industry this summer." The server uses the Twitter API and Instagram Graph API to collect the latest social media post data, cleansing and preprocessing the collected data. It runs an AI model using TensorFlow and obtains analysis results such as "yellow is this summer's trend color" and "beachwear is a popular item." Based on the AISAS model, a strategy for "a campaign that offers discount coupons for posts shared on social media" is generated and displayed on the device. The user provides feedback such as "This campaign is good, but I would like a more unique proposal," so a readjusted strategy is proposed again, and the process is repeated until the user is satisfied.

[1113] An example of a prompt might be, "How do you feel about this proposal?"

[1114] In this way, the present invention makes it possible to efficiently formulate marketing strategies and provides personalized strategies that correspond to the user's emotions, thereby supporting the implementation of more effective marketing measures.

[1115] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1116] Step 1:

[1117] The user specifies the industry for which they want to develop a marketing strategy from their terminal. The input includes the name of the industry and specific campaign content. The request is "I want to create a summer campaign strategy for the fashion industry." The output is that this request is sent to the server.

[1118] Step 2:

[1119] The server collects data related to the industry specified by the user from the internet and databases. The input is the specified industry name, and the output is the acquired social media post data, trend data, and purchase data. Specifically, the data is collected using the Twitter API, Instagram Graph API, etc.

[1120] Step 3:

[1121] The server preprocesses the collected data. The input is the collected raw data, and the output is the cleansed and normalized data. Specific operations include removing duplicate data, filtering out noisy data, and standardizing date formats.

[1122] Step 4:

[1123] The server inputs the preprocessed data into a deep learning model for analysis. The input is cleansed and normalized data, and the output is the analysis results. Specifically, TensorFlow and PyTorch are used to analyze market trends and consumer behavior, and to obtain specific insights such as "yellow is the trend color this summer."

[1124] Step 5:

[1125] The server generates a marketing strategy based on the analysis results. The input is the analysis results of the AI ​​model, and the output is a proposed marketing strategy. Specifically, it uses purchasing process models such as AISAS and AIDMA to generate strategies such as "a campaign that offers discount coupons for posts shared on social media."

[1126] Step 6:

[1127] The terminal visualizes the proposed marketing strategy and displays it to the user. The input is the proposed marketing strategy, and the output is visualized graphs and charts. For example, a dashboard displays a graph of trend colors and a ranking of products that attract consumer interest.

[1128] Step 7:

[1129] The user can review the proposals and provide feedback through the device. The input is the visualized marketing strategy, and the output is feedback and queries from the user. The user can provide comments such as, "This campaign is good, but I'd like a more unique proposal."

[1130] Step 8:

[1131] The server uses an emotion engine to recognize the user's emotions and adjust the content of the suggestions. The input is emotional data obtained from the user's facial expressions and tone of voice, and the output is an adjusted marketing strategy. For example, the server uses a camera and microphone to analyze the user's emotions, and if dissatisfaction is expressed, the content of the suggestions is changed.

[1132] Step 9:

[1133] The server again generates an adjusted proposal and displays it to the user through the terminal. The input is the adjusted marketing strategy, and the output is the re-proposed visualization. This process is repeated until the user is satisfied.

[1134] (Application example 2)

[1135] 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."

[1136] Traditional marketing strategy planning tools placed emphasis on data analysis, but were unable to provide personalized suggestions based on user sentiment. Real-time data updates and immediate responses to queries were also lacking, leaving marketing professionals with a lack of support for quickly and accurately formulating strategies. There is a need to address these shortcomings and provide more effective marketing strategies.

[1137] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for executing an artificial intelligence model that analyzes the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means for performing additional analysis and proposals in real time in response to user queries, and emotion recognition means for detecting the user's emotions and reflecting them in the proposal content. This makes it possible to propose a personalized marketing strategy based on the user's emotions, enabling more effective and rapid implementation of marketing measures.

[1138] The "data collection means" is a device or system for automatically acquiring data relating to an industry specified by a user from the Internet or various databases.

[1139] A "data pre-processing means" is a device or method for cleansing, normalizing, and converting collected raw data into a form suitable for analysis.

[1140] An "artificial intelligence model execution means" is a device or system that uses preprocessed data as input and executes artificial intelligence algorithms such as machine learning and deep learning to analyze consumer behavior and market trends.

[1141] The "marketing strategy proposal means" is a device or system for generating and proposing specific marketing strategies and campaigns to users based on the analysis results of the artificial intelligence model.

[1142] A "real-time analytics means" is a device or system that provides additional data analysis and suggestions in real time in response to user queries.

[1143] An "emotion recognition means" is a device or system that automatically detects emotions from a user's facial expressions, tone of voice, text feedback, etc., and adjusts marketing strategy suggestions based on those emotions.

[1144] A "visualization means" is a device or system for presenting analysis results and proposed marketing strategies to a user in a visual format such as graphs or charts.

[1145] System Overview

[1146] This invention is an advanced digital assistant system for optimizing effective advertising campaigns in real time. This system combines AI technology to analyze industry trends and consumer behavior with emotion recognition technology to detect user emotions and reflect them in recommendations. The main components of the system and their respective processing steps are described below.

[1147] Key Components

[1148] 1. Data Collection Methods

[1149] Data related to the industry specified by the user is automatically collected from social media, e-commerce sites, trend databases, etc. This allows for accurate and timely acquisition of the latest industry trends and consumer behavior.

[1150] 2. Data preprocessing methods

[1151] The collected raw data is first cleansed to remove noise and extract necessary data. The data is then normalized and converted into a format that is easy for AI models to process. These processes are the prerequisite for achieving highly efficient data analysis.

[1152] 3. AI model execution means

[1153] The pre-processed data is then fed into an AI model, which runs on a machine learning framework such as TensorFlow. The AI ​​model analyzes the collected data and predicts consumer behavior and market trends. The analysis results are then used to generate subsequent marketing strategies.

[1154] 4. Marketing strategy proposal methods

[1155] Based on the analysis results obtained from the AI ​​model, a marketing strategy is proposed. This proposal is generated using a purchasing process model such as the AISAS model or the AIDMA model, and is presented as the most effective advertising strategy for the user.

[1156] 5. Real-time analysis tools

[1157] In response to user queries, additional data analysis and suggestions are provided in real time, allowing users to instantly obtain the data and analysis results they need and quickly adjust their marketing strategies.

[1158] 6. Emotion recognition means

[1159] A sentiment analysis engine analyzes the user's facial expressions, tone of voice, and text feedback to detect their emotional state. This emotional data is used to adjust marketing proposals. If the user expresses dissatisfaction with a proposal, the system will readjust the proposal based on that feedback.

[1160] 7. Visualization Tools

[1161] The analysis results and proposed marketing strategies are presented to the user in visual formats such as graphs and charts, making it easier for users to intuitively understand the analysis results.

[1162] Explanation of program processing

[1163] 1. Data Collection

[1164] The server automatically collects data on the industry specified by the user from social media, e-commerce sites, and trend databases.

[1165] 2. Data Preprocessing

[1166] The server cleanses, denoises, and normalizes the collected data, resulting in a dataset suitable for analysis.

[1167] 3. AI analysis

[1168] The pre-processed data is then fed into an artificial intelligence model, which uses machine learning frameworks such as TensorFlow to analyze the data and predict consumer behavior and market trends.

[1169] 4. Strategic proposals

[1170] Based on the results of the AI ​​analysis, a marketing strategy is generated. This proposal is based on the AISAS and AIDMA models and is presented to the user as a specific advertising strategy.

[1171] 5. Real-time analytics

[1172] In response to user queries, the server performs additional data analysis and offers suggestions in real time, allowing users to quickly obtain the information they need.

[1173] 6. Emotion recognition

[1174] The emotion recognition engine analyzes users' facial expressions, tone of voice, and text feedback to detect their emotional state. This emotional data is used to tailor marketing recommendations.

[1175] 7. Visualization

[1176] The analysis results and proposed strategies are displayed to the user in visual formats such as graphs and charts, allowing for intuitive understanding.

[1177] Specific examples

[1178] For example, when a marketing expert is planning a new summer product campaign, the system collects and analyzes the latest trend data and social media post data to propose optimal social media advertising campaigns and e-commerce site promotion strategies. Users can provide feedback using their smartphone's camera and microphone, and the emotion recognition engine analyzes their reactions and adjusts the proposals as necessary.

[1179] Example prompt sentence:

[1180] "For our new summer product campaign, please collect and analyze the latest consumer trend data and social media post data, and propose an effective advertising strategy based on the AISAS model. Also, please adjust your proposal based on my emotional feedback."

[1181] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1182] Step 1:

[1183] Data collection

[1184] The server collects data related to the industry specified by the user. As input, it obtains the latest posts and purchase data from social media, e-commerce sites, and trend databases. The output is a collection of collected raw data. Specific operations include obtaining post data using the API of a social media site and collecting purchase history from the API of an e-commerce site.

[1185] Step 2:

[1186] Data Preprocessing

[1187] The server cleanses and normalizes the collected data. The input is the raw data collected in step 1. Data processing includes noise removal, standardization of data formats, and handling of missing data. The output is a clean, normalized dataset suitable for analysis. Specific operations include filtering out inappropriate data and standardizing timestamps.

[1188] Step 3:

[1189] AI analysis

[1190] The server inputs the preprocessed data into the artificial intelligence model. The input is the preprocessed clean data. For AI analysis, a machine learning model such as TensorFlow is used to perform data calculations to predict consumer behavior and market trends. The output is the analysis results that show consumer preferences and market trends. Specifically, the data is passed to the AI ​​model and prediction results are obtained from the trained model.

[1191] Step 4:

[1192] Strategic proposal

[1193] The server proposes a marketing strategy based on the analysis results of the AI ​​model. The input is the analysis results obtained in step 3. An optimal advertising strategy is generated using a purchasing process model such as the AISAS model or AIDMA model. The output is a proposal of a specific marketing strategy. Specific operations include designing campaign content and promotion methods in accordance with the analysis results.

[1194] Step 5:

[1195] Real-time analytics

[1196] The server performs additional data analysis in real time in response to user queries. The input is the user query. Data processing involves reanalyzing the dataset based on the query. The output is additional marketing suggestions in line with the query. Specifically, the server accesses the database in response to the user's request, and retrieves and analyzes the required information.

[1197] Step 6:

[1198] emotion recognition

[1199] The server recognizes the user's facial expressions and tone of voice and analyzes their emotional state. The input is the user's feedback (facial expression data and voice data). An emotion recognition engine (for example, a Transformers emotion analysis model) is used for data calculation. The output is the user's emotional state. Specifically, the system captures the user's reactions with a camera or microphone, inputs them into the emotion recognition model, and obtains the results.

[1200] Step 7:

[1201] Adjusting the proposal

[1202] The server readjusts the marketing strategy based on the emotion recognition results. The input is the emotional state obtained in step 6 and the marketing strategy proposed in step 4. Data processing involves changing the proposed content according to the emotional state. The output is the adjusted marketing strategy. Specifically, if the user expresses dissatisfaction, the proposed content is changed and presented to the user again.

[1203] Step 8:

[1204] Visualization

[1205] The server visualizes the analysis results and proposals and displays them to the user. The input is the marketing strategies obtained in steps 4 and 7. The data is then visualized in graphs and charts. The output is the visualized proposals. Specifically, the analysis results are displayed graphically using a data visualization tool.

[1206] 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.

[1207] 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.

[1208] 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.

[1209] [Fourth embodiment]

[1210] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1211] 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.

[1212] 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).

[1213] 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.

[1214] 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.

[1215] 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).

[1216] 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.

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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."

[1223] This invention is a digital assistant service designed for marketing professionals. This service uses AI technology to analyze real-time industry trends and consumer behavior and propose effective marketing strategies. Users can receive support for a wide range of projects, from short-term campaigns to long-term brand strategies.

[1224] System Overview

[1225] The system consists of the following main components:

[1226] 1. Data Collection Methods

[1227] The server collects data related to the industry specified by the user. For example, in the case of the fashion industry, the server collects the latest fashion trends, social media posting data, and e-commerce site purchase data.

[1228] 2. Data preprocessing methods

[1229] The server preprocesses the collected data and converts it into a format suitable for analysis by the AI ​​model, specifically by cleansing text data and normalizing numerical data.

[1230] 3. AI model execution means

[1231] The server inputs the pre-processed data into the AI ​​model to analyze consumer behavior and market trends, and the results of this analysis are presented to the user in visualizations such as graphs and charts.

[1232] 4. Marketing strategy proposal methods

[1233] The server proposes specific marketing strategies to users based on the analysis results of the AI ​​model. These proposals are generated using the AISAS and AIDMA models.

[1234] 5. User Interaction Methods

[1235] Users can receive suggestions through their devices and enter queries in real time, and the server will then perform additional analysis and provide suggestions accordingly.

[1236] Program processing

[1237] The program flow is as follows:

[1238] First, the user specifies the industry for which they want to develop a marketing strategy. Next, the server collects data related to the specified industry and preprocesses the collected data. The server then inputs the preprocessed data into an AI model to obtain analysis results. Based on the analysis results, the server proposes an optimal marketing strategy. The proposal is visualized and displayed to the user via their device. The user can review the proposal and enter a query. The server then performs additional analysis based on the query and provides the proposal to the user again.

[1239] Specific examples

[1240] For example, consider the case of a fashion industry campaigning for a new summer collection.

[1241] 1. A user requests suggestions for a summer campaign strategy for the fashion industry.

[1242] 2. The server collects the latest fashion trends, social media posts, and e-commerce site purchasing data.

[1243] 3. The server preprocesses the collected data by performing text cleansing and normalizing numeric data.

[1244] 4. The server inputs the preprocessed data into an AI model to analyze consumer purchasing patterns and popular items.

[1245] 5. Based on the AISAS model, the server will propose marketing strategies such as sharing campaigns on social media and limited-time sales on e-commerce sites.

[1246] 6. The device displays a visualization of these suggestions to the user.

[1247] 7. The user reviews the displayed suggestions and enters any follow-up questions.

[1248] 8. The server performs further analysis in response to the user's query and provides updated suggestions.

[1249] In this way, the present invention improves the efficiency of formulating marketing strategies and provides specific support for quickly implementing effective measures.

[1250] The processing flow will be explained below.

[1251] Step 1:

[1252] The user specifies the industry for which they want to develop a marketing strategy through the terminal, for example, requesting the collection of data on new collections in the fashion industry.

[1253] Step 2:

[1254] The server collects data related to the industry specified by the user, using web scraping technology and APIs to obtain the latest fashion industry trends, social media posts, and e-commerce site purchase data.

[1255] Step 3:

[1256] The server pre-processes the collected data.

[1257] Cleanse text data to remove unnecessary information and noise.

[1258] Normalize numeric data and convert it into a uniform format.

[1259] Step 4:

[1260] The server inputs the preprocessed data into the AI ​​model, which analyzes consumer behavior and market trends and obtains analytical results.

[1261] Step 5:

[1262] The server visualizes the analysis results in a form that is easy for the user to understand, for example by creating graphs or charts.

[1263] Step 6:

[1264] Based on the analysis results, the server proposes specific marketing strategies to the user, using the AISAS and AIDMA models to generate optimal strategies for social media sharing campaigns and e-commerce site exclusive sales.

[1265] Step 7:

[1266] The device displays the marketing strategy proposals received from the server to the user, allowing them to view visualized data on a dashboard or on the screen of a dedicated app.

[1267] Step 8:

[1268] The user can review the suggestions presented and enter additional questions or queries, such as "Who is the target audience for this campaign?"

[1269] Step 9:

[1270] The terminal sends the user's query to the server.

[1271] Step 10:

[1272] The server performs additional data analysis in response to user queries, collects and analyzes new information, and updates the marketing strategy again.

[1273] Step 11:

[1274] The server sends the updated proposal to the terminal, which displays the proposal to the user.

[1275] This series of processing steps allows users to quickly develop effective marketing strategies in real time.

[1276] Example 1

[1277] 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."

[1278] Conventional marketing strategy formulation systems have struggled to perform rapid and accurate data analysis and proposals. Furthermore, they lacked a means for users to quickly obtain additional analysis results by inputting specific queries, preventing the maximum effectiveness of marketing strategies. Furthermore, they had limited means for visually grasping the analysis results, making it difficult for users to receive proposals in a format that is easy for them to understand. Therefore, the present invention aims to solve these problems and provide a system that proposes efficient and effective marketing strategies in real time.

[1279] 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.

[1280] In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for executing an artificial intelligence model that analyzes the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means for performing additional analysis and proposals in real time in response to user queries, and means for visualizing and displaying the proposed marketing strategy. This allows the user to receive marketing strategy proposals based on rapid and accurate data analysis, and further allows the user to obtain analysis results in real time for additional queries. Furthermore, by visually grasping the analysis results, the user can receive proposals in a format that is easy for the user to understand.

[1281] The "means for collecting data" is a function for collecting information about an industry specified by the user.

[1282] "Means for pre-processing data" refers to processing functions for converting collected raw data into an analyzable format.

[1283] The "means for implementing an artificial intelligence model" is a computational function that uses AI techniques to analyze the pre-processed data.

[1284] The "means for proposing marketing strategies" is a function for presenting specific marketing measures to users based on the analysis results of the artificial intelligence model.

[1285] "Means for real-time analysis and proposals in response to queries" refers to a function that instantly provides more detailed analysis results and strategic proposals in response to additional questions entered by the user.

[1286] The "means for visualizing and displaying the proposed marketing strategy" is a function for visually expressing the analysis results and proposals in the form of graphs, charts, etc., and presenting them to the user in an easy-to-understand manner.

[1287] A "purchasing process model" is a model that shows the series of behavioral patterns that consumers follow when purchasing products or services, and is a basic framework used in building marketing strategies.

[1288] This is a digital assistant service designed for marketing professionals. It uses AI technology to analyze real-time industry trends and consumer behavior and propose effective marketing strategies. Users can receive support for a wide range of projects, from short-term campaigns to long-term brand strategies.

[1289] The system consists of the following main components:

[1290] 1. Data Collection Methods

[1291] The server collects data related to the industry specified by the user. For example, in the fashion industry, the server collects the latest fashion trends, social media posting data, and e-commerce site purchase data. Specifically, it uses web scraping tools (e.g., BeautifulSoup) and API access (e.g., Twitter API).

[1292] 2. Data preprocessing methods

[1293] The server preprocesses the collected data and converts it into a format suitable for analysis by the AI ​​model. Specifically, it uses Python and pandas to cleanse text data and normalize numerical data.

[1294] 3. AI model execution means

[1295] The server then uses the preprocessed data to run AI models, such as deep learning models built using TensorFlow and PyTorch, to analyze consumer behavior and market trends.

[1296] 4. Marketing strategy proposal methods

[1297] The server then proposes specific marketing strategies to the user based on the analysis results of the AI ​​model. These proposals are generated using the AISAS and AIDMA models. For example, sharing campaigns on social media or limited-time sales on e-commerce sites may be suggested.

[1298] 5. User Interaction Methods

[1299] Users can receive suggestions via their device and input queries in real time, and the server will then perform additional analysis and provide suggestions accordingly. For example, it can instantly answer questions such as, "Are there any other social media campaigns that are effective?"

[1300] 6. Visualization Tools

[1301] The device visually displays the proposed marketing strategy to the user, using tools such as Matplotlib and Tableau to display the analysis results in graphs and charts, allowing the user to intuitively understand the proposed content.

[1302] Specific examples

[1303] For example, consider the case of a fashion industry campaigning for a new summer collection.

[1304] 1. The user is looking for suggestions for a summer campaign strategy for the fashion industry. An example of a prompt sentence is, "Please suggest a marketing strategy for the fashion industry for next summer."

[1305] 2. The server collects the latest fashion trends, social media posts, and purchase data from e-commerce sites. It uses the Twitter API to collect posts containing relevant keywords and extracts sales data from e-commerce sites using BeautifulSoup.

[1306] 3. The server preprocesses the collected data, specifically cleansing text data and normalizing numeric data using Python and pandas.

[1307] 4. The server inputs the preprocessed data into a TensorFlow model to analyze consumer purchasing patterns and popular items.

[1308] 5. Based on the AISAS model, the server will propose marketing strategies such as sharing campaigns on social media and limited-time sales on e-commerce sites.

[1309] 6. The device displays these suggestions to the user in a visual format, such as a chart showing purchasing trends or an overview of recommended campaigns.

[1310] 7. The user reviews the suggestions and enters a follow-up question, such as, "What other social media campaigns have you seen that have worked?"

[1311] 8. The server performs further analysis in response to the user's query and provides updated suggestions.

[1312] In this way, the present invention provides specific support for making the formulation of marketing strategies more efficient and for quickly implementing effective measures.

[1313] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1314] Step 1:

[1315] User specifies industry

[1316] Through the system interface, users input the industry related to their business and the campaign information they wish to analyze. An example of a prompt sentence is, "Please suggest a marketing strategy for the fashion industry for next summer." This input is sent to the server as an instruction to the system.

[1317] Input: Industry and campaign information prompt text

[1318] Output: Instruction to start analysis on the server

[1319] Step 2:

[1320] The server collects the data

[1321] The server collects data related to the industry selected by the user. Specifically, it uses web scraping tools and APIs to obtain the following data:

[1322] Social Media Data: Use the Twitter API to collect posts with relevant keywords and hashtags.

[1323] E-commerce website data: Use web scraping tools to extract up-to-date sales data and product reviews.

[1324] Market Report Data: Gather the required data from published market research reports.

[1325] Input: Industry designation, campaign information

[1326] Output: Collected social media data, e-commerce site data, and other market data

[1327] Step 3:

[1328] The server preprocesses the data

[1329] The server preprocesses the collected raw data into a format suitable for analysis by the AI ​​model. The specific operations are as follows:

[1330] Text data cleansing: Use Python and pandas to remove unnecessary HTML tags, special characters, and noise data.

[1331] Normalization of numerical data: To standardize data with different scales, numerical data is normalized with z-scores.

[1332] Input: Collected social media data, e-commerce site data, and other market data

[1333] Output: Preprocessed data

[1334] Step 4:

[1335] The server runs the artificial intelligence model

[1336] The server runs an AI model (e.g., built with TensorFlow or PyTorch) on the preprocessed data. Specifically, it performs the following operations:

[1337] Data input: Input the preprocessed data into the AI ​​model.

[1338] Performing analytics: Models can analyze consumer behavior and market trends, such as the popularity of certain products and purchasing patterns.

[1339] Input: Preprocessed data

[1340] Output: Analysis results

[1341] Step 5:

[1342] The server proposes a marketing strategy

[1343] The server generates a marketing strategy to propose to the user based on the analysis results of the AI ​​model. This proposal is based on a purchasing process model such as the AISAS or AIDMA model. Specific proposals include:

[1344] Social media campaigns: Propose campaigns that utilize popular posts and hashtags.

[1345] Limited-time offer: Offering a discount or special offer on a specific product for a limited time.

[1346] Input: Analysis results

[1347] Output: Marketing strategy proposal

[1348] Step 6:

[1349] The device will visualize the suggestions and display them.

[1350] The terminal visually displays the marketing strategy proposals provided by the server to the user. The visualization uses the following tools:

[1351] Graphs and Charts: Use Matplotlib and Tableau to create graphs and charts that show consumer behavior and trends.

[1352] Dashboard: The proposed strategies are presented in a dashboard format that is easy for users to understand.

[1353] Input: Marketing strategy proposal

[1354] Output: Visualized proposal

[1355] Step 7:

[1356] The user enters a query

[1357] Users enter queries into the interface to ask follow-up questions or explore the suggestions presented, such as "What other social media campaigns are effective?"

[1358] Input: User query

[1359] Output: Request for further analysis to the server

[1360] Step 8:

[1361] The server performs additional analysis and offers suggestions

[1362] The server then analyzes the data again in response to user queries, providing additional strategies and insights. It does the following:

[1363] Additional data analysis: Reanalyze the required data based on the query.

[1364] Generate new proposals: Update your marketing strategy based on new insights.

[1365] Input: User query

[1366] Output: Additional analysis results and updated recommendations

[1367] In this way, the system provides users with real-time, data-driven marketing strategies tailored to their needs.

[1368] (Application example 1)

[1369] 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."

[1370] Traditional marketing strategies lack real-time monitoring and analysis of advertising trends and consumer behavior, making it difficult to develop fast and effective advertising strategies. In particular, the manual process of collecting, preprocessing, and analyzing complex data is time-consuming and inefficient. Another issue is that the proposed strategies are static, making them unable to adequately respond to changes in consumer behavior.

[1371] 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.

[1372] In this invention, the server includes means for collecting data related to a user-specified industry, means for pre-processing the collected data, and means for executing an artificial intelligence model that analyzes the pre-processed data, thereby enabling visualization and collection of advertising trends and campaign success stories in real time, and generating advertising strategies based on consumer purchasing patterns and popular items.

[1373] "Means for collecting data related to an industry specified by a user" refers to a system or method for obtaining necessary data related to a specific industry specified by a user from various sources (such as social media posts or purchase data from an e-commerce site).

[1374] "Means for preprocessing collected data" refers to processes or methods for converting collected data into a format suitable for analysis, such as by performing text cleansing or normalizing numerical data.

[1375] A "means for executing an artificial intelligence model that analyzes preprocessed data" is a system or method that uses preprocessed data as input and executes an artificial intelligence algorithm or model to perform data analysis.

[1376] "Means for proposing marketing strategies to users based on analysis results" refers to the process or method of presenting effective marketing measures to users based on the analysis results of an artificial intelligence model.

[1377] "Means for providing additional analysis and suggestions in real time in response to user queries" refers to a function that responds to user inquiries and questions, immediately performs additional data analysis, and re-proposes updated marketing strategies.

[1378] "A means of visualizing collected data as advertising trends and campaign success stories" is a function that displays acquired data in a visually easy-to-understand manner and visualizes the analysis results of advertising strategies and campaigns.

[1379] "Means for generating advertising strategies based on consumer purchasing patterns and popular items" refers to a system or method that automatically generates optimal advertising strategies based on analyzed consumer behavior data and trending product information.

[1380] This invention is a digital assistant service designed for marketing professionals and advertising managers. It is a system that uses AI technology to analyze real-time industry trends and consumer behavior and propose effective advertising strategies.

[1381] System configuration

[1382] The system consists of the following main components:

[1383] 1. A means of collecting data about a user-specified industry

[1384] The server collects data about a specified industry from multiple sources (e.g., social media posts, purchase data from an e-commerce site). The data is obtained via an API.

[1385] 2. Means of preprocessing the collected data

[1386] The server cleanses the collected data into a format suitable for analysis (e.g., removing noise from text data and normalizing numerical data).

[1387] 3. A means to run an artificial intelligence model that analyzes the preprocessed data

[1388] The server uses the preprocessed data as input and uses artificial intelligence models (e.g., Transformer-based models) for sentiment analysis and pattern recognition, such as the Transformers library from Hugging Face.

[1389] 4. A means of proposing marketing strategies to users based on the analysis results

[1390] Based on the analysis results of the AI ​​model, the server visualizes consumer purchasing patterns and popular items and proposes effective advertising strategies, which are generated based on the AISAS and AIDMA models.

[1391] 5. A means of providing additional analysis and suggestions in real time in response to user queries

[1392] The server receives queries from users, performs additional data analysis in real time, and generates and provides new suggestions.

[1393] Hardware and Software Used

[1394] Hardware

[1395] Server: A server with a high-performance CPU and GPU (e.g., NVIDIA GPU)

[1396] User devices: Display devices such as smartphones, tablets, and PCs

[1397] software

[1398] Data collection tools: API clients (e.g., Requests library)

[1399] Data preprocessing tools: Data frame manipulation tools (e.g., Pandas library), data normalization tools (e.g., Scikit-learn)

[1400] Artificial intelligence models: Sentiment analysis and pattern recognition tools (e.g., Hugging Face Transformers)

[1401] Visualization tools: Graphing tools (e.g., Matplotlib, Seaborn)

[1402] Specific use cases

[1403] For example, when planning a campaign for a new summer collection in the fashion industry, the following prompt might be used:

[1404] Prompt Sentence Examples

[1405] Please analyze the latest trends in the fashion industry and consumer behavior. Please provide specific suggestions to help us decide whether we should increase the volume of our next campaign.

[1406] Based on this prompt, the server collects, cleans, and analyzes the latest fashion trends, social media posts, and purchasing data from e-commerce sites. The analysis results visualize what items consumers are interested in and what purchasing patterns can be observed, and propose specific marketing strategies.

[1407] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1408] Program processing flow

[1409] Step 1:

[1410] The user inputs the specified prompt text into the server. The prompt text includes instructions on the industry to be analyzed and specific questions to ask. For example, the user inputs the prompt text, "Please analyze the latest trends and consumer behavior in the fashion industry. Please provide specific suggestions to help us decide whether we should increase the volume of our next campaign." The output of this step is the specified prompt text.

[1411] Step 2:

[1412] The server collects data related to a specified industry. Specifically, it obtains data such as social media posting data and e-commerce site purchase data from multiple APIs. The API tool used is, for example, the Requests library. The input for this step is a prompt statement and API endpoint information, and the output is the collected raw data.

[1413] Step 3:

[1414] The server preprocesses the collected data. For example, it cleanses text data and normalizes numerical data using the Pandas library or Scikit-learn. The input of this step is raw data, and the output is preprocessed, clean data.

[1415] Step 4:

[1416] The server runs an artificial intelligence model to analyze the preprocessed data. For example, it uses the Hugging Face Transformers library to perform sentiment analysis on text data. For numerical data analysis, it uses techniques such as regression analysis. The input for this step is the preprocessed data, and the output is the analysis results.

[1417] Step 5:

[1418] Based on the analysis results, the server proposes effective advertising strategies to the user. For example, using the AISAS model, it suggests "SNS sharing campaigns" or "limited sales on e-commerce sites." The input to this step is the analysis results, and the output is a specific marketing strategy proposal.

[1419] Step 6:

[1420] The server visualizes the proposed marketing strategy. Matplotlib and Seaborn are used to generate diagrams and charts and display them on the user's terminal. The input of this step is the proposed marketing strategy, and the output is the visualized graphs and charts.

[1421] Step 7:

[1422] The user inputs an additional query to the server, for example asking a specific question such as "Should we increase the budget for this campaign?" The input to this step is the user query, and the output is the query content.

[1423] Step 8:

[1424] The server performs additional analysis and new proposals in real time in response to the user's query. In this step, the data is analyzed again to generate new strategies and proposals in response to the user's query. The inputs to this step are the user query and existing data, and the output is new analysis results and proposals.

[1425] These steps allow marketing professionals to analyze data in real time and quickly develop effective advertising strategies.

[1426] 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.

[1427] This invention relates to an advanced digital assistant service designed for marketing professionals. This service utilizes AI technology to analyze real-time industry trends and consumer behavior, and then proposes effective marketing strategies based on this analysis. In addition, by incorporating an emotion engine that recognizes user emotions, more personalized strategy proposals are possible.

[1428] System Overview

[1429] The system consists of the following main components:

[1430] 1. Data Collection Methods

[1431] The server collects data related to the industry specified by the user. For example, in the case of the fashion industry, it obtains the latest trend data, social media posting data, and e-commerce site purchase data.

[1432] 2. Data preprocessing methods

[1433] The server preprocesses the collected data by cleansing, normalizing, format conversion, etc.

[1434] 3. AI model execution means

[1435] The server inputs the pre-processed data into an artificial intelligence model to analyze consumer behavior and market trends.

[1436] 4. Marketing strategy proposal methods

[1437] The server proposes specific marketing strategies to users based on the analysis results of the AI ​​model, and generates optimal strategies and campaigns using purchasing process models such as AISAS and AIDMA.

[1438] 5. User Interaction Methods

[1439] The device displays the suggestions received from the server to the user and accepts user queries in real time, and the server performs additional analysis and offers in response to the queries.

[1440] 6. Emotion Engine

[1441] The server is equipped with an emotion engine that recognizes the user's emotions and adjusts the content of the suggestions based on the user's emotions.The server analyzes the emotions shown by the user in response to the displayed suggestions and provides real-time feedback accordingly, thereby providing a more appropriate marketing strategy.

[1442] Program processing

[1443] The program flow is as follows:

[1444] First, the user selects the industry for which they wish to develop a marketing strategy. The server then collects data related to the selected industry and preprocesses the collected data. The server then inputs the preprocessed data into an artificial intelligence model to obtain analysis results. Based on the analysis results, the server proposes specific marketing strategies to the user. The proposals are visualized and displayed to the user via the device.

[1445] At this point, an emotion engine is activated to recognize emotions from the user's facial expressions, tone of voice, etc. For example, if the user expresses dissatisfaction with the proposal, the emotion engine analyzes that information and provides feedback to the server. Based on this feedback, the server adjusts the proposal and presents it to the user again.

[1446] Specific examples

[1447] For example, consider a campaign in the fashion industry for a new summer collection.

[1448] 1. A user requests to create a summer campaign strategy for the fashion industry.

[1449] 2. The server collects the latest fashion trends, social media posts, and e-commerce site purchasing data.

[1450] 3. The server cleanses and normalizes the collected data.

[1451] 4. The server inputs the preprocessed data into an AI model to analyze consumer trends and popular items.

[1452] 5. The server generates strategies for social media sharing campaigns and limited-time sales on e-commerce sites based on the AISAS model.

[1453] 6. The device visualizes these suggestions and displays them to the user.

[1454] 7. The user confirms the displayed suggestions, and the emotion engine analyzes the user's facial expressions and tone of voice.

[1455] 8. The server receives feedback from the emotion engine and adjusts the suggestions.

[1456] 9. The server displays the adjusted proposal to the user again.

[1457] In this way, the present invention makes it possible to efficiently formulate marketing strategies and provides personalized strategies that correspond to the user's emotions, thereby supporting the implementation of more effective marketing measures.

[1458] The processing flow will be explained below.

[1459] Step 1:

[1460] The user specifies a specific industry for which a marketing strategy is to be developed through the terminal, for example, by requesting that a campaign strategy for a new summer collection in the fashion industry be developed.

[1461] Step 2:

[1462] The server collects data related to the industry specified by the user. Specifically, it uses web scraping technology and APIs to obtain the latest fashion-related trend data, social media post data, and e-commerce site purchase data.

[1463] Step 3:

[1464] The server pre-processes the collected data, which includes:

[1465] Cleansing text data (removing unnecessary data, normalizing non-standard characters, etc.).

[1466] Normalization of numeric data (standardization of units, removal of outliers, etc.).

[1467] Step 4:

[1468] The server inputs the pre-processed data into an AI model for analysis, which analyzes consumer behavior and market trends to extract insights such as popular items and purchasing patterns.

[1469] Step 5:

[1470] The server generates visualized data based on the analysis results, specifically by creating graphs and charts and converting the data into a format that is easily understandable to users.

[1471] Step 6:

[1472] The server proposes specific marketing strategies based on the analysis results, using the AISAS and AIDMA models to create optimal strategies such as social media sharing campaigns and limited-time sales on e-commerce sites.

[1473] Step 7:

[1474] The device visualizes the marketing strategy proposals received from the server and displays them to the user, who can view the proposals on a dashboard or a dedicated app screen.

[1475] Step 8:

[1476] The device runs an emotion engine that recognizes the user's emotions in real time by analyzing the user's facial expressions and tone of voice using a camera and microphone, and evaluating the user's emotions regarding the suggestions.

[1477] Step 9:

[1478] The server receives feedback from the emotion engine, for example, if the user expresses dissatisfaction with a displayed suggestion, and incorporates that information into the analysis.

[1479] Step 10:

[1480] The server adjusts the content of the proposals based on the emotional feedback, specifically fine-tuning the marketing strategy according to the user's emotions and generating more appropriate proposals.

[1481] Step 11:

[1482] The terminal revisits and displays the adjusted new proposal to the user, who can then review the proposal again.

[1483] As a result, the present invention provides a personalized marketing strategy that corresponds to the user's emotions, and supports the implementation of more effective measures.

[1484] Example 2

[1485] 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."

[1486] In today's marketing industry, there is a need to quickly analyze industry trends and consumer behavior in real time and develop effective strategies. However, traditional methods require a significant amount of time and effort to collect, preprocess, and analyze the necessary data, making it difficult to respond quickly. Furthermore, there is a lack of personalized strategy proposals based on user sentiment and feedback, making it difficult to maximize marketing effectiveness.

[1487] 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.

[1488] In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for running an artificial intelligence model to analyze the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means having an emotion engine for recognizing the user's emotions and adjusting the content of the proposal, and means for performing additional analysis and proposals in real time in response to user queries, thereby enabling real-time data analysis and personalized strategy proposals.

[1489] "User" refers to an individual or corporation that uses this system to develop a marketing strategy.

[1490] "Server" refers to a computer system that processes collected data, runs artificial intelligence models, and provides analytical results to users.

[1491] "Data collection means" refers to a function for obtaining data related to the industry specified by the user from the Internet or other databases.

[1492] "Preprocessing means" refers to a function that processes collected data, such as cleansing, normalization, and format conversion.

[1493] "Means for running artificial intelligence models" refers to the capability to run artificial intelligence techniques, such as deep learning models, to analyze the pre-processed data.

[1494] "Means for proposing marketing strategies" refers to a function that proposes specific marketing strategies to users based on the analysis results of the artificial intelligence model.

[1495] "Means with an emotion engine" refers to a function that analyzes the user's facial expressions, tone of voice, etc., and adjusts the content of suggestions based on the user's emotions.

[1496] "Means for real-time additional analysis and suggestions" refers to the ability to provide additional analysis and suggestions on the fly in response to queries and feedback from users.

[1497] "Purchasing process model" refers to theories that model consumer purchasing behavior, such as AISAS and AIDMA.

[1498] "Visualization means" refers to the function of visually displaying analysis results and proposed marketing strategies using graphs, charts, etc.

[1499] This invention relates to an advanced digital assistant service designed for marketing professionals. This service utilizes AI technology to analyze real-time industry trends and consumer behavior, and then proposes effective marketing strategies based on this analysis. In addition, by incorporating an emotion engine that recognizes user emotions, more personalized strategy proposals can be made.

[1500] The system of the present invention is composed of multiple elements such as a server, a terminal, a user, etc. How this system functions will be described below in detail.

[1501] The server collects data related to the industry specified by the user from the Internet and databases, using services such as Twitter API and Instagram Graph API to obtain the latest social media post data.

[1502] The server then pre-processes the collected data, which includes data cleansing, normalization, and format conversion, removing duplicate data and filtering out noisy data.

[1503] The pre-processed data is then analyzed using deep learning models such as TensorFlow and PyTorch, which can analyze consumer and market trends to identify, for example, this summer's trending colors and popular items.

[1504] Based on the analysis results, the server generates specific marketing strategies using purchasing process models such as AISAS (Attention, Interest, Search, Action, Share) and AIDMA (Attention, Interest, Desire, Memory, Action). For example, strategies such as social media sharing campaigns and e-commerce site-exclusive sales are proposed.

[1505] The device then visualizes the marketing strategies received from the server using graphs and charts, such as a dashboard displaying trending color charts and rankings of products that are attracting consumer interest.

[1506] The user checks the displayed suggestions on the device. At this time, the emotion engine analyzes the user's facial expressions and tone of voice. The emotion engine uses the camera and microphone to determine the user's facial expressions and tone of voice in real time.

[1507] The server receives feedback from the emotion engine and adjusts the content of the suggestions based on the user's emotions, for example, changing the content of the suggested campaign if the user expresses dissatisfaction with the suggestions.

[1508] Finally, the server generates the adjusted proposal again and displays it to the user through the terminal, and this process is repeated until the user is satisfied.

[1509] As a concrete example, consider a campaign for a new summer collection in the fashion industry. The user requests, "I want to create a campaign strategy for the fashion industry this summer." The server uses the Twitter API and Instagram Graph API to collect the latest social media post data, cleansing and preprocessing the collected data. It runs an AI model using TensorFlow and obtains analysis results such as "yellow is this summer's trend color" and "beachwear is a popular item." Based on the AISAS model, a strategy for "a campaign that offers discount coupons for posts shared on social media" is generated and displayed on the device. The user provides feedback such as "This campaign is good, but I would like a more unique proposal," so a readjusted strategy is proposed again, and the process is repeated until the user is satisfied.

[1510] An example of a prompt might be, "How do you feel about this proposal?"

[1511] In this way, the present invention makes it possible to efficiently formulate marketing strategies and provides personalized strategies that correspond to the user's emotions, thereby supporting the implementation of more effective marketing measures.

[1512] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1513] Step 1:

[1514] The user specifies the industry for which they want to develop a marketing strategy from their terminal. The input includes the name of the industry and specific campaign content. The request is "I want to create a summer campaign strategy for the fashion industry." The output is that this request is sent to the server.

[1515] Step 2:

[1516] The server collects data related to the industry specified by the user from the internet and databases. The input is the specified industry name, and the output is the acquired social media post data, trend data, and purchase data. Specifically, the data is collected using the Twitter API, Instagram Graph API, etc.

[1517] Step 3:

[1518] The server preprocesses the collected data. The input is the collected raw data, and the output is the cleansed and normalized data. Specific operations include removing duplicate data, filtering out noisy data, and standardizing date formats.

[1519] Step 4:

[1520] The server inputs the preprocessed data into a deep learning model for analysis. The input is cleansed and normalized data, and the output is the analysis results. Specifically, TensorFlow and PyTorch are used to analyze market trends and consumer behavior, and to obtain specific insights such as "yellow is the trend color this summer."

[1521] Step 5:

[1522] The server generates a marketing strategy based on the analysis results. The input is the analysis results of the AI ​​model, and the output is a proposed marketing strategy. Specifically, it uses purchasing process models such as AISAS and AIDMA to generate strategies such as "a campaign that offers discount coupons for posts shared on social media."

[1523] Step 6:

[1524] The terminal visualizes the proposed marketing strategy and displays it to the user. The input is the proposed marketing strategy, and the output is visualized graphs and charts. For example, a dashboard displays a graph of trend colors and a ranking of products that attract consumer interest.

[1525] Step 7:

[1526] The user can review the proposals and provide feedback through the device. The input is the visualized marketing strategy, and the output is feedback and queries from the user. The user can provide comments such as, "This campaign is good, but I'd like a more unique proposal."

[1527] Step 8:

[1528] The server uses an emotion engine to recognize the user's emotions and adjust the content of the suggestions. The input is emotional data obtained from the user's facial expressions and tone of voice, and the output is an adjusted marketing strategy. For example, the server uses a camera and microphone to analyze the user's emotions, and if dissatisfaction is expressed, the content of the suggestions is changed.

[1529] Step 9:

[1530] The server again generates an adjusted proposal and displays it to the user through the terminal. The input is the adjusted marketing strategy, and the output is the re-proposed visualization. This process is repeated until the user is satisfied.

[1531] (Application example 2)

[1532] 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."

[1533] Traditional marketing strategy planning tools placed emphasis on data analysis, but were unable to provide personalized suggestions based on user sentiment. Real-time data updates and immediate responses to queries were also lacking, leaving marketing professionals with a lack of support for quickly and accurately formulating strategies. There is a need to address these shortcomings and provide more effective marketing strategies.

[1534] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data related to an industry specified by a user, means for preprocessing the collected data, means for executing an artificial intelligence model that analyzes the preprocessed data, means for proposing a marketing strategy to the user based on the analysis results, means for performing additional analysis and proposals in real time in response to user queries, and emotion recognition means for detecting the user's emotions and reflecting them in the proposal content. This makes it possible to propose a personalized marketing strategy based on the user's emotions, enabling more effective and rapid implementation of marketing measures.

[1535] The "data collection means" is a device or system for automatically acquiring data relating to an industry specified by a user from the Internet or various databases.

[1536] A "data pre-processing means" is a device or method for cleansing, normalizing, and converting collected raw data into a form suitable for analysis.

[1537] An "artificial intelligence model execution means" is a device or system that uses preprocessed data as input and executes artificial intelligence algorithms such as machine learning and deep learning to analyze consumer behavior and market trends.

[1538] The "marketing strategy proposal means" is a device or system for generating and proposing specific marketing strategies and campaigns to users based on the analysis results of the artificial intelligence model.

[1539] A "real-time analytics means" is a device or system that provides additional data analysis and suggestions in real time in response to user queries.

[1540] An "emotion recognition means" is a device or system that automatically detects emotions from a user's facial expressions, tone of voice, text feedback, etc., and adjusts marketing strategy suggestions based on those emotions.

[1541] A "visualization means" is a device or system for presenting analysis results and proposed marketing strategies to a user in a visual format such as graphs or charts.

[1542] System Overview

[1543] This invention is an advanced digital assistant system for optimizing effective advertising campaigns in real time. This system combines AI technology to analyze industry trends and consumer behavior with emotion recognition technology to detect user emotions and reflect them in recommendations. The main components of the system and their respective processing steps are described below.

[1544] Key Components

[1545] 1. Data Collection Methods

[1546] Data related to the industry specified by the user is automatically collected from social media, e-commerce sites, trend databases, etc. This allows for accurate and timely acquisition of the latest industry trends and consumer behavior.

[1547] 2. Data preprocessing methods

[1548] The collected raw data is first cleansed to remove noise and extract necessary data. The data is then normalized and converted into a format that is easy for AI models to process. These processes are the prerequisite for achieving highly efficient data analysis.

[1549] 3. AI model execution means

[1550] The pre-processed data is then fed into an AI model, which runs on a machine learning framework such as TensorFlow. The AI ​​model analyzes the collected data and predicts consumer behavior and market trends. The analysis results are then used to generate subsequent marketing strategies.

[1551] 4. Marketing strategy proposal methods

[1552] Based on the analysis results obtained from the AI ​​model, a marketing strategy is proposed. This proposal is generated using a purchasing process model such as the AISAS model or the AIDMA model, and is presented as the most effective advertising strategy for the user.

[1553] 5. Real-time analysis tools

[1554] In response to user queries, additional data analysis and suggestions are provided in real time, allowing users to instantly obtain the data and analysis results they need and quickly adjust their marketing strategies.

[1555] 6. Emotion recognition means

[1556] A sentiment analysis engine analyzes the user's facial expressions, tone of voice, and text feedback to detect their emotional state. This emotional data is used to adjust marketing proposals. If the user expresses dissatisfaction with a proposal, the system will readjust the proposal based on that feedback.

[1557] 7. Visualization Tools

[1558] The analysis results and proposed marketing strategies are presented to the user in visual formats such as graphs and charts, making it easier for users to intuitively understand the analysis results.

[1559] Explanation of program processing

[1560] 1. Data Collection

[1561] The server automatically collects data on the industry specified by the user from social media, e-commerce sites, and trend databases.

[1562] 2. Data Preprocessing

[1563] The server cleanses, denoises, and normalizes the collected data, resulting in a dataset suitable for analysis.

[1564] 3. AI analysis

[1565] The pre-processed data is then fed into an artificial intelligence model, which uses machine learning frameworks such as TensorFlow to analyze the data and predict consumer behavior and market trends.

[1566] 4. Strategic proposals

[1567] Based on the results of the AI ​​analysis, a marketing strategy is generated. This proposal is based on the AISAS and AIDMA models and is presented to the user as a specific advertising strategy.

[1568] 5. Real-time analytics

[1569] In response to user queries, the server performs additional data analysis and offers suggestions in real time, allowing users to quickly obtain the information they need.

[1570] 6. Emotion recognition

[1571] The emotion recognition engine analyzes users' facial expressions, tone of voice, and text feedback to detect their emotional state. This emotional data is used to tailor marketing recommendations.

[1572] 7. Visualization

[1573] The analysis results and proposed strategies are displayed to the user in visual formats such as graphs and charts, allowing for intuitive understanding.

[1574] Specific examples

[1575] For example, when a marketing expert is planning a new summer product campaign, the system collects and analyzes the latest trend data and social media post data to propose optimal social media advertising campaigns and e-commerce site promotion strategies. Users can provide feedback using their smartphone's camera and microphone, and the emotion recognition engine analyzes their reactions and adjusts the proposals as necessary.

[1576] Example prompt sentence:

[1577] "For our new summer product campaign, please collect and analyze the latest consumer trend data and social media post data, and propose an effective advertising strategy based on the AISAS model. Also, please adjust your proposal based on my emotional feedback."

[1578] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1579] Step 1:

[1580] Data collection

[1581] The server collects data related to the industry specified by the user. As input, it obtains the latest posts and purchase data from social media, e-commerce sites, and trend databases. The output is a collection of collected raw data. Specific operations include obtaining post data using the API of a social media site and collecting purchase history from the API of an e-commerce site.

[1582] Step 2:

[1583] Data Preprocessing

[1584] The server cleanses and normalizes the collected data. The input is the raw data collected in step 1. Data processing includes noise removal, standardization of data formats, and handling of missing data. The output is a clean, normalized dataset suitable for analysis. Specific operations include filtering out inappropriate data and standardizing timestamps.

[1585] Step 3:

[1586] AI analysis

[1587] The server inputs the preprocessed data into the artificial intelligence model. The input is the preprocessed clean data. For AI analysis, a machine learning model such as TensorFlow is used to perform data calculations to predict consumer behavior and market trends. The output is the analysis results that show consumer preferences and market trends. Specifically, the data is passed to the AI ​​model and prediction results are obtained from the trained model.

[1588] Step 4:

[1589] Strategic proposal

[1590] The server proposes a marketing strategy based on the analysis results of the AI ​​model. The input is the analysis results obtained in step 3. An optimal advertising strategy is generated using a purchasing process model such as the AISAS model or AIDMA model. The output is a proposal of a specific marketing strategy. Specific operations include designing campaign content and promotion methods in accordance with the analysis results.

[1591] Step 5:

[1592] Real-time analytics

[1593] The server performs additional data analysis in real time in response to user queries. The input is the user query. Data processing involves reanalyzing the dataset based on the query. The output is additional marketing suggestions in line with the query. Specifically, the server accesses the database in response to the user's request, and retrieves and analyzes the required information.

[1594] Step 6:

[1595] emotion recognition

[1596] The server recognizes the user's facial expressions and tone of voice and analyzes their emotional state. The input is the user's feedback (facial expression data and voice data). An emotion recognition engine (for example, a Transformers emotion analysis model) is used for data calculation. The output is the user's emotional state. Specifically, the system captures the user's reactions with a camera or microphone, inputs them into the emotion recognition model, and obtains the results.

[1597] Step 7:

[1598] Adjusting the proposal

[1599] The server readjusts the marketing strategy based on the emotion recognition results. The input is the emotional state obtained in step 6 and the marketing strategy proposed in step 4. Data processing involves changing the proposed content according to the emotional state. The output is the adjusted marketing strategy. Specifically, if the user expresses dissatisfaction, the proposed content is changed and presented to the user again.

[1600] Step 8:

[1601] Visualization

[1602] The server visualizes the analysis results and proposals and displays them to the user. The input is the marketing strategies obtained in steps 4 and 7. The data is then visualized in graphs and charts. The output is the visualized proposals. Specifically, the analysis results are displayed graphically using a data visualization tool.

[1603] 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.

[1604] 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.

[1605] 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 robot 414.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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).

[1610] 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.

[1611] 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."

[1612] 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.

[1613] 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).

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] The following is further disclosed regarding the above embodiment.

[1625] (Claim 1)

[1626] a means for collecting data relating to an industry specified by a user;

[1627] a means for pre-processing the collected data;

[1628] means for executing an artificial intelligence model that analyzes the preprocessed data;

[1629] A means for proposing a marketing strategy to the user based on the analysis results;

[1630] a means for providing additional analysis and suggestions in real time in response to user queries;

[1631] A system including:

[1632] (Claim 2)

[1633] 10. The system of claim 1, further comprising: means for generating a proposed marketing strategy based on the buying process model.

[1634] (Claim 3)

[1635] 10. The system of claim 1, further comprising means for visualizing the collected data and displaying it to a user.

[1636] "Example 1"

[1637] (Claim 1)

[1638] a means for collecting data relating to an industry specified by a user;

[1639] a means for pre-processing the collected data;

[1640] means for executing an artificial intelligence model that analyzes the preprocessed data;

[1641] A means for proposing a marketing strategy to the user based on the analysis results;

[1642] a means for providing additional analysis and suggestions in real time in response to user queries;

[1643] a means for visualizing and displaying the proposed marketing strategy;

[1644] A system including:

[1645] (Claim 2)

[1646] 10. The system of claim 1, further comprising: means for generating a proposed marketing strategy based on the buying process model.

[1647] (Claim 3)

[1648] 2. The system according to claim 1, further comprising means for visualizing the analysis results in graphs or charts and presenting the results to the user.

[1649] "Application Example 1"

[1650] (Claim 1)

[1651] a means for collecting data relating to an industry specified by a user;

[1652] a means for pre-processing the collected data;

[1653] means for executing an artificial intelligence model that analyzes the preprocessed data;

[1654] A means for proposing a marketing strategy to the user based on the analysis results;

[1655] a means for providing additional analysis and suggestions in real time in response to user queries;

[1656] A way to visualize the collected data as advertising trends and campaign success stories, and

[1657] A means of generating advertising strategies based on consumer purchasing patterns and popular items;

[1658] A system including:

[1659] (Claim 2)

[1660] 10. The system of claim 1, further comprising: means for generating a proposed marketing strategy based on the buying process model.

[1661] (Claim 3)

[1662] 10. The system of claim 1, further comprising means for visualizing the collected data and displaying it to a user.

[1663] "Example 2: Combining Emotion Engines"

[1664] (Claim 1)

[1665] a means for collecting data relating to an industry specified by a user;

[1666] a means for pre-processing the collected data;

[1667] means for executing an artificial intelligence model that analyzes the preprocessed data;

[1668] A means for proposing a marketing strategy to the user based on the analysis results;

[1669] means for detecting user emotions and adjusting the content of the suggestions;

[1670] a means for providing additional analysis and suggestions in real time in response to user queries;

[1671] A system including:

[1672] (Claim 2)

[1673] 10. The system of claim 1, further comprising: means for generating a proposed marketing strategy based on the buying process model.

[1674] (Claim 3)

[1675] 10. The system of claim 1, further comprising means for visualizing the collected data and displaying it to a user.

[1676] "Application example 2 when combining emotion engines"

[1677] (Claim 1)

[1678] a means for collecting data relating to an industry specified by a user;

[1679] a means for pre-processing the collected data;

[1680] means for executing an artificial intelligence model that analyzes the preprocessed data;

[1681] A means for proposing a marketing strategy to the user based on the analysis results;

[1682] a means for providing additional analysis and suggestions in real time in response to user queries;

[1683] An emotion recognition means for detecting the emotion of the user and reflecting it in the content of the proposal;

[1684] A system including:

[1685] (Claim 2)

[1686] 10. The system of claim 1, further comprising: means for generating a proposed marketing strategy based on the buying process model.

[1687] (Claim 3)

[1688] 10. The system of claim 1, further comprising means for visualizing the collected data and displaying it to a user. [Explanation of symbols]

[1689] 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 for collecting data relating to an industry specified by a user; a means for pre-processing the collected data; means for executing an artificial intelligence model that analyzes the preprocessed data; A means for proposing a marketing strategy to the user based on the analysis results; a means for providing additional analysis and suggestions in real time in response to user queries; A system including:

2. 10. The system of claim 1, further comprising means for generating a proposed marketing strategy based on the buying process model.

3. 2. The system of claim 1, further comprising means for visualizing the collected data and displaying it to a user.

Images