system

Abstract

We provide the system. [Solution] Means for receiving customer requirements, A means of searching for appropriate products from collected product information, past case information, and market information, A method for estimating the price of selected products and determining the optimal proposed price, A means of automatically generating a proposal based on customer requirements, selected products, and proposed price, A means of sending the proposal to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a modern business environment, when providing a large number of commercial products and composite proposals to customers, the process in which salespersons and system engineers individually collect and organize information and create an optimal proposal is very laborious and time-consuming. Also, price setting needs to refer to past cases and market information, and it is difficult to promptly present an appropriate price. Due to these problems, there is a lack of speed and accuracy in proposals, and a risk of losing competitiveness.

Means for Solving the Problems

[0005] The present invention is a system for solving the above problems, and includes means for receiving customer requirements, means for searching for appropriate products from collected product information, past case information, and market information, means for estimating the price of selected products and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected products, and proposed price, and means for sending the proposal to the user. Furthermore, by including means for checking inventory information and delivery date information from a database based on customer requirements, and means for providing an interface that allows the user to modify the proposal, the system enables the creation of proposals quickly and accurately, and responds quickly to customer needs.

[0006] "Customer requirements" refer to the specific conditions, functions, budget, delivery dates, and other requirements that customers have for the products or services they are interested in.

[0007] "Product information" refers to detailed data regarding the names, functions, prices, and availability of available products and services.

[0008] "Past case information" refers to data on records of proposals and contracts made in the past and their results, and is information that can be used as a reference for similar cases.

[0009] "Market information" refers to information about current market trends, competitor pricing, demand forecasts, and so on.

[0010] A "proposal" is a document that summarizes the selected products, their prices, delivery dates, and detailed specifications based on customer requirements, and serves as a plan to be presented to the customer.

[0011] "Means" refers to a program, device, or process designed to perform a specific function.

[0012] A "user" is a person who operates a system and is responsible for inputting, verifying, and modifying data. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0016] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, a labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. The processing of the system's program and specific examples thereof will be described below.

[0035] System Construction

[0036] 1. Data Collection

[0037] The server periodically connects to the database to collect the latest product information (product name, specifications, price, etc.), past case studies, and market information. This information is stored in an internal database for use in the subsequent proposal process.

[0038] 2. Enter customer requirements

[0039] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (e.g., product quantity, features, budget, delivery date, etc.) into this form and submits it to the system. Through this process, the system understands the customer's specific needs.

[0040] 3. Requirements matching

[0041] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets. Furthermore, it checks inventory and delivery information to select the combination of products and services that best suits the customer requirements.

[0042] 4. Price Estimation

[0043] The server estimates the price of the selected product based on past case studies and market information. In this process, it considers appropriate cumulative costs and profit margins to determine the optimal proposed price (winning price).

[0044] 5. Proposal generation and submission

[0045] The server automatically generates a proposal. This proposal includes details of the products selected based on customer requirements, estimated pricing, delivery dates, and customization options. The generated proposal is sent to the user's terminal, where the user reviews it, makes any necessary revisions, and finally submits it to the customer.

[0046] Specific example

[0047] For example, consider a scenario where an IT company receives the following requirements from a new customer.

[0048] Required products: 100 new servers

[0049] Additional requirements: High-speed storage options

[0050] Delivery time: within 1 month

[0051] Budget: Within 50 million yen

[0052] The user enters these requirements into an input form on the terminal and submits them to the system. The server analyzes the received requirements and searches its database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[0053] Next, the server estimates the price based on past case studies and market information, calculating the optimal winning price that fits within the budget. Finally, the server automatically generates a proposal document, including customer requirements, selected products, and estimated prices. This proposal document is sent to the user's terminal, where the user reviews the content, makes any necessary revisions, and submits it to the customer. This process enables a quick and accurate response to customer needs.

[0054] The following describes the processing flow.

[0055] Step 1:

[0056] The server periodically connects to the database to retrieve the latest product information (e.g., product name, specifications, price). It also collects past case study information and market data and stores it in the internal database.

[0057] Step 2:

[0058] The terminal displays a customer requirements input form for the user. This form includes input fields for product quantity, features, budget, and delivery date.

[0059] Step 3:

[0060] The user fills in the specific requirements received from the customer into an input form and submits it to the system. This registers the customer's request in the system.

[0061] Step 4:

[0062] The server analyzes the received customer requirements, compares them with product information in the database, and searches for products or assets that match the requirements.

[0063] Step 5:

[0064] The server checks inventory and delivery date information for merchandise and assets retrieved from the database and identifies combinations that match customer requirements.

[0065] Step 6:

[0066] The server estimates the price of selected products and assets based on past case studies and market information. Profit margins and cost structures are also considered during this process.

[0067] Step 7:

[0068] The server calculates the optimal proposed price (winning price) based on the estimated price. This calculation is important for enhancing market competitiveness.

[0069] Step 8:

[0070] The server automatically generates a proposal based on customer requirements, selected products, and estimated pricing. The proposal includes product details, pricing, delivery dates, and customization options.

[0071] Step 9:

[0072] The server sends the generated proposal to the user's terminal.

[0073] Step 10:

[0074] The user reviews the proposal sent to their device and makes revisions as needed. These revisions are designed to flexibly respond to the customer's specific requirements.

[0075] Step 11:

[0076] The user submits the finalized proposal to the client.

[0077] (Example 1)

[0078] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0079] Traditional proposal creation systems struggled to accurately grasp customer requirements and automatically generate accurate proposals quickly. Furthermore, the time-consuming manual requirements verification and price estimation processes led to inefficiencies in the sales process. Additionally, the lack of a user-friendly interface during the proposal revision process further reduced work efficiency.

[0080] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0081] In this invention, the server includes means for connecting to a database and collecting product information, past case information, and market information; means for receiving customer requirements; means for analyzing the received customer requirements and searching for appropriate products from the database; means for estimating the price of the selected products based on past case information and market information and determining the optimal proposed price; means for automatically generating a proposal based on the customer requirements, selected products, and proposed price; and means for sending the proposal to the user. This enables accurate understanding of customer requirements and the rapid and accurate automatic generation of proposals.

[0082] A "database" is a data structure that centrally manages information and allows for efficient access and retrieval.

[0083] "Product information" refers to a series of pieces of information such as product name, specifications, and price, and is the data necessary when creating a proposal.

[0084] "Past case information" refers to performance data such as proposals, contract details, and pricing from past projects.

[0085] "Market information" refers to data about the external environment, such as industry trends, competitor pricing, and product trends.

[0086] "Customer requirements" refer to the specific requirements that the customer expects from the proposal (such as product quantity, functions, budget, and delivery date).

[0087] "Receiving" refers to the process of bringing data or information from external sources into the system.

[0088] "Analysis" is the process of classifying, evaluating, and understanding received data and information.

[0089] "Searching" is the process of finding relevant information from a database based on specific criteria.

[0090] "Price estimation" is the process of calculating the selling price of selected products, taking into account cumulative costs and profit margins.

[0091] The "proposed price" is the final selling price presented to the customer.

[0092] A "proposal" is a document created based on customer requirements and includes product details, pricing, delivery dates, and customization options.

[0093] "Automatic generation" refers to a system creating documents such as proposals based on a program, without human intervention.

[0094] "Sending" refers to the action of distributing the created proposal from the system to the user interface.

[0095] A "user" is the entity that operates this system and ultimately submits a proposal to the customer.

[0096] An "interface" refers to the screens and functions that allow a user to interact with a system.

[0097] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. The system configuration and specific operation are described below.

[0098] Data collection

[0099] The server first connects to a database to collect product information, past case studies, and market information. MySQL (registered trademark) is often used as the database. Product information includes product name, specifications, and price. The server stores this collected data in an internal database such as MongoDB. In addition, market information is obtained from external sites using APIs or web scraping techniques (e.g., BeautifulSoup or Selenium).

[0100] Entering customer requirements

[0101] The terminal presents the user with a customer requirements input form via a web browser. This input form is built using a front-end framework such as React or Vue.js. The user enters requirements such as product quantity, features, budget, and delivery date, and clicks the submit button. This information is sent to the server as an HTTP request. The server's backend uses a web framework such as Node.js or Django.

[0102] Requirements matching

[0103] The server analyzes the received customer requirements. For this purpose, natural language processing (NLP) tools such as Python's NLTK library and spaCy are used. Based on the analyzed information, the server searches its internal database for relevant products and assets. SQL queries are used to retrieve appropriate information from the database, and inventory and delivery date information is confirmed.

[0104] Price estimate

[0105] The server estimates the price of selected products based on past case studies and market information. During this process, it performs detailed price analysis using machine learning libraries such as scikit-learn and TENSORFLOW®. It then calculates the optimal proposed price (Winning Price) considering cumulative costs and profit margins.

[0106] Proposal generation and submission

[0107] The server automatically generates a proposal using the Python ReportLab library. The proposal includes details of the products selected based on customer requirements, estimated pricing, delivery dates, and customization options. The generated proposal is created in PDF format and sent to the user's terminal as an HTTP response. The user reviews this proposal using Adobe Acrobat or similar software, makes any necessary revisions, and then submits it to the customer.

[0108] Specific example

[0109] For example, consider a scenario where an IT company receives the following requirements from a new customer:

[0110] Required products: 100 new servers

[0111] Additional requirements: High-speed storage options

[0112] Delivery time: within 1 month

[0113] Budget: Within 50 million yen

[0114] The user enters these requirements into an input form on their terminal's web browser and submits them to the system. The server uses NLP technology to analyze the received requirements and searches its database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[0115] Next, the server estimates the price based on past case studies and market information, and calculates the optimal winning price that fits within the budget. Finally, it automatically generates a proposal that includes the following items:

[0116] customer requirements

[0117] Selected products

[0118] Estimated price

[0119] Delivery time and customization options

[0120] This proposal is sent to the user's device, where they can review the content, make any necessary revisions, and submit it to the client, enabling quick and accurate proposals.

[0121] Example prompts for generative AI models

[0122] "The following customer requirements have been entered: '100 new servers, high-speed storage options, delivery within one month, budget under 50 million yen.' Based on this information, please generate the optimal proposal by referring to past case studies and market data."

[0123] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0124] Step 1: Data Collection

[0125] The server connects to a MySQL database to collect product information, past case studies, and market information. Specifically, it periodically executes a Python script to retrieve new data. The input requires database connection information and queries. The collected data is stored in an internal database (e.g., MongoDB). The server also retrieves external market information using APIs and web scraping techniques (such as BeautifulSoup or Selenium). This process ensures that product and market information remains up-to-date.

[0126] Step 2: Enter customer requirements

[0127] The device uses React or Vue.js to display a customer requirements input form in a web browser. Specifically, the form includes fields such as product quantity, features, budget, and delivery date. The user enters their requirements into these fields and clicks a submit button. The input is the customer requirements data entered by the user. The output from the device is sent to the server as an HTTP request, and the request payload contains the customer requirements.

[0128] Step 3: Requirements Analysis and Matching

[0129] The server retrieves customer requirements from received HTTP requests and parses the data using Python's NLTK and spaCy. The input is customer requirements data. The server uses natural language processing techniques to convert the requirements into structured data. Based on this parsed data, it searches the database for appropriate products and assets. Specifically, it uses SQL queries to retrieve relevant product information. The output is a list of products and assets found based on the parsed data.

[0130] Step 4: Check inventory and delivery information

[0131] The server checks inventory and delivery date information based on the product list obtained in step 3. The input is the product list. The server retrieves this information by calling an internal API. Specifically, it sends an API request and receives inventory and delivery date information as a response. The output is the product list including inventory and delivery date information.

[0132] Step 5: Price Estimation

[0133] The server estimates prices for selected products based on past case studies and market information. The input is a product list including inventory and delivery time information. Specifically, it uses a machine learning model with Python libraries (scikit-learn and TensorFlow) to predict prices. Cumulative costs and profit margins are considered during the estimation process. The output is the estimated price and the proposed price (winning price) for each product.

[0134] Step 6: Proposal Generation

[0135] The server automatically generates proposals using the Python ReportLab library. Inputs include customer requirements, selected products, estimated prices, and delivery date information. Specifically, it embeds a proposal template based on this data and generates a proposal in PDF format. The output is the generated proposal.

[0136] Step 7: Submitting and revising the proposal

[0137] The server sends the generated proposal to the user's terminal as an HTTP response. The input is the generated proposal. The user can review the proposal using tools such as Adobe Acrobat and make revisions as needed. The output is the final proposal, which is submitted to the client. This process ensures that clients receive a fast and accurate proposal.

[0138] (Application Example 1)

[0139] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0140] In customer service at logistics centers, the process from receiving requirements to generating proposals is complex, making it difficult to respond quickly and accurately. Furthermore, optimizing multiple products and distribution channels is often done manually, contributing to inefficiency. Additionally, verifying inventory and delivery information based on customer requirements is time-consuming, hindering accurate proposals.

[0141] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0142] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate products from collected product information, past case information, and market information, means for estimating the price of the selected product and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected products, and proposed price, means for presenting the generated proposal to the customer via a terminal, and means for selecting the optimal distribution route and product combination. This enables the logistics center to respond to customer requirements quickly and accurately, and to generate proposals efficiently and select the optimal distribution route.

[0143] "Means of receiving customer requirements" refers to devices or software used to collect specific customer requests and needs and input them into a system.

[0144] "Collected product information" refers to detailed product data obtained from sources such as the market, past transactions, and product databases.

[0145] "Past case information" refers to data based on past experience and examples of handling similar customer requirements.

[0146] "Market information" refers to data such as current market trends, price trends, and competitive conditions.

[0147] "Means for finding the right product" refers to algorithms and software used to identify and search for the most suitable product based on customer requirements, using collected product information, past case studies, and market data.

[0148] "Means for estimating the price of selected products" refers to a device or software that has the function of calculating the price of selected products based on past case information and market information.

[0149] "Means for determining the optimal proposed price" refers to algorithms or software that take into account cumulative costs and profit margins to determine the optimal price to propose to the customer.

[0150] "Methods for automatically generating proposals" refers to software that automatically creates proposals based on customer requirements, selected products, and estimated prices.

[0151] A "terminal" refers to a device used by people to input information or to check output.

[0152] "Means for selecting the optimal distribution route and product combination" refers to software or algorithms that have the functionality to select the optimal delivery method and combine multiple products according to customer requirements.

[0153] System Configuration

[0154] This invention is a system that receives customer requirements, searches for appropriate products from collected product information, past case information, and market information, calculates the optimal proposed price, and automatically generates a proposal. The system consists of three components: a server, a terminal, and a user.

[0155] Explanation of program processing

[0156] The server periodically connects to the database to collect product information (product name, specifications, price, etc.), past case studies, and market information, and stores it in the internal database. This makes it possible to always provide proposals based on the latest information.

[0157] The user uses a terminal to input customer requirements (e.g., product quantity, additional requirements, delivery date, budget, etc.). This entered data is then sent to the server.

[0158] The server analyzes the received customer requirements and searches its internal database for the most suitable product. Specifically, it selects the optimal product and distribution channel based on the quantity and functionality of the customer requirements, taking into account inventory and delivery time information.

[0159] Next, the server estimates the price of the selected product based on past case studies and market information. It then determines the optimal price to propose, taking into account cumulative costs and profit margins.

[0160] The server then automatically generates a proposal based on customer requirements, selected products, and estimated pricing. This proposal includes detailed product information and customization options.

[0161] Finally, the generated proposal is sent to the terminal, reviewed and revised by the user, and then presented to the client.

[0162] Hardware and software to be used

[0163] This system uses the following hardware and software:

[0164] Server: Collects information from the database, performs analysis and price estimation, and generates proposals. Software used includes Python and SQL.

[0165] Terminal: Used to input customer requirements and review / revise proposals. A variety of devices can be used, including smartphones, tablets, and PCs.

[0166] Database: Stores product information, past case studies, and market information. SQL databases are common.

[0167] Specific example

[0168] For example, a logistics center might receive the following requirements from a customer:

[0169] Required products: 100 high-performance servers

[0170] Additional requirements: High-speed storage options

[0171] Delivery time: within 1 month

[0172] Budget: Within 50 million yen

[0173] When the user enters these requirements via their terminal, the server analyzes the requirements, selects the optimal server and storage options, and estimates the price based on past case studies and market information. Next, it automatically generates a proposal and sends it to the user via their terminal.

[0174] Examples of prompts for a generative AI model are as follows:

[0175] "Based on the number of products requested by the customer and any additional requirements, please generate a proposal outlining the optimal product combination and pricing. The requirements are as follows: Number of products: 100, Additional requirements: High-speed storage option, Delivery time: within 1 month, Budget: within 50 million yen."

[0176] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0177] Step 1:

[0178] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (product quantity, additional requirements, delivery date, budget, etc.) into this form. The entered data is stored on the terminal and sent to the server. Specifically, the user enters 100 high-performance servers and high-speed storage options, a delivery date of less than one month, and a budget of 50 million yen.

[0179] input:

[0180] Customer's specific requirements: Product quantity, additional requirements, delivery date, budget

[0181] output:

[0182] Customer requirements data (JSON format)

[0183] Step 2:

[0184] The server analyzes the customer requirements received from the terminal. This analysis verifies that the entered requirements are accurate and complete, and fills in any unclear or missing information as needed. Based on the results of this analysis, the next steps proceed.

[0185] input:

[0186] Customer requirements data

[0187] output:

[0188] Analyzed customer requirements data

[0189] Step 3:

[0190] The server searches its internal database for appropriate products based on the analyzed customer requirements data. This search utilizes pre-collected product information, past case studies, and market information. For example, it might retrieve information on 100 high-performance servers and high-speed storage options from the database.

[0191] input:

[0192] Analyzed customer requirements data

[0193] Internal databases containing product information, past case studies, and market information.

[0194] output:

[0195] A list of suitable product candidates

[0196] Step 4:

[0197] The server checks inventory and delivery information based on a suitable list of product candidates. This allows for the confirmation of product availability and delivery dates according to customer requirements. For example, it checks whether the acquired high-performance server and high-speed storage can be delivered within one month.

[0198] input:

[0199] A list of suitable product candidates

[0200] Internal database inventory information, delivery date information

[0201] output:

[0202] Inventory information and delivery date information

[0203] Step 5:

[0204] The server estimates the price of the selected product based on inventory and delivery information. This estimation takes into account past sales data and market information, and determines the proposed price based on total cost and optimal profit margin.

[0205] input:

[0206] A list of suitable product candidates

[0207] Inventory information and delivery date information

[0208] Past case information, market information

[0209] output:

[0210] Estimated price information

[0211] Step 6:

[0212] The server automatically generates a proposal based on customer requirements, selected products, and estimated pricing information. This proposal includes product details, pricing information, stock availability, delivery dates, and customization options.

[0213] input:

[0214] customer requirements

[0215] Selected products

[0216] Estimated price information

[0217] output:

[0218] Automatically generated proposal (PDF or HTML format)

[0219] Step 7:

[0220] The server sends the generated proposal to the terminal. The user reviews the proposal and makes revisions as needed. They then submit the final version of the proposal to the client.

[0221] input:

[0222] Automatically generated proposal

[0223] output:

[0224] Revised and reviewed proposal

[0225] The above steps efficiently solve the problem that the invention aims to address (rapid and accurate customer response and proposal generation).

[0226] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0227] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The processing of the system's program and specific examples are described below.

[0228] System Construction

[0229] 1. Data Collection

[0230] The server periodically connects to the database to collect the latest product information (product name, specifications, price, etc.), past case studies, and market information. This information is stored in an internal database for use in the subsequent proposal process.

[0231] 2. Enter customer requirements

[0232] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (e.g., product quantity, features, budget, delivery date, etc.) into this form and submits it to the system. Through this process, the system understands the customer's specific needs.

[0233] 3. Emotion recognition

[0234] The terminal activates an emotion engine to recognize the user's emotions in real time while they are entering customer requirements. The emotion engine analyzes the user's facial expressions, tone of voice, input speed, and other factors.

[0235] 4. Requirements matching

[0236] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets. Furthermore, it checks inventory and delivery information to select the combination of products and services that best suits the customer requirements.

[0237] 5. Price Estimation

[0238] The server estimates the price of the selected product based on past case studies and market information. In this process, it considers appropriate cumulative costs and profit margins to determine the optimal proposed price (winning price).

[0239] 6. Proposal generation and emotional reflection

[0240] The server automatically generates a proposal based on customer requirements, selected products, and estimated prices. Based on the results of the emotion engine, it adjusts the tone and expression of the proposal, customizing it to be easier for users to understand and accept.

[0241] 7. Submitting and revising the proposal

[0242] The server sends the generated proposal to the user's terminal. The user reviews the proposal sent to their terminal and makes revisions as needed. These revisions are intended to flexibly respond to the customer's specific requirements.

[0243] 8. Submission of proposal

[0244] The user submits the finalized proposal to the client.

[0245] Specific example

[0246] For example, consider a scenario where an IT company receives the following requirements from a new customer.

[0247] Required products: 100 new servers

[0248] Additional requirements: High-speed storage options

[0249] Delivery time: within 1 month

[0250] Budget: Within 50 million yen

[0251] Emotional state: Feeling stressed while typing.

[0252] The user enters this requirement into an input form on their device and submits it to the system. During input, the emotion engine recognizes the user's stress level and adjusts the wording of the proposal to a calmer tone. For example, the system can change the phrase "We promise a prompt response" to "Please rest assured. We will provide you with the best possible solution tailored to your requirements."

[0253] The server analyzes the received requirements and searches the database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[0254] Subsequently, the server estimates the price based on past case studies and market information, calculating the optimal winning price within a budget of 50 million yen. Finally, the server automatically generates a proposal, incorporating the results of the emotion engine, and sends it to the user's terminal. The user reviews the content, makes revisions as needed, and finally submits it to the client. This process enables a rapid and accurate response to client needs.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The server periodically connects to the database to retrieve the latest product information (e.g., product name, specifications, price), past case studies, and market information. This information is stored in the internal database.

[0258] Step 2:

[0259] The terminal displays a customer requirements input form for the user. This form includes input fields for product quantity, features, budget, and delivery date.

[0260] Step 3:

[0261] The user enters the specific requirements received from the customer into an input form and sends that information to the system.

[0262] Step 4:

[0263] The terminal activates an emotion engine while the customer requirements are being entered. The emotion engine analyzes the user's facial expressions, voice, input speed, etc., to recognize emotions in real time.

[0264] Step 5:

[0265] The device sends the recognized emotion data to the server. This allows customer requirements and emotion information to be aggregated on the server.

[0266] Step 6:

[0267] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets.

[0268] Step 7:

[0269] The server checks inventory and delivery date information for merchandise and assets retrieved from the database and identifies combinations that match customer requirements.

[0270] Step 8:

[0271] The server estimates the price of selected products and assets based on past case studies and market information. In this process, it also considers appropriate cumulative costs and profit margins.

[0272] Step 9:

[0273] The server calculates the optimal proposed price (winning price) based on the estimated price.

[0274] Step 10:

[0275] The server automatically generates a proposal based on customer requirements, selected products, estimated pricing, and user sentiment information. The content of the proposal is then adjusted based on the results of the sentiment engine.

[0276] Step 11:

[0277] The server sends the generated proposal to the user's terminal. The sent proposal reflects a tone and expression that takes the user's feelings into consideration.

[0278] Step 12:

[0279] Users review the proposal on their devices and make revisions as needed. These revisions are designed to flexibly respond to the customer's specific requirements.

[0280] Step 13:

[0281] The user submits the finalized proposal to the customer. This enables quick and accurate response to the customer's needs.

[0282] Specific Example

[0283] For example, consider the case where an IT company receives the following requirements.

[0284] Required product: 100 new servers

[0285] Additional requirement: High-speed storage option

[0286] Delivery date: within 1 month

[0287] Budget: within 50 million yen

[0288] Emotional state: feeling stressed during input

[0289] Following the processing from Step 1 to Step 13, the system acquires the user's input and analyzes the emotion in real time through the emotion engine. The analysis result is reflected in the content of the proposal and adjusted to expressions that relieve stress, such as "We promise a prompt response."

[0290] Through this process, the system can quickly and effectively respond to the customer's needs and reduce the user's stress.

[0291] (Example 2)

[0292] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0293] Conventional proposal generation systems required a significant amount of time for analyzing customer requirements and creating proposals, making it difficult to improve the accuracy of proposals and customer satisfaction. Furthermore, proposals were not customized to consider the user's emotional state, failing to reduce user stress. This made it difficult to improve the efficiency of sales activities and the effective operation of the proposal process.

[0294] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0295] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate items from collected item information, past case information, and market information, means for estimating the price of selected items and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected items, and proposed price, means for sending the proposal to the user, and means for analyzing the user's emotions in real time and adjusting the content of the proposal. This enables the rapid and accurate generation of proposals based on customer requirements, and further allows for customization according to the user's emotional state, thereby improving customer satisfaction and streamlining sales activities.

[0296] "Customer requirements" refer to the specific needs of a customer regarding the quantity, functions, budget, and delivery date of the products or services they desire.

[0297] "Product information" refers to detailed information about a product, such as its name, specifications, and price.

[0298] "Past case information" refers to information about the content and results of similar proposals made in the past.

[0299] "Market information" refers to information about current market trends, such as competitors' prices and market trends.

[0300] "Search methods" refer to algorithms and database queries used to identify items that meet customer requirements based on collected information.

[0301] The "means for estimating" refers to methods and tools for calculating the price and cost of selected items and deriving an optimal proposed price.

[0302] The "proposal document" is a document that summarizes customer requirements, selected items, and estimated prices, and indicates the content of the proposal to be made to the customer.

[0303] The "means for automatically generating" refers to the function for the system to automatically create a proposal document based on the collected information and analysis results.

[0304] The "means for transmitting" refers to the communication means for sending the generated proposal document to the user's terminal.

[0305] The "means for analyzing and adjusting emotions" refers to the function for analyzing the user's expression, tone of voice, etc., and appropriately changing the tone and expression of the proposal document.

[0306] The system according to the present invention improves sales activities and the proposal process by efficiently receiving customer requirements and automatically generating a quick and accurate proposal document. Furthermore, by combining an emotion engine that recognizes the user's emotions, it is possible to more effectively adjust the content of the proposal document and reduce the user's stress. Hereinafter, the processing of the system program and its specific examples will be described.

[0307] System Configuration

[0308] The system uses the following hardware and software:

[0309] Server

[0310] Database: MySQL

[0311] ERP System

[0312] Data analysis libraries: Python, Pandas

[0313] Natural language generation model API (e.g., GPT-4 (registered trademark))

[0314] terminal

[0315] Web browser: GOOGLE CHROME (registered trademark)

[0316] Camera and microphone (for emotion recognition)

[0317] Facial expression analysis library: OpenCV

[0318] Speech analysis library: speech_recognition

[0319] Specific flow and content of the process

[0320] 1. Data Collection

[0321] The server periodically connects to the database to collect the latest product information, past case information, and market information. This information is retrieved from the MySQL database and stored in an internal database on the server.

[0322] 2. Enter customer requirements

[0323] The terminal displays a customer requirements input form on a web browser for the user. The user enters the product quantity, required functions, budget, delivery date, etc. into this form and submits it to the system. The terminal converts this input data into JSON format and sends it to the server.

[0324] 3. Emotion recognition

[0325] The device activates the emotion engine while the user is entering information into a form. The emotion engine captures camera footage and analyzes voice input to determine the user's emotional state in real time and sends the results to the server.

[0326] 4. Requirements matching

[0327] The server analyzes the received customer requirements and searches its internal database for appropriate items. During this process, it also uses the ERP system to check inventory and delivery information, identifying the combination of products and services best suited to the customer's requirements.

[0328] 5. Price Estimation

[0329] Based on past case studies and market information, the server uses data analysis libraries (Python, Pandas) to estimate the price of selected items and determine the optimal proposed price.

[0330] 6. Proposal generation and emotional reflection

[0331] The server automatically generates proposals based on customer requirements, selected items, and estimated prices using an automated generation model (e.g., GPT-4). It also adjusts the tone and expression of the proposals based on the results of an emotion engine, customizing them to be more easily understood and accepted by the user.

[0332] 7. Submitting and revising the proposal

[0333] The server converts the generated proposal into PDF format and sends it to the user's terminal. The user reviews and modifies the proposal using Microsoft Word, adding additional comments and details as needed.

[0334] 8. Submission of proposal

[0335] The user submits the finalized proposal to the client via email or an online submission form.

[0336] Examples of specific cases and prompt statements

[0337] For example, consider a scenario where an IT company receives the following requirements from a new customer:

[0338] Required products: 100 new servers

[0339] Additional requirements: High-speed storage options

[0340] Delivery time: within 1 month

[0341] Budget: Within 50 million yen

[0342] Emotional state: Feeling stressed while typing.

[0343] The user enters this information and sends it to the system. The emotion engine recognizes the user's stress level and adjusts the proposal content to be expressed in a calm tone. For example, it might change "We promise a prompt response" to "Please rest assured. We will provide the best proposal to meet your requirements."

[0344] The server analyzes the requirements and searches for and identifies appropriate products and delivery information from the MySQL database and ERP system. It then uses Pandas to estimate prices and derive the optimal proposed price within a budget of 50 million yen. Finally, GPT-4 generates a proposal, which, incorporating the results of the sentiment engine, is sent to the user's terminal. The user reviews and revises the proposal before finally submitting it to the customer.

[0345] Example of a prompt

[0346] "Create the optimal proposal based on customer requirements. Generate a proposal that meets the following requirements:

[0347] Requirements: 100 new servers, high-speed storage options

[0348] Delivery time: within 1 month

[0349] Budget: Within 50 million yen

[0350] Emotional state: Use a calm tone for users who are feeling stressed.

[0351] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0352] Step 1: Data Collection

[0353] The server periodically connects to the database and collects the following information:

[0354] Product information: Product name, specifications, price, etc.

[0355] Past case information: Previous proposals, success stories, etc.

[0356] Market information: Competitor pricing and market trends

[0357] Input data is retrieved from a MySQL database. Specifically, the server executes SQL queries such as "SELECT FROM product_info" and saves the results to an internal database.

[0358] The output is the most recent information stored in the internal database. This provides the latest data for use in the next processing step.

[0359] Step 2: Enter customer requirements

[0360] The terminal displays a customer requirements input form on a web browser for the user.

[0361] The input data includes the quantity of products entered by the user, the required functions, budget, and delivery date. Users operate this form using a browser such as Google Chrome, enter the information, and click the "Submit" button.

[0362] Specifically, the terminal converts this input data into JSON format and sends it to the server. The output is customer requirements data in JSON format and is sent to the server.

[0363] Step 3: Emotion Recognition

[0364] The device activates the emotion engine while the user is entering their requirements.

[0365] The input data consists of the user's facial expressions and voice tone. Specifically, the OpenCV library is used to analyze camera footage, and the speech_recognition library is used to analyze voice tone and input speed from the audio input.

[0366] The output is data about the user's emotional state. This is sent to the server in real time and used to adjust the content of the proposal.

[0367] Step 4: Requirements Matching

[0368] The server analyzes the received customer requirements and searches its internal database for the appropriate items.

[0369] The input data is customer requirements data in JSON format, sent to the server.

[0370] Specifically, the server executes SQL queries such as "SELECT FROM product_info WHERE ..." to search for items that match the requirements. It also sends API requests to the ERP system to check inventory information and delivery dates.

[0371] The output is a list of selected items and associated inventory and delivery information. This helps identify the best combination of products and services to meet customer requirements.

[0372] Step 5: Price Estimation

[0373] The server estimates the price of the selected items based on past case data and market information.

[0374] The input data consists of a list of selected items, historical case studies, and market information. Specifically, we will use Python and Pandas to compile the data into a data frame and analyze the historical price data.

[0375] The server executes queries such as "SELECT AVG(price) FROM past_cases WHERE ..." to estimate the optimal proposed price, taking into account cumulative costs and profit margins. The output is the estimated price information.

[0376] Step 6: Proposal generation and emotional reflection

[0377] The server automatically generates a proposal based on customer requirements, selected items, and estimated prices.

[0378] The input data includes customer requirements data, a list of selected items, estimated pricing information, and the results of the sentiment engine.

[0379] In terms of specific operation, the server sends a request to a natural language generation model (such as GPT-4) API to generate a proposal. Based on the results of the sentiment engine, the tone and expression of the proposal are adjusted. The output is a customized proposal.

[0380] Step 7: Submitting and revising the proposal

[0381] The server sends the generated proposal to the user's terminal.

[0382] The input data is the generated proposal. Specifically, the server converts the proposal to PDF format and sends it to the user's terminal.

[0383] The user will use Microsoft Word to review and revise the proposal, adding additional comments and details as needed. The output will be the final, approved proposal.

[0384] Step 8: Submitting the Proposal

[0385] The user submits the finalized proposal to the client.

[0386] The input data is the finalized proposal. Specifically, the user submits the proposal to the customer via email or an online submission form.

[0387] The output is a proposal submitted to the client. This allows for quick and accurate proposals to be made to the client.

[0388] (Application Example 2)

[0389] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0390] Traditional proposal creation systems, while possessing a certain degree of accuracy in receiving customer requirements and searching for product information, struggled to reflect the user's emotional state, making stress-free proposal creation difficult. Furthermore, the time-consuming process of refining proposal content resulted in inefficiency in situations requiring quick responses. Additionally, a lack of approaches to enhance the final proposal's level of satisfaction made it challenging to provide optimal solutions to customers.

[0391] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0392] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate products from collected product information, past case information, and market information, means for estimating the price of the selected product and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected products, and proposed price, means for sending the proposal to the user, emotion recognition means for recognizing the customer's emotions in real time, and means for adjusting the content of the proposal based on the results of emotion recognition. This makes it possible to make proposals quickly and effectively while taking into account the customer's emotional state.

[0393] "Customer requirements" refer to information that includes the specific conditions and preferences of the products and services that customers desire.

[0394] "Product information" refers to detailed data about the products or services offered, such as product name, specifications, and price.

[0395] "Past case information" refers to data that includes the history and results of proposals and transactions that have been carried out in the past.

[0396] "Market information" refers to data such as current market trends, competitor information, and demand forecasts.

[0397] "Emotion recognition" is a technology that analyzes a user's facial expressions, tone of voice, and other factors to determine their emotional state in real time.

[0398] "Inventory information" refers to data on the current inventory status and the quantity of products being managed.

[0399] "Delivery date information" refers to data regarding the scheduled delivery date and period for products and services.

[0400] A "proposal" is a document that outlines the specific products or services offered to a customer, including their content, price, and terms and conditions.

[0401] "Emotion recognition means" refers to hardware and software technologies for recognizing a user's emotional state in real time.

[0402] "Methods for adjusting the content of a proposal" refers to techniques that appropriately modify the wording and tone of a proposal based on the results of emotion recognition.

[0403] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. In particular, by combining it with an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The detailed configuration and operation of the system are described below.

[0404] System Configuration

[0405] This system consists of a server, a user terminal, and an emotion recognition device. The server connects to a database and collects the latest product information, past case studies, and market information. The user terminal provides a customer requirements input form and has an interface for sending the entered data to the server. The emotion recognition device analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[0406] Hardware and software to use

[0407] The hardware used is a robot that includes a facial recognition camera, microphone, and display. The software uses OpenCV for facial recognition, the Google Cloud Speech-to-Text API for speech analysis, Python for automatic proposal generation, and MySQL as the database.

[0408] Program processing

[0409] The server first connects to a database and periodically collects the latest product information, past case studies, and market information. Then, when customer requirements are entered from the user terminal, it searches for appropriate products and calculates prices based on this data. Furthermore, an emotion recognition device analyzes the user's face and voice to recognize their emotional state in real time. Based on the recognized emotional state, it adjusts the tone and expression of the proposal and sends the automatically generated proposal to the user terminal. The user then makes revisions as needed and submits the final proposal to the customer.

[0410] Specific example

[0411] For example, consider a scenario where an IT company receives the following requirements from a new client: 100 new servers are required, with the additional requirement being a high-speed storage option. The deadline is within one month, and the budget is under 50 million yen. Additionally, the client is experiencing stress while using the system.

[0412] In this case, the user enters their requirements into an input form on their device and submits it to the system. During the input process, the emotion engine recognizes the user's stress level and can change phrases like "We promise a prompt response" to "Please rest assured. We will provide you with the best solution tailored to your requirements."

[0413] Examples of prompts to input into a generative AI model are as follows:

[0414] "User Requirements: - Product: 100 new servers - Requirements: High-speed storage options - Delivery Time: Within 1 month - Budget: Within 50 million yen Please generate an optimal proposal based on past proposal examples and market information in the following format: - Product Name - Specifications - Price - Delivery Time - Notes Also, please present the proposal in a relaxed tone."

[0415] This allows us to respond to customer requirements quickly and accurately while taking user emotions into consideration.

[0416] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0417] Step 1:

[0418] The server connects to the database to collect the latest product information, past case studies, and market information. Input data includes product name, specifications, price, past case studies, and current market trends. This data is collected and stored in the internal database, ensuring that the latest product and market information is always accessible.

[0419] Step 2:

[0420] The user enters customer requirements (product quantity, features, budget, delivery date, etc.) using an input form on the terminal. The entered data is sent to the server in real time. This allows the server to understand the customer's specific requirements.

[0421] Step 3:

[0422] The device activates an emotion engine to recognize the user's emotions in real time while they are inputting data. The input data includes the user's facial expressions and tone of voice. The emotion engine analyzes this data and outputs the user's emotional state (stress, relaxation, etc.).

[0423] Step 4:

[0424] The server analyzes the received customer requirements and searches the database for appropriate products based on that information. Input data includes customer requirements, product information, past case studies, and market information. This data is then compared to output a list of the most suitable products.

[0425] Step 5:

[0426] The server checks the inventory and delivery date information for the searched product. It retrieves data from the inventory database and delivery date database and outputs whether the product is in stock and the period during which it can be delivered based on this data.

[0427] Step 6:

[0428] The server performs price estimation based on the received information. Input data includes information on the selected product, past case studies, and market information. Based on this, a price estimation algorithm is applied to output the optimal proposed price.

[0429] Step 7:

[0430] The server automatically generates proposals based on customer requirements, selected products, estimated prices, and the results of the sentiment engine. Input data includes customer requirements, product information, pricing information, and sentiment status. By combining these, the server outputs a proposal with the most appropriate expression and content for the customer.

[0431] Step 8:

[0432] The server sends the automatically generated proposal to the user's terminal. The user receives the proposal through their terminal and reviews its contents. They can then confirm that the proposal is written in a relaxed tone that is easy for them to understand.

[0433] Step 9:

[0434] The user modifies the proposal on their device. The user makes the necessary changes to the proposal and sends the final, confirmed proposal to the server. This results in a more optimal proposal that meets the customer's specific requirements.

[0435] Step 10:

[0436] The server submits the finalized proposal to the client. The submitted proposal reflects the user's perspective while quickly and accurately addressing the client's requirements.

[0437] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0438] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0439] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0440] [Second Embodiment]

[0441] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0442] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0443] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0444] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0445] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0446] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0447] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0448] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0449] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0450] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0451] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0452] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0453] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. The processing of the system's program and specific examples thereof will be described below.

[0454] System Construction

[0455] 1. Data Collection

[0456] The server periodically connects to the database to collect the latest product information (product name, specifications, price, etc.), past case studies, and market information. This information is stored in an internal database for use in the subsequent proposal process.

[0457] 2. Enter customer requirements

[0458] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (e.g., product quantity, features, budget, delivery date, etc.) into this form and submits it to the system. Through this process, the system understands the customer's specific needs.

[0459] 3. Requirements matching

[0460] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets. Furthermore, it checks inventory and delivery information to select the combination of products and services that best suits the customer requirements.

[0461] 4. Price Estimation

[0462] The server estimates the price of the selected product based on past case studies and market information. In this process, it considers appropriate cumulative costs and profit margins to determine the optimal proposed price (winning price).

[0463] 5. Proposal generation and submission

[0464] The server automatically generates a proposal. This proposal includes details of the products selected based on customer requirements, estimated pricing, delivery dates, and customization options. The generated proposal is sent to the user's terminal, where the user reviews it, makes any necessary revisions, and finally submits it to the customer.

[0465] Specific example

[0466] For example, consider a scenario where an IT company receives the following requirements from a new customer.

[0467] Required products: 100 new servers

[0468] Additional requirements: High-speed storage options

[0469] Delivery time: within 1 month

[0470] Budget: Within 50 million yen

[0471] The user enters these requirements into an input form on the terminal and submits them to the system. The server analyzes the received requirements and searches its database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[0472] Next, the server estimates the price based on past case studies and market information, calculating the optimal winning price that fits within the budget. Finally, the server automatically generates a proposal document, including customer requirements, selected products, and estimated prices. This proposal document is sent to the user's terminal, where the user reviews the content, makes any necessary revisions, and submits it to the customer. This process enables a quick and accurate response to customer needs.

[0473] The following describes the processing flow.

[0474] Step 1:

[0475] The server periodically connects to the database to retrieve the latest product information (e.g., product name, specifications, price). It also collects past case study information and market data and stores it in the internal database.

[0476] Step 2:

[0477] The terminal displays a customer requirements input form for the user. This form includes input fields for product quantity, features, budget, and delivery date.

[0478] Step 3:

[0479] The user fills in the specific requirements received from the customer into an input form and submits it to the system. This registers the customer's request in the system.

[0480] Step 4:

[0481] The server analyzes the received customer requirements, compares them with product information in the database, and searches for products or assets that match the requirements.

[0482] Step 5:

[0483] The server checks inventory and delivery date information for merchandise and assets retrieved from the database and identifies combinations that match customer requirements.

[0484] Step 6:

[0485] The server estimates the price of selected products and assets based on past case studies and market information. Profit margins and cost structures are also considered during this process.

[0486] Step 7:

[0487] The server calculates the optimal proposed price (winning price) based on the estimated price. This calculation is important for enhancing market competitiveness.

[0488] Step 8:

[0489] The server automatically generates a proposal based on customer requirements, selected products, and estimated pricing. The proposal includes product details, pricing, delivery dates, and customization options.

[0490] Step 9:

[0491] The server sends the generated proposal to the user's terminal.

[0492] Step 10:

[0493] The user reviews the proposal sent to their device and makes revisions as needed. These revisions are designed to flexibly respond to the customer's specific requirements.

[0494] Step 11:

[0495] The user submits the finalized proposal to the client.

[0496] (Example 1)

[0497] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0498] Traditional proposal creation systems struggled to accurately grasp customer requirements and automatically generate accurate proposals quickly. Furthermore, the time-consuming manual requirements verification and price estimation processes led to inefficiencies in the sales process. Additionally, the lack of a user-friendly interface during the proposal revision process further reduced work efficiency.

[0499] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0500] In this invention, the server includes means for connecting to a database and collecting product information, past case information, and market information; means for receiving customer requirements; means for analyzing the received customer requirements and searching for appropriate products from the database; means for estimating the price of the selected products based on past case information and market information and determining the optimal proposed price; means for automatically generating a proposal based on the customer requirements, selected products, and proposed price; and means for sending the proposal to the user. This enables accurate understanding of customer requirements and the rapid and accurate automatic generation of proposals.

[0501] A "database" is a data structure that centrally manages information and allows for efficient access and retrieval.

[0502] "Product information" refers to a series of pieces of information such as product name, specifications, and price, and is the data necessary when creating a proposal.

[0503] "Past case information" refers to performance data such as proposals, contract details, and pricing from past projects.

[0504] "Market information" refers to data about the external environment, such as industry trends, competitor pricing, and product trends.

[0505] "Customer requirements" refer to the specific requirements that the customer expects from the proposal (such as product quantity, functions, budget, and delivery date).

[0506] "Receiving" refers to the process of bringing data or information from external sources into the system.

[0507] "Analysis" is the process of classifying, evaluating, and understanding received data and information.

[0508] "Searching" is the process of finding relevant information from a database based on specific criteria.

[0509] "Price estimation" is the process of calculating the selling price of selected products, taking into account cumulative costs and profit margins.

[0510] The "proposed price" is the final selling price presented to the customer.

[0511] A "proposal" is a document created based on customer requirements and includes product details, pricing, delivery dates, and customization options.

[0512] "Automatic generation" refers to a system creating documents such as proposals based on a program, without human intervention.

[0513] "Sending" refers to the action of distributing the created proposal from the system to the user interface.

[0514] A "user" is the entity that operates this system and ultimately submits a proposal to the customer.

[0515] An "interface" refers to the screens and functions that allow a user to interact with a system.

[0516] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. The system configuration and specific operation are described below.

[0517] Data collection

[0518] The server first connects to a database to collect product information, past case studies, and market information. MySQL is often used as the database. Product information includes product name, specifications, and price. The server stores this collected data in an internal database such as MongoDB. In addition, market information is obtained from external sites using APIs or web scraping techniques (e.g., BeautifulSoup or Selenium).

[0519] Entering customer requirements

[0520] The terminal presents the user with a customer requirements input form via a web browser. This input form is built using a front-end framework such as React or Vue.js. The user enters requirements such as product quantity, features, budget, and delivery date, and clicks the submit button. This information is sent to the server as an HTTP request. The server's backend uses a web framework such as Node.js or Django.

[0521] Requirements matching

[0522] The server analyzes the received customer requirements. For this purpose, natural language processing (NLP) tools such as Python's NLTK library and spaCy are used. Based on the analyzed information, the server searches its internal database for relevant products and assets. SQL queries are used to retrieve appropriate information from the database, and inventory and delivery date information is confirmed.

[0523] Price estimate

[0524] The server estimates the price of selected products based on past case studies and market information. During this process, it performs detailed price analysis using machine learning libraries such as scikit-learn and TensorFlow. It then calculates the optimal proposed price (winning price) by considering cumulative costs and profit margins.

[0525] Proposal generation and submission

[0526] The server automatically generates a proposal using the Python ReportLab library. The proposal includes details of the products selected based on customer requirements, estimated pricing, delivery dates, and customization options. The generated proposal is created in PDF format and sent to the user's terminal as an HTTP response. The user reviews this proposal using Adobe Acrobat or similar software, makes any necessary revisions, and then submits it to the customer.

[0527] Specific example

[0528] For example, consider a scenario where an IT company receives the following requirements from a new customer:

[0529] Required products: 100 new servers

[0530] Additional requirements: High-speed storage options

[0531] Delivery time: within 1 month

[0532] Budget: Within 50 million yen

[0533] The user enters these requirements into an input form on their terminal's web browser and submits them to the system. The server uses NLP technology to analyze the received requirements and searches its database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[0534] Next, the server estimates the price based on past case studies and market information, and calculates the optimal winning price that fits within the budget. Finally, it automatically generates a proposal that includes the following items:

[0535] customer requirements

[0536] Selected products

[0537] Estimated price

[0538] Delivery time and customization options

[0539] This proposal is sent to the user's device, where they can review the content, make any necessary revisions, and submit it to the client, enabling quick and accurate proposals.

[0540] Example prompts for generative AI models

[0541] "The following customer requirements have been entered: '100 new servers, high-speed storage options, delivery within one month, budget under 50 million yen.' Based on this information, please generate the optimal proposal by referring to past case studies and market data."

[0542] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0543] Step 1: Data Collection

[0544] The server connects to a MySQL database to collect product information, past case studies, and market information. Specifically, it periodically executes a Python script to retrieve new data. The input requires database connection information and queries. The collected data is stored in an internal database (e.g., MongoDB). The server also retrieves external market information using APIs and web scraping techniques (such as BeautifulSoup or Selenium). This process ensures that product and market information remains up-to-date.

[0545] Step 2: Enter customer requirements

[0546] The device uses React or Vue.js to display a customer requirements input form in a web browser. Specifically, the form includes fields such as product quantity, features, budget, and delivery date. The user enters their requirements into these fields and clicks a submit button. The input is the customer requirements data entered by the user. The output from the device is sent to the server as an HTTP request, and the request payload contains the customer requirements.

[0547] Step 3: Requirements Analysis and Matching

[0548] The server retrieves customer requirements from received HTTP requests and parses the data using Python's NLTK and spaCy. The input is customer requirements data. The server uses natural language processing techniques to convert the requirements into structured data. Based on this parsed data, it searches the database for appropriate products and assets. Specifically, it uses SQL queries to retrieve relevant product information. The output is a list of products and assets found based on the parsed data.

[0549] Step 4: Check inventory and delivery information

[0550] The server checks inventory and delivery date information based on the product list obtained in step 3. The input is the product list. The server retrieves this information by calling an internal API. Specifically, it sends an API request and receives inventory and delivery date information as a response. The output is the product list including inventory and delivery date information.

[0551] Step 5: Price Estimation

[0552] The server estimates prices for selected products based on past case studies and market information. The input is a product list including inventory and delivery time information. Specifically, it uses a machine learning model with Python libraries (scikit-learn and TensorFlow) to predict prices. Cumulative costs and profit margins are considered during the estimation process. The output is the estimated price and the proposed price (winning price) for each product.

[0553] Step 6: Proposal Generation

[0554] The server automatically generates proposals using the Python ReportLab library. Inputs include customer requirements, selected products, estimated prices, and delivery date information. Specifically, it embeds a proposal template based on this data and generates a proposal in PDF format. The output is the generated proposal.

[0555] Step 7: Submitting and revising the proposal

[0556] The server sends the generated proposal to the user's terminal as an HTTP response. The input is the generated proposal. The user can review the proposal using tools such as Adobe Acrobat and make revisions as needed. The output is the final proposal, which is submitted to the client. This process ensures that clients receive a fast and accurate proposal.

[0557] (Application Example 1)

[0558] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0559] In customer service at logistics centers, the process from receiving requirements to generating proposals is complex, making it difficult to respond quickly and accurately. Furthermore, optimizing multiple products and distribution channels is often done manually, contributing to inefficiency. Additionally, verifying inventory and delivery information based on customer requirements is time-consuming, hindering accurate proposals.

[0560] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0561] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate products from collected product information, past case information, and market information, means for estimating the price of the selected product and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected products, and proposed price, means for presenting the generated proposal to the customer via a terminal, and means for selecting the optimal distribution route and product combination. This enables the logistics center to respond to customer requirements quickly and accurately, and to generate proposals efficiently and select the optimal distribution route.

[0562] "Means of receiving customer requirements" refers to devices or software used to collect specific customer requests and needs and input them into a system.

[0563] "Collected product information" refers to detailed product data obtained from sources such as the market, past transactions, and product databases.

[0564] "Past case information" refers to data based on past experience and examples of handling similar customer requirements.

[0565] "Market information" refers to data such as current market trends, price trends, and competitive conditions.

[0566] "Means for finding the right product" refers to algorithms and software used to identify and search for the most suitable product based on customer requirements, using collected product information, past case studies, and market data.

[0567] "Means for estimating the price of selected products" refers to a device or software that has the function of calculating the price of selected products based on past case information and market information.

[0568] "Means for determining the optimal proposed price" refers to algorithms or software that take into account cumulative costs and profit margins to determine the optimal price to propose to the customer.

[0569] "Methods for automatically generating proposals" refers to software that automatically creates proposals based on customer requirements, selected products, and estimated prices.

[0570] A "terminal" refers to a device used by people to input information or to check output.

[0571] "Means for selecting the optimal distribution route and product combination" refers to software or algorithms that have the functionality to select the optimal delivery method and combine multiple products according to customer requirements.

[0572] System Configuration

[0573] This invention is a system that receives customer requirements, searches for appropriate products from collected product information, past case information, and market information, calculates the optimal proposed price, and automatically generates a proposal. The system consists of three components: a server, a terminal, and a user.

[0574] Explanation of program processing

[0575] The server periodically connects to the database to collect product information (product name, specifications, price, etc.), past case studies, and market information, and stores it in the internal database. This makes it possible to always provide proposals based on the latest information.

[0576] The user uses a terminal to input customer requirements (e.g., product quantity, additional requirements, delivery date, budget, etc.). This entered data is then sent to the server.

[0577] The server analyzes the received customer requirements and searches its internal database for the most suitable product. Specifically, it selects the optimal product and distribution channel based on the quantity and functionality of the customer requirements, taking into account inventory and delivery time information.

[0578] Next, the server estimates the price of the selected product based on past case studies and market information. It then determines the optimal price to propose, taking into account cumulative costs and profit margins.

[0579] The server then automatically generates a proposal based on customer requirements, selected products, and estimated pricing. This proposal includes detailed product information and customization options.

[0580] Finally, the generated proposal is sent to the terminal, reviewed and revised by the user, and then presented to the client.

[0581] Hardware and software to be used

[0582] This system uses the following hardware and software:

[0583] Server: Collects information from the database, performs analysis and price estimation, and generates proposals. Software used includes Python and SQL.

[0584] Terminal: Used to input customer requirements and review / revise proposals. A variety of devices can be used, including smartphones, tablets, and PCs.

[0585] Database: Stores product information, past case studies, and market information. SQL databases are common.

[0586] Specific example

[0587] For example, a logistics center might receive the following requirements from a customer:

[0588] Required products: 100 high-performance servers

[0589] Additional requirements: High-speed storage options

[0590] Delivery time: within 1 month

[0591] Budget: Within 50 million yen

[0592] When the user enters these requirements via their terminal, the server analyzes the requirements, selects the optimal server and storage options, and estimates the price based on past case studies and market information. Next, it automatically generates a proposal and sends it to the user via their terminal.

[0593] Examples of prompts for a generative AI model are as follows:

[0594] "Based on the number of products requested by the customer and any additional requirements, please generate a proposal outlining the optimal product combination and pricing. The requirements are as follows: Number of products: 100, Additional requirements: High-speed storage option, Delivery time: within 1 month, Budget: within 50 million yen."

[0595] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0596] Step 1:

[0597] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (product quantity, additional requirements, delivery date, budget, etc.) into this form. The entered data is stored on the terminal and sent to the server. Specifically, the user enters 100 high-performance servers and high-speed storage options, a delivery date of less than one month, and a budget of 50 million yen.

[0598] input:

[0599] Customer's specific requirements: Product quantity, additional requirements, delivery date, budget

[0600] output:

[0601] Customer requirements data (JSON format)

[0602] Step 2:

[0603] The server analyzes the customer requirements received from the terminal. This analysis verifies that the entered requirements are accurate and complete, and fills in any unclear or missing information as needed. Based on the results of this analysis, the next steps proceed.

[0604] input:

[0605] Customer requirements data

[0606] output:

[0607] Analyzed customer requirements data

[0608] Step 3:

[0609] The server searches its internal database for appropriate products based on the analyzed customer requirements data. This search utilizes pre-collected product information, past case studies, and market information. For example, it might retrieve information on 100 high-performance servers and high-speed storage options from the database.

[0610] input:

[0611] Analyzed customer requirements data

[0612] Internal databases containing product information, past case studies, and market information.

[0613] output:

[0614] A list of suitable product candidates

[0615] Step 4:

[0616] The server checks inventory and delivery information based on a suitable list of product candidates. This allows for the confirmation of product availability and delivery dates according to customer requirements. For example, it checks whether the acquired high-performance server and high-speed storage can be delivered within one month.

[0617] input:

[0618] A list of suitable product candidates

[0619] Internal database inventory information, delivery date information

[0620] output:

[0621] Inventory information and delivery date information

[0622] Step 5:

[0623] The server estimates the price of the selected product based on inventory and delivery information. This estimation takes into account past sales data and market information, and determines the proposed price based on total cost and optimal profit margin.

[0624] input:

[0625] A list of suitable product candidates

[0626] Inventory information and delivery date information

[0627] Past case information, market information

[0628] output:

[0629] Estimated price information

[0630] Step 6:

[0631] The server automatically generates a proposal based on customer requirements, selected products, and estimated pricing information. This proposal includes product details, pricing information, stock availability, delivery dates, and customization options.

[0632] input:

[0633] customer requirements

[0634] Selected products

[0635] Estimated price information

[0636] output:

[0637] Automatically generated proposal (PDF or HTML format)

[0638] Step 7:

[0639] The server sends the generated proposal to the terminal. The user reviews the proposal and makes revisions as needed. They then submit the final version of the proposal to the client.

[0640] input:

[0641] Automatically generated proposal

[0642] output:

[0643] Revised and reviewed proposal

[0644] The above steps efficiently solve the problem that the invention aims to address (rapid and accurate customer response and proposal generation).

[0645] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0646] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The processing of the system's program and specific examples are described below.

[0647] System Construction

[0648] 1. Data Collection

[0649] The server periodically connects to the database to collect the latest product information (product name, specifications, price, etc.), past case studies, and market information. This information is stored in an internal database for use in the subsequent proposal process.

[0650] 2. Enter customer requirements

[0651] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (e.g., product quantity, features, budget, delivery date, etc.) into this form and submits it to the system. Through this process, the system understands the customer's specific needs.

[0652] 3. Emotion recognition

[0653] The terminal activates an emotion engine to recognize the user's emotions in real time while they are entering customer requirements. The emotion engine analyzes the user's facial expressions, tone of voice, input speed, and other factors.

[0654] 4. Requirements matching

[0655] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets. Furthermore, it checks inventory and delivery information to select the combination of products and services that best suits the customer requirements.

[0656] 5. Price Estimation

[0657] The server estimates the price of the selected product based on past case studies and market information. In this process, it considers appropriate cumulative costs and profit margins to determine the optimal proposed price (winning price).

[0658] 6. Proposal generation and emotional reflection

[0659] The server automatically generates a proposal based on customer requirements, selected products, and estimated prices. Based on the results of the emotion engine, it adjusts the tone and expression of the proposal, customizing it to be easier for users to understand and accept.

[0660] 7. Submitting and revising the proposal

[0661] The server sends the generated proposal to the user's terminal. The user reviews the proposal sent to their terminal and makes revisions as needed. These revisions are intended to flexibly respond to the customer's specific requirements.

[0662] 8. Submission of proposal

[0663] The user submits the finalized proposal to the client.

[0664] Specific example

[0665] For example, consider a scenario where an IT company receives the following requirements from a new customer.

[0666] Required products: 100 new servers

[0667] Additional requirements: High-speed storage options

[0668] Delivery time: within 1 month

[0669] Budget: Within 50 million yen

[0670] Emotional state: Feeling stressed while typing.

[0671] The user enters this requirement into an input form on their device and submits it to the system. During input, the emotion engine recognizes the user's stress level and adjusts the wording of the proposal to a calmer tone. For example, the system can change the phrase "We promise a prompt response" to "Please rest assured. We will provide you with the best possible solution tailored to your requirements."

[0672] The server analyzes the received requirements and searches the database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[0673] Subsequently, the server estimates the price based on past case studies and market information, calculating the optimal winning price within a budget of 50 million yen. Finally, the server automatically generates a proposal, incorporating the results of the emotion engine, and sends it to the user's terminal. The user reviews the content, makes revisions as needed, and finally submits it to the client. This process enables a rapid and accurate response to client needs.

[0674] The following describes the processing flow.

[0675] Step 1:

[0676] The server periodically connects to the database to retrieve the latest product information (e.g., product name, specifications, price), past case studies, and market information. This information is stored in the internal database.

[0677] Step 2:

[0678] The terminal displays a customer requirements input form for the user. This form includes input fields for product quantity, features, budget, and delivery date.

[0679] Step 3:

[0680] The user enters the specific requirements received from the customer into an input form and sends that information to the system.

[0681] Step 4:

[0682] The terminal activates an emotion engine while the customer requirements are being entered. The emotion engine analyzes the user's facial expressions, voice, input speed, etc., to recognize emotions in real time.

[0683] Step 5:

[0684] The device sends the recognized emotion data to the server. This allows customer requirements and emotion information to be aggregated on the server.

[0685] Step 6:

[0686] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets.

[0687] Step 7:

[0688] The server checks inventory and delivery date information for merchandise and assets retrieved from the database and identifies combinations that match customer requirements.

[0689] Step 8:

[0690] The server estimates the price of selected products and assets based on past case studies and market information. In this process, it also considers appropriate cumulative costs and profit margins.

[0691] Step 9:

[0692] The server calculates the optimal proposed price (winning price) based on the estimated price.

[0693] Step 10:

[0694] The server automatically generates a proposal based on customer requirements, selected products, estimated pricing, and user sentiment information. The content of the proposal is then adjusted based on the results of the sentiment engine.

[0695] Step 11:

[0696] The server sends the generated proposal to the user's terminal. The sent proposal reflects a tone and expression that takes the user's feelings into consideration.

[0697] Step 12:

[0698] Users review the proposal on their devices and make revisions as needed. These revisions are designed to flexibly respond to the customer's specific requirements.

[0699] Step 13:

[0700] The user submits the finalized proposal to the client, enabling them to respond to the client's needs quickly and accurately.

[0701] Specific example

[0702] For example, consider a scenario where an IT company receives the following requirements.

[0703] Required products: 100 new servers

[0704] Additional requirements: High-speed storage options

[0705] Delivery time: within 1 month

[0706] Budget: Within 50 million yen

[0707] Emotional state: Feeling stressed while typing.

[0708] Following steps 1 through 13, the system acquires user input and analyzes emotions in real time through an emotion engine. The analysis results are reflected in the proposal content, and are adjusted to reduce stress, for example, by using phrases like "We promise a prompt response."

[0709] This process allows the system to respond quickly and effectively to customer needs and reduce user stress.

[0710] (Example 2)

[0711] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0712] Conventional proposal generation systems required a significant amount of time for analyzing customer requirements and creating proposals, making it difficult to improve the accuracy of proposals and customer satisfaction. Furthermore, proposals were not customized to consider the user's emotional state, failing to reduce user stress. This made it difficult to improve the efficiency of sales activities and the effective operation of the proposal process.

[0713] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0714] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate items from collected item information, past case information, and market information, means for estimating the price of selected items and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected items, and proposed price, means for sending the proposal to the user, and means for analyzing the user's emotions in real time and adjusting the content of the proposal. This enables the rapid and accurate generation of proposals based on customer requirements, and further allows for customization according to the user's emotional state, thereby improving customer satisfaction and streamlining sales activities.

[0715] "Customer requirements" refer to the specific needs of a customer regarding the quantity, functions, budget, and delivery date of the products or services they desire.

[0716] "Product information" refers to detailed information about a product, such as its name, specifications, and price.

[0717] "Past case information" refers to information about the content and results of similar proposals made in the past.

[0718] "Market information" refers to information about current market trends, such as competitors' prices and market trends.

[0719] "Search methods" refer to algorithms and database queries used to identify items that meet customer requirements based on collected information.

[0720] "Methods for estimation" refer to methods or tools used to calculate the price or cost of selected items and derive the optimal proposed price.

[0721] A "proposal" is a document that summarizes customer requirements, selected items, and estimated prices, and outlines the proposal to be presented to the customer.

[0722] "Automatic generation means" refers to a function that allows the system to automatically create a proposal based on the collected information and analysis results.

[0723] "Means of transmission" refers to the means of communication used to send the generated proposal to the user's terminal.

[0724] "Means for analyzing and adjusting emotions" refers to a function that analyzes the user's facial expressions and tone of voice, and appropriately modifies the tone and expression of the proposal.

[0725] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The processing of the system's program and specific examples are described below.

[0726] System Configuration

[0727] The system uses the following hardware and software:

[0728] server

[0729] Database: MySQL

[0730] ERP system

[0731] Data analysis libraries: Python, Pandas

[0732] Natural language generation model API (e.g., GPT-4)

[0733] terminal

[0734] Web browser: Google Chrome

[0735] Camera and microphone (for emotion recognition)

[0736] Facial expression analysis library: OpenCV

[0737] Speech analysis library: speech_recognition

[0738] Specific flow and content of the process

[0739] 1. Data Collection

[0740] The server periodically connects to the database to collect the latest product information, past case information, and market information. This information is retrieved from the MySQL database and stored in an internal database on the server.

[0741] 2. Enter customer requirements

[0742] The terminal displays a customer requirements input form on a web browser for the user. The user enters the product quantity, required functions, budget, delivery date, etc. into this form and submits it to the system. The terminal converts this input data into JSON format and sends it to the server.

[0743] 3. Emotion recognition

[0744] The device activates the emotion engine while the user is entering information into a form. The emotion engine captures camera footage and analyzes voice input to determine the user's emotional state in real time and sends the results to the server.

[0745] 4. Requirements matching

[0746] The server analyzes the received customer requirements and searches its internal database for appropriate items. During this process, it also uses the ERP system to check inventory and delivery information, identifying the combination of products and services best suited to the customer's requirements.

[0747] 5. Price Estimation

[0748] Based on past case studies and market information, the server uses data analysis libraries (Python, Pandas) to estimate the price of selected items and determine the optimal proposed price.

[0749] 6. Proposal generation and emotional reflection

[0750] The server automatically generates proposals based on customer requirements, selected items, and estimated prices using an automated generation model (e.g., GPT-4). It also adjusts the tone and expression of the proposals based on the results of an emotion engine, customizing them to be more easily understood and accepted by the user.

[0751] 7. Submitting and revising the proposal

[0752] The server converts the generated proposal into PDF format and sends it to the user's terminal. The user then uses Microsoft Word to review and revise the proposal, adding additional comments and details as needed.

[0753] 8. Submission of proposal

[0754] The user submits the finalized proposal to the client via email or an online submission form.

[0755] Examples of specific cases and prompt statements

[0756] For example, consider a scenario where an IT company receives the following requirements from a new customer:

[0757] Required products: 100 new servers

[0758] Additional requirements: High-speed storage options

[0759] Delivery time: within 1 month

[0760] Budget: Within 50 million yen

[0761] Emotional state: Feeling stressed while typing.

[0762] The user enters this information and sends it to the system. The emotion engine recognizes the user's stress level and adjusts the proposal content to be expressed in a calm tone. For example, it might change "We promise a prompt response" to "Please rest assured. We will provide the best proposal to meet your requirements."

[0763] The server analyzes the requirements and searches for and identifies appropriate products and delivery information from the MySQL database and ERP system. It then uses Pandas to estimate prices and derive the optimal proposed price within a budget of 50 million yen. Finally, GPT-4 generates a proposal, which, incorporating the results of the sentiment engine, is sent to the user's terminal. The user reviews and revises the proposal before finally submitting it to the customer.

[0764] Example of a prompt

[0765] "Create the optimal proposal based on customer requirements. Generate a proposal that meets the following requirements:

[0766] Requirements: 100 new servers, high-speed storage options

[0767] Delivery time: within 1 month

[0768] Budget: Within 50 million yen

[0769] Emotional state: Use a calm tone for users who are feeling stressed.

[0770] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0771] Step 1: Data Collection

[0772] The server periodically connects to the database and collects the following information:

[0773] Product information: Product name, specifications, price, etc.

[0774] Past case information: Previous proposals, success stories, etc.

[0775] Market information: Competitor pricing and market trends

[0776] Input data is retrieved from a MySQL database. Specifically, the server executes SQL queries such as "SELECT FROM product_info" and saves the results to an internal database.

[0777] The output is the most recent information stored in the internal database. This provides the latest data for use in the next processing step.

[0778] Step 2: Enter customer requirements

[0779] The terminal displays a customer requirements input form on a web browser for the user.

[0780] The input data includes the quantity of products the user enters, the required functions, budget, and delivery date. The user operates this form using a browser such as Google Chrome, enters the information, and clicks the "Submit" button.

[0781] Specifically, the terminal converts this input data into JSON format and sends it to the server. The output is customer requirements data in JSON format and is sent to the server.

[0782] Step 3: Emotion Recognition

[0783] The device activates the emotion engine while the user is entering their requirements.

[0784] The input data consists of the user's facial expressions and voice tone. Specifically, the OpenCV library is used to analyze camera footage, and the speech_recognition library is used to analyze voice tone and input speed from the audio input.

[0785] The output is data about the user's emotional state. This is sent to the server in real time and used to adjust the content of the proposal.

[0786] Step 4: Requirements Matching

[0787] The server analyzes the received customer requirements and searches its internal database for the appropriate items.

[0788] The input data is customer requirements data in JSON format, sent to the server.

[0789] Specifically, the server executes SQL queries such as "SELECT FROM product_info WHERE ..." to search for items that match the requirements. It also sends API requests to the ERP system to check inventory information and delivery dates.

[0790] The output is a list of selected items and associated inventory and delivery information. This helps identify the best combination of products and services to meet customer requirements.

[0791] Step 5: Price Estimation

[0792] The server estimates the price of the selected items based on past case data and market information.

[0793] The input data consists of a list of selected items, historical case studies, and market information. Specifically, we will use Python and Pandas to compile the data into a data frame and analyze the historical price data.

[0794] The server executes queries such as "SELECT AVG(price) FROM past_cases WHERE ..." to estimate the optimal proposed price, taking into account cumulative costs and profit margins. The output is the estimated price information.

[0795] Step 6: Proposal generation and emotional reflection

[0796] The server automatically generates a proposal based on customer requirements, selected items, and estimated prices.

[0797] The input data includes customer requirements data, a list of selected items, estimated pricing information, and the results of the sentiment engine.

[0798] In terms of specific operation, the server sends a request to a natural language generation model (such as GPT-4) API to generate a proposal. Based on the results of the sentiment engine, the tone and expression of the proposal are adjusted. The output is a customized proposal.

[0799] Step 7: Submitting and revising the proposal

[0800] The server sends the generated proposal to the user's terminal.

[0801] The input data is the generated proposal. Specifically, the server converts the proposal to PDF format and sends it to the user's terminal.

[0802] The user will use Microsoft Word to review and revise the proposal, adding additional comments and details as needed. The output will be the final, approved proposal.

[0803] Step 8: Submitting the Proposal

[0804] The user submits the finalized proposal to the client.

[0805] The input data is the finalized proposal. Specifically, the user submits the proposal to the customer via email or an online submission form.

[0806] The output is a proposal submitted to the client. This allows for quick and accurate proposals to be made to the client.

[0807] (Application Example 2)

[0808] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0809] Traditional proposal creation systems, while possessing a certain degree of accuracy in receiving customer requirements and searching for product information, struggled to reflect the user's emotional state, making stress-free proposal creation difficult. Furthermore, the time-consuming process of refining proposal content resulted in inefficiency in situations requiring quick responses. Additionally, a lack of approaches to enhance the final proposal's level of satisfaction made it challenging to provide optimal solutions to customers.

[0810] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0811] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate products from collected product information, past case information, and market information, means for estimating the price of the selected product and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected products, and proposed price, means for sending the proposal to the user, emotion recognition means for recognizing the customer's emotions in real time, and means for adjusting the content of the proposal based on the results of emotion recognition. This makes it possible to make proposals quickly and effectively while taking into account the customer's emotional state.

[0812] "Customer requirements" refer to information that includes the specific conditions and preferences of the products and services that customers desire.

[0813] "Product information" refers to detailed data about the products or services offered, such as product name, specifications, and price.

[0814] "Past case information" refers to data that includes the history and results of proposals and transactions that have been carried out in the past.

[0815] "Market information" refers to data such as current market trends, competitor information, and demand forecasts.

[0816] "Emotion recognition" is a technology that analyzes a user's facial expressions, tone of voice, and other factors to determine their emotional state in real time.

[0817] "Inventory information" refers to data on the current inventory status and the quantity of products being managed.

[0818] "Delivery date information" refers to data regarding the scheduled delivery date and period for products and services.

[0819] A "proposal" is a document that outlines the specific products or services offered to a customer, including their content, price, and terms and conditions.

[0820] "Emotion recognition means" refers to hardware and software technologies for recognizing a user's emotional state in real time.

[0821] "Methods for adjusting the content of a proposal" refers to techniques that appropriately modify the wording and tone of a proposal based on the results of emotion recognition.

[0822] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. In particular, by combining it with an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The detailed configuration and operation of the system are described below.

[0823] System Configuration

[0824] This system consists of a server, a user terminal, and an emotion recognition device. The server connects to a database and collects the latest product information, past case studies, and market information. The user terminal provides a customer requirements input form and has an interface for sending the entered data to the server. The emotion recognition device analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[0825] Hardware and software to use

[0826] The hardware used is a robot that includes a facial recognition camera, microphone, and display. The software uses OpenCV for facial recognition, the Google Cloud Speech-to-Text API for speech analysis, Python for automatic proposal generation, and MySQL as the database.

[0827] Program processing

[0828] The server first connects to a database and periodically collects the latest product information, past case studies, and market information. Then, when customer requirements are entered from the user terminal, it searches for appropriate products and calculates prices based on this data. Furthermore, an emotion recognition device analyzes the user's face and voice to recognize their emotional state in real time. Based on the recognized emotional state, it adjusts the tone and expression of the proposal and sends the automatically generated proposal to the user terminal. The user then makes revisions as needed and submits the final proposal to the customer.

[0829] Specific example

[0830] For example, consider a scenario where an IT company receives the following requirements from a new client: 100 new servers are required, with the additional requirement being a high-speed storage option. The deadline is within one month, and the budget is under 50 million yen. Additionally, the client is experiencing stress while using the system.

[0831] In this case, the user enters their requirements into an input form on their device and submits it to the system. During the input process, the emotion engine recognizes the user's stress level and can change phrases like "We promise a prompt response" to "Please rest assured. We will provide you with the best solution tailored to your requirements."

[0832] Examples of prompts to input into a generative AI model are as follows:

[0833] "User Requirements: - Product: 100 new servers - Requirements: High-speed storage options - Delivery Time: Within 1 month - Budget: Within 50 million yen Please generate an optimal proposal based on past proposal examples and market information in the following format: - Product Name - Specifications - Price - Delivery Time - Notes Also, please present the proposal in a relaxed tone."

[0834] This allows us to respond to customer requirements quickly and accurately while taking user emotions into consideration.

[0835] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0836] Step 1:

[0837] The server connects to the database to collect the latest product information, past case studies, and market information. Input data includes product name, specifications, price, past case studies, and current market trends. This data is collected and stored in the internal database, ensuring that the latest product and market information is always accessible.

[0838] Step 2:

[0839] The user enters customer requirements (product quantity, features, budget, delivery date, etc.) using an input form on the terminal. The entered data is sent to the server in real time. This allows the server to understand the customer's specific requirements.

[0840] Step 3:

[0841] The device activates an emotion engine to recognize the user's emotions in real time while they are inputting data. The input data includes the user's facial expressions and tone of voice. The emotion engine analyzes this data and outputs the user's emotional state (stress, relaxation, etc.).

[0842] Step 4:

[0843] The server analyzes the received customer requirements and searches the database for appropriate products based on that information. Input data includes customer requirements, product information, past case studies, and market information. This data is then compared to output a list of the most suitable products.

[0844] Step 5:

[0845] The server checks the inventory and delivery date information for the searched product. It retrieves data from the inventory database and delivery date database and outputs whether the product is in stock and the period during which it can be delivered based on this data.

[0846] Step 6:

[0847] The server performs price estimation based on the received information. Input data includes information on the selected product, past case studies, and market information. Based on this, a price estimation algorithm is applied to output the optimal proposed price.

[0848] Step 7:

[0849] The server automatically generates proposals based on customer requirements, selected products, estimated prices, and the results of the sentiment engine. Input data includes customer requirements, product information, pricing information, and sentiment status. By combining these, the server outputs a proposal with the most appropriate expression and content for the customer.

[0850] Step 8:

[0851] The server sends the automatically generated proposal to the user's terminal. The user receives the proposal through their terminal and reviews its contents. They can then confirm that the proposal is written in a relaxed tone that is easy for them to understand.

[0852] Step 9:

[0853] The user modifies the proposal on their device. The user makes the necessary changes to the proposal and sends the final, confirmed proposal to the server. This results in a more optimal proposal that meets the customer's specific requirements.

[0854] Step 10:

[0855] The server submits the finalized proposal to the client. The submitted proposal reflects the user's perspective while quickly and accurately addressing the client's requirements.

[0856] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0857] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0858] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0859] [Third Embodiment]

[0860] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0861] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0862] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0863] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0864] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0865] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0866] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0867] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0868] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0869] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0870] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0871] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0872] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. The processing of the system's program and specific examples thereof will be described below.

[0873] System Construction

[0874] 1. Data Collection

[0875] The server periodically connects to the database to collect the latest product information (product name, specifications, price, etc.), past case studies, and market information. This information is stored in an internal database for use in the subsequent proposal process.

[0876] 2. Enter customer requirements

[0877] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (e.g., product quantity, features, budget, delivery date, etc.) into this form and submits it to the system. Through this process, the system understands the customer's specific needs.

[0878] 3. Requirements matching

[0879] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets. Furthermore, it checks inventory and delivery information to select the combination of products and services that best suits the customer requirements.

[0880] 4. Price Estimation

[0881] The server estimates the price of the selected product based on past case studies and market information. In this process, it considers appropriate cumulative costs and profit margins to determine the optimal proposed price (winning price).

[0882] 5. Proposal generation and submission

[0883] The server automatically generates a proposal. This proposal includes details of the products selected based on customer requirements, estimated pricing, delivery dates, and customization options. The generated proposal is sent to the user's terminal, where the user reviews it, makes any necessary revisions, and finally submits it to the customer.

[0884] Specific example

[0885] For example, consider a scenario where an IT company receives the following requirements from a new customer.

[0886] Required products: 100 new servers

[0887] Additional requirements: High-speed storage options

[0888] Delivery time: within 1 month

[0889] Budget: Within 50 million yen

[0890] The user enters these requirements into an input form on the terminal and submits them to the system. The server analyzes the received requirements and searches its database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[0891] Next, the server estimates the price based on past case studies and market information, calculating the optimal winning price that fits within the budget. Finally, the server automatically generates a proposal document, including customer requirements, selected products, and estimated prices. This proposal document is sent to the user's terminal, where the user reviews the content, makes any necessary revisions, and submits it to the customer. This process enables a quick and accurate response to customer needs.

[0892] The following describes the processing flow.

[0893] Step 1:

[0894] The server periodically connects to the database to retrieve the latest product information (e.g., product name, specifications, price). It also collects past case study information and market data and stores it in the internal database.

[0895] Step 2:

[0896] The terminal displays a customer requirements input form for the user. This form includes input fields for product quantity, features, budget, and delivery date.

[0897] Step 3:

[0898] The user fills in the specific requirements received from the customer into an input form and submits it to the system. This registers the customer's request in the system.

[0899] Step 4:

[0900] The server analyzes the received customer requirements, compares them with product information in the database, and searches for products or assets that match the requirements.

[0901] Step 5:

[0902] The server checks inventory and delivery date information for merchandise and assets retrieved from the database and identifies combinations that match customer requirements.

[0903] Step 6:

[0904] The server estimates the price of selected products and assets based on past case studies and market information. Profit margins and cost structures are also considered during this process.

[0905] Step 7:

[0906] The server calculates the optimal proposed price (winning price) based on the estimated price. This calculation is important for enhancing market competitiveness.

[0907] Step 8:

[0908] The server automatically generates a proposal based on customer requirements, selected products, and estimated pricing. The proposal includes product details, pricing, delivery dates, and customization options.

[0909] Step 9:

[0910] The server sends the generated proposal to the user's terminal.

[0911] Step 10:

[0912] The user reviews the proposal sent to their device and makes revisions as needed. These revisions are designed to flexibly respond to the customer's specific requirements.

[0913] Step 11:

[0914] The user submits the finalized proposal to the client.

[0915] (Example 1)

[0916] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0917] Traditional proposal creation systems struggled to accurately grasp customer requirements and automatically generate accurate proposals quickly. Furthermore, the time-consuming manual requirements verification and price estimation processes led to inefficiencies in the sales process. Additionally, the lack of a user-friendly interface during the proposal revision process further reduced work efficiency.

[0918] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0919] In this invention, the server includes means for connecting to a database and collecting product information, past case information, and market information; means for receiving customer requirements; means for analyzing the received customer requirements and searching for appropriate products from the database; means for estimating the price of the selected products based on past case information and market information and determining the optimal proposed price; means for automatically generating a proposal based on the customer requirements, selected products, and proposed price; and means for sending the proposal to the user. This enables accurate understanding of customer requirements and the rapid and accurate automatic generation of proposals.

[0920] A "database" is a data structure that centrally manages information and allows for efficient access and retrieval.

[0921] "Product information" refers to a series of pieces of information such as product name, specifications, and price, and is the data necessary when creating a proposal.

[0922] "Past case information" refers to performance data such as proposals, contract details, and pricing from past projects.

[0923] "Market information" refers to data about the external environment, such as industry trends, competitor pricing, and product trends.

[0924] "Customer requirements" refer to the specific requirements that the customer expects from the proposal (such as product quantity, functions, budget, and delivery date).

[0925] "Receiving" refers to the process of bringing data or information from external sources into the system.

[0926] "Analysis" is the process of classifying, evaluating, and understanding received data and information.

[0927] "Searching" is the process of finding relevant information from a database based on specific criteria.

[0928] "Price estimation" is the process of calculating the selling price of selected products, taking into account cumulative costs and profit margins.

[0929] The "proposed price" is the final selling price presented to the customer.

[0930] A "proposal" is a document created based on customer requirements and includes product details, pricing, delivery dates, and customization options.

[0931] "Automatic generation" refers to a system creating documents such as proposals based on a program, without human intervention.

[0932] "Sending" refers to the action of distributing the created proposal from the system to the user interface.

[0933] A "user" is the entity that operates this system and ultimately submits a proposal to the customer.

[0934] An "interface" refers to the screens and functions that allow a user to interact with a system.

[0935] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. The system configuration and specific operation are described below.

[0936] Data collection

[0937] The server first connects to a database to collect product information, past case studies, and market information. MySQL is often used as the database. Product information includes product name, specifications, and price. The server stores this collected data in an internal database such as MongoDB. In addition, market information is obtained from external sites using APIs or web scraping techniques (e.g., BeautifulSoup or Selenium).

[0938] Entering customer requirements

[0939] The terminal presents the user with a customer requirements input form via a web browser. This input form is built using a front-end framework such as React or Vue.js. The user enters requirements such as product quantity, features, budget, and delivery date, and clicks the submit button. This information is sent to the server as an HTTP request. The server's backend uses a web framework such as Node.js or Django.

[0940] Requirements matching

[0941] The server analyzes the received customer requirements. For this purpose, natural language processing (NLP) tools such as Python's NLTK library and spaCy are used. Based on the analyzed information, the server searches its internal database for relevant products and assets. SQL queries are used to retrieve appropriate information from the database, and inventory and delivery date information is confirmed.

[0942] Price estimate

[0943] The server estimates the price of selected products based on past case studies and market information. During this process, it performs detailed price analysis using machine learning libraries such as scikit-learn and TensorFlow. It then calculates the optimal proposed price (winning price) by considering cumulative costs and profit margins.

[0944] Proposal generation and submission

[0945] The server automatically generates a proposal using the Python ReportLab library. The proposal includes details of the products selected based on customer requirements, estimated pricing, delivery dates, and customization options. The generated proposal is created in PDF format and sent to the user's terminal as an HTTP response. The user reviews this proposal using Adobe Acrobat or similar software, makes any necessary revisions, and then submits it to the customer.

[0946] Specific example

[0947] For example, consider a scenario where an IT company receives the following requirements from a new customer:

[0948] Required products: 100 new servers

[0949] Additional requirements: High-speed storage options

[0950] Delivery time: within 1 month

[0951] Budget: Within 50 million yen

[0952] The user enters these requirements into an input form on their terminal's web browser and submits them to the system. The server uses NLP technology to analyze the received requirements and searches its database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[0953] Next, the server estimates the price based on past case studies and market information, and calculates the optimal winning price that fits within the budget. Finally, it automatically generates a proposal that includes the following items:

[0954] customer requirements

[0955] Selected products

[0956] Estimated price

[0957] Delivery time and customization options

[0958] This proposal is sent to the user's device, where they can review the content, make any necessary revisions, and submit it to the client, enabling quick and accurate proposals.

[0959] Example prompts for generative AI models

[0960] "The following customer requirements have been entered: '100 new servers, high-speed storage options, delivery within one month, budget under 50 million yen.' Based on this information, please generate the optimal proposal by referring to past case studies and market data."

[0961] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0962] Step 1: Data Collection

[0963] The server connects to a MySQL database to collect product information, past case studies, and market information. Specifically, it periodically executes a Python script to retrieve new data. The input requires database connection information and queries. The collected data is stored in an internal database (e.g., MongoDB). The server also retrieves external market information using APIs and web scraping techniques (such as BeautifulSoup or Selenium). This process ensures that product and market information remains up-to-date.

[0964] Step 2: Enter customer requirements

[0965] The device uses React or Vue.js to display a customer requirements input form in a web browser. Specifically, the form includes fields such as product quantity, features, budget, and delivery date. The user enters their requirements into these fields and clicks a submit button. The input is the customer requirements data entered by the user. The output from the device is sent to the server as an HTTP request, and the request payload contains the customer requirements.

[0966] Step 3: Requirements Analysis and Matching

[0967] The server retrieves customer requirements from received HTTP requests and parses the data using Python's NLTK and spaCy. The input is customer requirements data. The server uses natural language processing techniques to convert the requirements into structured data. Based on this parsed data, it searches the database for appropriate products and assets. Specifically, it uses SQL queries to retrieve relevant product information. The output is a list of products and assets found based on the parsed data.

[0968] Step 4: Check inventory and delivery information

[0969] The server checks inventory and delivery date information based on the product list obtained in step 3. The input is the product list. The server retrieves this information by calling an internal API. Specifically, it sends an API request and receives inventory and delivery date information as a response. The output is the product list including inventory and delivery date information.

[0970] Step 5: Price Estimation

[0971] The server estimates prices for selected products based on past case studies and market information. The input is a product list including inventory and delivery time information. Specifically, it uses a machine learning model with Python libraries (scikit-learn and TensorFlow) to predict prices. Cumulative costs and profit margins are considered during the estimation process. The output is the estimated price and the proposed price (winning price) for each product.

[0972] Step 6: Proposal Generation

[0973] The server automatically generates proposals using the Python ReportLab library. Inputs include customer requirements, selected products, estimated prices, and delivery date information. Specifically, it embeds a proposal template based on this data and generates a proposal in PDF format. The output is the generated proposal.

[0974] Step 7: Submitting and revising the proposal

[0975] The server sends the generated proposal to the user's terminal as an HTTP response. The input is the generated proposal. The user can review the proposal using tools such as Adobe Acrobat and make revisions as needed. The output is the final proposal, which is submitted to the client. This process ensures that clients receive a fast and accurate proposal.

[0976] (Application Example 1)

[0977] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0978] In customer service at logistics centers, the process from receiving requirements to generating proposals is complex, making it difficult to respond quickly and accurately. Furthermore, optimizing multiple products and distribution channels is often done manually, contributing to inefficiency. Additionally, verifying inventory and delivery information based on customer requirements is time-consuming, hindering accurate proposals.

[0979] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0980] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate products from collected product information, past case information, and market information, means for estimating the price of the selected product and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected products, and proposed price, means for presenting the generated proposal to the customer via a terminal, and means for selecting the optimal distribution route and product combination. This enables the logistics center to respond to customer requirements quickly and accurately, and to generate proposals efficiently and select the optimal distribution route.

[0981] "Means of receiving customer requirements" refers to devices or software used to collect specific customer requests and needs and input them into a system.

[0982] "Collected product information" refers to detailed product data obtained from sources such as the market, past transactions, and product databases.

[0983] "Past case information" refers to data based on past experience and examples of handling similar customer requirements.

[0984] "Market information" refers to data such as current market trends, price trends, and competitive conditions.

[0985] "Means for finding the right product" refers to algorithms and software used to identify and search for the most suitable product based on customer requirements, using collected product information, past case studies, and market data.

[0986] "Means for estimating the price of selected products" refers to a device or software that has the function of calculating the price of selected products based on past case information and market information.

[0987] "Means for determining the optimal proposed price" refers to algorithms or software that take into account cumulative costs and profit margins to determine the optimal price to propose to the customer.

[0988] "Methods for automatically generating proposals" refers to software that automatically creates proposals based on customer requirements, selected products, and estimated prices.

[0989] A "terminal" refers to a device used by people to input information or to check output.

[0990] "Means for selecting the optimal distribution route and product combination" refers to software or algorithms that have the functionality to select the optimal delivery method and combine multiple products according to customer requirements.

[0991] System Configuration

[0992] This invention is a system that receives customer requirements, searches for appropriate products from collected product information, past case information, and market information, calculates the optimal proposed price, and automatically generates a proposal. The system consists of three components: a server, a terminal, and a user.

[0993] Explanation of program processing

[0994] The server periodically connects to the database to collect product information (product name, specifications, price, etc.), past case studies, and market information, and stores it in the internal database. This makes it possible to always provide proposals based on the latest information.

[0995] The user uses a terminal to input customer requirements (e.g., product quantity, additional requirements, delivery date, budget, etc.). This entered data is then sent to the server.

[0996] The server analyzes the received customer requirements and searches its internal database for the most suitable product. Specifically, it selects the optimal product and distribution channel based on the quantity and functionality of the customer requirements, taking into account inventory and delivery time information.

[0997] Next, the server estimates the price of the selected product based on past case studies and market information. It then determines the optimal price to propose, taking into account cumulative costs and profit margins.

[0998] The server then automatically generates a proposal based on customer requirements, selected products, and estimated pricing. This proposal includes detailed product information and customization options.

[0999] Finally, the generated proposal is sent to the terminal, reviewed and revised by the user, and then presented to the client.

[1000] Hardware and software to be used

[1001] This system uses the following hardware and software:

[1002] Server: Collects information from the database, performs analysis and price estimation, and generates proposals. Software used includes Python and SQL.

[1003] Terminal: Used to input customer requirements and review / revise proposals. A variety of devices can be used, including smartphones, tablets, and PCs.

[1004] Database: Stores product information, past case studies, and market information. SQL databases are common.

[1005] Specific example

[1006] For example, a logistics center might receive the following requirements from a customer:

[1007] Required products: 100 high-performance servers

[1008] Additional requirements: High-speed storage options

[1009] Delivery time: within 1 month

[1010] Budget: Within 50 million yen

[1011] When the user enters these requirements via their terminal, the server analyzes the requirements, selects the optimal server and storage options, and estimates the price based on past case studies and market information. Next, it automatically generates a proposal and sends it to the user via their terminal.

[1012] Examples of prompts for a generative AI model are as follows:

[1013] "Based on the number of products requested by the customer and any additional requirements, please generate a proposal outlining the optimal product combination and pricing. The requirements are as follows: Number of products: 100, Additional requirements: High-speed storage option, Delivery time: within 1 month, Budget: within 50 million yen."

[1014] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1015] Step 1:

[1016] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (product quantity, additional requirements, delivery date, budget, etc.) into this form. The entered data is stored on the terminal and sent to the server. Specifically, the user enters 100 high-performance servers and high-speed storage options, a delivery date of less than one month, and a budget of 50 million yen.

[1017] input:

[1018] Customer's specific requirements: Product quantity, additional requirements, delivery date, budget

[1019] output:

[1020] Customer requirements data (JSON format)

[1021] Step 2:

[1022] The server analyzes the customer requirements received from the terminal. This analysis verifies that the entered requirements are accurate and complete, and fills in any unclear or missing information as needed. Based on the results of this analysis, the next steps proceed.

[1023] input:

[1024] Customer requirements data

[1025] output:

[1026] Analyzed customer requirements data

[1027] Step 3:

[1028] The server searches its internal database for appropriate products based on the analyzed customer requirements data. This search utilizes pre-collected product information, past case studies, and market information. For example, it might retrieve information on 100 high-performance servers and high-speed storage options from the database.

[1029] input:

[1030] Analyzed customer requirements data

[1031] Internal databases containing product information, past case studies, and market information.

[1032] output:

[1033] A list of suitable product candidates

[1034] Step 4:

[1035] The server checks inventory and delivery information based on a suitable list of product candidates. This allows for the confirmation of product availability and delivery dates according to customer requirements. For example, it checks whether the acquired high-performance server and high-speed storage can be delivered within one month.

[1036] input:

[1037] A list of suitable product candidates

[1038] Internal database inventory information, delivery date information

[1039] output:

[1040] Inventory information and delivery date information

[1041] Step 5:

[1042] The server estimates the price of the selected product based on inventory and delivery information. This estimation takes into account past sales data and market information, and determines the proposed price based on total cost and optimal profit margin.

[1043] input:

[1044] A list of suitable product candidates

[1045] Inventory information and delivery date information

[1046] Past case information, market information

[1047] output:

[1048] Estimated price information

[1049] Step 6:

[1050] The server automatically generates a proposal based on customer requirements, selected products, and estimated pricing information. This proposal includes product details, pricing information, stock availability, delivery dates, and customization options.

[1051] input:

[1052] customer requirements

[1053] Selected products

[1054] Estimated price information

[1055] output:

[1056] Automatically generated proposal (PDF or HTML format)

[1057] Step 7:

[1058] The server sends the generated proposal to the terminal. The user reviews the proposal and makes revisions as needed. They then submit the final version of the proposal to the client.

[1059] input:

[1060] Automatically generated proposal

[1061] output:

[1062] Revised and reviewed proposal

[1063] The above steps efficiently solve the problem that the invention aims to address (rapid and accurate customer response and proposal generation).

[1064] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1065] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The processing of the system's program and specific examples are described below.

[1066] System Construction

[1067] 1. Data Collection

[1068] The server periodically connects to the database to collect the latest product information (product name, specifications, price, etc.), past case studies, and market information. This information is stored in an internal database for use in the subsequent proposal process.

[1069] 2. Enter customer requirements

[1070] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (e.g., product quantity, features, budget, delivery date, etc.) into this form and submits it to the system. Through this process, the system understands the customer's specific needs.

[1071] 3. Emotion recognition

[1072] The terminal activates an emotion engine to recognize the user's emotions in real time while they are entering customer requirements. The emotion engine analyzes the user's facial expressions, tone of voice, input speed, and other factors.

[1073] 4. Requirements matching

[1074] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets. Furthermore, it checks inventory and delivery information to select the combination of products and services that best suits the customer requirements.

[1075] 5. Price Estimation

[1076] The server estimates the price of the selected product based on past case studies and market information. In this process, it considers appropriate cumulative costs and profit margins to determine the optimal proposed price (winning price).

[1077] 6. Proposal generation and emotional reflection

[1078] The server automatically generates a proposal based on customer requirements, selected products, and estimated prices. Based on the results of the emotion engine, it adjusts the tone and expression of the proposal, customizing it to be easier for users to understand and accept.

[1079] 7. Submitting and revising the proposal

[1080] The server sends the generated proposal to the user's terminal. The user reviews the proposal sent to their terminal and makes revisions as needed. These revisions are intended to flexibly respond to the customer's specific requirements.

[1081] 8. Submission of proposal

[1082] The user submits the finalized proposal to the client.

[1083] Specific example

[1084] For example, consider a scenario where an IT company receives the following requirements from a new customer.

[1085] Required products: 100 new servers

[1086] Additional requirements: High-speed storage options

[1087] Delivery time: within 1 month

[1088] Budget: Within 50 million yen

[1089] Emotional state: Feeling stressed while typing.

[1090] The user enters this requirement into an input form on their device and submits it to the system. During input, the emotion engine recognizes the user's stress level and adjusts the wording of the proposal to a calmer tone. For example, the system can change the phrase "We promise a prompt response" to "Please rest assured. We will provide you with the best possible solution tailored to your requirements."

[1091] The server analyzes the received requirements and searches the database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[1092] Subsequently, the server estimates the price based on past case studies and market information, calculating the optimal winning price within a budget of 50 million yen. Finally, the server automatically generates a proposal, incorporating the results of the emotion engine, and sends it to the user's terminal. The user reviews the content, makes revisions as needed, and finally submits it to the client. This process enables a rapid and accurate response to client needs.

[1093] The following describes the processing flow.

[1094] Step 1:

[1095] The server periodically connects to the database to retrieve the latest product information (e.g., product name, specifications, price), past case studies, and market information. This information is stored in the internal database.

[1096] Step 2:

[1097] The terminal displays a customer requirements input form for the user. This form includes input fields for product quantity, features, budget, and delivery date.

[1098] Step 3:

[1099] The user enters the specific requirements received from the customer into an input form and sends that information to the system.

[1100] Step 4:

[1101] The terminal activates an emotion engine while the customer requirements are being entered. The emotion engine analyzes the user's facial expressions, voice, input speed, etc., to recognize emotions in real time.

[1102] Step 5:

[1103] The device sends the recognized emotion data to the server. This allows customer requirements and emotion information to be aggregated on the server.

[1104] Step 6:

[1105] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets.

[1106] Step 7:

[1107] The server checks inventory and delivery date information for merchandise and assets retrieved from the database and identifies combinations that match customer requirements.

[1108] Step 8:

[1109] The server estimates the price of selected products and assets based on past case studies and market information. In this process, it also considers appropriate cumulative costs and profit margins.

[1110] Step 9:

[1111] The server calculates the optimal proposed price (winning price) based on the estimated price.

[1112] Step 10:

[1113] The server automatically generates a proposal based on customer requirements, selected products, estimated pricing, and user sentiment information. The content of the proposal is then adjusted based on the results of the sentiment engine.

[1114] Step 11:

[1115] The server sends the generated proposal to the user's terminal. The sent proposal reflects a tone and expression that takes the user's feelings into consideration.

[1116] Step 12:

[1117] Users review the proposal on their devices and make revisions as needed. These revisions are designed to flexibly respond to the customer's specific requirements.

[1118] Step 13:

[1119] The user submits the finalized proposal to the client, enabling them to respond to the client's needs quickly and accurately.

[1120] Specific example

[1121] For example, consider a scenario where an IT company receives the following requirements.

[1122] Required products: 100 new servers

[1123] Additional requirements: High-speed storage options

[1124] Delivery time: within 1 month

[1125] Budget: Within 50 million yen

[1126] Emotional state: Feeling stressed while typing.

[1127] Following steps 1 through 13, the system acquires user input and analyzes emotions in real time through an emotion engine. The analysis results are reflected in the proposal content, and are adjusted to reduce stress, for example, by using phrases like "We promise a prompt response."

[1128] This process allows the system to respond quickly and effectively to customer needs and reduce user stress.

[1129] (Example 2)

[1130] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1131] Conventional proposal generation systems required a significant amount of time for analyzing customer requirements and creating proposals, making it difficult to improve the accuracy of proposals and customer satisfaction. Furthermore, proposals were not customized to consider the user's emotional state, failing to reduce user stress. This made it difficult to improve the efficiency of sales activities and the effective operation of the proposal process.

[1132] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1133] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate items from collected item information, past case information, and market information, means for estimating the price of selected items and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected items, and proposed price, means for sending the proposal to the user, and means for analyzing the user's emotions in real time and adjusting the content of the proposal. This enables the rapid and accurate generation of proposals based on customer requirements, and further allows for customization according to the user's emotional state, thereby improving customer satisfaction and streamlining sales activities.

[1134] "Customer requirements" refer to the specific needs of a customer regarding the quantity, functions, budget, and delivery date of the products or services they desire.

[1135] "Product information" refers to detailed information about a product, such as its name, specifications, and price.

[1136] "Past case information" refers to information about the content and results of similar proposals made in the past.

[1137] "Market information" refers to information about current market trends, such as competitors' prices and market trends.

[1138] "Search methods" refer to algorithms and database queries used to identify items that meet customer requirements based on collected information.

[1139] "Methods for estimation" refer to methods or tools used to calculate the price or cost of selected items and derive the optimal proposed price.

[1140] A "proposal" is a document that summarizes customer requirements, selected items, and estimated prices, and outlines the proposal to be presented to the customer.

[1141] "Automatic generation means" refers to a function that allows the system to automatically create a proposal based on the collected information and analysis results.

[1142] "Means of transmission" refers to the means of communication used to send the generated proposal to the user's terminal.

[1143] "Means for analyzing and adjusting emotions" refers to a function that analyzes the user's facial expressions and tone of voice, and appropriately modifies the tone and expression of the proposal.

[1144] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The processing of the system's program and specific examples are described below.

[1145] System Configuration

[1146] The system uses the following hardware and software:

[1147] server

[1148] Database: MySQL

[1149] ERP system

[1150] Data analysis libraries: Python, Pandas

[1151] Natural language generation model API (e.g., GPT-4)

[1152] terminal

[1153] Web browser: Google Chrome

[1154] Camera and microphone (for emotion recognition)

[1155] Facial expression analysis library: OpenCV

[1156] Speech analysis library: speech_recognition

[1157] Specific flow and content of the process

[1158] 1. Data Collection

[1159] The server periodically connects to the database to collect the latest product information, past case information, and market information. This information is retrieved from the MySQL database and stored in an internal database on the server.

[1160] 2. Enter customer requirements

[1161] The terminal displays a customer requirements input form on a web browser for the user. The user enters the product quantity, required functions, budget, delivery date, etc. into this form and submits it to the system. The terminal converts this input data into JSON format and sends it to the server.

[1162] 3. Emotion recognition

[1163] The device activates the emotion engine while the user is entering information into a form. The emotion engine captures camera footage and analyzes voice input to determine the user's emotional state in real time and sends the results to the server.

[1164] 4. Requirements matching

[1165] The server analyzes the received customer requirements and searches its internal database for appropriate items. During this process, it also uses the ERP system to check inventory and delivery information, identifying the combination of products and services best suited to the customer's requirements.

[1166] 5. Price Estimation

[1167] Based on past case studies and market information, the server uses data analysis libraries (Python, Pandas) to estimate the price of selected items and determine the optimal proposed price.

[1168] 6. Proposal generation and emotional reflection

[1169] The server automatically generates proposals based on customer requirements, selected items, and estimated prices using an automated generation model (e.g., GPT-4). It also adjusts the tone and expression of the proposals based on the results of an emotion engine, customizing them to be more easily understood and accepted by the user.

[1170] 7. Submitting and revising the proposal

[1171] The server converts the generated proposal into PDF format and sends it to the user's terminal. The user then uses Microsoft Word to review and revise the proposal, adding additional comments and details as needed.

[1172] 8. Submission of proposal

[1173] The user submits the finalized proposal to the client via email or an online submission form.

[1174] Examples of specific cases and prompt statements

[1175] For example, consider a scenario where an IT company receives the following requirements from a new customer:

[1176] Required products: 100 new servers

[1177] Additional requirements: High-speed storage options

[1178] Delivery time: within 1 month

[1179] Budget: Within 50 million yen

[1180] Emotional state: Feeling stressed while typing.

[1181] The user enters this information and sends it to the system. The emotion engine recognizes the user's stress level and adjusts the proposal content to be expressed in a calm tone. For example, it might change "We promise a prompt response" to "Please rest assured. We will provide the best proposal to meet your requirements."

[1182] The server analyzes the requirements and searches for and identifies appropriate products and delivery information from the MySQL database and ERP system. It then uses Pandas to estimate prices and derive the optimal proposed price within a budget of 50 million yen. Finally, GPT-4 generates a proposal, which, incorporating the results of the sentiment engine, is sent to the user's terminal. The user reviews and revises the proposal before finally submitting it to the customer.

[1183] Example of a prompt

[1184] "Create the optimal proposal based on customer requirements. Generate a proposal that meets the following requirements:

[1185] Requirements: 100 new servers, high-speed storage options

[1186] Delivery time: within 1 month

[1187] Budget: Within 50 million yen

[1188] Emotional state: Use a calm tone for users who are feeling stressed.

[1189] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1190] Step 1: Data Collection

[1191] The server periodically connects to the database and collects the following information:

[1192] Product information: Product name, specifications, price, etc.

[1193] Past case information: Previous proposals, success stories, etc.

[1194] Market information: Competitor pricing and market trends

[1195] Input data is retrieved from a MySQL database. Specifically, the server executes SQL queries such as "SELECT FROM product_info" and saves the results to an internal database.

[1196] The output is the most recent information stored in the internal database. This provides the latest data for use in the next processing step.

[1197] Step 2: Enter customer requirements

[1198] The terminal displays a customer requirements input form on a web browser for the user.

[1199] The input data includes the quantity of products the user enters, the required functions, budget, and delivery date. The user operates this form using a browser such as Google Chrome, enters the information, and clicks the "Submit" button.

[1200] Specifically, the terminal converts this input data into JSON format and sends it to the server. The output is customer requirements data in JSON format and is sent to the server.

[1201] Step 3: Emotion Recognition

[1202] The device activates the emotion engine while the user is entering their requirements.

[1203] The input data consists of the user's facial expressions and voice tone. Specifically, the OpenCV library is used to analyze camera footage, and the speech_recognition library is used to analyze voice tone and input speed from the audio input.

[1204] The output is data about the user's emotional state. This is sent to the server in real time and used to adjust the content of the proposal.

[1205] Step 4: Requirements Matching

[1206] The server analyzes the received customer requirements and searches its internal database for the appropriate items.

[1207] The input data is customer requirements data in JSON format, sent to the server.

[1208] Specifically, the server executes SQL queries such as "SELECT FROM product_info WHERE ..." to search for items that match the requirements. It also sends API requests to the ERP system to check inventory information and delivery dates.

[1209] The output is a list of selected items and associated inventory and delivery information. This helps identify the best combination of products and services to meet customer requirements.

[1210] Step 5: Price Estimation

[1211] The server estimates the price of the selected items based on past case data and market information.

[1212] The input data consists of a list of selected items, historical case studies, and market information. Specifically, we will use Python and Pandas to compile the data into a data frame and analyze the historical price data.

[1213] The server executes queries such as "SELECT AVG(price) FROM past_cases WHERE ..." to estimate the optimal proposed price, taking into account cumulative costs and profit margins. The output is the estimated price information.

[1214] Step 6: Proposal generation and emotional reflection

[1215] The server automatically generates a proposal based on customer requirements, selected items, and estimated prices.

[1216] The input data includes customer requirements data, a list of selected items, estimated pricing information, and the results of the sentiment engine.

[1217] In terms of specific operation, the server sends a request to a natural language generation model (such as GPT-4) API to generate a proposal. Based on the results of the sentiment engine, the tone and expression of the proposal are adjusted. The output is a customized proposal.

[1218] Step 7: Submitting and revising the proposal

[1219] The server sends the generated proposal to the user's terminal.

[1220] The input data is the generated proposal. Specifically, the server converts the proposal to PDF format and sends it to the user's terminal.

[1221] The user will use Microsoft Word to review and revise the proposal, adding additional comments and details as needed. The output will be the final, approved proposal.

[1222] Step 8: Submitting the Proposal

[1223] The user submits the finalized proposal to the client.

[1224] The input data is the finalized proposal. Specifically, the user submits the proposal to the customer via email or an online submission form.

[1225] The output is a proposal submitted to the client. This allows for quick and accurate proposals to be made to the client.

[1226] (Application Example 2)

[1227] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1228] Traditional proposal creation systems, while possessing a certain degree of accuracy in receiving customer requirements and searching for product information, struggled to reflect the user's emotional state, making stress-free proposal creation difficult. Furthermore, the time-consuming process of refining proposal content resulted in inefficiency in situations requiring quick responses. Additionally, a lack of approaches to enhance the final proposal's level of satisfaction made it challenging to provide optimal solutions to customers.

[1229] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1230] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate products from collected product information, past case information, and market information, means for estimating the price of the selected product and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected products, and proposed price, means for sending the proposal to the user, emotion recognition means for recognizing the customer's emotions in real time, and means for adjusting the content of the proposal based on the results of emotion recognition. This makes it possible to make proposals quickly and effectively while taking into account the customer's emotional state.

[1231] "Customer requirements" refer to information that includes the specific conditions and preferences of the products and services that customers desire.

[1232] "Product information" refers to detailed data about the products or services offered, such as product name, specifications, and price.

[1233] "Past case information" refers to data that includes the history and results of proposals and transactions that have been carried out in the past.

[1234] "Market information" refers to data such as current market trends, competitor information, and demand forecasts.

[1235] "Emotion recognition" is a technology that analyzes a user's facial expressions, tone of voice, and other factors to determine their emotional state in real time.

[1236] "Inventory information" refers to data on the current inventory status and the quantity of products being managed.

[1237] "Delivery date information" refers to data regarding the scheduled delivery date and period for products and services.

[1238] A "proposal" is a document that outlines the specific products or services offered to a customer, including their content, price, and terms and conditions.

[1239] "Emotion recognition means" refers to hardware and software technologies for recognizing a user's emotional state in real time.

[1240] "Methods for adjusting the content of a proposal" refers to techniques that appropriately modify the wording and tone of a proposal based on the results of emotion recognition.

[1241] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. In particular, by combining it with an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The detailed configuration and operation of the system are described below.

[1242] System Configuration

[1243] This system consists of a server, a user terminal, and an emotion recognition device. The server connects to a database and collects the latest product information, past case studies, and market information. The user terminal provides a customer requirements input form and has an interface for sending the entered data to the server. The emotion recognition device analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[1244] Hardware and software to use

[1245] The hardware used is a robot that includes a facial recognition camera, microphone, and display. The software uses OpenCV for facial recognition, the Google Cloud Speech-to-Text API for speech analysis, Python for automatic proposal generation, and MySQL as the database.

[1246] Program processing

[1247] The server first connects to a database and periodically collects the latest product information, past case studies, and market information. Then, when customer requirements are entered from the user terminal, it searches for appropriate products and calculates prices based on this data. Furthermore, an emotion recognition device analyzes the user's face and voice to recognize their emotional state in real time. Based on the recognized emotional state, it adjusts the tone and expression of the proposal and sends the automatically generated proposal to the user terminal. The user then makes revisions as needed and submits the final proposal to the customer.

[1248] Specific example

[1249] For example, consider a scenario where an IT company receives the following requirements from a new client: 100 new servers are required, with the additional requirement being a high-speed storage option. The deadline is within one month, and the budget is under 50 million yen. Additionally, the client is experiencing stress while using the system.

[1250] In this case, the user enters their requirements into an input form on their device and submits it to the system. During the input process, the emotion engine recognizes the user's stress level and can change phrases like "We promise a prompt response" to "Please rest assured. We will provide you with the best solution tailored to your requirements."

[1251] Examples of prompts to input into a generative AI model are as follows:

[1252] "User Requirements: - Product: 100 new servers - Requirements: High-speed storage options - Delivery Time: Within 1 month - Budget: Within 50 million yen Please generate an optimal proposal based on past proposal examples and market information in the following format: - Product Name - Specifications - Price - Delivery Time - Notes Also, please present the proposal in a relaxed tone."

[1253] This allows us to respond to customer requirements quickly and accurately while taking user emotions into consideration.

[1254] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1255] Step 1:

[1256] The server connects to the database to collect the latest product information, past case studies, and market information. Input data includes product name, specifications, price, past case studies, and current market trends. This data is collected and stored in the internal database, ensuring that the latest product and market information is always accessible.

[1257] Step 2:

[1258] The user enters customer requirements (product quantity, features, budget, delivery date, etc.) using an input form on the terminal. The entered data is sent to the server in real time. This allows the server to understand the customer's specific requirements.

[1259] Step 3:

[1260] The device activates an emotion engine to recognize the user's emotions in real time while they are inputting data. The input data includes the user's facial expressions and tone of voice. The emotion engine analyzes this data and outputs the user's emotional state (stress, relaxation, etc.).

[1261] Step 4:

[1262] The server analyzes the received customer requirements and searches the database for appropriate products based on that information. Input data includes customer requirements, product information, past case studies, and market information. This data is then compared to output a list of the most suitable products.

[1263] Step 5:

[1264] The server checks the inventory and delivery date information for the searched product. It retrieves data from the inventory database and delivery date database and outputs whether the product is in stock and the period during which it can be delivered based on this data.

[1265] Step 6:

[1266] The server performs price estimation based on the received information. Input data includes information on the selected product, past case studies, and market information. Based on this, a price estimation algorithm is applied to output the optimal proposed price.

[1267] Step 7:

[1268] The server automatically generates proposals based on customer requirements, selected products, estimated prices, and the results of the sentiment engine. Input data includes customer requirements, product information, pricing information, and sentiment status. By combining these, the server outputs a proposal with the most appropriate expression and content for the customer.

[1269] Step 8:

[1270] The server sends the automatically generated proposal to the user's terminal. The user receives the proposal through their terminal and reviews its contents. They can then confirm that the proposal is written in a relaxed tone that is easy for them to understand.

[1271] Step 9:

[1272] The user modifies the proposal on their device. The user makes the necessary changes to the proposal and sends the final, confirmed proposal to the server. This results in a more optimal proposal that meets the customer's specific requirements.

[1273] Step 10:

[1274] The server submits the finalized proposal to the client. The submitted proposal reflects the user's perspective while quickly and accurately addressing the client's requirements.

[1275] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1276] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1277] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1278] [Fourth Embodiment]

[1279] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1280] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1281] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1282] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1283] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1284] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1285] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1286] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1287] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1288] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1289] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1290] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1291] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1292] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. The processing of the system's program and specific examples thereof will be described below.

[1293] System Construction

[1294] 1. Data Collection

[1295] The server periodically connects to the database to collect the latest product information (product name, specifications, price, etc.), past case studies, and market information. This information is stored in an internal database for use in the subsequent proposal process.

[1296] 2. Enter customer requirements

[1297] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (e.g., product quantity, features, budget, delivery date, etc.) into this form and submits it to the system. Through this process, the system understands the customer's specific needs.

[1298] 3. Requirements matching

[1299] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets. Furthermore, it checks inventory and delivery information to select the combination of products and services that best suits the customer requirements.

[1300] 4. Price Estimation

[1301] The server estimates the price of the selected product based on past case studies and market information. In this process, it considers appropriate cumulative costs and profit margins to determine the optimal proposed price (winning price).

[1302] 5. Proposal generation and submission

[1303] The server automatically generates a proposal. This proposal includes details of the products selected based on customer requirements, estimated pricing, delivery dates, and customization options. The generated proposal is sent to the user's terminal, where the user reviews it, makes any necessary revisions, and finally submits it to the customer.

[1304] Specific example

[1305] For example, consider a scenario where an IT company receives the following requirements from a new customer.

[1306] Required products: 100 new servers

[1307] Additional requirements: High-speed storage options

[1308] Delivery time: within 1 month

[1309] Budget: Within 50 million yen

[1310] The user enters these requirements into an input form on the terminal and submits them to the system. The server analyzes the received requirements and searches its database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[1311] Next, the server estimates the price based on past case studies and market information, calculating the optimal winning price that fits within the budget. Finally, the server automatically generates a proposal document, including customer requirements, selected products, and estimated prices. This proposal document is sent to the user's terminal, where the user reviews the content, makes any necessary revisions, and submits it to the customer. This process enables a quick and accurate response to customer needs.

[1312] The following describes the processing flow.

[1313] Step 1:

[1314] The server periodically connects to the database to retrieve the latest product information (e.g., product name, specifications, price). It also collects past case study information and market data and stores it in the internal database.

[1315] Step 2:

[1316] The terminal displays a customer requirements input form for the user. This form includes input fields for product quantity, features, budget, and delivery date.

[1317] Step 3:

[1318] The user fills in the specific requirements received from the customer into an input form and submits it to the system. This registers the customer's request in the system.

[1319] Step 4:

[1320] The server analyzes the received customer requirements, compares them with product information in the database, and searches for products or assets that match the requirements.

[1321] Step 5:

[1322] The server checks inventory and delivery date information for merchandise and assets retrieved from the database and identifies combinations that match customer requirements.

[1323] Step 6:

[1324] The server estimates the price of selected products and assets based on past case studies and market information. Profit margins and cost structures are also considered during this process.

[1325] Step 7:

[1326] The server calculates the optimal proposed price (winning price) based on the estimated price. This calculation is important for enhancing market competitiveness.

[1327] Step 8:

[1328] The server automatically generates a proposal based on customer requirements, selected products, and estimated pricing. The proposal includes product details, pricing, delivery dates, and customization options.

[1329] Step 9:

[1330] The server sends the generated proposal to the user's terminal.

[1331] Step 10:

[1332] The user reviews the proposal sent to their device and makes revisions as needed. These revisions are designed to flexibly respond to the customer's specific requirements.

[1333] Step 11:

[1334] The user submits the finalized proposal to the client.

[1335] (Example 1)

[1336] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1337] Traditional proposal creation systems struggled to accurately grasp customer requirements and automatically generate accurate proposals quickly. Furthermore, the time-consuming manual requirements verification and price estimation processes led to inefficiencies in the sales process. Additionally, the lack of a user-friendly interface during the proposal revision process further reduced work efficiency.

[1338] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1339] In this invention, the server includes means for connecting to a database and collecting product information, past case information, and market information; means for receiving customer requirements; means for analyzing the received customer requirements and searching for appropriate products from the database; means for estimating the price of the selected products based on past case information and market information and determining the optimal proposed price; means for automatically generating a proposal based on the customer requirements, selected products, and proposed price; and means for sending the proposal to the user. This enables accurate understanding of customer requirements and the rapid and accurate automatic generation of proposals.

[1340] A "database" is a data structure that centrally manages information and allows for efficient access and retrieval.

[1341] "Product information" refers to a series of pieces of information such as product name, specifications, and price, and is the data necessary when creating a proposal.

[1342] "Past case information" refers to performance data such as proposals, contract details, and pricing from past projects.

[1343] "Market information" refers to data about the external environment, such as industry trends, competitor pricing, and product trends.

[1344] "Customer requirements" refer to the specific requirements that the customer expects from the proposal (such as product quantity, functions, budget, and delivery date).

[1345] "Receiving" refers to the process of bringing data or information from external sources into the system.

[1346] "Analysis" is the process of classifying, evaluating, and understanding received data and information.

[1347] "Searching" is the process of finding relevant information from a database based on specific criteria.

[1348] "Price estimation" is the process of calculating the selling price of selected products, taking into account cumulative costs and profit margins.

[1349] The "proposed price" is the final selling price presented to the customer.

[1350] A "proposal" is a document created based on customer requirements and includes product details, pricing, delivery dates, and customization options.

[1351] "Automatic generation" refers to a system creating documents such as proposals based on a program, without human intervention.

[1352] "Sending" refers to the action of distributing the created proposal from the system to the user interface.

[1353] A "user" is the entity that operates this system and ultimately submits a proposal to the customer.

[1354] An "interface" refers to the screens and functions that allow a user to interact with a system.

[1355] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. The system configuration and specific operation are described below.

[1356] Data collection

[1357] The server first connects to a database to collect product information, past case studies, and market information. MySQL is often used as the database. Product information includes product name, specifications, and price. The server stores this collected data in an internal database such as MongoDB. In addition, market information is obtained from external sites using APIs or web scraping techniques (e.g., BeautifulSoup or Selenium).

[1358] Entering customer requirements

[1359] The terminal presents the user with a customer requirements input form via a web browser. This input form is built using a front-end framework such as React or Vue.js. The user enters requirements such as product quantity, features, budget, and delivery date, and clicks the submit button. This information is sent to the server as an HTTP request. The server's backend uses a web framework such as Node.js or Django.

[1360] Requirements matching

[1361] The server analyzes the received customer requirements. For this purpose, natural language processing (NLP) tools such as Python's NLTK library and spaCy are used. Based on the analyzed information, the server searches its internal database for relevant products and assets. SQL queries are used to retrieve appropriate information from the database, and inventory and delivery date information is confirmed.

[1362] Price estimate

[1363] The server estimates the price of selected products based on past case studies and market information. During this process, it performs detailed price analysis using machine learning libraries such as scikit-learn and TensorFlow. It then calculates the optimal proposed price (winning price) by considering cumulative costs and profit margins.

[1364] Proposal generation and submission

[1365] The server automatically generates a proposal using the Python ReportLab library. The proposal includes details of the products selected based on customer requirements, estimated pricing, delivery dates, and customization options. The generated proposal is created in PDF format and sent to the user's terminal as an HTTP response. The user reviews this proposal using Adobe Acrobat or similar software, makes any necessary revisions, and then submits it to the customer.

[1366] Specific example

[1367] For example, consider a scenario where an IT company receives the following requirements from a new customer:

[1368] Required products: 100 new servers

[1369] Additional requirements: High-speed storage options

[1370] Delivery time: within 1 month

[1371] Budget: Within 50 million yen

[1372] The user enters these requirements into an input form on their terminal's web browser and submits them to the system. The server uses NLP technology to analyze the received requirements and searches its database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[1373] Next, the server estimates the price based on past case studies and market information, and calculates the optimal winning price that fits within the budget. Finally, it automatically generates a proposal that includes the following items:

[1374] customer requirements

[1375] Selected products

[1376] Estimated price

[1377] Delivery time and customization options

[1378] This proposal is sent to the user's device, where they can review the content, make any necessary revisions, and submit it to the client, enabling quick and accurate proposals.

[1379] Example prompts for generative AI models

[1380] "The following customer requirements have been entered: '100 new servers, high-speed storage options, delivery within one month, budget under 50 million yen.' Based on this information, please generate the optimal proposal by referring to past case studies and market data."

[1381] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1382] Step 1: Data Collection

[1383] The server connects to a MySQL database to collect product information, past case studies, and market information. Specifically, it periodically executes a Python script to retrieve new data. The input requires database connection information and queries. The collected data is stored in an internal database (e.g., MongoDB). The server also retrieves external market information using APIs and web scraping techniques (such as BeautifulSoup or Selenium). This process ensures that product and market information remains up-to-date.

[1384] Step 2: Enter customer requirements

[1385] The device uses React or Vue.js to display a customer requirements input form in a web browser. Specifically, the form includes fields such as product quantity, features, budget, and delivery date. The user enters their requirements into these fields and clicks a submit button. The input is the customer requirements data entered by the user. The output from the device is sent to the server as an HTTP request, and the request payload contains the customer requirements.

[1386] Step 3: Requirements Analysis and Matching

[1387] The server retrieves customer requirements from received HTTP requests and parses the data using Python's NLTK and spaCy. The input is customer requirements data. The server uses natural language processing techniques to convert the requirements into structured data. Based on this parsed data, it searches the database for appropriate products and assets. Specifically, it uses SQL queries to retrieve relevant product information. The output is a list of products and assets found based on the parsed data.

[1388] Step 4: Check inventory and delivery information

[1389] The server checks inventory and delivery date information based on the product list obtained in step 3. The input is the product list. The server retrieves this information by calling an internal API. Specifically, it sends an API request and receives inventory and delivery date information as a response. The output is the product list including inventory and delivery date information.

[1390] Step 5: Price Estimation

[1391] The server estimates prices for selected products based on past case studies and market information. The input is a product list including inventory and delivery time information. Specifically, it uses a machine learning model with Python libraries (scikit-learn and TensorFlow) to predict prices. Cumulative costs and profit margins are considered during the estimation process. The output is the estimated price and the proposed price (winning price) for each product.

[1392] Step 6: Proposal Generation

[1393] The server automatically generates proposals using the Python ReportLab library. Inputs include customer requirements, selected products, estimated prices, and delivery date information. Specifically, it embeds a proposal template based on this data and generates a proposal in PDF format. The output is the generated proposal.

[1394] Step 7: Submitting and revising the proposal

[1395] The server sends the generated proposal to the user's terminal as an HTTP response. The input is the generated proposal. The user can review the proposal using tools such as Adobe Acrobat and make revisions as needed. The output is the final proposal, which is submitted to the client. This process ensures that clients receive a fast and accurate proposal.

[1396] (Application Example 1)

[1397] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1398] In customer service at logistics centers, the process from receiving requirements to generating proposals is complex, making it difficult to respond quickly and accurately. Furthermore, optimizing multiple products and distribution channels is often done manually, contributing to inefficiency. Additionally, verifying inventory and delivery information based on customer requirements is time-consuming, hindering accurate proposals.

[1399] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1400] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate products from collected product information, past case information, and market information, means for estimating the price of the selected product and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected products, and proposed price, means for presenting the generated proposal to the customer via a terminal, and means for selecting the optimal distribution route and product combination. This enables the logistics center to respond to customer requirements quickly and accurately, and to generate proposals efficiently and select the optimal distribution route.

[1401] "Means of receiving customer requirements" refers to devices or software used to collect specific customer requests and needs and input them into a system.

[1402] "Collected product information" refers to detailed product data obtained from sources such as the market, past transactions, and product databases.

[1403] "Past case information" refers to data based on past experience and examples of handling similar customer requirements.

[1404] "Market information" refers to data such as current market trends, price trends, and competitive conditions.

[1405] "Means for finding the right product" refers to algorithms and software used to identify and search for the most suitable product based on customer requirements, using collected product information, past case studies, and market data.

[1406] "Means for estimating the price of selected products" refers to a device or software that has the function of calculating the price of selected products based on past case information and market information.

[1407] "Means for determining the optimal proposed price" refers to algorithms or software that take into account cumulative costs and profit margins to determine the optimal price to propose to the customer.

[1408] "Methods for automatically generating proposals" refers to software that automatically creates proposals based on customer requirements, selected products, and estimated prices.

[1409] A "terminal" refers to a device used by people to input information or to check output.

[1410] "Means for selecting the optimal distribution route and product combination" refers to software or algorithms that have the functionality to select the optimal delivery method and combine multiple products according to customer requirements.

[1411] System Configuration

[1412] This invention is a system that receives customer requirements, searches for appropriate products from collected product information, past case information, and market information, calculates the optimal proposed price, and automatically generates a proposal. The system consists of three components: a server, a terminal, and a user.

[1413] Explanation of program processing

[1414] The server periodically connects to the database to collect product information (product name, specifications, price, etc.), past case studies, and market information, and stores it in the internal database. This makes it possible to always provide proposals based on the latest information.

[1415] The user uses a terminal to input customer requirements (e.g., product quantity, additional requirements, delivery date, budget, etc.). This entered data is then sent to the server.

[1416] The server analyzes the received customer requirements and searches its internal database for the most suitable product. Specifically, it selects the optimal product and distribution channel based on the quantity and functionality of the customer requirements, taking into account inventory and delivery time information.

[1417] Next, the server estimates the price of the selected product based on past case studies and market information. It then determines the optimal price to propose, taking into account cumulative costs and profit margins.

[1418] The server then automatically generates a proposal based on customer requirements, selected products, and estimated pricing. This proposal includes detailed product information and customization options.

[1419] Finally, the generated proposal is sent to the terminal, reviewed and revised by the user, and then presented to the client.

[1420] Hardware and software to be used

[1421] This system uses the following hardware and software:

[1422] Server: Collects information from the database, performs analysis and price estimation, and generates proposals. Software used includes Python and SQL.

[1423] Terminal: Used to input customer requirements and review / revise proposals. A variety of devices can be used, including smartphones, tablets, and PCs.

[1424] Database: Stores product information, past case studies, and market information. SQL databases are common.

[1425] Specific example

[1426] For example, a logistics center might receive the following requirements from a customer:

[1427] Required products: 100 high-performance servers

[1428] Additional requirements: High-speed storage options

[1429] Delivery time: within 1 month

[1430] Budget: Within 50 million yen

[1431] When the user enters these requirements via their terminal, the server analyzes the requirements, selects the optimal server and storage options, and estimates the price based on past case studies and market information. Next, it automatically generates a proposal and sends it to the user via their terminal.

[1432] Examples of prompts for a generative AI model are as follows:

[1433] "Based on the number of products requested by the customer and any additional requirements, please generate a proposal outlining the optimal product combination and pricing. The requirements are as follows: Number of products: 100, Additional requirements: High-speed storage option, Delivery time: within 1 month, Budget: within 50 million yen."

[1434] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1435] Step 1:

[1436] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (product quantity, additional requirements, delivery date, budget, etc.) into this form. The entered data is stored on the terminal and sent to the server. Specifically, the user enters 100 high-performance servers and high-speed storage options, a delivery date of less than one month, and a budget of 50 million yen.

[1437] input:

[1438] Customer's specific requirements: Product quantity, additional requirements, delivery date, budget

[1439] output:

[1440] Customer requirements data (JSON format)

[1441] Step 2:

[1442] The server analyzes the customer requirements received from the terminal. This analysis verifies that the entered requirements are accurate and complete, and fills in any unclear or missing information as needed. Based on the results of this analysis, the next steps proceed.

[1443] input:

[1444] Customer requirements data

[1445] output:

[1446] Analyzed customer requirements data

[1447] Step 3:

[1448] The server searches its internal database for appropriate products based on the analyzed customer requirements data. This search utilizes pre-collected product information, past case studies, and market information. For example, it might retrieve information on 100 high-performance servers and high-speed storage options from the database.

[1449] input:

[1450] Analyzed customer requirements data

[1451] Internal databases containing product information, past case studies, and market information.

[1452] output:

[1453] A list of suitable product candidates

[1454] Step 4:

[1455] The server checks inventory and delivery information based on a suitable list of product candidates. This allows for the confirmation of product availability and delivery dates according to customer requirements. For example, it checks whether the acquired high-performance server and high-speed storage can be delivered within one month.

[1456] input:

[1457] A list of suitable product candidates

[1458] Internal database inventory information, delivery date information

[1459] output:

[1460] Inventory information and delivery date information

[1461] Step 5:

[1462] The server estimates the price of the selected product based on inventory and delivery information. This estimation takes into account past sales data and market information, and determines the proposed price based on total cost and optimal profit margin.

[1463] input:

[1464] A list of suitable product candidates

[1465] Inventory information and delivery date information

[1466] Past case information, market information

[1467] output:

[1468] Estimated price information

[1469] Step 6:

[1470] The server automatically generates a proposal based on customer requirements, selected products, and estimated pricing information. This proposal includes product details, pricing information, stock availability, delivery dates, and customization options.

[1471] input:

[1472] customer requirements

[1473] Selected products

[1474] Estimated price information

[1475] output:

[1476] Automatically generated proposal (PDF or HTML format)

[1477] Step 7:

[1478] The server sends the generated proposal to the terminal. The user reviews the proposal and makes revisions as needed. They then submit the final version of the proposal to the client.

[1479] input:

[1480] Automatically generated proposal

[1481] output:

[1482] Revised and reviewed proposal

[1483] The above steps efficiently solve the problem that the invention aims to address (rapid and accurate customer response and proposal generation).

[1484] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1485] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The processing of the system's program and specific examples are described below.

[1486] System Construction

[1487] 1. Data Collection

[1488] The server periodically connects to the database to collect the latest product information (product name, specifications, price, etc.), past case studies, and market information. This information is stored in an internal database for use in the subsequent proposal process.

[1489] 2. Enter customer requirements

[1490] The terminal presents the user with a customer requirements input form. The user enters the customer's requirements (e.g., product quantity, features, budget, delivery date, etc.) into this form and submits it to the system. Through this process, the system understands the customer's specific needs.

[1491] 3. Emotion recognition

[1492] The terminal activates an emotion engine to recognize the user's emotions in real time while they are entering customer requirements. The emotion engine analyzes the user's facial expressions, tone of voice, input speed, and other factors.

[1493] 4. Requirements matching

[1494] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets. Furthermore, it checks inventory and delivery information to select the combination of products and services that best suits the customer requirements.

[1495] 5. Price Estimation

[1496] The server estimates the price of the selected product based on past case studies and market information. In this process, it considers appropriate cumulative costs and profit margins to determine the optimal proposed price (winning price).

[1497] 6. Proposal generation and emotional reflection

[1498] The server automatically generates a proposal based on customer requirements, selected products, and estimated prices. Based on the results of the emotion engine, it adjusts the tone and expression of the proposal, customizing it to be easier for users to understand and accept.

[1499] 7. Submitting and revising the proposal

[1500] The server sends the generated proposal to the user's terminal. The user reviews the proposal sent to their terminal and makes revisions as needed. These revisions are intended to flexibly respond to the customer's specific requirements.

[1501] 8. Submission of proposal

[1502] The user submits the finalized proposal to the client.

[1503] Specific example

[1504] For example, consider a scenario where an IT company receives the following requirements from a new customer.

[1505] Required products: 100 new servers

[1506] Additional requirements: High-speed storage options

[1507] Delivery time: within 1 month

[1508] Budget: Within 50 million yen

[1509] Emotional state: Feeling stressed while typing.

[1510] The user enters this requirement into an input form on their device and submits it to the system. During input, the emotion engine recognizes the user's stress level and adjusts the wording of the proposal to a calmer tone. For example, the system can change the phrase "We promise a prompt response" to "Please rest assured. We will provide you with the best possible solution tailored to your requirements."

[1511] The server analyzes the received requirements and searches the database for suitable servers and high-speed storage options. Furthermore, it checks inventory and delivery information to identify product combinations that can be delivered within one month.

[1512] Subsequently, the server estimates the price based on past case studies and market information, calculating the optimal winning price within a budget of 50 million yen. Finally, the server automatically generates a proposal, incorporating the results of the emotion engine, and sends it to the user's terminal. The user reviews the content, makes revisions as needed, and finally submits it to the client. This process enables a rapid and accurate response to client needs.

[1513] The following describes the processing flow.

[1514] Step 1:

[1515] The server periodically connects to the database to retrieve the latest product information (e.g., product name, specifications, price), past case studies, and market information. This information is stored in the internal database.

[1516] Step 2:

[1517] The terminal displays a customer requirements input form for the user. This form includes input fields for product quantity, features, budget, and delivery date.

[1518] Step 3:

[1519] The user enters the specific requirements received from the customer into an input form and sends that information to the system.

[1520] Step 4:

[1521] The terminal activates an emotion engine while the customer requirements are being entered. The emotion engine analyzes the user's facial expressions, voice, input speed, etc., to recognize emotions in real time.

[1522] Step 5:

[1523] The device sends the recognized emotion data to the server. This allows customer requirements and emotion information to be aggregated on the server.

[1524] Step 6:

[1525] The server analyzes the received customer requirements and uses that information to search the database for appropriate products and assets.

[1526] Step 7:

[1527] The server checks inventory and delivery date information for merchandise and assets retrieved from the database and identifies combinations that match customer requirements.

[1528] Step 8:

[1529] The server estimates the price of selected products and assets based on past case studies and market information. In this process, it also considers appropriate cumulative costs and profit margins.

[1530] Step 9:

[1531] The server calculates the optimal proposed price (winning price) based on the estimated price.

[1532] Step 10:

[1533] The server automatically generates a proposal based on customer requirements, selected products, estimated pricing, and user sentiment information. The content of the proposal is then adjusted based on the results of the sentiment engine.

[1534] Step 11:

[1535] The server sends the generated proposal to the user's terminal. The sent proposal reflects a tone and expression that takes the user's feelings into consideration.

[1536] Step 12:

[1537] Users review the proposal on their devices and make revisions as needed. These revisions are designed to flexibly respond to the customer's specific requirements.

[1538] Step 13:

[1539] The user submits the finalized proposal to the client, enabling them to respond to the client's needs quickly and accurately.

[1540] Specific example

[1541] For example, consider a scenario where an IT company receives the following requirements.

[1542] Required products: 100 new servers

[1543] Additional requirements: High-speed storage options

[1544] Delivery time: within 1 month

[1545] Budget: Within 50 million yen

[1546] Emotional state: Feeling stressed while typing.

[1547] Following steps 1 through 13, the system acquires user input and analyzes emotions in real time through an emotion engine. The analysis results are reflected in the proposal content, and are adjusted to reduce stress, for example, by using phrases like "We promise a prompt response."

[1548] This process allows the system to respond quickly and effectively to customer needs and reduce user stress.

[1549] (Example 2)

[1550] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1551] Conventional proposal generation systems required a significant amount of time for analyzing customer requirements and creating proposals, making it difficult to improve the accuracy of proposals and customer satisfaction. Furthermore, proposals were not customized to consider the user's emotional state, failing to reduce user stress. This made it difficult to improve the efficiency of sales activities and the effective operation of the proposal process.

[1552] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1553] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate items from collected item information, past case information, and market information, means for estimating the price of selected items and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected items, and proposed price, means for sending the proposal to the user, and means for analyzing the user's emotions in real time and adjusting the content of the proposal. This enables the rapid and accurate generation of proposals based on customer requirements, and further allows for customization according to the user's emotional state, thereby improving customer satisfaction and streamlining sales activities.

[1554] "Customer requirements" refer to the specific needs of a customer regarding the quantity, functions, budget, and delivery date of the products or services they desire.

[1555] "Product information" refers to detailed information about a product, such as its name, specifications, and price.

[1556] "Past case information" refers to information about the content and results of similar proposals made in the past.

[1557] "Market information" refers to information about current market trends, such as competitors' prices and market trends.

[1558] "Search methods" refer to algorithms and database queries used to identify items that meet customer requirements based on collected information.

[1559] "Methods for estimation" refer to methods or tools used to calculate the price or cost of selected items and derive the optimal proposed price.

[1560] A "proposal" is a document that summarizes customer requirements, selected items, and estimated prices, and outlines the proposal to be presented to the customer.

[1561] "Automatic generation means" refers to a function that allows the system to automatically create a proposal based on the collected information and analysis results.

[1562] "Means of transmission" refers to the means of communication used to send the generated proposal to the user's terminal.

[1563] "Means for analyzing and adjusting emotions" refers to a function that analyzes the user's facial expressions and tone of voice, and appropriately modifies the tone and expression of the proposal.

[1564] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. Furthermore, by incorporating an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The processing of the system's program and specific examples are described below.

[1565] System Configuration

[1566] The system uses the following hardware and software:

[1567] server

[1568] Database: MySQL

[1569] ERP system

[1570] Data analysis libraries: Python, Pandas

[1571] Natural language generation model API (e.g., GPT-4)

[1572] terminal

[1573] Web browser: Google Chrome

[1574] Camera and microphone (for emotion recognition)

[1575] Facial expression analysis library: OpenCV

[1576] Speech analysis library: speech_recognition

[1577] Specific flow and content of the process

[1578] 1. Data Collection

[1579] The server periodically connects to the database to collect the latest product information, past case information, and market information. This information is retrieved from the MySQL database and stored in an internal database on the server.

[1580] 2. Enter customer requirements

[1581] The terminal displays a customer requirements input form on a web browser for the user. The user enters the product quantity, required functions, budget, delivery date, etc. into this form and submits it to the system. The terminal converts this input data into JSON format and sends it to the server.

[1582] 3. Emotion recognition

[1583] The device activates the emotion engine while the user is entering information into a form. The emotion engine captures camera footage and analyzes voice input to determine the user's emotional state in real time and sends the results to the server.

[1584] 4. Requirements matching

[1585] The server analyzes the received customer requirements and searches its internal database for appropriate items. During this process, it also uses the ERP system to check inventory and delivery information, identifying the combination of products and services best suited to the customer's requirements.

[1586] 5. Price Estimation

[1587] Based on past case studies and market information, the server uses data analysis libraries (Python, Pandas) to estimate the price of selected items and determine the optimal proposed price.

[1588] 6. Proposal generation and emotional reflection

[1589] The server automatically generates proposals based on customer requirements, selected items, and estimated prices using an automated generation model (e.g., GPT-4). It also adjusts the tone and expression of the proposals based on the results of an emotion engine, customizing them to be more easily understood and accepted by the user.

[1590] 7. Submitting and revising the proposal

[1591] The server converts the generated proposal into PDF format and sends it to the user's terminal. The user then uses Microsoft Word to review and revise the proposal, adding additional comments and details as needed.

[1592] 8. Submission of proposal

[1593] The user submits the finalized proposal to the client via email or an online submission form.

[1594] Examples of specific cases and prompt statements

[1595] For example, consider a scenario where an IT company receives the following requirements from a new customer:

[1596] Required products: 100 new servers

[1597] Additional requirements: High-speed storage options

[1598] Delivery time: within 1 month

[1599] Budget: Within 50 million yen

[1600] Emotional state: Feeling stressed while typing.

[1601] The user enters this information and sends it to the system. The emotion engine recognizes the user's stress level and adjusts the proposal content to be expressed in a calm tone. For example, it might change "We promise a prompt response" to "Please rest assured. We will provide the best proposal to meet your requirements."

[1602] The server analyzes the requirements and searches for and identifies appropriate products and delivery information from the MySQL database and ERP system. It then uses Pandas to estimate prices and derive the optimal proposed price within a budget of 50 million yen. Finally, GPT-4 generates a proposal, which, incorporating the results of the sentiment engine, is sent to the user's terminal. The user reviews and revises the proposal before finally submitting it to the customer.

[1603] Example of a prompt

[1604] "Create the optimal proposal based on customer requirements. Generate a proposal that meets the following requirements:

[1605] Requirements: 100 new servers, high-speed storage options

[1606] Delivery time: within 1 month

[1607] Budget: Within 50 million yen

[1608] Emotional state: Use a calm tone for users who are feeling stressed.

[1609] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1610] Step 1: Data Collection

[1611] The server periodically connects to the database and collects the following information:

[1612] Product information: Product name, specifications, price, etc.

[1613] Past case information: Previous proposals, success stories, etc.

[1614] Market information: Competitor pricing and market trends

[1615] Input data is retrieved from a MySQL database. Specifically, the server executes SQL queries such as "SELECT FROM product_info" and saves the results to an internal database.

[1616] The output is the most recent information stored in the internal database. This provides the latest data for use in the next processing step.

[1617] Step 2: Enter customer requirements

[1618] The terminal displays a customer requirements input form on a web browser for the user.

[1619] The input data includes the quantity of products the user enters, the required functions, budget, and delivery date. The user operates this form using a browser such as Google Chrome, enters the information, and clicks the "Submit" button.

[1620] Specifically, the terminal converts this input data into JSON format and sends it to the server. The output is customer requirements data in JSON format and is sent to the server.

[1621] Step 3: Emotion Recognition

[1622] The device activates the emotion engine while the user is entering their requirements.

[1623] The input data consists of the user's facial expressions and voice tone. Specifically, the OpenCV library is used to analyze camera footage, and the speech_recognition library is used to analyze voice tone and input speed from the audio input.

[1624] The output is data about the user's emotional state. This is sent to the server in real time and used to adjust the content of the proposal.

[1625] Step 4: Requirements Matching

[1626] The server analyzes the received customer requirements and searches its internal database for the appropriate items.

[1627] The input data is customer requirements data in JSON format, sent to the server.

[1628] Specifically, the server executes SQL queries such as "SELECT FROM product_info WHERE ..." to search for items that match the requirements. It also sends API requests to the ERP system to check inventory information and delivery dates.

[1629] The output is a list of selected items and associated inventory and delivery information. This helps identify the best combination of products and services to meet customer requirements.

[1630] Step 5: Price Estimation

[1631] The server estimates the price of the selected items based on past case data and market information.

[1632] The input data consists of a list of selected items, historical case studies, and market information. Specifically, we will use Python and Pandas to compile the data into a data frame and analyze the historical price data.

[1633] The server executes queries such as "SELECT AVG(price) FROM past_cases WHERE ..." to estimate the optimal proposed price, taking into account cumulative costs and profit margins. The output is the estimated price information.

[1634] Step 6: Proposal generation and emotional reflection

[1635] The server automatically generates a proposal based on customer requirements, selected items, and estimated prices.

[1636] The input data includes customer requirements data, a list of selected items, estimated pricing information, and the results of the sentiment engine.

[1637] In terms of specific operation, the server sends a request to a natural language generation model (such as GPT-4) API to generate a proposal. Based on the results of the sentiment engine, the tone and expression of the proposal are adjusted. The output is a customized proposal.

[1638] Step 7: Submitting and revising the proposal

[1639] The server sends the generated proposal to the user's terminal.

[1640] The input data is the generated proposal. Specifically, the server converts the proposal to PDF format and sends it to the user's terminal.

[1641] The user will use Microsoft Word to review and revise the proposal, adding additional comments and details as needed. The output will be the final, approved proposal.

[1642] Step 8: Submitting the Proposal

[1643] The user submits the finalized proposal to the client.

[1644] The input data is the finalized proposal. Specifically, the user submits the proposal to the customer via email or an online submission form.

[1645] The output is a proposal submitted to the client. This allows for quick and accurate proposals to be made to the client.

[1646] (Application Example 2)

[1647] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1648] Traditional proposal creation systems, while possessing a certain degree of accuracy in receiving customer requirements and searching for product information, struggled to reflect the user's emotional state, making stress-free proposal creation difficult. Furthermore, the time-consuming process of refining proposal content resulted in inefficiency in situations requiring quick responses. Additionally, a lack of approaches to enhance the final proposal's level of satisfaction made it challenging to provide optimal solutions to customers.

[1649] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1650] In this invention, the server includes means for receiving customer requirements, means for searching for appropriate products from collected product information, past case information, and market information, means for estimating the price of the selected product and determining the optimal proposed price, means for automatically generating a proposal based on customer requirements, selected products, and proposed price, means for sending the proposal to the user, emotion recognition means for recognizing the customer's emotions in real time, and means for adjusting the content of the proposal based on the results of emotion recognition. This makes it possible to make proposals quickly and effectively while taking into account the customer's emotional state.

[1651] "Customer requirements" refer to information that includes the specific conditions and preferences of the products and services that customers desire.

[1652] "Product information" refers to detailed data about the products or services offered, such as product name, specifications, and price.

[1653] "Past case information" refers to data that includes the history and results of proposals and transactions that have been carried out in the past.

[1654] "Market information" refers to data such as current market trends, competitor information, and demand forecasts.

[1655] "Emotion recognition" is a technology that analyzes a user's facial expressions, tone of voice, and other factors to determine their emotional state in real time.

[1656] "Inventory information" refers to data on the current inventory status and the quantity of products being managed.

[1657] "Delivery date information" refers to data regarding the scheduled delivery date and period for products and services.

[1658] A "proposal" is a document that outlines the specific products or services offered to a customer, including their content, price, and terms and conditions.

[1659] "Emotion recognition means" refers to hardware and software technologies for recognizing a user's emotional state in real time.

[1660] "Methods for adjusting the content of a proposal" refers to techniques that appropriately modify the wording and tone of a proposal based on the results of emotion recognition.

[1661] The system according to the present invention improves sales activities and proposal processes by efficiently receiving customer requirements and automatically generating proposals quickly and accurately. In particular, by combining it with an emotion engine that recognizes user emotions, it is possible to more effectively adjust the content of proposals and reduce user stress. The detailed configuration and operation of the system are described below.

[1662] System Configuration

[1663] This system consists of a server, a user terminal, and an emotion recognition device. The server connects to a database and collects the latest product information, past case studies, and market information. The user terminal provides a customer requirements input form and has an interface for sending the entered data to the server. The emotion recognition device analyzes the user's facial expressions and voice and recognizes their emotional state in real time.

[1664] Hardware and software to use

[1665] The hardware used is a robot that includes a facial recognition camera, microphone, and display. The software uses OpenCV for facial recognition, the Google Cloud Speech-to-Text API for speech analysis, Python for automatic proposal generation, and MySQL as the database.

[1666] Program processing

[1667] The server first connects to a database and periodically collects the latest product information, past case studies, and market information. Then, when customer requirements are entered from the user terminal, it searches for appropriate products and calculates prices based on this data. Furthermore, an emotion recognition device analyzes the user's face and voice to recognize their emotional state in real time. Based on the recognized emotional state, it adjusts the tone and expression of the proposal and sends the automatically generated proposal to the user terminal. The user then makes revisions as needed and submits the final proposal to the customer.

[1668] Specific example

[1669] For example, consider a scenario where an IT company receives the following requirements from a new client: 100 new servers are required, with the additional requirement being a high-speed storage option. The deadline is within one month, and the budget is under 50 million yen. Additionally, the client is experiencing stress while using the system.

[1670] In this case, the user enters their requirements into an input form on their device and submits it to the system. During the input process, the emotion engine recognizes the user's stress level and can change phrases like "We promise a prompt response" to "Please rest assured. We will provide you with the best solution tailored to your requirements."

[1671] Examples of prompts to input into a generative AI model are as follows:

[1672] "User Requirements: - Product: 100 new servers - Requirements: High-speed storage options - Delivery Time: Within 1 month - Budget: Within 50 million yen Please generate an optimal proposal based on past proposal examples and market information in the following format: - Product Name - Specifications - Price - Delivery Time - Notes Also, please present the proposal in a relaxed tone."

[1673] This allows us to respond to customer requirements quickly and accurately while taking user emotions into consideration.

[1674] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1675] Step 1:

[1676] The server connects to the database to collect the latest product information, past case studies, and market information. Input data includes product name, specifications, price, past case studies, and current market trends. This data is collected and stored in the internal database, ensuring that the latest product and market information is always accessible.

[1677] Step 2:

[1678] The user enters customer requirements (product quantity, features, budget, delivery date, etc.) using an input form on the terminal. The entered data is sent to the server in real time. This allows the server to understand the customer's specific requirements.

[1679] Step 3:

[1680] The device activates an emotion engine to recognize the user's emotions in real time while they are inputting data. The input data includes the user's facial expressions and tone of voice. The emotion engine analyzes this data and outputs the user's emotional state (stress, relaxation, etc.).

[1681] Step 4:

[1682] The server analyzes the received customer requirements and searches the database for appropriate products based on that information. Input data includes customer requirements, product information, past case studies, and market information. This data is then compared to output a list of the most suitable products.

[1683] Step 5:

[1684] The server checks the inventory and delivery date information for the searched product. It retrieves data from the inventory database and delivery date database and outputs whether the product is in stock and the period during which it can be delivered based on this data.

[1685] Step 6:

[1686] The server performs price estimation based on the received information. Input data includes information on the selected product, past case studies, and market information. Based on this, a price estimation algorithm is applied to output the optimal proposed price.

[1687] Step 7:

[1688] The server automatically generates proposals based on customer requirements, selected products, estimated prices, and the results of the sentiment engine. Input data includes customer requirements, product information, pricing information, and sentiment status. By combining these, the server outputs a proposal with the most appropriate expression and content for the customer.

[1689] Step 8:

[1690] The server sends the automatically generated proposal to the user's terminal. The user receives the proposal through their terminal and reviews its contents. They can then confirm that the proposal is written in a relaxed tone that is easy for them to understand.

[1691] Step 9:

[1692] The user modifies the proposal on their device. The user makes the necessary changes to the proposal and sends the final, confirmed proposal to the server. This results in a more optimal proposal that meets the customer's specific requirements.

[1693] Step 10:

[1694] The server submits the finalized proposal to the client. The submitted proposal reflects the user's perspective while quickly and accurately addressing the client's requirements.

[1695] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1696] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1697] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1698] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1699] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1700] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1701] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1702] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1703] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1704] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1705] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1706] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1707] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1708] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1709] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1710] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1711] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1712] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1713] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1714] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1715] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1716] The following is further disclosed regarding the embodiments described above.

[1717] (Claim 1)

[1718] Means of receiving customer requirements,

[1719] A means of searching for appropriate products from collected product information, past case information, and market information,

[1720] A method for estimating the price of selected products and determining the optimal proposed price,

[1721] A means of automatically generating a proposal based on customer requirements, selected products, and proposed price,

[1722] A means of sending the proposal to the user,

[1723] A system that includes this.

[1724] (Claim 2)

[1725] The system according to claim 1, further comprising means for checking inventory information and delivery date information from a database based on customer requirements.

[1726] (Claim 3)

[1727] The system according to claim 1, further comprising means for providing a user-modifiable interface for the proposal.

[1728] "Example 1"

[1729] (Claim 1)

[1730] A means of connecting to a database and collecting product information, past case information, and market information,

[1731] Means of receiving customer requirements,

[1732] A means of analyzing received customer requirements and searching for appropriate products from the database,

[1733] A method for estimating the price of selected products based on past case studies and market information, and determining the optimal proposed price,

[1734] A means of automatically generating a proposal based on customer requirements, selected products, and proposed price,

[1735] A means of sending the proposal to the user,

[1736] A system that includes this.

[1737] (Claim 2)

[1738] The system according to claim 1, further comprising means for checking inventory information and delivery date information from a database based on customer requirements.

[1739] (Claim 3)

[1740] The system according to claim 1, further comprising means for providing a user-modifiable interface for the proposal.

[1741] "Application Example 1"

[1742] (Claim 1)

[1743] Means of receiving customer requirements,

[1744] A means of searching for appropriate products from collected product information, past case information, and market information,

[1745] A method for estimating the price of selected products and determining the optimal proposed price,

[1746] A means for automatically generating a proposal based on customer requirements, selected products, and proposed price,

[1747] A means of presenting the generated proposal to the customer via a terminal,

[1748] A means of selecting the optimal distribution channels and product combinations,

[1749] A system that includes this.

[1750] (Claim 2)

[1751] The system according to claim 1, further comprising means for checking inventory information and delivery date information from a database based on customer requirements.

[1752] (Claim 3)

[1753] The system according to claim 1, further comprising means for providing a terminal interface that allows the user to modify the proposal.

[1754] "Example 2 of combining an emotion engine"

[1755] (Claim 1)

[1756] Means of receiving customer requirements,

[1757] A means for searching for appropriate items from collected item information, past case information, and market information,

[1758] A means of estimating the price of selected items and determining the optimal proposed price,

[1759] A means for automatically generating a proposal based on customer requirements, selected items, and proposed price,

[1760] A means of sending the proposal to the user,

[1761] A means to analyze user emotions in real time and adjust the content of the proposal,

[1762] A system that includes this.

[1763] (Claim 2)

[1764] The system according to claim 1, further comprising means for checking inventory information and delivery date information from a database based on customer requirements.

[1765] (Claim 3)

[1766] The system according to claim 1, further comprising means for providing a user-modifiable interface for the proposal.

[1767] "Application example 2 when combining with an emotional engine"

[1768] (Claim 1)

[1769] Means of receiving customer requirements,

[1770] A means of searching for appropriate products from collected product information, past case information, and market information,

[1771] A method for estimating the price of selected products and determining the optimal proposed price,

[1772] A means of automatically generating a proposal based on customer requirements, selected products, and proposed price,

[1773] A means of sending the proposal to the user,

[1774] A means of recognizing customer emotions in real time,

[1775] A means of adjusting the content of the proposal based on the results of emotion recognition,

[1776] A system that includes this.

[1777] (Claim 2)

[1778] The system according to claim 1, further comprising means for checking inventory information and delivery date information from a database based on customer requirements.

[1779] (Claim 3)

[1780] The system according to claim 1, further comprising means for providing a user-modifiable interface for the proposal. [Explanation of symbols]

[1781] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of receiving customer requirements, A means of searching for appropriate products from collected product information, past case information, and market information, A method for estimating the price of selected products and determining the optimal proposed price, A means of automatically generating a proposal based on customer requirements, selected products, and proposed price, A means of sending the proposal to the user, A system that includes this.

2. The system according to claim 1, further comprising means for checking inventory information and delivery date information from a database based on customer requirements.

3. The system according to claim 1, further comprising means for providing a user-modifiable interface for the proposal.

Images