System

Abstract

To provide a system.SOLUTION: The system includes: means of collecting product information from the website; means of storing the collected data in a database; means of calculating a recommendation ranking of the product by using a machine learning algorithm; means of collecting emotional data of the user; means of analyzing the emotion of the user by using an emotion analysis algorithm; and means of adjusting the timing and content of the information provided to a sales representative based on the analysis results.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] We aim to improve the efficiency of sales activities by conducting competitive analysis and organizing information on the diverse range of products in corporate sales, but with the ever-increasing number of products, it takes time to find the optimal solution to customer problems. [Means for solving the problem]

[0005] We propose a system that automates comparative analysis, including that of competing services, to increase the speed of knowledge acquisition. Specifically, it collects information such as product characteristics, prices, and customer reviews, and then performs comparative analysis between products based on this information. Furthermore, it automatically calculates the recommended ranking of products based on the collected information and provides it to sales representatives. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The present invention is a system for conducting competitive analysis of products and organizing information. Specifically, it includes a means for collecting information on product characteristics, prices, customer reviews, etc., a means for automating comparative analysis between products based on that information, and a means for accelerating the speed of knowledge acquisition.

[0029] "Example 2"

[0030] For example, web scraping technology, which automatically collects necessary information from internet databases and websites, can be used to collect information such as product characteristics, prices, customer reviews, etc. Furthermore, machine learning algorithms can be used to automatically calculate the recommended ranking of products based on the collected information to automate comparative analysis between products.

[0031] "Example 3"

[0032] Furthermore, to speed up the acquisition of knowledge, the system is equipped with an interface that provides sales representatives with the calculated recommended rankings. Specifically, by providing a dashboard that visually displays the recommended rankings in an easy-to-understand manner, sales representatives can quickly grasp the information and make their sales activities more efficient.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Collect information such as product characteristics, prices, customer reviews, etc. In this step, web scraping technology is used to automatically collect the necessary information from databases and websites on the Internet.

[0036] Step 2: Based on the collected information, a comparative analysis between products is conducted. In this step, a machine learning algorithm is used to automatically calculate the recommended ranking of products.

[0037] Step 3: Provide the calculated recommendation ranking to the sales representative. In this step, a dashboard is provided that visually displays the recommendation ranking in an easy-to-understand manner.

[0038] "Example 2"

[0039] Step 1: Collect information such as product characteristics, prices, customer reviews, etc. In this step, web scraping technology is used to automatically collect the necessary information from databases and websites on the Internet.

[0040] Step 2: Based on the collected information, a comparative analysis between products is conducted. In this step, a machine learning algorithm is used to automatically calculate the recommended ranking of products.

[0041] Step 3: Provide the calculated recommendation ranking to the sales representative. In this step, a dashboard is provided that visually displays the recommendation ranking in an easy-to-understand manner.

[0042] "Example 3"

[0043] Step 1: Collect information such as product characteristics, prices, customer reviews, etc. In this step, web scraping technology is used to automatically collect the necessary information from databases and websites on the Internet.

[0044] Step 2: Based on the collected information, a comparative analysis between products is conducted. In this step, a machine learning algorithm is used to automatically calculate the recommended ranking of products.

[0045] Step 3: Provide the calculated recommendation ranking to the sales representative. In this step, a dashboard is provided that visually displays the recommendation ranking in an easy-to-understand manner.

[0046] Example 1

[0047] Next, a description will be given of Example 1 of Form 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."

[0048] Conventional competitive analysis and information organization systems for products often required manual processes of information collection, data cleansing, and comparative analysis, which was time-consuming and labor-intensive. Additionally, knowledge acquisition was slow, limiting the efficiency of sales activities. Furthermore, there was a lack of a way to quickly summarize the characteristics and competitiveness of products based on the collected information, making it difficult for sales representatives to make quick decisions.

[0049] 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.

[0050] In this invention, the server includes means for collecting information such as product characteristics, prices, and customer reviews, means for cleansing the collected information and converting it into a unified format, means for performing comparative analysis between products based on the cleansed data, means for automatically summarizing the product characteristics and competitiveness using a generative AI model, means for generating prompt sentences to be input to the generative AI model, and means for inputting the prompt sentences to the generative AI model and summarizing the results of the comparison of the products. This automates the process from information collection to data cleansing, comparative analysis, and summarization, improving the speed of knowledge acquisition and enabling more efficient sales activities.

[0051] "Merchandise" is a general term for goods and services sold in the market.

[0052] "Competitive analysis" is the process of comparing multiple products and evaluating their competitiveness and market positioning.

[0053] "Information organization" is the process of systematically organizing collected data and converting it into an easy-to-understand format.

[0054] "Sales activities" refers to a series of tasks and processes for selling products.

[0055] "Efficiency" means improving operations and processes so that they can be performed with less time and effort.

[0056] "Comparative analysis" is the process of comparing the characteristics, prices, customer reviews, etc. of multiple products and evaluating their relative merits.

[0057] "Speed ​​of knowledge acquisition" refers to the speed at which it takes to gather and understand the necessary information and knowledge.

[0058] "Information gathering" is the process of obtaining data about a product from the internet and other sources.

[0059] "Cleansing" is the process of removing unnecessary or incorrect information from collected data and converting it into an accurate and consistent format.

[0060] A "generative AI model" is a model that uses artificial intelligence to analyze data and automatically perform specific tasks.

[0061] A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

[0062] "Summarizing" is the process of concisely summarizing collected information and extracting the main points.

[0063] MODE FOR CARRYING OUT THE INVENTION

[0064] This invention relates to a system for conducting competitive analysis and information organization for commercial products. Specifically, it includes a means for collecting information on the characteristics, prices, customer reviews, etc. of commercial products, automating comparative analysis between commercial products based on the collected information, and a means for accelerating the speed of knowledge acquisition.

[0065] Generating a Program

[0066] The server generates a program for a system that performs competitive analysis of products and organizes information. This program has the function of collecting information such as product characteristics, prices, and customer reviews, and automating comparative analysis between products based on that information. It also has a means to increase the speed of knowledge acquisition.

[0067] Program processing explanation

[0068] The server executes the program in the following procedure.

[0069] 1. Information Collection:

[0070] The server collects information such as product characteristics, prices, and customer reviews from the Internet using web scraping tools (e.g., BeautifulSoup, Scrapy).

[0071] The collected data is stored in a database (e.g., MySQL (registered trademark), PostgreSQL).

[0072] 2. Data cleansing:

[0073] The server cleanses the collected data and converts it into the required format, for example, converting price information into a uniform currency unit.

[0074] Use a data processing library (e.g., Pandas) to remove unnecessary or duplicate data and transform it into an accurate and consistent format.

[0075] 3. Data Analysis:

[0076] The server performs comparative analysis between products based on the cleansed data, specifically calculating average prices and the distribution of customer ratings.

[0077] Use data analysis tools (e.g., NumPy, Scikit-learn) to compare the characteristics of different products.

[0078] 4. Speed ​​up knowledge acquisition:

[0079] The server uses a generative AI model (e.g., GPT-4 (registered trademark)) to automatically summarize the product's features and competitive advantages based on the collected information.

[0080] A prompt sentence is generated and input to the generative AI model. For example, a prompt sentence such as "Compare the characteristics and prices of product A and product B, and summarize which is more competitive" can be used.

[0081] Adding specific examples

[0082] When a user wants to conduct a competitive analysis of a new product, he or she can use the system by following the steps below.

[0083] 1. Information Collection:

[0084] The user inputs a list of products to be analyzed into the system.

[0085] The server uses a web scraping tool to collect information such as the characteristics, price, and customer reviews of each product.

[0086] 2. Data cleansing:

[0087] The server cleanses the collected data and converts it into a unified format. For example, if price information is expressed in different currency units, such as "$100" and "1000 yen," the server converts these into a unified currency unit (e.g., yen). Also, if customer ratings are expressed as strings, such as "★★★★★," the server converts them into numbers (e.g., 5).

[0088] 3. Data Analysis:

[0089] The server performs comparative analysis between products based on the cleansed data. For example, it calculates that the average price of smartphone A is 50,000 yen and the average price of smartphone B is 60,000 yen. It also analyzes the distribution of customer ratings and confirms that the average rating of smartphone A is 4.5 and the average rating of smartphone B is 4.0.

[0090] 4. Speed ​​up knowledge acquisition:

[0091] The server inputs the following prompt into the generative AI model: "Compare the features and prices of smartphone A and smartphone B, and summarize which one is more competitive."

[0092] Based on this prompt, the generative AI model summarizes the results of the comparison between smartphone A and smartphone B. For example, it generates a summary result such as, "Smartphone A is competitive because it is inexpensive and has high customer ratings."

[0093] In this way, the user can efficiently perform competitive analysis of merchandise and organize information.

[0094] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0095] Step 1:

[0096] Information gathering

[0097] Based on the product list entered by the user, the server collects information such as product characteristics, prices, and customer reviews from the Internet. Specifically, it uses a web scraping tool (e.g., BeautifulSoup, Scrapy) to obtain information about each product. The input is the product list provided by the user, and the output is the collected data such as product characteristics, prices, and customer reviews. For example, if the user enters "smartphone A" and "smartphone B," the server obtains the prices and customer reviews of these products from Amazon and other e-commerce sites.

[0098] Step 2:

[0099] Data Cleansing

[0100] The server cleanses the collected data and converts it into the required format. Specifically, it uses a data processing library (e.g., Pandas) to remove unnecessary and duplicate data and convert price information into a unified currency unit. It also quantifies customer ratings. The input is the collected raw data, and the output is cleansed, consistent data. For example, if price information is expressed in different currency units, such as "$100" and "1,000 yen," the server converts it into a unified currency unit (e.g., yen). Also, if customer ratings are expressed as strings, such as "★★★★★," the server converts them into numbers (e.g., 5).

[0101] Step 3:

[0102] Data analysis

[0103] The server performs comparative analysis between products based on the cleansed data. Specifically, it uses data analysis tools (e.g., NumPy, Scikit-learn) to calculate the average price, distribution of customer ratings, etc. The input is the cleansed data, and the output is the comparison results between products. For example, it calculates that the average price of smartphone A is 50,000 yen, and the average price of smartphone B is 60,000 yen. It also analyzes the distribution of customer ratings and confirms that the average rating of smartphone A is 4.5, and the average rating of smartphone B is 4.0.

[0104] Step 4:

[0105] Speed ​​up knowledge acquisition

[0106] The server uses a generative AI model (e.g., GPT-4) to automatically summarize the features and competitiveness of products based on the collected information. Specifically, it generates prompts to be input into the generative AI model and inputs them into the model. The inputs are the cleansed data and the generated prompts, and the output is a summary of the product comparison results. For example, a prompt might be used such as, "Compare the features and prices of product A and product B, and summarize which is more competitive." The generative AI model summarizes the comparison results between product A and product B based on this prompt. For example, it generates a summary such as, "Product A is competitive because it is inexpensive and has high customer ratings."

[0107] In this way, the user can efficiently perform competitive analysis of merchandise and organize information.

[0108] (Application example 1)

[0109] Next, a description will be given of Application Example 1 of Embodiment 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."

[0110] In today's product market, efficiently collecting information on the characteristics, prices, customer reviews, and other aspects of various products and quickly and accurately conducting comparative analysis with competing products is an important challenge for improving sales efficiency and customer satisfaction. However, conventional methods require a great deal of time and effort to collect and analyze information, slowing down the speed of knowledge acquisition. In addition, there was a lack of a way to automatically calculate the recommended product ranking and present it appropriately to users, making it difficult for sales representatives and consumers to select the most suitable product.

[0111] 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.

[0112] In this invention, the server includes means for performing competitive analysis and information organization of various products, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for collecting information such as product characteristics, price, and customer reviews and generating a report comparing the product with other similar products, means for performing comparative analysis of products using a generative AI model, and means for presenting a recommended ranking of products to the user using prompt sentences. This automates the collection of product information and comparative analysis, improves the speed of knowledge acquisition, and enables sales representatives and consumers to quickly select the optimal product.

[0113] "Means for conducting competitive analysis and organizing information on a variety of products" refers to a means for collecting information on the characteristics, prices, customer reviews, etc. of multiple products available on the market, and organizing this information to evaluate their competitiveness.

[0114] "Means aimed at improving the efficiency of sales activities" are means for quickly providing necessary information and optimizing business processes so that sales representatives can carry out their work efficiently.

[0115] "Means for automating comparative analysis including competing services" refers to means for automatically conducting comparative analysis with competing products and services based on information such as product characteristics, price, and customer evaluations.

[0116] "Means for increasing the speed of knowledge acquisition" refers to means for quickly processing collected information and acquiring the necessary knowledge in a short amount of time.

[0117] "Means for collecting information on product characteristics, price, customer reviews, etc., and generating a report for comparing with other similar products" refers to means for collecting detailed information on a product and automatically generating a report for comparing with other similar products based on that information.

[0118] "Means for comparative analysis of products using generative AI models" refers to means for using artificial intelligence models to analyze information such as product characteristics, prices, and customer reviews, and for comparative analysis of products.

[0119] "Means for presenting users with a recommended ranking of products using prompt sentences" refers to a means for generating and displaying prompt sentences for presenting users with a recommended ranking of products based on the analysis results obtained by a generative AI model.

[0120] The following system configuration will be described as an embodiment of the present invention.

[0121] System Configuration

[0122] This system consists of a server, a user terminal, and a database. The server collects information such as product characteristics, prices, and customer reviews, and performs comparative analysis of products using a generative AI model. The user terminal provides an interface that allows users to search for products and check the recommended product ranking using prompts. The database stores the collected product information.

[0123] Hardware and software used

[0124] Hardware: Server, smartphone (user device)

[0125] Software: Python, BeautifulSoup, requests, pandas, scikit-learn, generative AI models

[0126] Data processing and calculation

[0127] The server first collects information such as product characteristics, price, and customer ratings. Specifically, it uses the requests library to retrieve product information from the specified URL and parses the HTML using BeautifulSoup. Next, it stores the collected information in a pandas data frame and vectorizes the product characteristics using TfidfVectorizer. It calculates the text similarity between products using cosine_similarity and performs a comparative analysis of the products using a generative AI model.

[0128] When a user searches for a product, the user device generates a prompt based on the comparative analysis results obtained from the server and presents the user with a recommended ranking of products. The prompt is generated based on the analysis results obtained by the generative AI model.

[0129] Specific examples

[0130] For example, suppose a user opens the "Smart Shopping Assistant" app on their smartphone and enters "Smartphone A" in the search bar. The app will automatically collect the features, price, and customer reviews of "Smartphone A" and compare it with other similar smartphones (e.g., Smartphone B, Smartphone C). A comparison report will be generated and the user will be prompted with the following:

[0131] Prompt Sentence Examples

[0132] Open the "Smart Shopping Assistant" app and enter "Smartphone A" in the search bar. The app will automatically collect the features, price, and customer reviews of Smartphone A and compare it with other smartphones (e.g., Smartphone B, Smartphone C). A comparison report will be displayed, allowing you to easily decide which smartphone is best for you.

[0133] In this way, the user can quickly select the most suitable product.

[0134] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0135] Step 1:

[0136] The user searches for a product on their device.

[0137] Input: The product name entered by the user in the search bar (e.g., "Smartphone A").

[0138] How it works: A user opens the app on their smartphone and enters the name of a product in the search bar.

[0139] Output: The product name is sent to the server.

[0140] Step 2:

[0141] The server collects information about the products.

[0142] Input: The product name entered by the user.

[0143] How it works: The server uses the requests library to retrieve product information from the specified URL. It then uses BeautifulSoup to parse the HTML and extract information such as product characteristics, price, and customer ratings.

[0144] Output: Information such as product characteristics, price, and customer ratings is saved in a database.

[0145] Step 3:

[0146] The server vectorizes the product information.

[0147] Input: Product characteristics information stored in the database.

[0148] How it works: The server stores product information in a pandas data frame and uses TfidfVectorizer to vectorize the product characteristics.

[0149] Output: Vectorized product characteristics information.

[0150] Step 4:

[0151] The server calculates the similarity between the products.

[0152] Input: Vectorized product characteristics information.

[0153] Operation: The server uses cosine_similarity to calculate the text similarity between products.

[0154] Output: Similarity matrix between products.

[0155] Step 5:

[0156] The server uses the generated AI model to perform a comparative analysis of the products.

[0157] Input: Similarity matrix between products.

[0158] How it works: The server uses the generative AI model to analyze information such as product characteristics, price, and customer reviews, and conducts comparative analysis between products.

[0159] Output: Comparative analysis results of products.

[0160] Step 6:

[0161] The server generates a prompt.

[0162] Input: Results of comparative analysis of products.

[0163] Operation: Based on the analysis results obtained by the generative AI model, the server generates a prompt message to present the user with a recommended ranking of products.

[0164] Output: The prompt statement.

[0165] Step 7:

[0166] The terminal displays the prompt.

[0167] Input: The prompt text sent by the server.

[0168] Operation: The user terminal displays the prompt received from the server on the screen.

[0169] Output: User can check the recommended ranking of products.

[0170] Example 2

[0171] Next, a description will be given of Example 2 of Form 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."

[0172] Traditionally, competitive analysis and information organization for products have often been done manually, which takes time and effort, making it difficult to streamline sales activities. Furthermore, there was a lack of automated comparative analysis, including that of competing services, making it difficult to speed up knowledge acquisition. Furthermore, there was a need for a system that could efficiently collect vast amounts of information on the Internet and automatically calculate the recommended ranking of products.

[0173] 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.

[0174] In this invention, the server includes means for performing competitive analysis and information organization of various products, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet, means for automatically calculating a recommended ranking of products based on the collected information using a machine learning algorithm, and means for providing the calculated recommended ranking to users. This allows for efficient competitive analysis of products and information organization, thereby improving the efficiency of sales activities. Furthermore, the comparative analysis including competing services is automated, increasing the speed of knowledge acquisition. Furthermore, it is possible to efficiently collect vast amounts of information on the Internet and automatically calculate a recommended ranking of products.

[0175] "Competitive analysis of diverse products" involves comparing products of different types and categories and evaluating their competitiveness in their respective markets.

[0176] "Information organization" means systematically classifying collected data and arranging it in an easy-to-understand format.

[0177] "Improving sales efficiency" means optimizing the sales process and making effective use of time and resources.

[0178] "Automated comparative analysis" means that the system automatically compares products without having to do it manually.

[0179] "Increasing the speed of knowledge acquisition" means improving the ability to quickly gather and understand necessary information.

[0180] "Internet databases and websites" means information sources that are accessible online.

[0181] "Characteristics of the product" refers to the specific features and specifications of the product.

[0182] "Price" means the selling price of the product.

[0183] "Customer ratings" refers to feedback and reviews from customers who have purchased a product.

[0184] "Automatically collect information" means that the system obtains the required data without manual intervention.

[0185] A "machine learning algorithm" is a computational method for learning patterns based on data and making predictions and classifications.

[0186] "Recommended Ranking" refers to a prioritized list of products that have been evaluated.

[0187] "Providing to the user" means displaying the results calculated by the system to the user.

[0188] This invention is a system that collects information such as product characteristics, prices, and customer reviews, and performs comparative analysis between products based on this information. A specific embodiment of this system is described below.

[0189] Hardware and software used

[0190] Server: This is the central component for collecting information, processing data, conducting comparative analysis, and providing results. The server should be a computer equipped with a high-performance processor and sufficient memory.

[0191] Web scraping libraries: Use Python libraries such as BeautifulSoup and Scrapy to automatically scrape information from databases and websites on the internet.

[0192] Data processing libraries: Use Python libraries such as Pandas to shape the collected data and convert it into the required format.

[0193] Machine learning libraries: Python libraries such as Scikit-learn and TENSORFLOW (registered trademark) are used to calculate the recommended ranking of products based on collected data.

[0194] Web application framework: Use a framework such as Flask or Django to build a web interface to provide the calculated recommendation rankings to users.

[0195] Explanation of program processing

[0196] 1. Information gathering

[0197] The server uses a web scraping library to automatically collect information such as product characteristics, prices, and customer reviews from databases and websites on the Internet.

[0198] Specifically, the server accesses a specific website and extracts price information and customer ratings from the product details page.

[0199] 2. Data processing

[0200] The server uses a data processing library to format the collected data and convert it into the required format.

[0201] Specifically, the server converts the collected pricing information into a numerical format and converts the customer ratings from text to a numerical score.

[0202] 3. Comparative analysis

[0203] The server uses a machine learning library to calculate the recommended ranking of products based on the formatted data.

[0204] Specifically, the server takes the price and customer ratings as input and calculates the recommended ranking of products using a random forest algorithm.

[0205] 4. Providing results

[0206] The server uses a web application framework to display the results and provide the calculated recommendation ranking to the user.

[0207] Specifically, the server generates a dashboard displaying the ranking of recommendations, which the user can access through a web browser.

[0208] Examples and prompts

[0209] Example: The server collects prices and customer ratings for "smartphones" from a specific website and uses a machine learning algorithm to calculate the recommended ranking.

[0210] Example prompt: "Collect smartphone prices and customer reviews from a specific website and calculate the best smartphone recommendation."

[0211] This system allows users to efficiently collect vast amounts of information on the Internet and perform comparative analysis. This allows for efficient competitive analysis of products and information organization, making sales activities more efficient. It also automates comparative analysis, including that of competing services, increasing the speed at which knowledge can be acquired. Furthermore, it makes it possible to efficiently collect vast amounts of information on the Internet and automatically calculate the recommended ranking of products.

[0212] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0213] Step 1:

[0214] Information gathering

[0215] The server uses a web scraping library (e.g., BeautifulSoup, Scrapy) to automatically collect information such as product characteristics, prices, and customer reviews from databases and websites on the Internet.

[0216] Input: A specific website URL or search keyword (e.g., "smartphone").

[0217] Specific operations: The server accesses a specific website and extracts price information and customer reviews from the product detail page. For example, the server searches for the keyword "smartphone" and accesses the detail page of each product from the search results page to collect information.

[0218] Output: Collected data such as product characteristics, prices, and customer ratings.

[0219] Step 2:

[0220] Data Processing

[0221] The server uses a data processing library (e.g., Pandas) to format the collected data and convert it into the required format.

[0222] Input: Data collected in Step 1, such as product characteristics, price, and customer ratings.

[0223] What happens: The server converts the collected price information into a numeric format and converts the customer ratings from text to a numeric score. For example, the server converts a price of "$299.99" to the numeric value 299.99, and converts a rating of "4.5 out of 5 stars" to the numeric value 4.5.

[0224] Output: Formatted data such as product characteristics, price, and customer ratings.

[0225] Step 3:

[0226] comparative analysis

[0227] The server uses machine learning libraries (e.g., Scikit-learn, TensorFlow) to calculate the recommended ranking of products based on the formatted data.

[0228] Input: Data such as product characteristics, price, and customer ratings formatted in Step 2.

[0229] Specific operation: The server inputs the price and customer rating and uses the random forest algorithm to calculate the product recommendation ranking. For example, the server sets the algorithm to prioritize recommending products with low prices and high customer ratings.

[0230] Output: The calculated recommended ranking of products.

[0231] Step 4:

[0232] Providing results

[0233] The server displays the results using a web application framework (e.g., Flask, Django) to provide the calculated recommendation ranking to the user.

[0234] Input: The recommended product ranking calculated in Step 3.

[0235] Specific behavior: The server generates a dashboard displaying the ranking of recommendations and makes it accessible to the user through a web browser. For example, the user can access a specific URL in their browser and see a page displaying the ranking of recommendations.

[0236] Output: A web page with the ranking of recommendations that will be served to the user.

[0237] (Application example 2)

[0238] Next, a description will be given of Application Example 2 of Form 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."

[0239] Traditionally, competitive analysis and information organization for products was often done manually, which required time and effort, and the information was often incomplete and inaccurate. Furthermore, comparative analysis between products and calculation of recommended rankings were also done manually, making it difficult to conduct efficient sales activities. Furthermore, there was a lack of means to collect and properly analyze the vast amount of information available on the Internet, making it difficult to recommend optimal products to users. To solve these issues, a system was needed that could automate the entire process, from information collection to analysis and proposals, efficiently and accurately.

[0240] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0241] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet, means for automatically calculating a recommended ranking of products using a machine learning algorithm based on the collected information, and means for proposing optimal products to users. This makes it possible to efficiently and accurately perform processes from information collection to analysis and proposals.

[0242] "Means for conducting competitive analysis and organizing information on various products" is a method for evaluating the competitiveness of different types of products and systematically organizing that information.

[0243] "Measures aimed at improving sales efficiency" are methods for optimizing sales processes and making effective use of time and resources.

[0244] "Means for automating comparative analysis including competing services" refers to a method for automatically conducting comparative analysis including competing services or products.

[0245] "Means to increase the speed of knowledge acquisition" are methods for quickly acquiring necessary information and knowledge.

[0246] "Means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet" refers to a method for automatically collecting data about products from various sources on the Internet.

[0247] "Means for automatically calculating the recommended ranking of products using a machine learning algorithm based on collected information" refers to a method for automatically calculating the recommended ranking of products using machine learning technology based on collected data.

[0248] "Means for suggesting optimal products to users" refers to methods for suggesting optimal products based on the user's needs and preferences.

[0249] A system for carrying out this invention has the following configuration: A server includes means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet, means for automatically calculating a recommended product ranking using a machine learning algorithm based on the collected information, and means for suggesting optimal products to users.

[0250] Hardware and software used

[0251] Hardware: Servers, smartphones

[0252] Software: Python, BeautifulSoup (for web scraping), Scikit-learn (for machine learning), Flask (for backend API)

[0253] Data processing and calculation

[0254] Web scraping

[0255] The server uses BeautifulSoup to collect information such as product characteristics, prices, and customer reviews from the specified website. The collected data is saved in a CSV file.

[0256] Data analysis

[0257] The server trains a machine learning model based on the collected data using Scikit-learn, and uses the trained model to calculate the recommended ranking of products.

[0258] Product suggestion

[0259] The server uses Flask to build a backend API and returns recommended products in response to user requests. Users can access this API using their smartphones to receive optimal product suggestions.

[0260] Specific examples

[0261] For example, if a user searches for "smartphone," the following prompt sentence is input into the generative AI model:

[0262] import requests

[0263] from bs4 import BeautifulSoup

[0264] import pandas as pd

[0265] from sklearn.ensemble import RandomForestClassifier

[0266] from flask import Flask, request, jsonify

[0267] app = Flask(__name__)

[0268] Web scraping

[0269] def scrape_data():

[0270] url = "https: / / example.com / smartphones"

[0271] response = requests.get(url)

[0272] soup = BeautifulSoup(response.text, 'html.parser')

[0273] data = []

[0274] for item in soup.find_all('div', class_='product'):

[0275] name = item.find('h2').text

[0276] price = item.find('span', class_='price').text

[0277] rating = item.find('span', class_='rating').text <​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​Product suggestion API

[0290] @app.route(' / recommend', methods=['GET'])

[0291] def recommend():

[0292] model = train_model()

[0293] user_input = request.args.get('input')

[0294] This is where product recommendations are calculated based on user input.

[0295] Example: Returning recommended products

[0296] recommended_product = model.predict([[user_input['price'], user_input['rating']]])

[0297] return jsonify({'recommended_product': recommended_product})

[0298] if __name__ == '__main__':

[0299] scrape_data()

[0300] app.run(debug=True)

[0301] The program provides an API that collects smartphone information from designated websites, trains a machine learning model, and recommends the best smartphone for users.

[0302] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0303] Step 1:

[0304] The server accesses specified websites on the Internet and collects information such as product characteristics, prices, and customer reviews. Specifically, it uses BeautifulSoup to analyze the HTML structure of the webpage and extract the necessary data. The input is the website URL, and the output is a list of product information.

[0305] Step 2:

[0306] The server saves the collected product information in a CSV file. Specifically, it creates a data frame using the Pandas library and saves it in CSV format. The input is a list of product information, and the output is a CSV file.

[0307] Step 3:

[0308] The server reads the saved CSV file and trains a machine learning model. Specifically, it preprocesses the data using Scikit-learn and trains a random forest classifier. The input is the CSV file, and the output is the trained machine learning model.

[0309] Step 4:

[0310] The server uses Flask to build a backend API and accepts requests from users. Specifically, users access the API using their smartphones and enter information such as product characteristics, price, and customer ratings. The input is the user's request data, and the output is a list of recommended products.

[0311] Step 5:

[0312] The server uses a trained machine learning model to calculate the recommended ranking of products based on the request data from the user. Specifically, the model inputs the product characteristics, price, customer ratings, and other data entered by the user, and calculates the recommended ranking. The input is the user's request data, and the output is a list of recommended products.

[0313] Step 6:

[0314] The server returns the calculated list of recommended products to the user. Specifically, it uses Flask to return the list of recommended products in JSON format as an API response. The input is the list of recommended products, and the output is the response to the user.

[0315] Example 3

[0316] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0317] In conventional sales activities, competitive analysis, information organization, and comparative analysis of products are often done manually, resulting in inefficiencies. Furthermore, there was a lack of a way for sales representatives to quickly obtain the necessary information and conduct effective sales activities. Furthermore, the process for calculating the recommended ranking was complicated, and there was a lack of a way to display it visually in an easy-to-understand manner.

[0318] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0319] In this invention, the server includes means for performing competitive analysis and information organization for various products, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for calculating a recommendation ranking using a generative AI model, means for generating prompt sentences and inputting them into the generative AI model, means for generating a dashboard that visually displays the recommendation ranking, and means for displaying the dashboard on a terminal, thereby enabling sales representatives to quickly obtain necessary information and conduct effective sales activities.

[0320] "Merchandise" is a general term for the products and services sold.

[0321] "Competitive analysis" is the process of comparing competitors and products in the same market and evaluating their strengths and weaknesses.

[0322] "Information organization" is the process of systematically classifying collected data and information and arranging it in an easy-to-understand form.

[0323] "Sales activities" are a series of actions taken to propose products and services to customers and promote sales.

[0324] "Efficiency" refers to optimizing work and processes, eliminating waste, and carrying them out effectively.

[0325] "Comparative analysis" is the process of comparing multiple subjects and identifying their differences and similarities.

[0326] "Automation" refers to the process by which machines or software perform tasks automatically, without human intervention.

[0327] "Speed ​​of knowledge acquisition" is an indicator of how quickly necessary information and knowledge can be acquired.

[0328] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate new information or predictions from data.

[0329] "Recommendation Rank" refers to the result of prioritizing targets based on specific criteria.

[0330] A "prompt" refers to an instruction or question input to a generative AI model.

[0331] A "dashboard" is an interface for visually displaying data and information.

[0332] "Terminal" refers to a device that allows a user to input and output information.

[0333] The present invention is a system for automating competitive analysis, information organization, and comparative analysis of commercial products, with the aim of improving the efficiency of sales activities. A specific embodiment of this system will be described below.

[0334] The server first collects sales representative activity data and customer information. This data is obtained from CRM systems and sales support tools. Specifically, it connects to these systems via API to obtain the necessary data. Common examples of CRM systems include Salesforce and HubSpot.

[0335] Next, the server analyzes the collected data. For analysis, it uses the Python pandas library. The server cleans the data and extracts necessary features. For example, it extracts features such as customer purchasing history and the frequency of sales activities.

[0336] The server then uses the generative AI model to calculate a recommendation ranking for each salesperson. For example, OpenAI's (registered trademark) GPT-4 is used as the generative AI model. The server generates a prompt sentence and inputs it into the AI ​​model. An example of a specific prompt sentence is, "Based on Salesperson A's customer list, please calculate the recommendation ranking for each customer."

[0337] The server generates a dashboard that visually displays the recommendation ranking obtained from the generative AI model. The dashboard is built using React, a JavaScript (registered trademark) framework. The server passes data including the recommendation ranking to the React component to generate the dashboard.

[0338] Finally, the device (sales representative's PC or tablet) displays the dashboard generated by the server. The sales representative accesses the dashboard through a browser and checks the recommended ranking. Specifically, the device opens a browser, accesses the server's URL, and displays the generated dashboard.

[0339] For example, when calculating the recommendation ranking based on the customer list of sales representative A, the following specific operations are performed:

[0340] 1. The server calls the CRM system's API and retrieves sales representative A's activity log.

[0341] 2. The server uses the API of the sales support tool to obtain customer information for sales representative A.

[0342] 3. The server uses pandas to clean the data and extract features such as customer purchasing history and frequency of sales activities.

[0343] 4. The server generates a prompt sentence: "Based on Salesperson A's customer list, calculate the recommendation ranking for each customer." and inputs it into GPT-4.

[0344] 5. The server passes the recommendation ranking obtained from GPT-4 to the React application and generates a dashboard.

[0345] 6. The device opens a browser, accesses the server URL, and displays the generated dashboard.

[0346] This allows the salesperson to quickly obtain the necessary information and carry out effective sales activities. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0347] Step 1: Data collection

[0348] The server collects sales representative activity data and customer information. As input, it uses the API of the CRM system and sales support tool. Specifically, the server calls the API of the CRM system to obtain the sales representative activity log. It also obtains customer information using the API of the sales support tool. As output, the collected data is stored in a database.

[0349] Step 2: Data analysis

[0350] The server analyzes the collected data. As input, it uses the sales activity data and customer information stored in the database. Specifically, the server uses Python's pandas library to create a data frame and handle missing values. It also extracts features such as customer purchasing history and sales activity frequency. The analyzed data is obtained as output.

[0351] Step 3: Calculating the recommended ranking

[0352] The server uses a generative AI model to calculate the recommendation ranking. The parsed data and a prompt are used as input. Specifically, the server generates a prompt such as "Based on Salesperson A's customer list, please calculate the recommendation ranking for each customer." and inputs it into the generative AI model (e.g., GPT-4). The output from the generative AI model is the recommendation ranking.

[0353] Step 4: Generate a dashboard

[0354] The server generates a dashboard that visually displays the recommendation rankings. It uses the recommendation ranking data as input. Specifically, the server uses React, a JavaScript framework, to generate tables and graphs that display the recommendation rankings. The generated dashboard is obtained as output.

[0355] Step 5: View the dashboard

[0356] The terminal displays the dashboard generated from the server. As input, it uses a browser to access the server's URL. Specifically, the terminal opens a browser, accesses the server's URL, and displays the generated dashboard. As output, it displays a dashboard where the sales representative can check the recommendation ranking.

[0357] This allows sales personnel to quickly obtain the necessary information and carry out effective sales activities.

[0358] (Application example 3)

[0359] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0360] In traditional sales activities, competitive analysis of products, organizing information, and comparative analysis with competing services are often done manually, resulting in inefficiency. Furthermore, there is a lack of support for sales representatives to quickly grasp information and develop optimal sales strategies. As a result, sales activities are not streamlined, making it difficult to maximize sales. Furthermore, there is a lack of ways to effectively utilize customer data and sales history, making it difficult to optimize sales strategies.

[0361] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0362] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for providing a dashboard that visually displays recommended rankings, and means for analyzing customer data and sales history using a generative AI model and proposing an optimal sales strategy, thereby enabling sales representatives to quickly grasp information and develop an optimal sales strategy.

[0363] A "multi-product competitive analysis" is an evaluation and comparison of the competitive landscape in a market for different types of products.

[0364] "Information organization" means systematically classifying collected data and information and organizing it into an easy-to-understand form.

[0365] "Improving sales efficiency" means optimizing sales processes and making effective use of time and resources to maximize sales results.

[0366] "Comparative analysis including competing services" means comparing and analyzing your company's products with those of your competitors from various perspectives.

[0367] "Increasing the speed of knowledge acquisition" means improving the ability to quickly gather and understand necessary information and knowledge.

[0368] A "dashboard that visually displays recommended rankings" is an interface that visually and clearly displays which products and customers sales representatives should prioritize.

[0369] A "generative AI model" is a model that uses machine learning algorithms to analyze data and make predictions and classifications.

[0370] "Customer Data" refers to information about a customer, including age, gender, purchase history, number of interactions, etc.

[0371] "Sales history" is a record of past sales activities, and is data indicating which products were sold, when, and to which customers.

[0372] "Proposing the optimal sales strategy" means presenting specific policies and action plans for carrying out effective sales activities based on collected data.

[0373] The following system configuration will be described as an embodiment of the present invention.

[0374] The server includes means for conducting competitive analysis and organizing information on a variety of products, means for streamlining sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for providing a dashboard that visually displays recommended rankings, and means for analyzing customer data and sales history using a generative AI model to propose optimal sales strategies.

[0375] Hardware and software used

[0376] Hardware: Servers, smartphones

[0377] Software: Python, Pandas, Scikit-learn, Matplotlib, Streamlit

[0378] Data processing and calculation

[0379] 1. Data Loading: The server loads a dataset containing customer data and sales history, including customer age, purchase history, number of interactions, etc.

[0380] 2. Feature and target setting: The server sets the customer's age, purchase history, and number of interactions as features and the likelihood of purchase as a target.

[0381] 3. Data Splitting: The server splits the data into training data and test data.

[0382] 4. Train the model: The server trains the model using a random forest classifier.

[0383] 5. Calculation of recommendation ranking: The server makes predictions on the test data and calculates the recommendation ranking.

[0384] 6. Creating a dashboard: The server uses Streamlit to create a dashboard that visually displays the recommendation rankings.

[0385] Specific examples

[0386] For example, Customer A is 35 years old, has made 5 purchases in the past 6 months, and has 10 interactions, while Customer B is 28 years old, has made 2 purchases in the past 6 months, and has 5 interactions. Based on this data, the server uses a generative AI model to predict the likelihood of purchase and calculate a recommendation ranking.

[0387] Prompt Sentence Examples

[0388] Use customer data to create a dashboard that predicts purchase likelihood and calculates recommendation rankings. Use customer age, purchase history, and number of interactions as features to train a model using a random forest classifier. Use Streamlit to create a dashboard that visually displays the recommendation rankings.

[0389] In this way, the server provides a system that enables sales personnel to quickly grasp information and formulate optimal sales strategies.

[0390] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0391] Step 1:

[0392] The server loads a dataset containing customer data and sales history. Specifically, it loads data from the sales_data.csv file and retrieves information such as customer age, purchase history, and number of interactions. The input is the sales_data.csv file, and the output is customer data in a data frame format.

[0393] Step 2:

[0394] The server sets features and targets from customer data. Specifically, the customer's age, purchase history, and number of interactions are set as features (X), and the likelihood of purchase is set as target (y). The input is customer data in data frame format, and the output is a dataset of features (X) and targets (y).

[0395] Step 3:

[0396] The server splits the data into training data and test data. Specifically, it uses Scikit-learn's train_test_split function to split the dataset into 80% training data and 20% test data. The input is a dataset of features (X) and targets (y), and the output is training data (X_train, y_train) and test data (X_test, y_test).

[0397] Step 4:

[0398] The server trains a model using a random forest classifier. Specifically, it uses Scikit-learn's RandomForestClassifier to train a model based on training data (X_train, y_train). The input is the training data (X_train, y_train), and the output is a trained random forest model.

[0399] Step 5:

[0400] The server makes predictions on the test data and calculates the recommendation ranking. Specifically, it uses a trained random forest model to make predictions on the test data (X_test) and calculates the likelihood of purchase. The input is the test data (X_test) and the trained model, and the output is the prediction result (likelihood of purchase).

[0401] Step 6:

[0402] The server uses Streamlit to create a dashboard that visually displays the recommendation ranking. Specifically, it calculates the recommendation ranking based on the prediction results and creates graphs and tables that visually display each customer's likelihood of purchase. The input is the prediction result (likelihood of purchase), and the output is a visually displayed dashboard.

[0403] In this way, the server provides a system that enables sales personnel to quickly grasp information and formulate optimal sales strategies.

[0404] 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.

[0405] "Example 1"

[0406] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes a user's emotions and adjusts the recommendation ranking of products based on those emotions. Specifically, it raises the recommendation ranking for products that the user feels happy or excited about, and lowers the recommendation ranking for products that the user feels displeasure or anger about. This emotion engine recognizes emotions from the user's facial expressions, tone of voice, and content posted on social media.

[0407] "Example 2"

[0408] Another embodiment is a system in which an emotion engine adjusts the method of providing information to a salesperson. This system adjusts the timing and content of information provided to the salesperson according to the user's emotions. Specifically, when a user shows joy or excitement, the system provides information that encourages sales activities toward that user, and conversely, when the user shows displeasure or anger, the system provides information that discourages sales activities toward that user.

[0409] "Example 3"

[0410] Furthermore, as a concrete example, let's consider a scenario in which a system incorporating an emotion engine is actually in operation. Suppose a user expresses joy toward a particular product. The emotion engine captures this information and raises the product's recommendation ranking. This information is then provided to a sales representative, who then uses this information to conduct sales activities toward the user. In this way, a system incorporating an emotion engine accurately captures user emotions and reflects them in the product recommendation ranking and sales activities, thereby achieving more effective sales activities.

[0411] The processing flow of each embodiment will be described below.

[0412] "Example 1"

[0413] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are recognized from the user's facial expressions, tone of voice, and the content of posts on social media.

[0414] Step 2: The emotion engine adjusts the recommendation ranking based on the emotions it recognizes. Specifically, it raises the recommendation ranking for products that make the user feel happy or excited, and lowers the recommendation ranking for products that make the user feel displeased or angry.

[0415] "Example 2"

[0416] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are recognized from the user's facial expressions, tone of voice, and the content of posts on social media.

[0417] Step 2: Based on the emotions recognized by the emotion engine, the way information is provided to the salesperson is adjusted. Specifically, when the user shows joy or excitement, information is provided that encourages sales activities toward that user. Conversely, when the user shows displeasure or anger, information is provided that discourages sales activities toward that user.

[0418] "Example 3"

[0419] Step 1: Let's say a user expresses joy about a particular product. This information is captured by the emotion engine.

[0420] Step 2: The emotional engine increases the product's recommendation ranking.

[0421] Step 3: The emotion engine provides that information to the salesperson.

[0422] Step 4: The sales representative uses this information to conduct sales activities toward the user.

[0423] Example 1

[0424] Next, a description will be given of Example 1 of Form 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."

[0425] Conventional competitive analysis systems for products can collect information such as product characteristics, prices, and customer ratings, and perform comparative analysis. However, they are unable to adjust the recommendation ranking based on user sentiment, making it difficult to increase user satisfaction. Furthermore, the collected information is often managed and analyzed manually, making it difficult to conduct efficient sales activities. Furthermore, there is a lack of means to increase the speed of knowledge acquisition, making this insufficient in today's business environment, where rapid decision-making is required.

[0426] 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.

[0427] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for recognizing a user's emotions and adjusting the ranking of recommended products based on the emotions, means for storing collected information in a database, means for analyzing collected data, means for recognizing emotions from a user's facial expressions, tone of voice, and text data, and means for displaying the recommendation results through a user interface. This enables product recommendations that take user emotions into consideration, thereby increasing user satisfaction. Furthermore, the automation of information collection, management, and analysis enables efficient sales activities and supports rapid decision-making.

[0428] "Diverse merchandise" refers to goods and services that belong to different types or categories.

[0429] "Competitive analysis" refers to the process of comparing multiple products and evaluating their respective strengths and weaknesses.

[0430] "Information organization" refers to the systematic classification of collected data and arranging it in a form that is easy to understand.

[0431] "Improving sales efficiency" refers to optimizing sales processes and making effective use of time and resources.

[0432] "Automated comparative analysis" refers to the process of comparing products using a system rather than manually.

[0433] "Increasing the speed of knowledge acquisition" refers to improving the ability to quickly gather and understand necessary information.

[0434] "Recognizing user emotions" refers to analyzing emotions from the user's facial expressions, tone of voice, text data, etc.

[0435] "Adjusting the recommendation order" refers to changing the priority of products based on the user's emotional data.

[0436] "Storing in a database" refers to storing collected information in a database system.

[0437] "Analyzing data" refers to analyzing collected data using statistical methods and algorithms.

[0438] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[0439] This invention is a system for conducting competitive analysis and information organization for various products, specifically including means for collecting information such as product characteristics, prices, and customer reviews, and automating comparative analysis between products based on this information. It also includes means for increasing the speed of knowledge acquisition and means for recognizing user emotions and adjusting the order of recommended products based on those emotions.

[0440] The server uses a web scraping tool (e.g., BeautifulSoup, Scrapy) to collect information from the Internet, such as product characteristics, prices, and customer reviews. The collected data is stored in a database such as MySQL or PostgreSQL. The server uses Python libraries such as Pandas and NumPy to analyze the collected data and compare products.

[0441] The device uses a camera to recognize the user's facial expressions and analyzes them using libraries such as OpenCV and Dlib. The device also uses a microphone to collect the user's tone of voice and performs voice analysis using libraries such as Librosa. The device also collects social media posts and performs text analysis using libraries such as NLTK and Transformers.

[0442] The server adjusts the recommendation ranking of products based on the user's emotional data obtained from the emotion engine. Specifically, it raises the recommendation ranking for products that the user feels happy or excited about, and lowers the recommendation ranking for products that the user feels displeasure or anger about. The terminal displays the most suitable products for the user based on the recommendation ranking received from the server. A list of recommended products is displayed through the user interface, and detailed information is provided.

[0443] As a concrete example, consider a user looking for a new smartphone. The server collects the characteristics (e.g., battery life, camera performance), price, and customer ratings of each smartphone. Based on the collected data, it calculates an overall rating for each smartphone and performs a comparative analysis. If the user expresses a happy expression after reading a review of a particular smartphone, it raises the recommendation ranking of that smartphone. Based on the user's emotional data, it adjusts the recommendation ranking and suggests the most suitable smartphone.

[0444] Example prompt sentence:

[0445] "I'm looking for a new smartphone. Can you recommend a model with a long battery life and a good camera?"

[0446] In this way, the server and the terminal cooperate to realize a system that proposes the most suitable products to the user.

[0447] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0448] Step 1: Data collection

[0449] The server uses a web scraping tool to collect information such as product characteristics, prices, and customer reviews from the Internet. Specifically, the server accesses the specified URLs and analyzes the HTML structure to extract the required data. The input is a list of URLs containing product information, and the output is a data list containing product characteristics, prices, customer reviews, and other information.

[0450] Step 2: Database Management

[0451] The server stores the collected data in a database. Specifically, the server establishes a database connection and inserts the collected data into the appropriate tables. The input is the collected product data, and the output is the product data stored in the database.

[0452] Step 3: Data analysis

[0453] The server analyzes the collected data. Specifically, it uses Python libraries such as Pandas and NumPy to clean, filter, and aggregate the data and compare products. The input is product data obtained from the database, and the output is comparison data for the products as the analysis results.

[0454] Step 4: Emotion Recognition

[0455] The device uses a camera to recognize the user's facial expressions and analyzes them using libraries such as OpenCV and Dlib. The device also uses a microphone to collect the user's tone of voice and performs voice analysis using libraries such as Librosa. The device also collects social media posts and performs text analysis using libraries such as NLTK and Transformers. The inputs are the user's facial expressions, tone of voice, and text data, and the output is the user's emotional data.

[0456] Step 5: Adjust the recommended ranking

[0457] The server adjusts the recommendation ranking of products based on the user's emotional data obtained from the emotion engine. Specifically, it raises the recommendation ranking for products that the user feels happy or excited about, and lowers the recommendation ranking for products that the user feels displeasure or anger about. The inputs are the user's emotional data and product comparison data, and the output is the adjusted recommendation ranking for the products.

[0458] Step 6: Viewing recommended results

[0459] The terminal displays the most suitable products for the user based on the recommendation ranking received from the server. Specifically, the terminal displays a list of recommended products and provides detailed information through a user interface. The input is the adjusted recommendation ranking of the products, and the output is the list of products to be displayed to the user.

[0460] (Application example 1)

[0461] Next, a description will be given of Application Example 1 of Embodiment 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."

[0462] Conventional product competition analysis systems can collect information on product characteristics, prices, customer reviews, etc., and perform comparative analysis, but they have the problem of being unable to adjust the recommendation ranking based on user emotions, making it difficult to increase user satisfaction.In addition, they lack the functionality to recognize user emotions in real time and adjust the recommendation ranking based on that, which means they are unable to maximize users' purchasing motivation.

[0463] 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.

[0464] In this invention, the server includes means for performing competitive analysis and information organization of various products, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for recognizing a user's emotions and adjusting the ranking of recommended products based on those emotions, and means for recognizing emotions from the user's facial expressions, tone of voice, and text content. This makes it possible to recommend products that take the user's emotions into consideration, thereby increasing user satisfaction and maximizing the user's purchasing motivation.

[0465] "Diverse merchandise" is a general term for products and services with different types and characteristics.

[0466] "Competitive analysis" is the process of comparing the characteristics, prices, customer reviews, etc. of multiple products or services to evaluate their competitiveness.

[0467] "Information organization" is the process of systematically classifying collected data and arranging it in an easy-to-understand form.

[0468] "Improving sales efficiency" refers to optimizing sales processes and making effective use of time and resources.

[0469] "Automated comparative analysis" refers to the use of algorithms or software to automatically perform comparative analysis that would otherwise be performed manually.

[0470] "Increasing the speed of knowledge acquisition" means quickly gathering the necessary information and knowledge and making it available.

[0471] "Recognizing the user's emotions" refers to analyzing and understanding the user's emotions from facial expressions, tone of voice, text content, etc.

[0472] "Adjust recommended ranking" refers to changing the display order of products based on specific criteria.

[0473] "Facial expression" refers to changes in emotion and mood expressed through the movement of facial muscles.

[0474] "Vocal tone" refers to vocal characteristics such as pitch, strength, and rhythm, and is an element that conveys emotion and intention.

[0475] "Text content" refers to information including the meaning and emotion of sentences and words.

[0476] As an embodiment of the present invention, we will explain how to implement an emotion-based product recommendation system as a smartphone application. This system has the function of recognizing a user's emotion in real time and adjusting the order of recommended products based on that emotion.

[0477] Hardware and software used

[0478] Hardware

[0479] Smartphone: camera, microphone

[0480] software

[0481] OpenCV: Image processing library

[0482] Keras: A deep learning library

[0483] TextBlob: A text sentiment analysis library

[0484] Requests: HTTP request library

[0485] Data processing and calculation

[0486] Facial Emotion Recognition

[0487] The server captures the user's facial expressions using the smartphone camera and detects the face using OpenCV. The detected facial image is input to a Keras emotion recognition model to analyze the user's emotions. This model identifies emotions such as joy, anger, and surprise from facial expressions.

[0488] Emotion recognition of tone of voice

[0489] The server captures the user's voice using the smartphone's microphone and analyzes the voice data, analyzing voice characteristics such as pitch, intensity, and rhythm to identify the user's emotions.

[0490] Emotion recognition of text content

[0491] The server collects text content posted by users on social media and reviews, analyzes the sentiment of the text using TextBlob, and identifies positive, negative, and neutral sentiments.

[0492] Adjustment of recommended product rankings

[0493] The server adjusts the order of recommended products based on the collected emotional data. For example, if a user expresses joy or excitement, highly rated products that match that emotion are displayed first. On the other hand, if a user expresses displeasure or anger, products that do not match that emotion are displayed lower in the display order.

[0494] Specific examples

[0495] When a user is browsing products on their smartphone, if the camera detects that the user is smiling, the system will prioritize displaying highly rated products to that user. Also, if a user posts on social media, "This product is great!", the system will analyze that emotion and recommend similarly highly rated products.

[0496] Prompt Sentence Examples

[0497] Develop an application that recognizes a user's emotions in real time and recommends products based on those emotions. The application should recognize emotions from the user's facial expressions, tone of voice, and social media posts, and prioritize displaying products that indicate joy or excitement, and lower the ranking of products that indicate displeasure or anger.

[0498] In this way, it becomes possible to recommend products that take the user's emotions into consideration, thereby increasing user satisfaction and maximizing the user's purchasing motivation.

[0499] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0500] Step 1:

[0501] The server captures the user's facial expressions using the smartphone's camera. The input is real-time video from the camera, and the output is a facial image. Specifically, the camera detects the user's face and captures its image.

[0502] Step 2:

[0503] The server uses OpenCV to detect faces from the captured facial image. The input is the facial image obtained in step 1, and the output is an image with the facial area cut out. Specifically, the face detection algorithm identifies the position of the face and cuts out that area.

[0504] Step 3:

[0505] The server inputs the facial image into the Keras emotion recognition model and analyzes the user's emotions. The input is the facial image obtained in step 2, and the output is the emotion identification result (e.g., joy, anger, surprise, etc.). Specifically, the facial image is input into the model and the probability distribution of emotions is calculated.

[0506] Step 4:

[0507] The server captures the user's voice using the smartphone's microphone. The input is audio data from the microphone, and the output is an audio file. Specifically, the microphone records the user's voice and saves the data.

[0508] Step 5:

[0509] The server analyzes the audio data and identifies emotions from the tone of the voice. The input is the audio file obtained in step 4, and the output is the emotion identification result. Specifically, the audio analysis algorithm analyzes the pitch, intensity, and rhythm of the voice to identify the emotion.

[0510] Step 6:

[0511] The server collects text content posted by users on social media and reviews, and analyzes the sentiment of the text using TextBlob. The input is text data, and the output is the sentiment identification result. Specifically, the text analysis algorithm identifies positive, negative, or neutral sentiment in the text.

[0512] Step 7:

[0513] The server adjusts the product recommendation ranking based on the collected emotion data. The input is the emotion data obtained in steps 3, 5, and 6, and the output is the adjusted product recommendation ranking. Specifically, the server integrates the emotion data and applies an algorithm to change the product display order.

[0514] Step 8:

[0515] The server displays the adjusted product recommendation ranking on the user's smartphone. The input is the recommendation ranking obtained in step 7, and the output is a product list displayed on the user's smartphone screen. Specifically, the server generates a product list based on the recommendation ranking and displays it on the user's screen.

[0516] Example 2

[0517] Next, a description will be given of Example 2 of Form 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."

[0518] Conventional product information collection and analysis systems have difficulty efficiently collecting information such as product characteristics, prices, and customer reviews, and conducting comparative analysis. Furthermore, sales activities often had to be adjusted manually based on user sentiment, placing a heavy burden on sales representatives. This resulted in insufficient efficiency in sales activities, and sometimes led to inappropriate calculations of product recommendation rankings and inappropriate timing for providing information.

[0519] 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.

[0520] In this invention, the server includes means for collecting product information from websites, means for storing the collected data in a database, means for calculating a recommended product ranking using a machine learning algorithm, means for collecting user emotion data, means for analyzing user emotions using an emotion analysis algorithm, and means for adjusting the timing and content of information provided to sales representatives based on the analysis results. This enables efficient collection and analysis of product information and realizes appropriate adjustment of sales activities in accordance with user emotions.

[0521] A "website" is a collection of information made publicly available on the Internet and is a page with a specific URL.

[0522] "Product information" refers to information such as product characteristics, price, and customer reviews, and is detailed data about the product.

[0523] A "database" is a system for efficiently storing, managing, and searching collected data.

[0524] A "machine learning algorithm" is a computational method for learning patterns based on data and making predictions and classifications.

[0525] The "recommended ranking" is the result of evaluating and prioritizing products based on specific criteria.

[0526] "User emotion data" is information about emotions obtained from user input and actions.

[0527] An "emotion analysis algorithm" is a computational method for analyzing a user's text and behavioral data to identify their emotions.

[0528] A "sales representative" is someone whose job is to sell products and deal with customers.

[0529] "Timing of providing information" refers to the optimal time or moment for a sales representative to provide information to a user.

[0530] The "contents of information provided" refers to specific information that the sales representative provides to the user.

[0531] The present invention is a system for collecting and analyzing product information, calculating recommendation rankings, and adjusting sales activities based on user sentiment. A specific embodiment of this system will be described below.

[0532] Collection and analysis of product information

[0533] The server uses web scraping technologies such as Python's BeautifulSoup and Scrapy to collect information such as product characteristics, prices, and customer reviews, automatically gathering the necessary information from databases and websites on the Internet.

[0534] The terminal stores the collected data for subsequent processing. MySQL or PostgreSQL is generally used as the database.

[0535] The server automatically calculates the recommended product rankings based on the collected information using machine learning algorithms, specifically machine learning libraries such as Scikit-learn and TensorFlow.

[0536] Examples:

[0537] The server collects product information from a specific website.

[0538] The device stores the collected data in a MySQL database.

[0539] The server uses Scikit-learn to calculate the recommended ranking of products based on the collected data.

[0540] Example prompt for a generative AI model:

[0541] "Collect product information from specific websites and calculate recommendation rankings based on customer ratings and prices."

[0542] Adjusting information provision with an emotion engine

[0543] The server collects user input and behavioral data to analyze user sentiment. Specifically, it uses JavaScript and Python's Flask to collect user text input and click history.

[0544] The device stores the collected emotion data for subsequent processing. MongoDB or Firebase is commonly used as the database.

[0545] The server analyzes the user's emotions using a sentiment analysis algorithm, specifically using NLP (natural language processing) libraries such as NLTK and Transformers.

[0546] The server adjusts the timing and content of information provided to the sales representative based on the analysis results. For example, when the user shows signs of joy or excitement, the server provides information that encourages sales activities toward the user, and conversely, when the user shows signs of displeasure or anger, the server provides information that discourages sales activities toward the user.

[0547] Examples:

[0548] The server collects users' chat histories and performs sentiment analysis.

[0549] The device stores the collected data in MongoDB.

[0550] The server uses Transformers to analyze the user's emotions and provide appropriate information to the sales representative.

[0551] Example prompt for a generative AI model:

[0552] "Analyze users' chat histories and tailor the information you provide to your salespeople based on their sentiment."

[0553] The above is a specific embodiment for carrying out the present invention. This system enables efficient collection and analysis of product information, and realizes appropriate adjustment of sales activities according to user emotions.

[0554] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0555] Collection and analysis of product information

[0556] Step 1:

[0557] The server collects product information from the website.

[0558] Input: URL of a specific website

[0559] Specific operation: The server uses Python's BeautifulSoup or Scrapy to access the specified website and extract information such as product characteristics, price, and customer reviews.

[0560] Output: List of extracted product information

[0561] Step 2:

[0562] The terminal stores the collected data in a database.

[0563] Input: List of collected product information

[0564] Specific operation: The terminal uses MySQL or PostgreSQL to insert the collected product information into a database table.

[0565] Output: Product information stored in the database

[0566] Step 3:

[0567] The server calculates the recommended ranking of products using a machine learning algorithm.

[0568] Input: Product information stored in the database

[0569] Specific operation: The server uses Scikit-learn and TensorFlow to apply random forest algorithms based on product information to calculate the recommended ranking of products.

[0570] Output: A list of recommended products with ranking

[0571] Adjusting information provision with an emotion engine

[0572] Step 1:

[0573] The server collects the user's emotion data.

[0574] Input: User text input and click history

[0575] How it works: The server uses JavaScript and Python's Flask to collect users' chat history and click history.

[0576] Output: Collected emotion data

[0577] Step 2:

[0578] The device stores the collected emotion data in a database.

[0579] Input: Collected emotion data

[0580] Specific operation: The device inserts the collected emotion data into a database collection using MongoDB or Firebase.

[0581] Output: Emotion data stored in a database

[0582] Step 3:

[0583] The server analyzes the user's emotions using an emotion analysis algorithm.

[0584] Input: Emotion data stored in a database

[0585] Specific operation: The server uses NLTK and Transformers, which are NLP (natural language processing) libraries, to analyze emotion data and identify the user's emotion.

[0586] Output: Analyzed user emotion information

[0587] Step 4:

[0588] The server adjusts the timing and content of information provided to sales representatives based on the analysis results.

[0589] Input: Analyzed user emotion information

[0590] Specific operation: If the user shows signs of joy or excitement, the server provides the sales representative with "information that will promote sales activities toward this user," and conversely, if the user shows signs of displeasure or anger, the server provides "information that will discourage sales activities."

[0591] Output: Pertinent information provided to salespeople

[0592] The above are the specific processing steps of the program of this system.

[0593] (Application example 2)

[0594] Next, a description will be given of Application Example 2 of Form 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."

[0595] Conventional systems aimed at analyzing product competition, organizing information, and streamlining sales activities do not provide information that takes user emotions into consideration, making it difficult to maximize users' purchasing motivation. Furthermore, they lack real-time promotional information notifications, which can result in missed opportunities to pique users' interest. This results in limited effectiveness in calculating product recommendation rankings and sales activities.

[0596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0597] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for analyzing user emotions and providing information according to the emotions, and means for notifying promotion information in real time. This makes it possible to provide information at an appropriate time according to the user's emotions, thereby maximizing the effectiveness of calculation of recommended product rankings and sales activities.

[0598] A "multi-product competitive analysis" is the process of evaluating and comparing the market competitiveness of several different products or services.

[0599] "Information organization" is the process of systematically classifying collected data and information and summarizing it in an easy-to-understand format.

[0600] "Improving sales efficiency" refers to efforts to optimize sales processes and maximize results while reducing effort and time.

[0601] "Comparative analysis including competing services" is an analytical method that compares a company's products and services with those of its competitors to identify advantages and areas for improvement.

[0602] "Increasing the speed of knowledge acquisition" means improving the ability to quickly gather and understand necessary information and knowledge.

[0603] "Analyzing user emotions" is a technology that reads and analyzes emotions from a user's facial expressions, voice, text, etc.

[0604] "Providing information according to emotions" means providing information with appropriate timing and content based on the user's emotional state.

[0605] "Real-time promotion information notification" means sending promotion information instantly in response to the user's actions and emotions.

[0606] The system for implementing this invention comprises a server, a user terminal, and various software components. The details of each component and its role will be explained below.

[0607] server

[0608] The server includes the following means:

[0609] 1. Data collection methods:

[0610] Web scraping: Using libraries such as BeautifulSoup and Scrapy to gather product information from databases and websites on the internet.

[0611] API integration: Use an API that provides product information (e.g., product advertising API) to obtain detailed product data.

[0612] 2. Data analysis methods:

[0613] Machine learning algorithms: Libraries such as scikit-learn and TensorFlow are used to calculate product recommendation rankings based on collected data.

[0614] Sentiment analysis: To analyze user sentiment, we use a sentiment analysis model (e.g., BERT) that uses NLP (Natural Language Processing) techniques.

[0615] 3. Information provision method:

[0616] Real-time notifications: Use Firebase Cloud Messaging to send product suggestions and promotional information based on user sentiment in real time.

[0617] Dashboard: Provides a dashboard to display products that users are interested in and recommendation rankings.

[0618] User terminal

[0619] The user terminal is a mobile device such as a smartphone or tablet, and has the following functions:

[0620] 1. Sentiment analysis function:

[0621] The user's facial expressions and voice are analyzed in real time and their emotional state is sent to the server.

[0622] 2. Notification function:

[0623] Receive real-time notifications sent from the server and display them to the user.

[0624] Specific examples

[0625] For example, consider a case where a user is using an online shopping app on a smartphone. The user searches for a specific product (e.g., a smartphone) and while browsing the product page, the app analyzes the user's emotions from their facial expressions and voice. If the user is excited, the app sends a notification saying, "This product is currently 20% off!" to encourage the purchase.

[0626] Prompt Sentence Examples

[0627] Design an application that analyzes the user's facial and voice expressions while they are browsing a specific product page, and notifies them of promotional information in real time if they are excited. The technologies used are web scraping, machine learning algorithms, sentiment analysis, and Firebase Cloud Messaging.

[0628] In this way, by having the server and user terminal work together, it becomes possible to provide information at the appropriate time according to the user's emotions, thereby maximizing the effectiveness of calculation of product recommendation rankings and sales activities.

[0629] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0630] Step 1:

[0631] Data collection

[0632] The server uses web scraping technology to collect product information from databases and websites on the Internet. Specifically, it uses libraries such as BeautifulSoup and Scrapy to obtain data such as product names, prices, and customer ratings. It also uses APIs that provide product information (e.g., product advertising APIs) to obtain detailed product data. The input is data from websites and APIs, and the output is a dataset of collected product information.

[0633] Step 2:

[0634] Data analysis

[0635] The server uses a machine learning algorithm based on the collected product information to calculate the recommended product ranking. Specifically, it uses libraries such as scikit-learn and TensorFlow to analyze data such as product characteristics, price, and customer ratings, and calculates the recommended ranking. The input is a dataset of collected product information, and the output is a list of products with a recommended ranking.

[0636] Step 3:

[0637] Emotion analysis

[0638] The user device analyzes the user's facial expressions and voice in real time and transmits the emotional state to the server. Specifically, it captures the user's facial expressions and voice using a camera and microphone, and analyzes the emotions using an emotion analysis model using NLP technology (e.g., BERT). The input is the user's facial expressions and voice data, and the output is the analyzed emotional state data.

[0639] Step 4:

[0640] Information provision

[0641] The server notifies the user of product suggestions and promotion information in real time at the appropriate time based on the user's emotional state. Specifically, it uses Firebase Cloud Messaging to send notifications according to the user's emotions. The input is the analyzed emotional state data and a list of recommended products with an order of recommendation, and the output is a notification message sent to the user's device.

[0642] Step 5:

[0643] Dashboard View

[0644] The user terminal displays the product list with the recommended ranking sent from the server on a dashboard. Specifically, the products in which the user is interested and the recommended ranking are visually displayed through a user interface. The input is the product list with the recommended ranking sent from the server, and the output is the dashboard screen displayed to the user.

[0645] In this way, by having each processing step work in conjunction with one another, it becomes possible to provide information at the appropriate time according to the user's emotions, thereby maximizing the effectiveness of calculation of product recommendation rankings and sales activities.

[0646] Example 3

[0647] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0648] In conventional sales activities, competitive analysis of products and information organization were often done manually, resulting in inefficiency. Furthermore, comparative analysis with competing services was also done manually, which took time and effort, and slowed down the speed of knowledge acquisition. Furthermore, it was difficult to accurately grasp user emotions and reflect them in sales activities, making it difficult to achieve effective sales activities.

[0649] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes means for performing competitive analysis and information organization of various products, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for collecting user emotion data, means for analyzing the collected emotion data, means for calculating a recommended ranking of products based on the analyzed emotion data, means for generating a dashboard that visually displays the recommended ranking, and means for providing the recommended ranking to sales representatives. This automates the competitive analysis of products and information organization, thereby enabling the efficiency of sales activities. Furthermore, calculating and providing a recommended ranking based on user emotion data enables more effective sales activities.

[0650] "A means of conducting competitive analysis and organizing information on a variety of products" is a function for collecting data on multiple products, comparing, analyzing, and organizing them.

[0651] "Means aimed at improving the efficiency of sales activities" are functions that support sales representatives in carrying out their work efficiently.

[0652] "Means for automating comparative analysis, including competing services" refers to a function for automatically collecting information on competing services and products and comparing and analyzing them.

[0653] "Means for increasing the speed of knowledge acquisition" refers to functions that enable necessary information and knowledge to be acquired quickly.

[0654] The "means for collecting user emotion data" is a function for collecting data relating to emotions displayed by the user.

[0655] The "means for analyzing collected emotion data" is a function for analyzing collected user emotion data and understanding its contents.

[0656] The "means for calculating the recommendation ranking of a product based on the analyzed emotion data" is a function for calculating the recommendation ranking of a product based on the analysis results.

[0657] The "means for generating a dashboard that visually displays the recommendation ranking" is a function for generating a dashboard that visually displays the calculated recommendation ranking in an easy-to-understand manner.

[0658] The "means for providing a sales representative with a recommended ranking" is a function for providing the calculated recommended ranking to the sales representative and for using it in sales activities.

[0659] MODE FOR CARRYING OUT THE INVENTION

[0660] The present invention is a system for collecting user emotion data, calculating a recommendation ranking for products based on the collected data, and providing the ranking to a sales representative. A specific embodiment of this system will be described below.

[0661] 1. Generating the system program

[0662] The server generates a program incorporating an emotion engine and a recommendation ranking calculation algorithm. This program has the function of collecting user emotion data and calculating the recommendation ranking of products based on that data.

[0663] 2. Explanation of program processing

[0664] The server uses an emotion engine (e.g., IBM Watson® emotion analysis API) to collect user emotion data. The emotion engine analyzes the emotions (e.g., joy, interest) expressed by the user toward a specific product and stores the results in a database.

[0665] Next, the server runs a recommendation ranking calculation algorithm based on the stored emotion data. This algorithm calculates the recommendation ranking for each product, taking into account the user's emotion data and the characteristics of the product. For example, products for which the user expressed "joy" emotion will be ranked higher.

[0666] The server then generates a dashboard that visually displays the recommended rankings. This dashboard is displayed in a web browser using HTML5 and JavaScript. The dashboard displays a list of products and their recommended rankings.

[0667] The terminal (salesperson's PC or tablet) displays the dashboard provided by the server. The salesperson checks the recommendation ranking based on the user's emotional data through the dashboard and carries out sales activities. For example, they may propose products with a high recommendation ranking to the user.

[0668] 3. Examples and prompts

[0669] As a concrete example, suppose a user expresses "joy" about a new smartphone. The emotion engine captures this information and raises the smartphone's recommendation ranking. This information is then provided to sales representatives via a dashboard. Sales representatives then use this information to make sales calls to the user.

[0670] Example prompts to input to a generative AI model:

[0671] "Please explain the program that calculates the ranking of recommended products based on the sentiment data that users have shown toward specific products and generates a dashboard to provide to sales representatives."

[0672] In this way, the system accurately captures the user's emotions and reflects them in the product recommendation ranking and sales activities, thereby achieving more effective sales activities. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0673] Step 1: Collecting user emotion data

[0674] A user browses a specific product on an online shopping site and posts a review or comment. At this time, the user's emotional data (e.g., joy, interest) is collected. The input is the user's text comment, and the output is emotional data. Specifically, a user posts a comment such as "This smartphone is great!"

[0675] Step 2: Analyze the emotion data

[0676] The server sends the collected user emotion data to an emotion engine (for example, IBM Watson's emotion analysis API). The emotion engine analyzes the text data and quantifies the user emotion. The input is the user's text comment, and the output is quantified emotion data. Specifically, the emotion of "joy" is highly evaluated based on the comment "This smartphone is great!"

[0677] Step 3: Calculating the recommended ranking

[0678] The server runs a recommendation ranking calculation algorithm based on the analyzed emotional data. The algorithm calculates the recommendation ranking for each product by taking into account the user's emotional data and the product's characteristics. The input is quantified emotional data, and the output is the product's recommended ranking. Specifically, it raises the recommendation ranking of smartphones for which the user expresses the emotion of "joy."

[0679] Step 4: Generate a dashboard

[0680] The server generates a dashboard to visually display the calculated recommendation ranking. The dashboard is displayed on a web browser using HTML5 and JavaScript. The input is the recommended ranking of products, and the output is a visually displayed dashboard. Specifically, smartphones with high recommendation rankings are displayed at the top of the list.

[0681] Step 5: Provide information to sales representatives

[0682] The device (salesperson's PC or tablet) displays the dashboard provided by the server. The salesperson checks the recommendation ranking based on the user's emotional data through the dashboard and carries out sales activities. The input is the visually displayed dashboard, and the output is the salesperson's actions. Specifically, the smartphone with the highest recommendation ranking is suggested to the user.

[0683] (Application example 3)

[0684] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0685] In conventional sales activities, it was difficult to accurately grasp customer emotions and recommend products based on them, making it difficult for sales representatives to quickly grasp information and conduct efficient sales activities.In addition, because real-time analysis of customer emotions and the recommendation of products based on that analysis were not performed, improvement of customer satisfaction and maximization of sales results were not fully achieved.

[0686] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0687] In this invention, the server includes means for performing competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for analyzing customer sentiment in real time and calculating a recommended ranking of products based on the analysis, means having an interface for visually displaying the recommended ranking, and means for displaying recommended products using a smart device. This enables real-time recommendation of products based on customer sentiment, enabling sales representatives to quickly grasp information and conduct efficient sales activities.

[0688] "Diverse merchandise" is a general term for products and services with different types and characteristics.

[0689] "Competitive analysis" is the process of comparative evaluation of competitors and competing products.

[0690] "Information organization" is the process of systematically classifying and organizing collected data and information.

[0691] "Sales activities" are a series of actions taken to propose and sell products and services to customers.

[0692] "Efficiency" means aiming to perform tasks or processes with less time and effort.

[0693] "Comparative analysis" is the process of comparing multiple subjects and identifying their differences and similarities.

[0694] "Automation" refers to machines or systems performing tasks automatically without human intervention.

[0695] "Knowledge acquisition rate" refers to the speed at which new information and knowledge are acquired.

[0696] "Customer sentiment" refers to the emotional response a customer has to a particular situation or product.

[0697] "Real-time" refers to the immediate processing and display of ongoing events and situations.

[0698] "Recommended Rank" is the result of prioritizing products and services based on specific criteria.

[0699] An "interface" is a point of contact or means by which a user and a system interact with each other.

[0700] "Smart device" is a general term for electronic devices that have internet connectivity and advanced computing capabilities.

[0701] "Recommended Products" are products or services suggested to users based on certain criteria or conditions.

[0702] A system for carrying out this invention is configured as follows: The server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for analyzing customer sentiment in real time and calculating a recommended ranking of products based on the analysis, means having an interface for visually displaying the recommended ranking, and means for displaying recommended products using a smart device.

[0703] Hardware and software used

[0704] Hardware

[0705] Smart glasses (e.g., Google® Glass®)

[0706] Camera (built into smart glasses)

[0707] software

[0708] EmotionRecognizer: Emotion recognition engine (e.g. TensorFlow model)

[0709] RecommendationEngine: Recommendation engine (e.g. custom algorithm)

[0710] SmartGlassesDisplay: A library for controlling smart glasses displays

[0711] Data processing and calculation

[0712] Camera Input

[0713] Images are captured in real time from a camera built into the device (smart glasses), and the image of the customer's face is sent to the server.

[0714] emotion recognition

[0715] The server uses EmotionRecognizer to detect the customer's face from the video and recognize their emotions. The emotion recognition engine uses a TensorFlow model to analyze emotions such as "happiness," "sadness," and "surprise" from the customer's facial expressions.

[0716] Recommended product calculation

[0717] The server then uses a Recommendation Engine to recommend appropriate products based on the recognized emotions. The recommendation engine uses a custom algorithm to match customer emotion data with product data and select the most suitable products.

[0718] display

[0719] The server displays the recommended products on the smart glasses via SmartGlassesDisplay, allowing salespeople wearing the device (smart glasses) to check the recommended products in real time.

[0720] Specific examples

[0721] A customer approaches a salesperson wearing smart glasses, looks at a particular product, and smiles. The server uses an emotion recognition engine to detect "happiness," and the recommendation engine lists related products. The smart glasses display shows, "You seem to be interested in this product. Related products: Product A, Product B, Product C."

[0722] Prompt Sentence Examples

[0723] If a customer smiles while looking at a particular product, design a system that recognizes that emotion and recommends related products. Use smart glasses to analyze emotions in real time and display product recommendations.

[0724] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0725] Step 1:

[0726] Video is acquired in real time from the camera built into the device (smart glasses). The input is the camera image, and the output is video data. Specifically, the camera captures video including the customer's face and sends the data to the server.

[0727] Step 2:

[0728] The server uses EmotionRecognizer to detect customer faces from video data and recognize emotions. The input is video data, and the output is recognized emotion data. Specifically, the server uses a TensorFlow model to analyze facial features in the video data and identify emotions such as "happiness," "sadness," and "surprise."

[0729] Step 3:

[0730] The server's Recommendation Engine recommends appropriate products based on the recognized emotion data. The input is emotion data, and the output is a list of recommended products. Specifically, the server uses a custom algorithm to match the emotion data with product data and select the most suitable product.

[0731] Step 4:

[0732] The server displays the recommended product list on the smart glasses via SmartGlassesDisplay. The input is the recommended product list, and the output is the information displayed on the smart glasses display. Specifically, the server sends the recommended product list to the smart glasses display control library, allowing the salesperson to check the recommended products in real time.

[0733] Step 5:

[0734] The user (salesperson) conducts effective sales activities with customers based on the recommended products displayed on the smart glasses' display. The input is the information displayed on the smart glasses' display, and the output is the proposal to the customer. Specifically, the salesperson introduces the recommended products to the customer and provides an explanation to attract their interest.

[0735] 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.

[0736] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0737] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0738] 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.

[0739] [Second embodiment]

[0740] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0741] 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.

[0742] 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).

[0743] 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.

[0744] 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.

[0745] 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).

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0752] "Example 1"

[0753] The present invention is a system for conducting competitive analysis of products and organizing information. Specifically, it includes a means for collecting information on product characteristics, prices, customer reviews, etc., a means for automating comparative analysis between products based on that information, and a means for accelerating the speed of knowledge acquisition.

[0754] "Example 2"

[0755] For example, web scraping technology, which automatically collects necessary information from internet databases and websites, can be used to collect information such as product characteristics, prices, customer reviews, etc. Furthermore, machine learning algorithms can be used to automatically calculate the recommended ranking of products based on the collected information to automate comparative analysis between products.

[0756] "Example 3"

[0757] Furthermore, to speed up the acquisition of knowledge, the system is equipped with an interface that provides sales representatives with the calculated recommended rankings. Specifically, by providing a dashboard that visually displays the recommended rankings in an easy-to-understand manner, sales representatives can quickly grasp the information and make their sales activities more efficient.

[0758] The processing flow of each embodiment will be described below.

[0759] "Example 1"

[0760] Step 1: Collect information such as product characteristics, prices, customer reviews, etc. In this step, web scraping technology is used to automatically collect the necessary information from databases and websites on the Internet.

[0761] Step 2: Based on the collected information, a comparative analysis between products is conducted. In this step, a machine learning algorithm is used to automatically calculate the recommended ranking of products.

[0762] Step 3: Provide the calculated recommendation ranking to the sales representative. In this step, a dashboard is provided that visually displays the recommendation ranking in an easy-to-understand manner.

[0763] "Example 2"

[0764] Step 1: Collect information such as product characteristics, prices, customer reviews, etc. In this step, web scraping technology is used to automatically collect the necessary information from databases and websites on the Internet.

[0765] Step 2: Based on the collected information, a comparative analysis between products is conducted. In this step, a machine learning algorithm is used to automatically calculate the recommended ranking of products.

[0766] Step 3: Provide the calculated recommendation ranking to the sales representative. In this step, a dashboard is provided that visually displays the recommendation ranking in an easy-to-understand manner.

[0767] "Example 3"

[0768] Step 1: Collect information such as product characteristics, prices, customer reviews, etc. In this step, web scraping technology is used to automatically collect the necessary information from databases and websites on the Internet.

[0769] Step 2: Based on the collected information, a comparative analysis between products is conducted. In this step, a machine learning algorithm is used to automatically calculate the recommended ranking of products.

[0770] Step 3: Provide the calculated recommendation ranking to the sales representative. In this step, a dashboard is provided that visually displays the recommendation ranking in an easy-to-understand manner.

[0771] Example 1

[0772] Next, a description will be given of Example 1 of Form 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."

[0773] Conventional competitive analysis and information organization systems for products often required manual processes of information collection, data cleansing, and comparative analysis, which was time-consuming and labor-intensive. Additionally, knowledge acquisition was slow, limiting the efficiency of sales activities. Furthermore, there was a lack of a way to quickly summarize the characteristics and competitiveness of products based on the collected information, making it difficult for sales representatives to make quick decisions.

[0774] 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.

[0775] In this invention, the server includes means for collecting information such as product characteristics, prices, and customer reviews, means for cleansing the collected information and converting it into a unified format, means for performing comparative analysis between products based on the cleansed data, means for automatically summarizing the product characteristics and competitiveness using a generative AI model, means for generating prompt sentences to be input to the generative AI model, and means for inputting the prompt sentences to the generative AI model and summarizing the results of the comparison of the products. This automates the process from information collection to data cleansing, comparative analysis, and summarization, improving the speed of knowledge acquisition and enabling more efficient sales activities.

[0776] "Merchandise" is a general term for goods and services sold in the market.

[0777] "Competitive analysis" is the process of comparing multiple products and evaluating their competitiveness and market positioning.

[0778] "Information organization" is the process of systematically organizing collected data and converting it into an easy-to-understand format.

[0779] "Sales activities" refers to a series of tasks and processes for selling products.

[0780] "Efficiency" means improving operations and processes so that they can be performed with less time and effort.

[0781] "Comparative analysis" is the process of comparing the characteristics, prices, customer reviews, etc. of multiple products and evaluating their relative merits.

[0782] "Speed ​​of knowledge acquisition" refers to the speed at which it takes to gather and understand the necessary information and knowledge.

[0783] "Information gathering" is the process of obtaining data about a product from the internet and other sources.

[0784] "Cleansing" is the process of removing unnecessary or incorrect information from collected data and converting it into an accurate and consistent format.

[0785] A "generative AI model" is a model that uses artificial intelligence to analyze data and automatically perform specific tasks.

[0786] A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

[0787] "Summarizing" is the process of concisely summarizing collected information and extracting the main points.

[0788] MODE FOR CARRYING OUT THE INVENTION

[0789] This invention relates to a system for conducting competitive analysis of products and organizing information. Specifically, it is equipped with a means for collecting information on product characteristics, prices, customer reviews, etc., and automating comparative analysis between products based on this information, as well as a means for accelerating the speed of knowledge acquisition.

[0790] Program Generation

[0791] The server generates a program for a system that performs competitive analysis of products and organizes information. This program has the function of collecting information such as product characteristics, prices, and customer reviews, and automating comparative analysis between products based on that information. It also has a means to speed up knowledge acquisition.

[0792] Program processing explanation

[0793] The server executes the program in the following procedure.

[0794] 1. Information Collection:

[0795] The server collects information such as product characteristics, prices, and customer reviews from the Internet using web scraping tools (e.g., BeautifulSoup, Scrapy).

[0796] The collected data is stored in a database (e.g., MySQL, PostgreSQL).

[0797] 2. Data cleansing:

[0798] The server cleanses the collected data and converts it into the required format, for example, converting price information into a uniform currency unit.

[0799] Use a data processing library (e.g., Pandas) to remove unnecessary or duplicate data and transform it into an accurate and consistent format.

[0800] 3. Data Analysis:

[0801] The server performs comparative analysis between products based on the cleansed data, specifically calculating average prices and the distribution of customer ratings.

[0802] Use data analysis tools (e.g., NumPy, Scikit-learn) to compare the characteristics of different products.

[0803] 4. Speed ​​up knowledge acquisition:

[0804] The server uses a generative AI model (e.g., GPT-4) to automatically summarize the product's features and competitive advantages based on the collected information.

[0805] A prompt sentence is generated and input to the generative AI model. For example, a prompt sentence such as "Compare the characteristics and prices of product A and product B, and summarize which is more competitive" can be used.

[0806] Adding specific examples

[0807] When a user wants to conduct a competitive analysis of a new product, he or she can use the system by following the steps below.

[0808] 1. Information Collection:

[0809] The user inputs a list of products to be analyzed into the system.

[0810] The server uses a web scraping tool to collect information such as the characteristics, price, and customer reviews of each product.

[0811] 2. Data cleansing:

[0812] The server cleanses the collected data and converts it into a unified format. For example, if price information is expressed in different currency units, such as "$100" and "1000 yen," the server converts these into a unified currency unit (e.g., yen). Also, if customer ratings are expressed as strings, such as "★★★★★," the server converts them into numbers (e.g., 5).

[0813] 3. Data Analysis:

[0814] The server performs comparative analysis between products based on the cleansed data. For example, it calculates that the average price of smartphone A is 50,000 yen and the average price of smartphone B is 60,000 yen. It also analyzes the distribution of customer ratings and confirms that the average rating of smartphone A is 4.5 and the average rating of smartphone B is 4.0.

[0815] 4. Speed ​​up knowledge acquisition:

[0816] The server inputs the following prompt into the generative AI model: "Compare the features and prices of smartphone A and smartphone B, and summarize which one is more competitive."

[0817] Based on this prompt, the generative AI model summarizes the results of the comparison between smartphone A and smartphone B. For example, it generates a summary result such as, "Smartphone A is competitive because it is inexpensive and has high customer ratings."

[0818] In this way, the user can efficiently perform competitive analysis of merchandise and organize information.

[0819] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0820] Step 1:

[0821] Information gathering

[0822] Based on the product list entered by the user, the server collects information such as product characteristics, prices, and customer reviews from the Internet. Specifically, it uses a web scraping tool (e.g., BeautifulSoup, Scrapy) to obtain information about each product. The input is the product list provided by the user, and the output is the collected data such as product characteristics, prices, and customer reviews. For example, if the user enters "smartphone A" and "smartphone B," the server obtains the prices and customer reviews of these products from Amazon and other e-commerce sites.

[0823] Step 2:

[0824] Data Cleansing

[0825] The server cleanses the collected data and converts it into the required format. Specifically, it uses a data processing library (e.g., Pandas) to remove unnecessary and duplicate data and convert price information into a unified currency unit. It also quantifies customer ratings. The input is the collected raw data, and the output is cleansed, consistent data. For example, if price information is expressed in different currency units, such as "$100" and "1,000 yen," the server converts it into a unified currency unit (e.g., yen). Also, if customer ratings are expressed as strings, such as "★★★★★," the server converts them into numbers (e.g., 5).

[0826] Step 3:

[0827] Data analysis

[0828] The server performs comparative analysis between products based on the cleansed data. Specifically, it uses data analysis tools (e.g., NumPy, Scikit-learn) to calculate the average price, distribution of customer ratings, etc. The input is the cleansed data, and the output is the comparison results between products. For example, it calculates that the average price of smartphone A is 50,000 yen, and the average price of smartphone B is 60,000 yen. It also analyzes the distribution of customer ratings and confirms that the average rating of smartphone A is 4.5, and the average rating of smartphone B is 4.0.

[0829] Step 4:

[0830] Speed ​​up knowledge acquisition

[0831] The server uses a generative AI model (e.g., GPT-4) to automatically summarize the features and competitiveness of products based on the collected information. Specifically, it generates prompts to be input into the generative AI model and inputs them into the model. The inputs are the cleansed data and the generated prompts, and the output is a summary of the product comparison results. For example, a prompt might be used such as, "Compare the features and prices of product A and product B, and summarize which is more competitive." The generative AI model summarizes the comparison results between product A and product B based on this prompt. For example, it generates a summary such as, "Product A is competitive because it is inexpensive and has high customer ratings."

[0832] In this way, the user can efficiently perform competitive analysis of merchandise and organize information.

[0833] (Application example 1)

[0834] Next, a description will be given of Application Example 1 of Form 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."

[0835] In today's product market, efficiently collecting information on the characteristics, prices, customer reviews, and other aspects of various products and quickly and accurately conducting comparative analysis with competing products is an important challenge for improving sales efficiency and customer satisfaction. However, conventional methods require a great deal of time and effort to collect and analyze information, slowing down the speed of knowledge acquisition. In addition, there was a lack of a way to automatically calculate the recommended product ranking and present it appropriately to users, making it difficult for sales representatives and consumers to select the most suitable product.

[0836] 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.

[0837] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for collecting information such as product characteristics, price, and customer reviews and generating a report comparing the product with other similar products, means for conducting comparative analysis of products using a generative AI model, and means for presenting a recommended ranking of products to the user using prompt sentences. This automates the collection and comparison of product information, improves the speed of knowledge acquisition, and enables sales representatives and consumers to quickly select the optimal product.

[0838] "Means for competitive analysis and information organization for a variety of products" refers to a means for collecting information on the characteristics, prices, customer reviews, etc. of multiple products available in the market, and organizing this information to evaluate their competitiveness.

[0839] "Means aimed at improving the efficiency of sales activities" are means for quickly providing necessary information and optimizing business processes so that sales representatives can carry out their work efficiently.

[0840] "Means for automating comparative analysis including competing services" refers to means for automatically conducting comparative analysis with competing products and services based on information such as product characteristics, price, and customer evaluations.

[0841] "Means for increasing the speed of knowledge acquisition" refers to means for quickly processing collected information and acquiring the necessary knowledge in a short amount of time.

[0842] "Means for collecting information on product characteristics, price, customer reviews, etc., and generating a report for comparing with other similar products" refers to means for collecting detailed information on a product and automatically generating a report for comparing with other similar products based on that information.

[0843] "Means for comparative analysis of products using generative AI models" refers to means for using artificial intelligence models to analyze information such as product characteristics, prices, and customer reviews, and for comparative analysis of products.

[0844] "Means for presenting users with a recommended ranking of products using prompt sentences" refers to a means for generating and displaying prompt sentences for presenting users with a recommended ranking of products based on the analysis results obtained by a generative AI model.

[0845] The following system configuration will be described as an embodiment of the present invention.

[0846] System Configuration

[0847] This system consists of a server, a user terminal, and a database. The server collects information such as product characteristics, prices, and customer reviews, and performs comparative analysis of products using a generative AI model. The user terminal provides an interface that allows users to search for products and check the recommended product ranking using prompts. The database stores the collected product information.

[0848] Hardware and software used

[0849] Hardware: Server, smartphone (user device)

[0850] Software: Python, BeautifulSoup, requests, pandas, scikit-learn, generative AI models

[0851] Data processing and calculation

[0852] The server first collects information such as product characteristics, price, and customer ratings. Specifically, it uses the requests library to retrieve product information from the specified URL and parses the HTML using BeautifulSoup. Next, it stores the collected information in a pandas data frame and vectorizes the product characteristics using TfidfVectorizer. It calculates the text similarity between products using cosine_similarity and performs a comparative analysis of the products using a generative AI model.

[0853] When a user searches for a product, the user device generates a prompt based on the comparative analysis results obtained from the server and presents the user with a recommended ranking of products. The prompt is generated based on the analysis results obtained by the generative AI model.

[0854] Specific examples

[0855] For example, suppose a user opens the "Smart Shopping Assistant" app on their smartphone and enters "Smartphone A" in the search bar. The app will automatically collect the features, price, and customer reviews of "Smartphone A" and compare it with other similar smartphones (e.g., Smartphone B, Smartphone C). A comparison report will be generated and the user will be prompted with the following:

[0856] Prompt Sentence Examples

[0857] Open the "Smart Shopping Assistant" app and enter "Smartphone A" in the search bar. The app will automatically collect the features, price, and customer reviews of Smartphone A and compare it with other smartphones (e.g., Smartphone B, Smartphone C). A comparison report will be displayed, allowing you to easily decide which smartphone is best for you.

[0858] In this way, the user can quickly select the most suitable product.

[0859] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0860] Step 1:

[0861] The user searches for a product on their device.

[0862] Input: The product name entered by the user in the search bar (e.g., "Smartphone A").

[0863] How it works: A user opens the app on their smartphone and enters the name of a product in the search bar.

[0864] Output: The product name is sent to the server.

[0865] Step 2:

[0866] The server collects information about the products.

[0867] Input: The product name entered by the user.

[0868] How it works: The server uses the requests library to retrieve product information from the specified URL. It then parses the HTML using BeautifulSoup to extract information such as product characteristics, price, and customer ratings.

[0869] Output: Information such as product characteristics, price, and customer ratings is saved in a database.

[0870] Step 3:

[0871] The server vectorizes the product information.

[0872] Input: Product characteristics information stored in the database.

[0873] How it works: The server stores product information in a pandas data frame and uses TfidfVectorizer to vectorize the product characteristics.

[0874] Output: Vectorized product characteristics information.

[0875] Step 4:

[0876] The server calculates the similarity between the products.

[0877] Input: Vectorized product characteristics information.

[0878] Operation: The server uses cosine_similarity to calculate the text similarity between products.

[0879] Output: Similarity matrix between products.

[0880] Step 5:

[0881] The server uses the generated AI model to perform a comparative analysis of the products.

[0882] Input: Similarity matrix between products.

[0883] How it works: The server uses the generative AI model to analyze information such as product characteristics, price, and customer reviews, and conducts comparative analysis between products.

[0884] Output: Comparative analysis results of products.

[0885] Step 6:

[0886] The server generates a prompt.

[0887] Input: Results of comparative analysis of products.

[0888] Operation: Based on the analysis results obtained by the generative AI model, the server generates a prompt message to present the user with a recommended ranking of products.

[0889] Output: The prompt statement.

[0890] Step 7:

[0891] The terminal displays the prompt.

[0892] Input: The prompt text sent by the server.

[0893] Operation: The user terminal displays the prompt received from the server on the screen.

[0894] Output: User can check the recommended ranking of products.

[0895] Example 2

[0896] Next, a description will be given of Example 2 of Form 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."

[0897] Traditionally, competitive analysis and information organization for products have often been done manually, which takes time and effort, making it difficult to streamline sales activities. Furthermore, there was a lack of automated comparative analysis, including that of competing services, making it difficult to speed up knowledge acquisition. Furthermore, there was a need for a system that could efficiently collect vast amounts of information on the Internet and automatically calculate the recommended ranking of products.

[0898] 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.

[0899] In this invention, the server includes means for performing competitive analysis and information organization of various products, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet, means for automatically calculating a recommended ranking of products based on the collected information using a machine learning algorithm, and means for providing the calculated recommended ranking to users. This allows for efficient competitive analysis of products and information organization, thereby improving the efficiency of sales activities. Furthermore, the automation of comparative analysis including competing services increases the speed of knowledge acquisition. Furthermore, it is possible to efficiently collect vast amounts of information on the Internet and automatically calculate a recommended ranking of products.

[0900] "Competitive analysis of diverse products" involves comparing products of different types and categories and evaluating their competitiveness in their respective markets.

[0901] "Information organization" means systematically classifying collected data and arranging it in an easy-to-understand format.

[0902] "Improving sales efficiency" means optimizing the sales process and making effective use of time and resources.

[0903] "Automated comparative analysis" means that the system automatically compares products without having to do it manually.

[0904] "Increasing the speed of knowledge acquisition" means improving the ability to quickly gather and understand necessary information.

[0905] "Internet databases and websites" means information sources that are accessible online.

[0906] "Characteristics of the product" refers to the specific features and specifications of the product.

[0907] "Price" means the selling price of the product.

[0908] "Customer ratings" refers to feedback and reviews from customers who have purchased a product.

[0909] "Automatically collect information" means that the system obtains the required data without manual intervention.

[0910] A "machine learning algorithm" is a computational method for learning patterns based on data and making predictions and classifications.

[0911] "Recommended Ranking" refers to a prioritized list of products that have been evaluated.

[0912] "Providing to the user" means displaying the results calculated by the system to the user.

[0913] This invention is a system that collects information such as product characteristics, prices, and customer reviews, and performs comparative analysis between products based on this information. A specific embodiment of this system is described below.

[0914] Hardware and software used

[0915] Server: This is the central component for collecting information, processing data, conducting comparative analysis, and providing results. The server should be a computer with a high-performance processor and sufficient memory.

[0916] Web scraping libraries: Use Python libraries such as BeautifulSoup and Scrapy to automatically scrape information from databases and websites on the internet.

[0917] Data processing libraries: Use Python libraries such as Pandas to shape the collected data and convert it into the required format.

[0918] Machine learning libraries: Python libraries such as Scikit-learn and TensorFlow are used to calculate the recommended ranking of products based on collected data.

[0919] Web application framework: Use a framework such as Flask or Django to build a web interface to provide the calculated recommendation rankings to users.

[0920] Explanation of program processing

[0921] 1. Information gathering

[0922] The server uses a web scraping library to automatically collect information such as product characteristics, prices, and customer reviews from databases and websites on the Internet.

[0923] Specifically, the server accesses a specific website and extracts price information and customer ratings from the product details page.

[0924] 2. Data processing

[0925] The server uses a data processing library to format the collected data and convert it into the required format.

[0926] Specifically, the server converts the collected pricing information into a numerical format and converts the customer ratings from text to a numerical score.

[0927] 3. Comparative analysis

[0928] The server uses a machine learning library to calculate the recommended ranking of products based on the formatted data.

[0929] Specifically, the server takes the price and customer ratings as input and calculates the recommended ranking of products using a random forest algorithm.

[0930] 4. Providing results

[0931] The server uses a web application framework to display the results and provide the calculated recommendation ranking to the user.

[0932] Specifically, the server generates a dashboard displaying the ranking of recommendations, which the user can access through a web browser.

[0933] Examples and prompts

[0934] Example: The server collects prices and customer ratings for "smartphones" from a specific website and uses a machine learning algorithm to calculate the recommended ranking.

[0935] Example prompt: "Collect smartphone prices and customer reviews from a specific website and calculate the best smartphone recommendation."

[0936] This system allows users to efficiently collect vast amounts of information on the Internet and perform comparative analysis. This allows for efficient competitive analysis of products and information organization, making sales activities more efficient. It also automates comparative analysis, including that of competing services, increasing the speed at which knowledge can be acquired. Furthermore, it makes it possible to efficiently collect vast amounts of information on the Internet and automatically calculate the recommended ranking of products.

[0937] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0938] Step 1:

[0939] Information gathering

[0940] The server uses a web scraping library (e.g., BeautifulSoup, Scrapy) to automatically collect information such as product characteristics, prices, and customer reviews from databases and websites on the Internet.

[0941] Input: A specific website URL or search keyword (e.g., "smartphone").

[0942] Specific operations: The server accesses a specific website and extracts price information and customer reviews from the product detail page. For example, the server searches for the keyword "smartphone" and accesses the detail page of each product from the search results page to collect information.

[0943] Output: Collected data such as product characteristics, prices, and customer ratings.

[0944] Step 2:

[0945] Data Processing

[0946] The server uses a data processing library (e.g., Pandas) to format the collected data and convert it into the required format.

[0947] Input: Data collected in Step 1, such as product characteristics, price, and customer ratings.

[0948] What happens: The server converts the collected price information into a numeric format and converts the customer ratings from text to a numeric score. For example, the server converts a price of "$299.99" to the numeric value 299.99, and converts a rating of "4.5 out of 5 stars" to the numeric value 4.5.

[0949] Output: Formatted data such as product characteristics, price, and customer ratings.

[0950] Step 3:

[0951] comparative analysis

[0952] The server uses machine learning libraries (e.g., Scikit-learn, TensorFlow) to calculate the recommended ranking of products based on the formatted data.

[0953] Input: Data such as product characteristics, price, and customer ratings formatted in Step 2.

[0954] Specific operation: The server inputs the price and customer rating and uses the random forest algorithm to calculate the product recommendation ranking. For example, the server sets the algorithm to prioritize recommending products with low prices and high customer ratings.

[0955] Output: The calculated recommended ranking of products.

[0956] Step 4:

[0957] Providing results

[0958] The server displays the results using a web application framework (e.g., Flask, Django) to provide the calculated recommendation ranking to the user.

[0959] Input: The recommended product ranking calculated in Step 3.

[0960] Specific behavior: The server generates a dashboard displaying the ranking of recommendations and makes it accessible to the user through a web browser. For example, the user can access a specific URL in their browser and see a page displaying the ranking of recommendations.

[0961] Output: A web page with the ranking of recommendations that will be served to the user.

[0962] (Application example 2)

[0963] Next, a description will be given of Application Example 2 of Form 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."

[0964] Traditionally, competitive analysis and information organization for products was often done manually, which required time and effort, and the information was often incomplete and inaccurate. Furthermore, comparative analysis between products and calculation of recommended rankings were also done manually, making it difficult to conduct efficient sales activities. Furthermore, there was a lack of means to collect and properly analyze the vast amount of information available on the Internet, making it difficult to recommend optimal products to users. To solve these issues, a system was needed that could automate the entire process, from information collection to analysis and proposals, efficiently and accurately.

[0965] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0966] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet, means for automatically calculating a recommended ranking of products using a machine learning algorithm based on the collected information, and means for proposing optimal products to users. This makes it possible to efficiently and accurately perform processes from information collection to analysis and proposals.

[0967] "Means for competitive analysis and information organization for various products" is a method for evaluating the competitiveness of different types of products and systematically organizing that information.

[0968] "Measures aimed at improving sales efficiency" are methods for optimizing sales processes and making effective use of time and resources.

[0969] "Means for automating comparative analysis including competing services" refers to a method for automatically conducting comparative analysis including competing services or products.

[0970] "Means to increase the speed of knowledge acquisition" are methods for quickly acquiring necessary information and knowledge.

[0971] "Means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet" refers to a method for automatically collecting data about products from various sources on the Internet.

[0972] "Means for automatically calculating the recommended ranking of products using a machine learning algorithm based on collected information" refers to a method for automatically calculating the recommended ranking of products using machine learning technology based on collected data.

[0973] "Means for suggesting optimal products to users" refers to methods for suggesting optimal products based on the user's needs and preferences.

[0974] A system for carrying out this invention has the following configuration: A server includes means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet, means for automatically calculating a recommended product ranking using a machine learning algorithm based on the collected information, and means for suggesting optimal products to users.

[0975] Hardware and software used

[0976] Hardware: Servers, smartphones

[0977] Software: Python, BeautifulSoup (for web scraping), Scikit-learn (for machine learning), Flask (for backend API)

[0978] Data processing and calculation

[0979] Web scraping

[0980] The server uses BeautifulSoup to collect information such as product characteristics, prices, and customer reviews from the specified website. The collected data is saved in a CSV file.

[0981] Data analysis

[0982] The server trains a machine learning model based on the collected data using Scikit-learn, and uses the trained model to calculate the recommended ranking of products.

[0983] Product suggestion

[0984] The server uses Flask to build a backend API and returns recommended products in response to user requests. Users can access this API using their smartphones to receive optimal product suggestions.

[0985] Specific examples

[0986] For example, if a user searches for "smartphone," the following prompt sentence is input into the generative AI model:

[0987] import requests

[0988] from bs4 import BeautifulSoup

[0989] import pandas as pd

[0990] from sklearn.ensemble import RandomForestClassifier

[0991] from flask import Flask, request, jsonify

[0992] app = Flask(__name__)

[0993] Web scraping

[0994] def scrape_data():

[0995] url = "https: / / example.com / smartphones"

[0996] response = requests.get(url)

[0997] soup = BeautifulSoup(response.text, 'html.parser')

[0998] data = []

[0999] for item in soup.find_all('div', class_='product'):

[1000] name = item.find('h2').text

[1001] price = item.find('span', class_='price').text

[1002] rating = item.find('span', class_='rating').text

[1003] data.append([name, price, rating])

[1004] df = pd.DataFrame(data, columns=['Name', 'Price', 'Rating'])

[1005] df.to_csv('smartphones.csv', index=False)

[1006] Training of machine learning model

[1007] def train_model():

[1008] df = pd.read_csv('smartphones.csv')

[1009] X = df[['Price', 'Rating']]

[1010] y = df['Name']

[1011] model = RandomForestClassifier()

[1012] model.fit(X, y)

[1013] return model

[1014] Product suggestion API

[1015] @app.route(' / recommend', methods=['GET'])

[1016] def recommend():

[1017] model = train_model()

[1018] user_input = request.args.get('input')

[1019] This is where product recommendations are calculated based on user input.

[1020] Example: Returning recommended products

[1021] recommended_product = model.predict([[user_input['price'], user_input['rating']]])

[1022] return jsonify({'recommended_product': recommended_product})

[1023] if __name__ == '__main__':

[1024] scrape_data()

[1025] app.run(debug=True)

[1026] The program provides an API that collects smartphone information from designated websites, trains a machine learning model, and recommends the best smartphone for users.

[1027] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1028] Step 1:

[1029] The server accesses specified websites on the Internet and collects information such as product characteristics, prices, and customer reviews. Specifically, it uses BeautifulSoup to analyze the HTML structure of the webpage and extract the necessary data. The input is the website URL, and the output is a list of product information.

[1030] Step 2:

[1031] The server saves the collected product information in a CSV file. Specifically, it creates a data frame using the Pandas library and saves it in CSV format. The input is a list of product information, and the output is a CSV file.

[1032] Step 3:

[1033] The server reads the saved CSV file and trains a machine learning model. Specifically, it preprocesses the data using Scikit-learn and trains a random forest classifier. The input is the CSV file, and the output is the trained machine learning model.

[1034] Step 4:

[1035] The server uses Flask to build a backend API and accepts requests from users. Specifically, users access the API using their smartphones and enter information such as product characteristics, price, and customer ratings. The input is the user's request data, and the output is a list of recommended products.

[1036] Step 5:

[1037] The server uses a trained machine learning model to calculate the recommended ranking of products based on the request data from the user. Specifically, the model inputs the product characteristics, price, customer ratings, and other data entered by the user, and calculates the recommended ranking. The input is the user's request data, and the output is a list of recommended products.

[1038] Step 6:

[1039] The server returns the calculated list of recommended products to the user. Specifically, it uses Flask to return the list of recommended products in JSON format as an API response. The input is the list of recommended products, and the output is the response to the user.

[1040] Example 3

[1041] Next, a description will be given of Example 3 of Form Example 3. 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."

[1042] In conventional sales activities, competitive analysis, information organization, and comparative analysis of products are often done manually, resulting in inefficiencies. Furthermore, there was a lack of a way for sales representatives to quickly obtain the necessary information and conduct effective sales activities. Furthermore, the process for calculating the recommended ranking was complicated, and there was a lack of a way to display it visually in an easy-to-understand manner.

[1043] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1044] In this invention, the server includes means for performing competitive analysis and information organization for various products, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for calculating a recommendation ranking using a generative AI model, means for generating prompt sentences and inputting them into the generative AI model, means for generating a dashboard that visually displays the recommendation ranking, and means for displaying the dashboard on a terminal, thereby enabling sales representatives to quickly obtain necessary information and conduct effective sales activities.

[1045] "Merchandise" is a general term for the products and services sold.

[1046] "Competitive analysis" is the process of comparing competitors and products in the same market and evaluating their strengths and weaknesses.

[1047] "Information organization" is the process of systematically classifying collected data and information and arranging it in an easy-to-understand form.

[1048] "Sales activities" are a series of actions taken to propose products and services to customers and promote sales.

[1049] "Efficiency" refers to optimizing work and processes, eliminating waste, and carrying them out effectively.

[1050] "Comparative analysis" is the process of comparing multiple subjects and identifying their differences and similarities.

[1051] "Automation" refers to the process by which machines or software perform tasks automatically, without human intervention.

[1052] "Speed ​​of knowledge acquisition" is an indicator of how quickly necessary information and knowledge can be acquired.

[1053] A "generative AI model" refers to an algorithm or system that uses artificial intelligence techniques to generate new information or predictions from data.

[1054] "Recommendation Rank" refers to the result of prioritizing targets based on specific criteria.

[1055] A "prompt" refers to an instruction or question input to a generative AI model.

[1056] A "dashboard" is an interface for visually displaying data and information.

[1057] "Terminal" refers to a device that allows a user to input and output information.

[1058] The present invention is a system for automating competitive analysis, information organization, and comparative analysis of commercial products, with the aim of improving the efficiency of sales activities. A specific embodiment of this system will be described below.

[1059] The server first collects sales representative activity data and customer information. This data is obtained from CRM systems and sales support tools. Specifically, it connects to these systems via API to obtain the necessary data. Common examples of CRM systems include Salesforce and HubSpot.

[1060] Next, the server analyzes the collected data using the Python pandas library. The server cleans the data and extracts necessary features, such as customer purchasing history and the frequency of sales activities.

[1061] The server then uses a generative AI model to calculate a recommendation ranking for each sales representative. For example, OpenAI's GPT-4 is used as the generative AI model. The server generates a prompt sentence and inputs it into the AI ​​model. An example of a specific prompt sentence is, "Based on Sales Representative A's customer list, please calculate the recommendation ranking for each customer."

[1062] The server generates a dashboard that visually displays the recommendation rankings obtained from the generative AI model. The dashboard is built using React, a JavaScript framework. The server passes data including the recommendation rankings to a React component to generate the dashboard.

[1063] Finally, the device (sales representative's PC or tablet) displays the dashboard generated by the server. The sales representative accesses the dashboard through a browser and checks the recommended ranking. Specifically, the device opens a browser, accesses the server's URL, and displays the generated dashboard.

[1064] For example, when calculating the recommendation ranking based on the customer list of sales representative A, the following specific operations are performed:

[1065] 1. The server calls the CRM system's API and retrieves sales representative A's activity log.

[1066] 2. The server uses the API of the sales support tool to obtain customer information for sales representative A.

[1067] 3. The server uses pandas to clean the data and extract features such as customer purchasing history and frequency of sales activities.

[1068] 4. The server generates a prompt sentence: "Based on Salesperson A's customer list, calculate the recommendation ranking for each customer." and inputs it into GPT-4.

[1069] 5. The server passes the recommendation ranking obtained from GPT-4 to the React application and generates a dashboard.

[1070] 6. The device opens a browser, accesses the server URL, and displays the generated dashboard.

[1071] This allows the salesperson to quickly obtain the necessary information and carry out effective sales activities. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1072] Step 1: Data collection

[1073] The server collects sales representative activity data and customer information. As input, it uses the API of the CRM system and sales support tool. Specifically, the server calls the API of the CRM system to obtain the sales representative activity log. It also obtains customer information using the API of the sales support tool. As output, the collected data is stored in a database.

[1074] Step 2: Data analysis

[1075] The server analyzes the collected data. As input, it uses the sales activity data and customer information stored in the database. Specifically, the server uses Python's pandas library to create a data frame and handle missing values. It also extracts features such as customer purchasing history and sales activity frequency. The analyzed data is obtained as output.

[1076] Step 3: Calculating the recommended ranking

[1077] The server uses a generative AI model to calculate the recommendation ranking. The parsed data and a prompt are used as input. Specifically, the server generates a prompt such as "Based on Salesperson A's customer list, please calculate the recommendation ranking for each customer." and inputs it into the generative AI model (e.g., GPT-4). The output from the generative AI model is the recommendation ranking.

[1078] Step 4: Generate a dashboard

[1079] The server generates a dashboard that visually displays the recommendation rankings. It uses the recommendation ranking data as input. Specifically, the server uses React, a JavaScript framework, to generate tables and graphs that display the recommendation rankings. The generated dashboard is obtained as output.

[1080] Step 5: View the dashboard

[1081] The terminal displays the dashboard generated from the server. As input, it uses a browser to access the server's URL. Specifically, the terminal opens a browser, accesses the server's URL, and displays the generated dashboard. As output, it displays a dashboard where the sales representative can check the recommendation ranking.

[1082] This allows sales personnel to quickly obtain the necessary information and carry out effective sales activities.

[1083] (Application example 3)

[1084] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1085] In traditional sales activities, competitive analysis of products, organizing information, and comparative analysis with competing services are often done manually, resulting in inefficiency. Furthermore, there is a lack of support for sales representatives to quickly grasp information and develop optimal sales strategies. As a result, sales activities are not streamlined, making it difficult to maximize sales. Furthermore, there is a lack of ways to effectively utilize customer data and sales history, making it difficult to optimize sales strategies.

[1086] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1087] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for providing a dashboard that visually displays recommended rankings, and means for analyzing customer data and sales history using a generative AI model and proposing optimal sales strategies, thereby enabling sales representatives to quickly grasp information and develop optimal sales strategies.

[1088] A "multi-product competitive analysis" is the evaluation and comparison of the competitive situation in the market for different types of products.

[1089] "Information organization" means systematically classifying collected data and information and organizing it into an easy-to-understand form.

[1090] "Improving sales efficiency" means optimizing sales processes and making effective use of time and resources to maximize sales results.

[1091] "Comparative analysis including competing services" means comparing and analyzing your company's products with those of your competitors from various perspectives.

[1092] "Increasing the speed of knowledge acquisition" means improving the ability to quickly gather and understand necessary information and knowledge.

[1093] A "dashboard that visually displays recommended rankings" is an interface that visually and clearly displays which products and customers sales representatives should prioritize.

[1094] A "generative AI model" is a model that uses machine learning algorithms to analyze data and make predictions and classifications.

[1095] "Customer Data" refers to information about a customer, including age, gender, purchase history, number of interactions, etc.

[1096] "Sales history" is a record of past sales activities, and is data indicating which products were sold, when, and to which customers.

[1097] "Proposing the optimal sales strategy" means presenting specific policies and action plans for carrying out effective sales activities based on collected data.

[1098] The following system configuration will be described as an embodiment of the present invention.

[1099] The server includes means for conducting competitive analysis and organizing information on a variety of products, means for streamlining sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for providing a dashboard that visually displays recommended rankings, and means for analyzing customer data and sales history using a generative AI model to propose optimal sales strategies.

[1100] Hardware and software used

[1101] Hardware: Servers, smartphones

[1102] Software: Python, Pandas, Scikit-learn, Matplotlib, Streamlit

[1103] Data processing and calculation

[1104] 1. Data Loading: The server loads a dataset containing customer data and sales history, including customer age, purchase history, number of interactions, etc.

[1105] 2. Feature and target setting: The server sets the customer's age, purchase history, and number of interactions as features and the likelihood of purchase as a target.

[1106] 3. Data Splitting: The server splits the data into training data and test data.

[1107] 4. Train the model: The server trains the model using a random forest classifier.

[1108] 5. Calculation of recommendation ranking: The server makes predictions on the test data and calculates the recommendation ranking.

[1109] 6. Creating a dashboard: The server uses Streamlit to create a dashboard that visually displays the recommendation rankings.

[1110] Specific examples

[1111] For example, Customer A is 35 years old, has made 5 purchases in the past 6 months, and has 10 interactions, while Customer B is 28 years old, has made 2 purchases in the past 6 months, and has 5 interactions. Based on this data, the server uses a generative AI model to predict the likelihood of purchase and calculate a recommendation ranking.

[1112] Prompt Sentence Examples

[1113] Use customer data to create a dashboard that predicts purchase likelihood and calculates recommendation rankings. Use customer age, purchase history, and number of interactions as features to train a model using a random forest classifier. Use Streamlit to create a dashboard that visually displays the recommendation rankings.

[1114] In this way, the server provides a system that enables sales personnel to quickly grasp information and formulate optimal sales strategies.

[1115] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1116] Step 1:

[1117] The server loads a dataset containing customer data and sales history. Specifically, it loads data from the sales_data.csv file and retrieves information such as customer age, purchase history, and number of interactions. The input is the sales_data.csv file, and the output is customer data in a data frame format.

[1118] Step 2:

[1119] The server sets features and targets from customer data. Specifically, the customer's age, purchase history, and number of interactions are set as features (X), and the likelihood of purchase is set as target (y). The input is customer data in data frame format, and the output is a dataset of features (X) and targets (y).

[1120] Step 3:

[1121] The server splits the data into training data and test data. Specifically, it uses Scikit-learn's train_test_split function to split the dataset into 80% training data and 20% test data. The input is a dataset of features (X) and targets (y), and the output is training data (X_train, y_train) and test data (X_test, y_test).

[1122] Step 4:

[1123] The server trains a model using a random forest classifier. Specifically, it uses Scikit-learn's RandomForestClassifier to train a model based on training data (X_train, y_train). The input is the training data (X_train, y_train), and the output is a trained random forest model.

[1124] Step 5:

[1125] The server makes predictions on the test data and calculates the recommendation ranking. Specifically, it uses a trained random forest model to make predictions on the test data (X_test) and calculates the likelihood of purchase. The input is the test data (X_test) and the trained model, and the output is the prediction result (likelihood of purchase).

[1126] Step 6:

[1127] The server uses Streamlit to create a dashboard that visually displays the recommendation ranking. Specifically, it calculates the recommendation ranking based on the prediction results and creates graphs and tables that visually display each customer's likelihood of purchase. The input is the prediction result (likelihood of purchase), and the output is a visually displayed dashboard.

[1128] In this way, the server provides a system that enables sales personnel to quickly grasp information and formulate optimal sales strategies.

[1129] 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.

[1130] "Example 1"

[1131] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes a user's emotions and adjusts the recommendation ranking of products based on those emotions. Specifically, it raises the recommendation ranking for products that the user feels happy or excited about, and lowers the recommendation ranking for products that the user feels displeasure or anger about. This emotion engine recognizes emotions from the user's facial expressions, tone of voice, and content posted on social media.

[1132] "Example 2"

[1133] Another embodiment is a system in which an emotion engine adjusts the method of providing information to a salesperson. This system adjusts the timing and content of information provided to the salesperson according to the user's emotions. Specifically, when a user shows joy or excitement, the system provides information that encourages sales activities toward that user, and conversely, when the user shows displeasure or anger, the system provides information that discourages sales activities toward that user.

[1134] "Example 3"

[1135] Furthermore, as a concrete example, let's consider a scenario in which a system incorporating an emotion engine is actually in operation. Suppose a user expresses joy toward a particular product. The emotion engine captures this information and raises the product's recommendation ranking. This information is then provided to a sales representative, who then uses this information to conduct sales activities toward the user. In this way, a system incorporating an emotion engine accurately captures user emotions and reflects them in the product recommendation ranking and sales activities, thereby achieving more effective sales activities.

[1136] The processing flow of each embodiment will be described below.

[1137] "Example 1"

[1138] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are recognized from the user's facial expressions, tone of voice, and the content of posts on social media.

[1139] Step 2: The emotion engine adjusts the recommendation ranking based on the emotions it recognizes. Specifically, it raises the recommendation ranking for products that evoke joy or excitement in the user, and lowers the recommendation ranking for products that evoke displeasure or anger.

[1140] "Example 2"

[1141] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are recognized from the user's facial expressions, tone of voice, and the content of posts on social media.

[1142] Step 2: Based on the emotions recognized by the emotion engine, the way information is provided to the salesperson is adjusted. Specifically, when the user shows joy or excitement, information is provided that encourages sales activities toward that user. Conversely, when the user shows displeasure or anger, information is provided that discourages sales activities toward that user.

[1143] "Example 3"

[1144] Step 1: Let's say a user expresses joy about a particular product. This information is captured by the emotion engine.

[1145] Step 2: The emotional engine increases the product's recommendation ranking.

[1146] Step 3: The emotion engine provides that information to the salesperson.

[1147] Step 4: The sales representative uses this information to conduct sales activities toward the user.

[1148] Example 1

[1149] Next, a description will be given of Example 1 of Form 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."

[1150] Conventional competitive analysis systems for products can collect information such as product characteristics, prices, and customer ratings, and perform comparative analysis. However, they are unable to adjust the recommendation ranking based on user sentiment, making it difficult to increase user satisfaction. Furthermore, the collected information is often managed and analyzed manually, making it difficult to conduct efficient sales activities. Furthermore, there is a lack of means to increase the speed of knowledge acquisition, making this insufficient in today's business environment, where rapid decision-making is required.

[1151] 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.

[1152] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for recognizing a user's emotions and adjusting the ranking of recommended products based on the emotions, means for storing collected information in a database, means for analyzing collected data, means for recognizing emotions from a user's facial expressions, tone of voice, and text data, and means for displaying the recommendation results through a user interface. This enables product recommendations that take the user's emotions into consideration, thereby increasing user satisfaction. Furthermore, the automation of information collection, management, and analysis enables efficient sales activities and supports rapid decision-making.

[1153] "Diverse merchandise" refers to goods and services that belong to different types or categories.

[1154] "Competitive analysis" refers to the process of comparing multiple products and evaluating their respective strengths and weaknesses.

[1155] "Information organization" refers to the systematic classification of collected data and arranging it in a form that is easy to understand.

[1156] "Improving sales efficiency" refers to optimizing sales processes and making effective use of time and resources.

[1157] "Automated comparative analysis" refers to the process of comparing products using a system rather than manually.

[1158] "Increasing the speed of knowledge acquisition" refers to improving the ability to quickly gather and understand necessary information.

[1159] "Recognizing user emotions" refers to analyzing emotions from the user's facial expressions, tone of voice, text data, etc.

[1160] "Adjusting the recommendation order" refers to changing the priority of products based on the user's emotional data.

[1161] "Storing in a database" refers to storing collected information in a database system.

[1162] "Analyzing data" refers to analyzing collected data using statistical methods and algorithms.

[1163] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[1164] This invention is a system for conducting competitive analysis and information organization for various products, specifically including means for collecting information such as product characteristics, prices, and customer reviews, and automating comparative analysis between products based on this information. It also includes means for increasing the speed of knowledge acquisition and means for recognizing user emotions and adjusting the order of recommended products based on those emotions.

[1165] The server uses a web scraping tool (e.g., BeautifulSoup, Scrapy) to collect information from the Internet, such as product characteristics, prices, and customer reviews. The collected data is stored in a database such as MySQL or PostgreSQL. The server uses Python libraries such as Pandas and NumPy to analyze the collected data and compare products.

[1166] The device uses a camera to recognize the user's facial expressions and analyzes them using libraries such as OpenCV and Dlib. The device also uses a microphone to collect the user's tone of voice and performs voice analysis using libraries such as Librosa. The device also collects social media posts and performs text analysis using libraries such as NLTK and Transformers.

[1167] The server adjusts the recommendation ranking of products based on the user's emotional data obtained from the emotion engine. Specifically, it raises the recommendation ranking for products that the user feels happy or excited about, and lowers the recommendation ranking for products that the user feels displeasure or anger about. The terminal displays the most suitable products for the user based on the recommendation ranking received from the server. A list of recommended products is displayed through the user interface, and detailed information is provided.

[1168] As a concrete example, consider a user looking for a new smartphone. The server collects the characteristics (e.g., battery life, camera performance), price, and customer ratings of each smartphone. Based on the collected data, it calculates an overall rating for each smartphone and performs a comparative analysis. If the user expresses a happy expression after reading a review of a particular smartphone, it raises the recommendation ranking of that smartphone. Based on the user's emotional data, it adjusts the recommendation ranking and suggests the most suitable smartphone.

[1169] Example prompt sentence:

[1170] "I'm looking for a new smartphone. Can you recommend a model with a long battery life and a good camera?"

[1171] In this way, the server and the terminal cooperate to realize a system that proposes the most suitable products to the user.

[1172] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1173] Step 1: Data collection

[1174] The server uses a web scraping tool to collect information such as product characteristics, prices, and customer reviews from the Internet. Specifically, the server accesses the specified URLs and analyzes the HTML structure to extract the required data. The input is a list of URLs containing product information, and the output is a data list containing product characteristics, prices, customer reviews, and other information.

[1175] Step 2: Database Management

[1176] The server stores the collected data in a database. Specifically, the server establishes a database connection and inserts the collected data into the appropriate tables. The input is the collected product data, and the output is the product data stored in the database.

[1177] Step 3: Data analysis

[1178] The server analyzes the collected data. Specifically, it uses Python libraries such as Pandas and NumPy to clean, filter, and aggregate the data and compare products. The input is product data obtained from the database, and the output is comparison data for the products as the analysis results.

[1179] Step 4: Emotion Recognition

[1180] The device uses a camera to recognize the user's facial expressions and analyzes them using libraries such as OpenCV and Dlib. The device also uses a microphone to collect the user's tone of voice and performs voice analysis using libraries such as Librosa. The device also collects social media posts and performs text analysis using libraries such as NLTK and Transformers. The inputs are the user's facial expressions, tone of voice, and text data, and the output is the user's emotional data.

[1181] Step 5: Adjust the recommended ranking

[1182] The server adjusts the recommendation ranking of products based on the user's emotional data obtained from the emotion engine. Specifically, it raises the recommendation ranking for products that the user feels happy or excited about, and lowers the recommendation ranking for products that the user feels displeasure or anger about. The inputs are the user's emotional data and product comparison data, and the output is the adjusted recommendation ranking for the products.

[1183] Step 6: Viewing recommended results

[1184] The terminal displays the most suitable products for the user based on the recommendation ranking received from the server. Specifically, the terminal displays a list of recommended products and provides detailed information through a user interface. The input is the adjusted recommendation ranking of the products, and the output is the list of products to be displayed to the user.

[1185] (Application example 1)

[1186] Next, a description will be given of Application Example 1 of Form 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."

[1187] Conventional product competition analysis systems can collect information on product characteristics, prices, customer reviews, etc., and perform comparative analysis, but they have the problem of being unable to adjust the recommendation ranking based on user emotions, making it difficult to increase user satisfaction.In addition, they lack the functionality to recognize user emotions in real time and adjust the recommendation ranking based on that, which means they are unable to maximize users' purchasing motivation.

[1188] 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.

[1189] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for recognizing a user's emotions and adjusting the ranking of recommended products based on those emotions, and means for recognizing emotions from the user's facial expressions, tone of voice, and text content. This makes it possible to recommend products that take the user's emotions into consideration, thereby increasing user satisfaction and maximizing the user's purchasing motivation.

[1190] "Diverse merchandise" is a general term for products and services with different types and characteristics.

[1191] "Competitive analysis" is the process of comparing the characteristics, prices, customer reviews, etc. of multiple products or services to evaluate their competitiveness.

[1192] "Information organization" is the process of systematically classifying collected data and arranging it in an easy-to-understand form.

[1193] "Improving sales efficiency" refers to optimizing sales processes and making effective use of time and resources.

[1194] "Automated comparative analysis" refers to the use of algorithms or software to automatically perform comparative analysis that would otherwise be performed manually.

[1195] "Increasing the speed of knowledge acquisition" means quickly gathering the necessary information and knowledge and making it available.

[1196] "Recognizing the user's emotions" refers to analyzing and understanding the user's emotions from facial expressions, tone of voice, text content, etc.

[1197] "Adjust recommended ranking" refers to changing the display order of products based on specific criteria.

[1198] "Facial expression" refers to changes in emotion and mood expressed through the movement of facial muscles.

[1199] "Vocal tone" refers to vocal characteristics such as pitch, strength, and rhythm, and is an element that conveys emotion and intention.

[1200] "Text content" refers to information including the meaning and emotion of sentences and words.

[1201] As an embodiment of the present invention, we will explain how to implement an emotion-based product recommendation system as a smartphone application. This system has the function of recognizing a user's emotion in real time and adjusting the order of recommended products based on that emotion.

[1202] Hardware and software used

[1203] Hardware

[1204] Smartphone: camera, microphone

[1205] software

[1206] OpenCV: Image processing library

[1207] Keras: A deep learning library

[1208] TextBlob: A text sentiment analysis library

[1209] Requests: HTTP request library

[1210] Data processing and calculation

[1211] Facial Emotion Recognition

[1212] The server captures the user's facial expressions using the smartphone camera and detects the face using OpenCV. The detected facial image is input to a Keras emotion recognition model to analyze the user's emotions. This model identifies emotions such as joy, anger, and surprise from facial expressions.

[1213] Emotion recognition of tone of voice

[1214] The server captures the user's voice using the smartphone's microphone and analyzes the voice data, analyzing voice characteristics such as pitch, intensity, and rhythm to identify the user's emotions.

[1215] Emotion recognition of text content

[1216] The server collects text content posted by users on social media and reviews, analyzes the sentiment of the text using TextBlob, and identifies positive, negative, and neutral sentiments.

[1217] Adjustment of recommended product rankings

[1218] The server adjusts the order of recommended products based on the collected emotional data. For example, if a user expresses joy or excitement, highly rated products that match that emotion are displayed first. On the other hand, if a user expresses displeasure or anger, products that do not match that emotion are displayed lower in the display order.

[1219] Specific examples

[1220] When a user is browsing products on their smartphone, if the camera detects that the user is smiling, the system will prioritize displaying highly rated products to that user. Also, if a user posts on social media, "This product is great!", the system will analyze that emotion and recommend similarly highly rated products.

[1221] Prompt Sentence Examples

[1222] Develop an application that recognizes a user's emotions in real time and recommends products based on those emotions. The application should recognize emotions from the user's facial expressions, tone of voice, and social media posts, and prioritize displaying products that indicate joy or excitement, and lower the ranking of products that indicate displeasure or anger.

[1223] In this way, it becomes possible to recommend products that take the user's emotions into consideration, thereby increasing user satisfaction and maximizing the user's purchasing motivation.

[1224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1225] Step 1:

[1226] The server captures the user's facial expressions using the smartphone's camera. The input is real-time video from the camera, and the output is a facial image. Specifically, the camera detects the user's face and captures its image.

[1227] Step 2:

[1228] The server uses OpenCV to detect faces from the captured facial image. The input is the facial image obtained in step 1, and the output is an image with the facial area cut out. Specifically, the face detection algorithm identifies the position of the face and cuts out that area.

[1229] Step 3:

[1230] The server inputs the facial image into the Keras emotion recognition model and analyzes the user's emotions. The input is the facial image obtained in step 2, and the output is the emotion identification result (e.g., joy, anger, surprise, etc.). Specifically, the facial image is input into the model and the probability distribution of emotions is calculated.

[1231] Step 4:

[1232] The server captures the user's voice using the smartphone's microphone. The input is audio data from the microphone, and the output is an audio file. Specifically, the microphone records the user's voice and saves the data.

[1233] Step 5:

[1234] The server analyzes the audio data and identifies emotions from the tone of the voice. The input is the audio file obtained in step 4, and the output is the emotion identification result. Specifically, the audio analysis algorithm analyzes the pitch, intensity, and rhythm of the voice to identify the emotion.

[1235] Step 6:

[1236] The server collects text content posted by users on social media and reviews, and analyzes the sentiment of the text using TextBlob. The input is text data, and the output is the sentiment identification result. Specifically, the text analysis algorithm identifies positive, negative, or neutral sentiment in the text.

[1237] Step 7:

[1238] The server adjusts the product recommendation ranking based on the collected emotion data. The input is the emotion data obtained in steps 3, 5, and 6, and the output is the adjusted product recommendation ranking. Specifically, the server integrates the emotion data and applies an algorithm to change the product display order.

[1239] Step 8:

[1240] The server displays the adjusted product recommendation ranking on the user's smartphone. The input is the recommendation ranking obtained in step 7, and the output is a product list displayed on the user's smartphone screen. Specifically, the server generates a product list based on the recommendation ranking and displays it on the user's screen.

[1241] Example 2

[1242] Next, a description will be given of Example 2 of Form 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."

[1243] Conventional product information collection and analysis systems have difficulty efficiently collecting information such as product characteristics, prices, and customer reviews, and conducting comparative analysis. Furthermore, sales activities often had to be adjusted manually based on user sentiment, placing a heavy burden on sales representatives. This resulted in insufficient efficiency in sales activities, and sometimes led to inappropriate calculations of product recommendation rankings and inappropriate timing for providing information.

[1244] 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.

[1245] In this invention, the server includes means for collecting product information from websites, means for storing the collected data in a database, means for calculating a recommended product ranking using a machine learning algorithm, means for collecting user emotion data, means for analyzing user emotions using an emotion analysis algorithm, and means for adjusting the timing and content of information provided to sales representatives based on the analysis results. This enables efficient collection and analysis of product information and realizes appropriate adjustment of sales activities in accordance with user emotions.

[1246] A "website" is a collection of information made publicly available on the Internet and is a page with a specific URL.

[1247] "Product information" refers to information such as product characteristics, price, and customer reviews, and is detailed data about the product.

[1248] A "database" is a system for efficiently storing, managing, and searching collected data.

[1249] A "machine learning algorithm" is a computational method for learning patterns based on data and making predictions and classifications.

[1250] The "recommended ranking" is the result of evaluating and prioritizing products based on specific criteria.

[1251] "User emotion data" is information about emotions obtained from user input and actions.

[1252] An "emotion analysis algorithm" is a computational method for analyzing a user's text and behavioral data to identify their emotions.

[1253] A "sales representative" is someone whose job is to sell products and deal with customers.

[1254] "Timing of providing information" refers to the optimal time or moment for a sales representative to provide information to a user.

[1255] The "contents of information provided" refers to specific information that the sales representative provides to the user.

[1256] The present invention is a system for collecting and analyzing product information, calculating recommendation rankings, and adjusting sales activities based on user sentiment. A specific embodiment of this system will be described below.

[1257] Collection and analysis of product information

[1258] The server uses web scraping technologies such as Python's BeautifulSoup and Scrapy to collect information such as product characteristics, prices, and customer reviews, automatically gathering the necessary information from databases and websites on the Internet.

[1259] The terminal stores the collected data for subsequent processing. MySQL or PostgreSQL is generally used as the database.

[1260] The server automatically calculates the recommended product rankings based on the collected information using machine learning algorithms, specifically machine learning libraries such as Scikit-learn and TensorFlow.

[1261] Examples:

[1262] The server collects product information from a specific website.

[1263] The device stores the collected data in a MySQL database.

[1264] The server uses Scikit-learn to calculate the recommended ranking of products based on the collected data.

[1265] Example prompt for a generative AI model:

[1266] "Collect product information from specific websites and calculate recommendation rankings based on customer ratings and prices."

[1267] Adjusting information provision with an emotion engine

[1268] The server collects user input and behavioral data to analyze user sentiment. Specifically, it uses JavaScript and Python's Flask to collect user text input and click history.

[1269] The device stores the collected emotion data for subsequent processing. MongoDB or Firebase is commonly used as the database.

[1270] The server analyzes the user's emotions using a sentiment analysis algorithm, specifically using NLP (natural language processing) libraries such as NLTK and Transformers.

[1271] The server adjusts the timing and content of information provided to the sales representative based on the analysis results. For example, when the user shows signs of joy or excitement, the server provides information that encourages sales activities toward the user, and conversely, when the user shows signs of displeasure or anger, the server provides information that discourages sales activities toward the user.

[1272] Examples:

[1273] The server collects users' chat histories and performs sentiment analysis.

[1274] The device stores the collected data in MongoDB.

[1275] The server uses Transformers to analyze the user's emotions and provide appropriate information to the sales representative.

[1276] Example prompt for a generative AI model:

[1277] "Analyze users' chat histories and tailor the information you provide to your salespeople based on their sentiment."

[1278] The above is a specific embodiment for carrying out the present invention. This system enables efficient collection and analysis of product information, and realizes appropriate adjustment of sales activities according to user emotions.

[1279] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1280] Collection and analysis of product information

[1281] Step 1:

[1282] The server collects product information from the website.

[1283] Input: URL of a specific website

[1284] Specific operation: The server uses Python's BeautifulSoup or Scrapy to access the specified website and extract information such as product characteristics, price, and customer reviews.

[1285] Output: List of extracted product information

[1286] Step 2:

[1287] The terminal stores the collected data in a database.

[1288] Input: List of collected product information

[1289] Specific operation: The terminal uses MySQL or PostgreSQL to insert the collected product information into a database table.

[1290] Output: Product information stored in the database

[1291] Step 3:

[1292] The server calculates the recommended ranking of products using a machine learning algorithm.

[1293] Input: Product information stored in the database

[1294] Specific operation: The server uses Scikit-learn and TensorFlow to apply random forest algorithms based on product information to calculate the recommended ranking of products.

[1295] Output: A list of recommended products with ranking

[1296] Adjusting information provision with an emotion engine

[1297] Step 1:

[1298] The server collects the user's emotion data.

[1299] Input: User text input and click history

[1300] How it works: The server uses JavaScript and Python's Flask to collect users' chat history and click history.

[1301] Output: Collected emotion data

[1302] Step 2:

[1303] The device stores the collected emotion data in a database.

[1304] Input: Collected emotion data

[1305] Specific operation: The device inserts the collected emotion data into a database collection using MongoDB or Firebase.

[1306] Output: Emotion data stored in a database

[1307] Step 3:

[1308] The server analyzes the user's emotions using an emotion analysis algorithm.

[1309] Input: Emotion data stored in a database

[1310] Specific operation: The server uses NLTK and Transformers, which are NLP (natural language processing) libraries, to analyze emotion data and identify the user's emotion.

[1311] Output: Analyzed user emotion information

[1312] Step 4:

[1313] The server adjusts the timing and content of information provided to sales representatives based on the analysis results.

[1314] Input: Analyzed user emotion information

[1315] Specific operation: If the user shows signs of joy or excitement, the server provides the sales representative with "information that will promote sales activities toward this user," and conversely, if the user shows signs of displeasure or anger, the server provides "information that will discourage sales activities."

[1316] Output: Pertinent information provided to salespeople

[1317] The above are the specific processing steps of the program of this system.

[1318] (Application example 2)

[1319] Next, a description will be given of Application Example 2 of Form 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."

[1320] Conventional systems aimed at analyzing product competition, organizing information, and streamlining sales activities do not provide information that takes user emotions into consideration, making it difficult to maximize users' purchasing motivation. Furthermore, they lack real-time promotional information notifications, which can result in missed opportunities to pique users' interest. This results in limited effectiveness in calculating product recommendation rankings and sales activities.

[1321] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1322] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for analyzing user emotions and providing information according to the emotions, and means for notifying promotion information in real time. This makes it possible to provide information at an appropriate time according to the user's emotions, thereby maximizing the effectiveness of calculation of recommended product rankings and sales activities.

[1323] A "multi-product competitive analysis" is the process of evaluating and comparing the market competitiveness of several different products or services.

[1324] "Information organization" is the process of systematically classifying collected data and information and summarizing it in an easy-to-understand format.

[1325] "Improving sales efficiency" refers to efforts to optimize sales processes and maximize results while reducing effort and time.

[1326] "Comparative analysis including competing services" is an analytical method that compares a company's products and services with those of its competitors to identify advantages and areas for improvement.

[1327] "Increasing the speed of knowledge acquisition" means improving the ability to quickly gather and understand necessary information and knowledge.

[1328] "Analyzing user emotions" is a technology that reads and analyzes emotions from a user's facial expressions, voice, text, etc.

[1329] "Providing information according to emotions" means providing information with appropriate timing and content based on the user's emotional state.

[1330] "Real-time promotion information notification" means sending promotion information instantly in response to the user's actions and emotions.

[1331] The system for implementing this invention comprises a server, a user terminal, and various software components. The details of each component and its role will be explained below.

[1332] server

[1333] The server includes the following means:

[1334] 1. Data collection methods:

[1335] Web scraping: Using libraries such as BeautifulSoup and Scrapy to gather product information from databases and websites on the internet.

[1336] API integration: Use an API that provides product information (e.g., product advertising API) to obtain detailed product data.

[1337] 2. Data analysis methods:

[1338] Machine learning algorithms: Libraries such as scikit-learn and TensorFlow are used to calculate product recommendation rankings based on collected data.

[1339] Sentiment analysis: To analyze user sentiment, we use a sentiment analysis model (e.g., BERT) that uses NLP (Natural Language Processing) techniques.

[1340] 3. Information provision method:

[1341] Real-time notifications: Use Firebase Cloud Messaging to send product suggestions and promotional information based on user sentiment in real time.

[1342] Dashboard: Provides a dashboard to display products that users are interested in and recommendation rankings.

[1343] User terminal

[1344] The user terminal is a mobile device such as a smartphone or tablet, and has the following functions:

[1345] 1. Sentiment analysis function:

[1346] The user's facial expressions and voice are analyzed in real time and their emotional state is sent to the server.

[1347] 2. Notification function:

[1348] Receive real-time notifications sent from the server and display them to the user.

[1349] Specific examples

[1350] For example, consider a case where a user is using an online shopping app on a smartphone. The user searches for a specific product (e.g., a smartphone) and while browsing the product page, the app analyzes the user's emotions from their facial expressions and voice. If the user is excited, the app sends a notification saying, "This product is currently 20% off!" to encourage the purchase.

[1351] Prompt Sentence Examples

[1352] Design an application that analyzes the user's facial and voice expressions while they are browsing a specific product page, and notifies them of promotional information in real time if they are excited. The technologies used are web scraping, machine learning algorithms, sentiment analysis, and Firebase Cloud Messaging.

[1353] In this way, by having the server and user terminal work together, it becomes possible to provide information at the appropriate time according to the user's emotions, thereby maximizing the effectiveness of calculation of product recommendation rankings and sales activities.

[1354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1355] Step 1:

[1356] Data collection

[1357] The server uses web scraping technology to collect product information from databases and websites on the Internet. Specifically, it uses libraries such as BeautifulSoup and Scrapy to obtain data such as product names, prices, and customer ratings. It also uses APIs that provide product information (e.g., product advertising APIs) to obtain detailed product data. The input is data from websites and APIs, and the output is a dataset of collected product information.

[1358] Step 2:

[1359] Data analysis

[1360] The server uses a machine learning algorithm based on the collected product information to calculate the recommended product ranking. Specifically, it uses libraries such as scikit-learn and TensorFlow to analyze data such as product characteristics, price, and customer ratings, and calculates the recommended ranking. The input is a dataset of collected product information, and the output is a list of products with a recommended ranking.

[1361] Step 3:

[1362] Emotion analysis

[1363] The user device analyzes the user's facial expressions and voice in real time and transmits the emotional state to the server. Specifically, it captures the user's facial expressions and voice using a camera and microphone, and analyzes the emotions using an emotion analysis model using NLP technology (e.g., BERT). The input is the user's facial expressions and voice data, and the output is the analyzed emotional state data.

[1364] Step 4:

[1365] Information provision

[1366] The server notifies the user of product suggestions and promotion information in real time at the appropriate time based on the user's emotional state. Specifically, it uses Firebase Cloud Messaging to send notifications according to the user's emotions. The input is the analyzed emotional state data and a list of recommended products with an order of recommendation, and the output is a notification message sent to the user's device.

[1367] Step 5:

[1368] Dashboard View

[1369] The user terminal displays the product list with the recommended ranking sent from the server on a dashboard. Specifically, the products in which the user is interested and the recommended ranking are visually displayed through a user interface. The input is the product list with the recommended ranking sent from the server, and the output is the dashboard screen displayed to the user.

[1370] In this way, by having each processing step work in conjunction with one another, it becomes possible to provide information at the appropriate time according to the user's emotions, thereby maximizing the effectiveness of calculation of product recommendation rankings and sales activities.

[1371] Example 3

[1372] Next, a description will be given of Example 3 of Form Example 3. 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."

[1373] In conventional sales activities, competitive analysis of products and information organization were often done manually, resulting in inefficiency. Furthermore, comparative analysis with competing services was also done manually, which took time and effort, and slowed down the speed of knowledge acquisition. Furthermore, it was difficult to accurately grasp user emotions and reflect them in sales activities, making it difficult to achieve effective sales activities.

[1374] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes means for performing competitive analysis and information organization of various products, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for collecting user emotion data, means for analyzing the collected emotion data, means for calculating a recommended ranking of products based on the analyzed emotion data, means for generating a dashboard that visually displays the recommended ranking, and means for providing the recommended ranking to sales representatives. This automates the competitive analysis of products and information organization, thereby enabling the efficiency of sales activities. Furthermore, calculating and providing a recommended ranking based on user emotion data enables more effective sales activities.

[1375] "A means of conducting competitive analysis and organizing information on a variety of products" is a function for collecting data on multiple products, comparing, analyzing, and organizing them.

[1376] "Means aimed at improving the efficiency of sales activities" are functions that support sales representatives in carrying out their work efficiently.

[1377] "Means for automating comparative analysis, including competing services" refers to a function for automatically collecting information on competing services and products and comparing and analyzing them.

[1378] "Means for increasing the speed of knowledge acquisition" refers to functions that enable necessary information and knowledge to be acquired quickly.

[1379] The "means for collecting user emotion data" is a function for collecting data relating to emotions displayed by the user.

[1380] The "means for analyzing collected emotion data" is a function for analyzing collected user emotion data and understanding its contents.

[1381] The "means for calculating the recommendation ranking of a product based on the analyzed emotion data" is a function for calculating the recommendation ranking of a product based on the analysis results.

[1382] The "means for generating a dashboard that visually displays the recommendation ranking" is a function for generating a dashboard that visually displays the calculated recommendation ranking in an easy-to-understand manner.

[1383] The "means for providing a sales representative with a recommended ranking" is a function for providing the calculated recommended ranking to the sales representative and for using it in sales activities.

[1384] MODE FOR CARRYING OUT THE INVENTION

[1385] The present invention is a system for collecting user emotion data, calculating a recommendation ranking for products based on the collected data, and providing the ranking to a sales representative. A specific embodiment of this system will be described below.

[1386] 1. Generating the system program

[1387] The server generates a program incorporating an emotion engine and a recommendation ranking calculation algorithm. This program has the function of collecting user emotion data and calculating the recommendation ranking of products based on that data.

[1388] 2. Explanation of program processing

[1389] The server uses an emotion engine (e.g., IBM Watson's emotion analysis API) to collect user emotion data. The emotion engine analyzes the emotions (e.g., joy, interest) that users show toward a specific product and stores the results in a database.

[1390] Next, the server runs a recommendation ranking calculation algorithm based on the stored emotion data. This algorithm calculates the recommendation ranking for each product, taking into account the user's emotion data and the characteristics of the product. For example, products for which the user expressed "joy" emotion will be ranked higher.

[1391] The server then generates a dashboard that visually displays the recommended rankings. This dashboard is displayed in a web browser using HTML5 and JavaScript. The dashboard displays a list of products and their recommended rankings.

[1392] The terminal (salesperson's PC or tablet) displays the dashboard provided by the server. The salesperson checks the recommendation ranking based on the user's emotional data through the dashboard and carries out sales activities. For example, they may propose products with a high recommendation ranking to the user.

[1393] 3. Examples and prompts

[1394] As a concrete example, suppose a user expresses "joy" about a new smartphone. The emotion engine captures this information and raises the smartphone's recommendation ranking. This information is then provided to sales representatives via a dashboard. Sales representatives then use this information to make sales calls to the user.

[1395] Example prompts to input to the generative AI model:

[1396] "Please explain the program that calculates the ranking of recommended products based on the sentiment data that users have shown toward specific products and generates a dashboard to provide to sales representatives."

[1397] In this way, the system accurately captures the user's emotions and reflects them in the product recommendation ranking and sales activities, thereby achieving more effective sales activities. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1398] Step 1: Collecting user emotion data

[1399] A user browses a specific product on an online shopping site and posts a review or comment. At this time, the user's emotional data (e.g., joy, interest) is collected. The input is the user's text comment, and the output is emotional data. Specifically, a user posts a comment such as "This smartphone is great!"

[1400] Step 2: Analyze the emotion data

[1401] The server sends the collected user emotion data to an emotion engine (for example, IBM Watson's emotion analysis API). The emotion engine analyzes the text data and quantifies the user emotion. The input is the user's text comment, and the output is quantified emotion data. Specifically, the emotion of "joy" is highly evaluated based on the comment "This smartphone is great!"

[1402] Step 3: Calculating the recommended ranking

[1403] The server runs a recommendation ranking calculation algorithm based on the analyzed emotional data. The algorithm calculates the recommendation ranking for each product by taking into account the user's emotional data and the product's characteristics. The input is quantified emotional data, and the output is the product's recommended ranking. Specifically, it raises the recommendation ranking of smartphones for which the user expresses the emotion of "joy."

[1404] Step 4: Generate a dashboard

[1405] The server generates a dashboard to visually display the calculated recommendation ranking. The dashboard is displayed on a web browser using HTML5 and JavaScript. The input is the recommended ranking of products, and the output is a visually displayed dashboard. Specifically, smartphones with high recommendation rankings are displayed at the top of the list.

[1406] Step 5: Provide information to sales representatives

[1407] The device (salesperson's PC or tablet) displays the dashboard provided by the server. The salesperson checks the recommendation ranking based on the user's emotional data through the dashboard and carries out sales activities. The input is the visually displayed dashboard, and the output is the salesperson's actions. Specifically, the smartphone with the highest recommendation ranking is suggested to the user.

[1408] (Application example 3)

[1409] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1410] In conventional sales activities, it was difficult to accurately grasp customer emotions and recommend products based on them, making it difficult for sales representatives to quickly grasp information and conduct efficient sales activities.In addition, because real-time analysis of customer emotions and the recommendation of products based on that analysis were not performed, improvement of customer satisfaction and maximization of sales results were not fully achieved.

[1411] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1412] In this invention, the server includes means for performing competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for analyzing customer sentiment in real time and calculating a recommended ranking of products based on the analysis, means having an interface for visually displaying the recommended ranking, and means for displaying recommended products using a smart device. This enables real-time recommendation of products based on customer sentiment, enabling sales representatives to quickly grasp information and conduct efficient sales activities.

[1413] "Diverse merchandise" is a general term for products and services with different types and characteristics.

[1414] "Competitive analysis" is the process of comparative evaluation of competitors and competing products.

[1415] "Information organization" is the process of systematically classifying and organizing collected data and information.

[1416] "Sales activities" are a series of actions taken to propose and sell products and services to customers.

[1417] "Efficiency" means aiming to perform tasks or processes with less time and effort.

[1418] "Comparative analysis" is the process of comparing multiple subjects and identifying their differences and similarities.

[1419] "Automation" refers to machines or systems performing tasks automatically without human intervention.

[1420] "Knowledge acquisition rate" refers to the speed at which new information and knowledge are acquired.

[1421] "Customer sentiment" refers to the emotional response a customer has to a particular situation or product.

[1422] "Real-time" refers to the immediate processing and display of ongoing events and situations.

[1423] "Recommended Rank" is the result of prioritizing products and services based on specific criteria.

[1424] An "interface" is a point of contact or means by which a user and a system interact with each other.

[1425] "Smart device" is a general term for electronic devices that have internet connectivity and advanced computing capabilities.

[1426] "Recommended Products" are products or services suggested to users based on certain criteria or conditions.

[1427] A system for carrying out the present invention is configured as follows: The server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for analyzing customer sentiment in real time and calculating a recommended ranking of products based on the analysis, means having an interface for visually displaying the recommended ranking, and means for displaying recommended products using a smart device.

[1428] Hardware and software used

[1429] Hardware

[1430] Smart glasses (e.g. Google Glass)

[1431] Camera (built into smart glasses)

[1432] software

[1433] EmotionRecognizer: Emotion recognition engine (e.g. TensorFlow model)

[1434] RecommendationEngine: Recommendation engine (e.g. custom algorithm)

[1435] SmartGlassesDisplay: A library for controlling smart glasses displays

[1436] Data processing and calculation

[1437] Camera Input

[1438] Images are captured in real time from a camera built into the device (smart glasses), and the image of the customer's face is sent to the server.

[1439] emotion recognition

[1440] The server uses EmotionRecognizer to detect the customer's face from the video and recognize their emotions. The emotion recognition engine uses a TensorFlow model to analyze emotions such as "happiness," "sadness," and "surprise" from the customer's facial expressions.

[1441] Recommended product calculation

[1442] The server then uses a Recommendation Engine to recommend appropriate products based on the recognized emotions. The recommendation engine uses a custom algorithm to match customer emotion data with product data and select the most suitable products.

[1443] display

[1444] The server displays the recommended products on the smart glasses via SmartGlassesDisplay, allowing salespeople wearing the device (smart glasses) to check the recommended products in real time.

[1445] Specific examples

[1446] A customer approaches a salesperson wearing smart glasses, looks at a particular product, and smiles. The server uses an emotion recognition engine to detect "happiness," and the recommendation engine lists related products. The smart glasses display shows, "You seem to be interested in this product. Related products: Product A, Product B, Product C."

[1447] Prompt Sentence Examples

[1448] If a customer smiles while looking at a particular product, design a system that recognizes that emotion and recommends related products. Use smart glasses to analyze emotions in real time and display product recommendations.

[1449] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1450] Step 1:

[1451] Video is acquired in real time from the camera built into the device (smart glasses). The input is the camera image, and the output is video data. Specifically, the camera captures video including the customer's face and sends the data to the server.

[1452] Step 2:

[1453] The server uses EmotionRecognizer to detect customer faces from video data and recognize emotions. The input is video data, and the output is recognized emotion data. Specifically, the server uses a TensorFlow model to analyze facial features in the video data and identify emotions such as "happiness," "sadness," and "surprise."

[1454] Step 3:

[1455] The server's Recommendation Engine recommends appropriate products based on the recognized emotion data. The input is emotion data, and the output is a list of recommended products. Specifically, the server uses a custom algorithm to match the emotion data with product data and select the most suitable product.

[1456] Step 4:

[1457] The server displays the recommended product list on the smart glasses via SmartGlassesDisplay. The input is the recommended product list, and the output is the information displayed on the smart glasses display. Specifically, the server sends the recommended product list to the smart glasses display control library, allowing the salesperson to check the recommended products in real time.

[1458] Step 5:

[1459] The user (salesperson) conducts effective sales activities with customers based on the recommended products displayed on the smart glasses' display. The input is the information displayed on the smart glasses' display, and the output is the proposal to the customer. Specifically, the salesperson introduces the recommended products to the customer and provides an explanation to attract their interest.

[1460] 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.

[1461] 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> ) 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.

[1462] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1463] 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.

[1464] [Third embodiment]

[1465] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1466] 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.

[1467] 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).

[1468] 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.

[1469] 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.

[1470] 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).

[1471] 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.

[1472] 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.

[1473] 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.

[1474] 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.

[1475] 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.

[1476] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1477] "Example 1"

[1478] The present invention is a system for conducting competitive analysis of products and organizing information. Specifically, it includes a means for collecting information on product characteristics, prices, customer reviews, etc., a means for automating comparative analysis between products based on that information, and a means for accelerating the speed of knowledge acquisition.

[1479] "Example 2"

[1480] For example, web scraping technology, which automatically collects necessary information from internet databases and websites, can be used to collect information such as product characteristics, prices, customer reviews, etc. Furthermore, machine learning algorithms can be used to automatically calculate the recommended ranking of products based on the collected information to automate comparative analysis between products.

[1481] "Example 3"

[1482] Furthermore, to speed up the acquisition of knowledge, the system is equipped with an interface that provides sales representatives with the calculated recommended rankings. Specifically, by providing a dashboard that visually displays the recommended rankings in an easy-to-understand manner, sales representatives can quickly grasp the information and make their sales activities more efficient.

[1483] The processing flow of each embodiment will be described below.

[1484] "Example 1"

[1485] Step 1: Collect information such as product characteristics, prices, customer reviews, etc. In this step, web scraping technology is used to automatically collect the necessary information from databases and websites on the Internet.

[1486] Step 2: Conduct a comparative analysis of products based on the collected information. In this step, a machine learning algorithm is used to automatically calculate the recommended ranking of products.

[1487] Step 3: Provide the calculated recommendation ranking to the sales representative. In this step, a dashboard is provided that visually displays the recommendation ranking in an easy-to-understand manner.

[1488] "Example 2"

[1489] Step 1: Collect information such as product characteristics, prices, customer reviews, etc. In this step, web scraping technology is used to automatically collect the necessary information from databases and websites on the Internet.

[1490] Step 2: Conduct a comparative analysis of products based on the collected information. In this step, a machine learning algorithm is used to automatically calculate the recommended ranking of products.

[1491] Step 3: Provide the calculated recommendation ranking to the sales representative. In this step, a dashboard is provided that visually displays the recommendation ranking in an easy-to-understand manner.

[1492] "Example 3"

[1493] Step 1: Collect information such as product characteristics, prices, customer reviews, etc. In this step, web scraping technology is used to automatically collect the necessary information from databases and websites on the Internet.

[1494] Step 2: Based on the collected information, a comparative analysis between products is conducted. In this step, a machine learning algorithm is used to automatically calculate the recommended ranking of products.

[1495] Step 3: Provide the calculated recommendation ranking to the sales representative. In this step, a dashboard is provided that visually displays the recommendation ranking in an easy-to-understand manner.

[1496] Example 1

[1497] Next, a description will be given of Example 1 of Form 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."

[1498] Conventional competitive analysis and information organization systems for products often required manual processes of information collection, data cleansing, and comparative analysis, which was time-consuming and labor-intensive. Additionally, knowledge acquisition was slow, limiting the efficiency of sales activities. Furthermore, there was a lack of a way to quickly summarize the characteristics and competitiveness of products based on the collected information, making it difficult for sales representatives to make quick decisions.

[1499] 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.

[1500] In this invention, the server includes means for collecting information such as product characteristics, prices, and customer reviews, means for cleansing the collected information and converting it into a unified format, means for performing comparative analysis between products based on the cleansed data, means for automatically summarizing the product characteristics and competitiveness using a generative AI model, means for generating prompt sentences to be input to the generative AI model, and means for inputting the prompt sentences to the generative AI model and summarizing the results of the comparison of the products. This automates the process from information collection to data cleansing, comparative analysis, and summarization, improving the speed of knowledge acquisition and enabling more efficient sales activities.

[1501] "Merchandise" is a general term for goods and services sold in the market.

[1502] "Competitive analysis" is the process of comparing multiple products and evaluating their competitiveness and market positioning.

[1503] "Information organization" is the process of systematically organizing collected data and converting it into an easy-to-understand format.

[1504] "Sales activities" refers to a series of tasks and processes for selling products.

[1505] "Efficiency" means improving operations and processes so that they can be performed with less time and effort.

[1506] "Comparative analysis" is the process of comparing the characteristics, prices, customer reviews, etc. of multiple products and evaluating their relative merits.

[1507] "Speed ​​of knowledge acquisition" refers to the speed at which it takes to gather and understand the necessary information and knowledge.

[1508] "Information gathering" is the process of obtaining data about a product from the internet and other sources.

[1509] "Cleansing" is the process of removing unnecessary or incorrect information from collected data and converting it into an accurate and consistent format.

[1510] A "generative AI model" is a model that uses artificial intelligence to analyze data and automatically perform specific tasks.

[1511] A "prompt" is an instruction entered into a generative AI model to make it perform a specific task.

[1512] "Summarizing" is the process of concisely summarizing collected information and extracting the main points.

[1513] MODE FOR CARRYING OUT THE INVENTION

[1514] This invention relates to a system for conducting competitive analysis of products and organizing information. Specifically, it is equipped with a means for collecting information on product characteristics, prices, customer reviews, etc., and automating comparative analysis between products based on this information, as well as a means for accelerating the speed of knowledge acquisition.

[1515] Generating a Program

[1516] The server generates a program for a system that performs competitive analysis of products and organizes information. This program has the function of collecting information such as product characteristics, prices, and customer reviews, and automating comparative analysis between products based on that information. It also has a means to speed up knowledge acquisition.

[1517] Program processing explanation

[1518] The server executes the program in the following procedure.

[1519] 1. Information Collection:

[1520] The server collects information such as product characteristics, prices, and customer reviews from the Internet using web scraping tools (e.g., BeautifulSoup, Scrapy).

[1521] The collected data is stored in a database (e.g., MySQL, PostgreSQL).

[1522] 2. Data cleansing:

[1523] The server cleanses the collected data and converts it into the required format, for example, converting price information into a uniform currency unit.

[1524] Use a data processing library (e.g., Pandas) to remove unnecessary or duplicate data and transform it into an accurate and consistent format.

[1525] 3. Data Analysis:

[1526] The server performs comparative analysis between products based on the cleansed data, specifically calculating average prices and the distribution of customer ratings.

[1527] Use data analysis tools (e.g., NumPy, Scikit-learn) to compare the characteristics of different products.

[1528] 4. Speed ​​up knowledge acquisition:

[1529] The server uses a generative AI model (e.g., GPT-4) to automatically summarize the product's features and competitive advantages based on the collected information.

[1530] A prompt sentence is generated and input to the generative AI model. For example, a prompt sentence such as "Compare the characteristics and prices of product A and product B, and summarize which is more competitive" can be used.

[1531] Adding specific examples

[1532] When a user wants to conduct a competitive analysis of a new product, he or she can use the system by following the steps below.

[1533] 1. Information Collection:

[1534] The user inputs a list of products to be analyzed into the system.

[1535] The server uses a web scraping tool to collect information such as the characteristics, price, and customer reviews of each product.

[1536] 2. Data cleansing:

[1537] The server cleanses the collected data and converts it into a unified format. For example, if price information is expressed in different currency units, such as "$100" and "1000 yen," the server converts these into a unified currency unit (e.g., yen). Also, if customer ratings are expressed as strings, such as "★★★★★," the server converts them into numbers (e.g., 5).

[1538] 3. Data Analysis:

[1539] The server performs comparative analysis between products based on the cleansed data. For example, it calculates that the average price of smartphone A is 50,000 yen and the average price of smartphone B is 60,000 yen. It also analyzes the distribution of customer ratings and confirms that the average rating of smartphone A is 4.5 and the average rating of smartphone B is 4.0.

[1540] 4. Speed ​​up knowledge acquisition:

[1541] The server inputs the following prompt into the generative AI model: "Compare the features and prices of smartphone A and smartphone B, and summarize which one is more competitive."

[1542] Based on this prompt, the generative AI model summarizes the results of the comparison between smartphone A and smartphone B. For example, it generates a summary result such as, "Smartphone A is competitive because it is inexpensive and has high customer ratings."

[1543] In this way, the user can efficiently perform competitive analysis of merchandise and organize information.

[1544] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1545] Step 1:

[1546] Information gathering

[1547] Based on the product list entered by the user, the server collects information such as product characteristics, prices, and customer reviews from the Internet. Specifically, it uses a web scraping tool (e.g., BeautifulSoup, Scrapy) to obtain information about each product. The input is the product list provided by the user, and the output is the collected data such as product characteristics, prices, and customer reviews. For example, if the user enters "smartphone A" and "smartphone B," the server obtains the prices and customer reviews of these products from Amazon and other e-commerce sites.

[1548] Step 2:

[1549] Data Cleansing

[1550] The server cleanses the collected data and converts it into the required format. Specifically, it uses a data processing library (e.g., Pandas) to remove unnecessary and duplicate data and convert price information into a unified currency unit. It also quantifies customer ratings. The input is the collected raw data, and the output is cleansed, consistent data. For example, if price information is expressed in different currency units, such as "$100" and "1,000 yen," the server converts it into a unified currency unit (e.g., yen). Also, if customer ratings are expressed as strings, such as "★★★★★," the server converts them into numbers (e.g., 5).

[1551] Step 3:

[1552] Data analysis

[1553] The server performs comparative analysis between products based on the cleansed data. Specifically, it uses data analysis tools (e.g., NumPy, Scikit-learn) to calculate the average price, distribution of customer ratings, etc. The input is the cleansed data, and the output is the comparison results between products. For example, it calculates that the average price of smartphone A is 50,000 yen, and the average price of smartphone B is 60,000 yen. It also analyzes the distribution of customer ratings and confirms that the average rating of smartphone A is 4.5, and the average rating of smartphone B is 4.0.

[1554] Step 4:

[1555] Speed ​​up knowledge acquisition

[1556] The server uses a generative AI model (e.g., GPT-4) to automatically summarize the features and competitiveness of products based on the collected information. Specifically, it generates prompts to be input into the generative AI model and inputs them into the model. The inputs are the cleansed data and the generated prompts, and the output is a summary of the product comparison results. For example, a prompt might be used such as, "Compare the features and prices of product A and product B, and summarize which is more competitive." The generative AI model summarizes the comparison results between product A and product B based on this prompt. For example, it generates a summary such as, "Product A is competitive because it is inexpensive and has high customer ratings."

[1557] In this way, the user can efficiently perform competitive analysis of merchandise and organize information.

[1558] (Application example 1)

[1559] Next, a description will be given of Application Example 1 of Form 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."

[1560] In today's product market, efficiently collecting information on the characteristics, prices, customer reviews, and other aspects of various products and quickly and accurately conducting comparative analysis with competing products is an important challenge for improving sales efficiency and customer satisfaction. However, conventional methods require a great deal of time and effort to collect and analyze information, slowing down the speed of knowledge acquisition. In addition, there was a lack of a way to automatically calculate the recommended product ranking and present it appropriately to users, making it difficult for sales representatives and consumers to select the most suitable product.

[1561] 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.

[1562] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for collecting information such as product characteristics, price, and customer reviews and generating a report comparing the product with other similar products, means for conducting comparative analysis of products using a generative AI model, and means for presenting a recommended ranking of products to the user using prompt sentences. This automates the collection and comparison of product information, improves the speed of knowledge acquisition, and enables sales representatives and consumers to quickly select the optimal product.

[1563] "Means for competitive analysis and information organization for a variety of products" refers to a means for collecting information on the characteristics, prices, customer reviews, etc. of multiple products available in the market, and organizing this information to evaluate their competitiveness.

[1564] "Means aimed at improving the efficiency of sales activities" are means for quickly providing necessary information and optimizing business processes so that sales representatives can carry out their work efficiently.

[1565] "Means for automating comparative analysis including competing services" refers to means for automatically conducting comparative analysis with competing products and services based on information such as product characteristics, price, and customer evaluations.

[1566] "Means for increasing the speed of knowledge acquisition" refers to means for quickly processing collected information and acquiring the necessary knowledge in a short amount of time.

[1567] "Means for collecting information on product characteristics, price, customer reviews, etc., and generating a report for comparing with other similar products" refers to means for collecting detailed information on a product and automatically generating a report for comparing with other similar products based on that information.

[1568] "Means for comparative analysis of products using generative AI models" refers to means for using artificial intelligence models to analyze information such as product characteristics, prices, and customer reviews, and for comparative analysis of products.

[1569] "Means for presenting users with a recommended ranking of products using prompt sentences" refers to a means for generating and displaying prompt sentences for presenting users with a recommended ranking of products based on the analysis results obtained by a generative AI model.

[1570] The following system configuration will be described as an embodiment of the present invention.

[1571] System Configuration

[1572] This system consists of a server, a user terminal, and a database. The server collects information such as product characteristics, prices, and customer reviews, and performs comparative analysis of products using a generative AI model. The user terminal provides an interface that allows users to search for products and check the recommended product ranking using prompts. The database stores the collected product information.

[1573] Hardware and software used

[1574] Hardware: Server, smartphone (user device)

[1575] Software: Python, BeautifulSoup, requests, pandas, scikit-learn, generative AI models

[1576] Data processing and calculation

[1577] The server first collects information such as product characteristics, price, and customer ratings. Specifically, it uses the requests library to retrieve product information from the specified URL and parses the HTML using BeautifulSoup. Next, it stores the collected information in a pandas data frame and vectorizes the product characteristics using TfidfVectorizer. It calculates the text similarity between products using cosine_similarity and performs a comparative analysis of the products using a generative AI model.

[1578] When a user searches for a product, the user device generates a prompt based on the comparative analysis results obtained from the server and presents the user with a recommended ranking of products. The prompt is generated based on the analysis results obtained by the generative AI model.

[1579] Specific examples

[1580] For example, suppose a user opens the "Smart Shopping Assistant" app on their smartphone and enters "Smartphone A" in the search bar. The app will automatically collect the features, price, and customer reviews of "Smartphone A" and compare it with other similar smartphones (e.g., Smartphone B, Smartphone C). A comparison report will be generated and the user will be prompted with the following:

[1581] Prompt Sentence Examples

[1582] Open the "Smart Shopping Assistant" app and enter "Smartphone A" in the search bar. The app will automatically collect the features, price, and customer reviews of Smartphone A and compare it with other smartphones (e.g., Smartphone B, Smartphone C). A comparison report will be displayed, allowing you to easily decide which smartphone is best for you.

[1583] In this way, the user can quickly select the most suitable product.

[1584] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1585] Step 1:

[1586] The user searches for a product on their device.

[1587] Input: The product name entered by the user in the search bar (e.g., "Smartphone A").

[1588] How it works: A user opens the app on their smartphone and enters the name of a product in the search bar.

[1589] Output: The product name is sent to the server.

[1590] Step 2:

[1591] The server collects information about the products.

[1592] Input: The product name entered by the user.

[1593] How it works: The server uses the requests library to retrieve product information from the specified URL. It then parses the HTML using BeautifulSoup to extract information such as product characteristics, price, and customer ratings.

[1594] Output: Information such as product characteristics, price, and customer ratings is saved in a database.

[1595] Step 3:

[1596] The server vectorizes the product information.

[1597] Input: Product characteristics information stored in the database.

[1598] How it works: The server stores product information in a pandas data frame and uses TfidfVectorizer to vectorize the product characteristics.

[1599] Output: Vectorized product characteristics information.

[1600] Step 4:

[1601] The server calculates the similarity between the products.

[1602] Input: Vectorized product characteristics information.

[1603] Operation: The server uses cosine_similarity to calculate the text similarity between products.

[1604] Output: Similarity matrix between products.

[1605] Step 5:

[1606] The server uses the generated AI model to perform a comparative analysis of the products.

[1607] Input: Similarity matrix between products.

[1608] How it works: The server uses the generative AI model to analyze information such as product characteristics, price, and customer reviews, and conducts comparative analysis between products.

[1609] Output: Comparative analysis results of products.

[1610] Step 6:

[1611] The server generates a prompt.

[1612] Input: Results of comparative analysis of products.

[1613] Operation: Based on the analysis results obtained by the generative AI model, the server generates a prompt message to present the user with a recommended ranking of products.

[1614] Output: The prompt statement.

[1615] Step 7:

[1616] The terminal displays the prompt.

[1617] Input: The prompt text sent by the server.

[1618] Operation: The user terminal displays the prompt received from the server on the screen.

[1619] Output: User can check the recommended ranking of products.

[1620] Example 2

[1621] Next, a description will be given of Example 2 of Form 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."

[1622] Traditionally, competitive analysis and information organization for products have often been done manually, which takes time and effort, making it difficult to streamline sales activities. Furthermore, there was a lack of automated comparative analysis, including that of competing services, making it difficult to speed up knowledge acquisition. Furthermore, there was a need for a system that could efficiently collect vast amounts of information on the Internet and automatically calculate the recommended ranking of products.

[1623] 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.

[1624] In this invention, the server includes means for performing competitive analysis and information organization of various products, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet, means for automatically calculating a recommended ranking of products based on the collected information using a machine learning algorithm, and means for providing the calculated recommended ranking to users. This allows for efficient competitive analysis of products and information organization, thereby improving the efficiency of sales activities. Furthermore, the comparative analysis including competing services is automated, increasing the speed of knowledge acquisition. Furthermore, it is possible to efficiently collect vast amounts of information on the Internet and automatically calculate a recommended ranking of products.

[1625] "Competitive analysis of diverse products" involves comparing products of different types and categories and evaluating their competitiveness in their respective markets.

[1626] "Information organization" means systematically classifying collected data and arranging it in an easy-to-understand format.

[1627] "Improving sales efficiency" means optimizing the sales process and making effective use of time and resources.

[1628] "Automated comparative analysis" means that the system automatically compares products without having to do it manually.

[1629] "Increasing the speed of knowledge acquisition" means improving the ability to quickly gather and understand necessary information.

[1630] "Internet databases and websites" means information sources that are accessible online.

[1631] "Characteristics of the product" refers to the specific features and specifications of the product.

[1632] "Price" means the selling price of the product.

[1633] "Customer ratings" refers to feedback and reviews from customers who have purchased a product.

[1634] "Automatically collect information" means that the system obtains the required data without manual intervention.

[1635] A "machine learning algorithm" is a computational method for learning patterns based on data and making predictions and classifications.

[1636] "Recommended Ranking" refers to a prioritized list of products that have been evaluated.

[1637] "Providing to the user" means displaying the results calculated by the system to the user.

[1638] This invention is a system that collects information such as product characteristics, prices, and customer reviews, and performs comparative analysis between products based on this information. A specific embodiment of this system is described below.

[1639] Hardware and software used

[1640] Server: This is the central component for collecting information, processing data, conducting comparative analysis, and providing results. The server should be a computer equipped with a high-performance processor and sufficient memory.

[1641] Web scraping libraries: Use Python libraries such as BeautifulSoup and Scrapy to automatically scrape information from databases and websites on the internet.

[1642] Data processing libraries: Use Python libraries such as Pandas to shape the collected data and convert it into the required format.

[1643] Machine learning libraries: Python libraries such as Scikit-learn and TensorFlow are used to calculate the recommended ranking of products based on collected data.

[1644] Web application framework: Use a framework such as Flask or Django to build a web interface to provide the calculated recommendation rankings to users.

[1645] Explanation of program processing

[1646] 1. Information gathering

[1647] The server uses a web scraping library to automatically collect information such as product characteristics, prices, and customer reviews from databases and websites on the Internet.

[1648] Specifically, the server accesses a specific website and extracts price information and customer ratings from the product details page.

[1649] 2. Data processing

[1650] The server uses a data processing library to format the collected data and convert it into the required format.

[1651] Specifically, the server converts the collected pricing information into a numerical format and converts the customer ratings from text to a numerical score.

[1652] 3. Comparative analysis

[1653] The server uses a machine learning library to calculate the recommended ranking of products based on the formatted data.

[1654] Specifically, the server takes the price and customer ratings as input and calculates the recommended ranking of products using a random forest algorithm.

[1655] 4. Providing results

[1656] The server uses a web application framework to display the results and provide the calculated recommendation ranking to the user.

[1657] Specifically, the server generates a dashboard displaying the ranking of recommendations, which the user can access through a web browser.

[1658] Examples and prompts

[1659] Example: The server collects prices and customer ratings for "smartphones" from a specific website and uses a machine learning algorithm to calculate the recommended ranking.

[1660] Example prompt: "Collect smartphone prices and customer reviews from a specific website and calculate the best smartphone recommendation."

[1661] This system allows users to efficiently collect vast amounts of information on the Internet and perform comparative analysis. This allows for efficient competitive analysis of products and information organization, making sales activities more efficient. It also automates comparative analysis, including that of competing services, increasing the speed at which knowledge can be acquired. Furthermore, it makes it possible to efficiently collect vast amounts of information on the Internet and automatically calculate the recommended ranking of products.

[1662] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1663] Step 1:

[1664] Information gathering

[1665] The server uses a web scraping library (e.g., BeautifulSoup, Scrapy) to automatically collect information such as product characteristics, prices, and customer reviews from databases and websites on the Internet.

[1666] Input: A specific website URL or search keyword (e.g., "smartphone").

[1667] Specific operations: The server accesses a specific website and extracts price information and customer reviews from the product detail page. For example, the server searches for the keyword "smartphone" and accesses the detail page of each product from the search results page to collect information.

[1668] Output: Collected data such as product characteristics, prices, and customer ratings.

[1669] Step 2:

[1670] Data Processing

[1671] The server uses a data processing library (e.g., Pandas) to format the collected data and convert it into the required format.

[1672] Input: Data collected in Step 1, such as product characteristics, price, and customer ratings.

[1673] What happens: The server converts the collected price information into a numeric format and converts the customer ratings from text to a numeric score. For example, the server converts a price of "$299.99" to the numeric value 299.99, and converts a rating of "4.5 out of 5 stars" to the numeric value 4.5.

[1674] Output: Formatted data such as product characteristics, price, and customer ratings.

[1675] Step 3:

[1676] comparative analysis

[1677] The server uses machine learning libraries (e.g., Scikit-learn, TensorFlow) to calculate the recommended ranking of products based on the formatted data.

[1678] Input: Data such as product characteristics, price, and customer ratings formatted in Step 2.

[1679] Specific operation: The server inputs the price and customer rating and uses the random forest algorithm to calculate the product recommendation ranking. For example, the server sets the algorithm to prioritize recommending products with low prices and high customer ratings.

[1680] Output: The calculated recommended ranking of products.

[1681] Step 4:

[1682] Providing results

[1683] The server displays the results using a web application framework (e.g., Flask, Django) to provide the calculated recommendation ranking to the user.

[1684] Input: The recommended product ranking calculated in Step 3.

[1685] Specific behavior: The server generates a dashboard displaying the ranking of recommendations and makes it accessible to the user through a web browser. For example, the user can access a specific URL in their browser and see a page displaying the ranking of recommendations.

[1686] Output: A web page with the ranking of recommendations that will be served to the user.

[1687] (Application example 2)

[1688] Next, a description will be given of Application Example 2 of Form 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."

[1689] Traditionally, competitive analysis and information organization for products was often done manually, which required time and effort, and the information was often incomplete and inaccurate. Furthermore, comparative analysis between products and calculation of recommended rankings were also done manually, making it difficult to conduct efficient sales activities. Furthermore, there was a lack of means to collect and properly analyze the vast amount of information available on the Internet, making it difficult to recommend optimal products to users. To solve these issues, a system was needed that could automate the entire process, from information collection to analysis and proposals, efficiently and accurately.

[1690] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1691] In this invention, the server includes means for conducting competitive analysis of various products and organizing information, means for improving the efficiency of sales activities, means for automating comparative analysis including competing services, means for increasing the speed of knowledge acquisition, means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet, means for automatically calculating a recommended ranking of products using a machine learning algorithm based on the collected information, and means for proposing optimal products to users. This makes it possible to efficiently and accurately perform processes from information collection to analysis and proposals.

[1692] "Means for competitive analysis and information organization for various products" is a method for evaluating the competitiveness of different types of products and systematically organizing that information.

[1693] "Measures aimed at improving sales efficiency" are methods for optimizing sales processes and making effective use of time and resources.

[1694] "Means for automating comparative analysis including competing services" refers to a method for automatically conducting comparative analysis including competing services or products.

[1695] "Means to increase the speed of knowledge acquisition" are methods for quickly acquiring necessary information and knowledge.

[1696] "Means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet" refers to a method for automatically collecting data about products from various sources on the Internet.

[1697] "Means for automatically calculating the recommended ranking of products using a machine learning algorithm based on collected information" refers to a method for automatically calculating the recommended ranking of products using machine learning technology based on collected data.

[1698] "Means for suggesting optimal products to users" refers to methods for suggesting optimal products based on the user's needs and preferences.

[1699] A system for carrying out this invention has the following configuration: A server includes means for automatically collecting information such as product characteristics, prices, and customer reviews from databases and websites on the Internet, means for automatically calculating a recommended product ranking using a machine learning algorithm based on the collected information, and means for suggesting optimal products to users.

[1700] Hardware and software used

[1701] Hardware: Servers, smartphones

[1702] Software: Python, BeautifulSoup (for web scraping), Scikit-learn (for machine learning), Flask (for backend API)

[1703] Data processing and calculation

[1704] Web scraping

[1705] The server uses BeautifulSoup to collect information such as product characteristics, prices, and customer reviews from the specified website. The collected data is saved in a CSV file.

[1706] Data analysis

[1707] The server trains a machine learning model based on the collected data using Scikit-learn, and uses the trained model to calculate the recommended ranking of products.

[1708] Product suggestion

[1709] The server uses Flask to build a backend API and returns recommended products in response to user requests. Users can access this API using their smartphones to receive optimal product suggestions.

[1710] Specific examples

[1711] For example, if a user searches for "smartphone," the following prompt sentence is input into the generative AI model:

[1712] import requests

[1713] from bs4 import BeautifulSoup

[1714] import pandas as pd

[1715] from sklearn.ensemble import RandomForestClassifier

[1716] from flask import Flask, request, jsonify

[1717] app = Flask(__name__)

[1718] Web scraping

[1719] def scrape_data():

[1720] url = "https: / / example.com / smartphones"

[1721] response = requests.get(url)

[1722] soup = BeautifulSoup(response.text, 'html.parser')

[1723] data = []

[1724] for item in soup.find_all('div', class_='product'):

[1725] name = item.find('h2').text

[1726] price = item.find('span', class_='price').text

[1727] rating = item.find('span', class_='rating').text

[1728] data.append([name, price, rating])

[1729] df = pd.DataFrame(data, columns=['Name', 'Price', 'Rating'])

[1730] df.to_csv('smartphones.csv', index=False)

[1731] Training of the machine learning model

[1732] def train_model():

[1733] df = pd.read_csv('smartphones.csv')

[1734] X = df[['Price', 'Rating']]

[1735] y = df['Name']

[1736] model = RandomForestClassifier()

[1737] model.fit(X, y)

[1738] return model

[1739] Product suggestion API

[1740] @app.route(' / recommend', methods=['GET'])

[1741] def recommend():

[1742] model = train_model()

[1743] user_input = request.args.get('input')

[1744] This is where product recommendations are calculated based on user input.

[1745] Example: Returning recommended products

[1746] recommended_product = model.predict([[user_input['price'], user_input['rating']]])

[1747] return jsonify({'recommended_product': recommended_product})

[1748] if __name__ == '__main__':

[1749] scrape_data()

[1750] app.run(debug=True)

[1751] The program provides an API that collects smartphone information from designated websites, trains a machine learning model, and recommends the best smartphone for users.

[1752] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1753] Step 1:

[1754] The server accesses specified websites on the Internet and collects information such as product characteristics, prices, and customer reviews. Specifically, it uses BeautifulSoup to analyze the HTML structure of the webpage and extract the necessary data. The input is the website URL, and the output is a list of product information.

[1755] Step 2:

[1756] The server saves the collected product information in a CSV file. Specifically, it creates a data frame using the Pandas library and saves it in CSV format. The input is a list of product information, and the output is a CSV file.

[1757] Step 3:

[1758] The server reads the saved CSV file and trains a machine learning model. Specifi...

Claims

1. A means for collecting product information from the website; A means for storing the collected data in a database; A means for calculating a recommended ranking of products using a machine learning algorithm; A means for collecting user emotion data; means for analyzing the user's emotions using an emotion analysis algorithm; A means for adjusting the timing and content of information provided to sales representatives based on the analysis results; A system including:

2. 2. The system according to claim 1, wherein said means for collecting product information from websites automatically collects information such as product characteristics, prices, and customer reviews from databases and websites on the Internet.

3. The system according to claim 1 , wherein the means for calculating a recommended ranking of products using the machine learning algorithm automatically calculates a recommended ranking of products based on the collected information and provides it to a sales representative.

Images