System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting customer information; means for collecting industry data; means for collecting public information of a company; means for collecting product information; means for integrating and analyzing the collected information; means for automatically generating hypothesis suggestions based on the analysis results; and means for outputting the generated hypothesis suggestions.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In field sales, when moving from an initial proposal to a detailed proposal, challenges exist, such as "not being able to properly capture the customer's needs" or "not being able to move on to a full-scale consideration phase." Furthermore, because the proposal content is generic and not tailored to each customer, many customers tend to remain in long-term follow-up without moving on to the next step. Furthermore, sales representatives often lack time, do not know how to gather information, or do not know how to form hypotheses based on the information, resulting in a decline in the quality of their proposals. The goal is to improve this situation by providing a means to improve the efficiency of sales activities and increase order rates. [Means for solving the problem]

[0005] The present invention provides a system including a means for collecting customer information, a means for collecting industry data, a means for collecting public company information, a means for collecting product information, a means for integrating and analyzing the collected information, a means for automatically generating hypothetical proposals based on the analysis results, and a means for outputting the generated hypothetical proposals. This system can improve the quality of proposals in field sales, shorten preparation time, and ultimately increase the success rate. Furthermore, by analyzing the collected information using a natural language processing algorithm, it is possible to accurately grasp the specific challenges and needs of each customer and provide high-quality hypothetical proposals based on that understanding. Furthermore, the system includes a means for inserting specific application examples into the hypothetical proposals generated based on the analysis results, thereby enhancing the persuasiveness of the proposals by demonstrating specific benefits to customers.

[0006] "Customer information" refers to data including basic information about the customer company, past transaction history, and sales activity records.

[0007] "Industry data" refers to information about the latest trends, challenges, success stories, and other information related to a specific industry.

[0008] "Corporate public information" refers to information that a company provides to the public, including IR reports, press releases, and recruitment information.

[0009] "Product information" refers to data about the features, advantages, application examples, etc. of the proposed product.

[0010] "Collection means" refers to the methods and technologies used to obtain the necessary data, as well as the equipment and software used to carry them out.

[0011] "Integration means" refers to methods and techniques for combining data collected from different sources into a single database.

[0012] "Means of analysis" refers to technologies such as natural language processing algorithms that use integrated data to understand customer needs and challenges.

[0013] "Means for automatically generating hypothetical proposals" refers to methods and technologies for automatically creating optimal proposals for customers based on analysis results.

[0014] "Means for output" refers to the method or technology for displaying the generated hypothetical proposal on the sales representative's terminal. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention relates to a system that supports the creation of hypothetical proposals in field sales, and it collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates and outputs high-quality hypothetical proposals based on that information. Below, we will explain the system's program processing and provide concrete examples.

[0037] System program processing

[0038] 1. Data Collection:

[0039] The server retrieves sales data from the SFA system, which refers to records of past transactions and sales activities related to client companies.

[0040] The server collects the latest trends, challenges, success stories, and other information related to manufacturing from an industry information database.

[0041] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from companies' official websites and financial information sites.

[0042] The server obtains product information such as the features, advantages, and application examples of the proposed product from an internal database or from product personnel.

[0043] 2. Data integration and analysis:

[0044] The server integrates the various data collected above into a centralized database.

[0045] The server extracts sales-useful data points (e.g., growth strategies, industry trends, past purchase history, etc.) from the integrated database.

[0046] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges.

[0047] 3. Hypothesis proposal generation:

[0048] The server automatically generates hypothesis proposals optimized for each customer based on the collected, integrated, and analyzed data.

[0049] The hypothetical proposal includes the customer's specific challenges, industry trends, and the benefits of the proposed product.

[0050] 4. Hypothesis proposal output:

[0051] The server outputs the generated hypothesis proposal to the sales representative's terminal (e.g., PC or tablet).

[0052] The sales representative checks the proposal on the terminal, edits and saves it as necessary, and completes the final proposal.

[0053] Specific examples

[0054] Situation: Creating a hypothetical proposal for client company A

[0055] Customer Company A: Medium-sized manufacturing company

[0056] Proposed product: Production management software

[0057] 1. Data Collection:

[0058] The server obtains the past transaction history and contact history of customer company A from the SFA system.

[0059] The server collects the latest trends and issues related to manufacturing from an industry information database.

[0060] The server retrieves Company A's IR report and recent news articles from its official website and financial information sites.

[0061] The server retrieves product information such as the features and application examples of the production management software from the company's internal database.

[0062] 2. Data integration and analysis:

[0063] The server integrates the collected data into a centralized database and extracts data points related to client company A's growth strategy and the latest trends in the manufacturing industry.

[0064] The server analyzes the details of Company A's new capital investment from the IR report and determines the applicability of production management software.

[0065] 3. Hypothesis proposal generation:

[0066] The server automatically generates hypothetical proposals such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%."

[0067] Proposals will include concrete examples of application (e.g., success stories from other manufacturing companies).

[0068] 4. Hypothesis proposal output:

[0069] The server displays the generated hypothesis proposal on the sales representative's terminal.

[0070] The user (sales representative) checks the proposal contents, edits them as necessary, and creates a proposal document.

[0071] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[0075] Step 2:

[0076] The server connects to an industry information database to gather information on the latest trends, challenges, and success stories related to the target industry (e.g., manufacturing), including specific industry reports, research papers, and industry news.

[0077] Step 3:

[0078] The server uses web scraping technology to obtain public information about the company (e.g., IR reports, press releases, and recruitment information) from the company's official website and financial information site. In this step, the contents of the latest IR reports and press releases are captured in text format.

[0079] Step 4:

[0080] The server obtains product information such as the features, advantages, and application examples of the proposed product (e.g., production management software) from an internal database or from product personnel.

[0081] Step 5:

[0082] The server consolidates the various data collected into a centralized database that includes customer information, industry information, company disclosures, and product information.

[0083] Step 6:

[0084] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[0085] Step 7:

[0086] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges, analyzing IR reports and press releases to extract specific needs such as "the need to expand production capacity."

[0087] Step 8:

[0088] The server automatically generates a hypothesis proposal based on the analysis results. For example, it creates a proposal such as, "Company A will expand its production capacity by introducing production management software, which will reduce annual costs by XX%."

[0089] Step 9:

[0090] The server inserts specific application examples into the generated hypothesis proposal. For example, it adds a specific example such as "Through the implementation example at another company B, an improvement in production efficiency of XX% is expected."

[0091] Step 10:

[0092] The server outputs the generated and edited hypothesis proposal to the sales representative's device (PC, smartphone, tablet, etc.), where a preview of the proposal is displayed.

[0093] Step 11:

[0094] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[0095] Step 12:

[0096] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[0097] In this way, the HYPOS system quickly creates high-quality hypothetical proposals and provides them to customers based on their specific needs, which is expected to improve the quality of proposals, increase order acceptance rates, and streamline sales activities.

[0098] Example 1

[0099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0100] In the past, the creation of hypothesis proposals in field sales required manual collection, integration, and analysis of information from a wide variety of data sources, which resulted in inefficiency and a lack of accuracy. Furthermore, the speed and consistency of proposal creation by individual sales representatives was also an issue. As a result, the quality of proposals declined, making it difficult to improve conversion rates.

[0101] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0102] In this invention, the server includes means for acquiring customer information, means for acquiring industry data, means for acquiring public company information, means for acquiring product information, means for integrating the acquired information into a centralized database, means for analyzing the integrated information, means for analyzing company needs and issues using a natural language processing algorithm, means for automatically generating a hypothesis proposal based on the analysis results using a generation AI model, and means for outputting the generated hypothesis proposal to a user's terminal. This automates the proposal creation process and makes it possible to provide hypothesis proposals quickly and with high accuracy.

[0103] 1. "Customer Information" means information related to a customer company regarding its business activities and transaction history.

[0104] 2. "Industry Data" means information about trends, challenges, success stories, and other information related to a particular industry sector.

[0105] 3. "Public corporate information" refers to information officially published by a company, such as IR reports, press releases, and recruitment information.

[0106] 4. "Product Information" means information about the features, benefits, applications, etc. of the products offered.

[0107] 5. "Means of collection" refers to the technical methods and devices used to automatically collect the required information from each data source.

[0108] 6. A "centralized database" is a database that uniformly manages and stores information collected from multiple data sources.

[0109] 7. "Integration means" means the technical methods or devices used to aggregate data collected from different sources into a centralized database.

[0110] 8. “Analytical tools” refers to algorithms or devices used to analyze collected and integrated data and extract useful data points or patterns.

[0111] 9. "Natural language processing algorithm" refers to a technical method for analyzing text data and understanding its meaning and intent.

[0112] 10. "Generative AI model" refers to a model that uses artificial intelligence technology to automatically generate hypotheses and proposals for specific problems.

[0113] 11. "User Device" refers to a device, such as a computer or tablet, used by a sales representative.

[0114] 12. "Output means" refers to the technical methods or devices for displaying the generated hypothesis proposals on the user's terminal or saving them as a file.

[0115] This invention is a system that supports the creation of hypothetical proposals in field sales, collecting, integrating, and analyzing customer information, industry data, public company information, and product information, and automatically generating and outputting high-quality hypothetical proposals based on that information. To implement this system, the following hardware and software are used to process and calculate data.

[0116] Hardware used

[0117] Server: A server equipped with a high-performance processor and large memory capacity, which allows for efficient processing and analysis of large amounts of data.

[0118] Device: PC or tablet used by sales representatives. These devices are used to check, edit, and save hypothesis proposals.

[0119] Software used

[0120] SFA system: Manage customer information using the SalesForce Automation system.

[0121] Industry Information Database: A database that provides industry data such as trends and issues related to the manufacturing industry.

[0122] Web scraping software: BeautifulSoup, Selenium, and other similar software are used to automatically collect publicly available information from companies.

[0123] Natural Language Processing (NLP) algorithms: Used to analyze text data and understand a company's needs and challenges.

[0124] Generative AI model: Uses generative models such as GPT-4 to automatically generate hypothesis proposals.

[0125] Data processing and calculation

[0126] Data collection: The server collects various data using the SFA system, industry information database, and web scraping. It obtains customer information, industry data, company public information, and product information, and automatically collects data from each data source.

[0127] Data integration: The server integrates the collected data into a centralized database, unifying data of different formats and content.

[0128] Data analysis: The server analyzes the integrated data using natural language processing algorithms to extract the company's needs and challenges, and then uses a generative AI model to generate hypothesis proposals based on the data.

[0129] Proposal output: The server outputs the generated hypothetical proposal to the sales representative's terminal. The sales representative checks the proposal content on the terminal and edits and saves it as necessary.

[0130] Specific examples

[0131] Situation: Creating a hypothetical proposal for client company A

[0132] Customer Company A: Medium-sized manufacturing company

[0133] Proposed product: Production management software

[0134] 1. Data Collection:

[0135] The server obtains the past transaction history and contact history of customer company A from the SFA system.

[0136] The server collects the latest trends and issues related to manufacturing from an industry information database.

[0137] The server retrieves Company A's IR report and recent news articles from its official website and financial information sites.

[0138] The server retrieves product information such as the features and application examples of the production management software from the company's internal database.

[0139] 2. Data integration and analysis:

[0140] The server integrates the collected data into a centralized database and extracts data points related to client company A's growth strategy and the latest trends in the manufacturing industry.

[0141] The server analyzes the details of Company A's new capital investment from the IR report and determines the applicability of production management software.

[0142] 3. Hypothesis proposal generation:

[0143] The server automatically generates hypothetical proposals such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%." The proposals include specific application examples (e.g., success stories from other manufacturing companies).

[0144] 4. Hypothesis proposal output:

[0145] The server displays the generated hypothetical proposal on the sales representative's terminal. The user (sales representative) checks the proposal content, edits it as necessary, and creates a proposal.

[0146] Prompt Sentence Examples

[0147] Example 1: Data collection for customer company A

[0148] "Collect information about Client Company A's past transaction history, the latest industry trends, public information about the company, and the features of its production management software. Please explain the source of each information and how you obtained it."

[0149] Example 2: Generating hypothesis proposals

[0150] "Generate a hypothetical proposal for Client Company A, including the cost reduction effects of introducing production management software. Please also consider detailed information about new capital investment."

[0151] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] System program processing flow

[0154] Step 1: Gather customer information

[0155] Specific operation: The server obtains customer information from the SFA system via API.

[0156] Input: Basic information such as customer company A's ID and name

[0157] Data processing / calculation: By calling the API, records of past transactions and sales activities of client company A are obtained and converted into a database format.

[0158] Output: Saved in the database as "Customer A_Transaction Data".

[0159] Step 2: Gather industry information

[0160] Specific operations: The server executes queries against an industry information database to gather the required information.

[0161] Input: Query criteria related to manufacturing industry

[0162] Data processing / calculation: Extract the latest trends, challenges, and success stories in the manufacturing industry from the query results, convert them into a format, and store them in a database.

[0163] Output: Saved in the database as "Manufacturing_Trend_Data".

[0164] Step 3: Gather public company information

[0165] Specific operations: The server uses web scraping software to collect information from official company websites and financial information sites.

[0166] Input: URL of Company A's official website or financial information site

[0167] Data processing / calculation: Analyze the HTML structure of web pages, extract IR reports, press releases, and recruitment information, convert them into text format, and analyze them to extract important information.

[0168] Output: Saved in the database as "Company A_Public Information".

[0169] Step 4: Gather product information

[0170] Specific operation: The server accesses the company's internal database to obtain information such as the features, benefits, and application examples of the production management software.

[0171] Input: Query terms related to production management software

[0172] Data processing / calculation: Extract product information through database queries, convert it into the appropriate format and store it.

[0173] Output: Saved as "Production Management Software_Features" data.

[0174] Step 5: Integrate the data

[0175] Specific operation: The server consolidates all the data collected above into a centralized database.

[0176] Input: "Customer A_Transaction Data", "Manufacturing Industry_Trend Data", "Company A_Public Information", "Production Management Software_Features"

[0177] Data processing / calculation: Each dataset is converted into a unified format and integrated into a centralized database.

[0178] Output: All data stored in a consolidated database.

[0179] Step 6: Analyze the data

[0180] What it does: The server extracts useful data points from the aggregated data and analyzes them using natural language processing algorithms.

[0181] Input: All data in the integrated database

[0182] Data processing / calculation: Execute natural language processing algorithms to analyze and extract corporate needs and issues.

[0183] Output: Saved as "Company A_Needs Analysis Results".

[0184] Step 7: Generate hypothesis proposals

[0185] Specific operation: The server automatically generates hypothesis proposals using a generative AI model.

[0186] Input: "Company A_Needs Analysis Results" and other integrated data

[0187] Data processing / computation: Using a generative AI model (e.g., GPT-4), generate hypothesis proposals based on the analyzed data.

[0188] Output: Saved as "Hypothesis Proposal".

[0189] Step 8: Output of hypothesis proposals

[0190] Specific operation: The server displays the generated hypothesis proposal on the sales representative's terminal.

[0191] Input: "Hypothesis Proposal"

[0192] Data processing / calculation: Convert the data format into a format suitable for the device used by the sales representative and transfer it.

[0193] Output: The proposal is displayed on the sales representative's terminal.

[0194] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[0195] (Application example 1)

[0196] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0197] In field sales, generating optimal hypothesis proposals for each customer quickly and with high quality is extremely time-consuming, placing a heavy burden on sales representatives. Furthermore, there is a lack of an integrated system for effectively collecting and analyzing customer information and industry data to make accurate proposals, making it difficult to improve order rates and streamline sales activities.

[0198] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0199] In this invention, the server includes means for collecting customer information, means for collecting industry data, means for collecting public company information, means for collecting product information, means for integrating and analyzing the collected information, means for automatically generating a hypothetical proposal based on the analysis results, means for outputting the generated hypothetical proposal, means for generating an appropriate hypothetical proposal from the customer information and industry data using a generative AI model, and means for supplying input data to the generative AI model using prompt statements. This makes it possible to effectively collect and analyze customer information and industry data and quickly generate individually optimized hypothetical proposals.

[0200] "Customer information" refers to data relating to a customer, including past transaction history, contact history, purchasing trends, and the like.

[0201] "Industry Data" is data that includes statistics, trends, challenges, success stories, etc. related to a particular industry.

[0202] "Corporate public information" refers to information such as IR reports, press releases, and recruitment information that is officially released by a company.

[0203] "Product information" is detailed data about a product, such as its features, benefits, and application examples.

[0204] "Collection" is the act of gathering necessary data and information from various sources.

[0205] "Integration" is the act of centralizing multiple collected data.

[0206] "Analysis" is the act of using collected and integrated data to derive specific patterns and meanings.

[0207] A "hypothetical proposal" is a proposal that automatically generates solutions and strategies proposed to address customer issues and needs.

[0208] A "generative AI model" is an algorithm or system that uses artificial intelligence to process data and generate new information or suggestions.

[0209] A "prompt" is a document or text that instructs the input data for a generative AI model.

[0210] A "natural language processing algorithm" is an algorithm for analyzing and understanding human language, and is a technology used to analyze collected information.

[0211] This invention is a system that collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates high-quality hypothesis proposals based on that information. This system is composed of three main players: a server, a terminal, and a user.

[0212] The server first collects customer information. This is done by retrieving past transaction history and contact history from the SFA system. Industry data is also collected, and the latest trends, issues, and success stories are retrieved from industry information databases. Next, publicly available company information is obtained using web scraping technology. Specifically, IR reports, press releases, and recruitment information are collected from official company websites and financial information sites. Product information such as the features, benefits, and application examples of the proposed product is also obtained from internal databases and product personnel.

[0213] The server integrates the various collected data into a centralized database. From this integrated database, the server extracts data points useful for sales, such as customer growth strategies, industry trends, and past purchase history. The server also uses natural language processing (NLP) algorithms to analyze the needs and challenges of companies.

[0214] Next, a hypothesis proposal is automatically generated based on the analysis results. During this process, a generative AI model is utilized to generate appropriate hypothesis proposals from customer information and industry data. Input data is provided to the generative AI model using prompt statements. The generated hypothesis proposal includes the customer's specific challenges, industry trends, and the benefits of the proposed product, and also includes specific application examples.

[0215] The generated hypothetical proposal is output from the server to the sales representative's device (e.g., PC or tablet), where the sales representative can check the proposal content, edit and save it as necessary, and complete the final proposal.

[0216] The implementation of this system uses the following specific hardware and software: A PC or tablet is used as the hardware, and Python 3.x, the requests library (to process HTTP requests), BeautifulSoup (for web scraping), pandas (for data manipulation), and scikit-learn (a machine learning library).

[0217] As a specific example, consider the case of creating a hypothetical proposal for Client Company A. Client Company A is a mid-sized manufacturing company, and the proposed product is production management software. The server obtains Client Company A's past transaction history and contact history from the SFA system, and collects the latest trends and issues related to the manufacturing industry from an industry information database. In addition, it obtains Company A's IR reports and recent news articles from official websites and financial information sites, and obtains product information such as the features and application examples of the production management software from an internal database. By integrating and analyzing this data, a hypothetical proposal is automatically generated, such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%."

[0218] An example of a prompt is, "Please generate a hypothesis proposal that corresponds to the latest industry trends based on the autonomous driving products that client company A has purchased in the past." By inputting this prompt into the generative AI model, it is possible to generate an optimal hypothesis proposal.

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] The server uses the means for collecting customer information to obtain sales data from the SFA system. Specifically, it obtains records of past transactions and sales activities related to the client company. The input is the customer's ID and name, and the output is detailed data on past transaction history and sales activities. This allows the server to understand the customer's purchasing patterns and areas of interest.

[0222] Step 2:

[0223] The server uses the industry data collection means to collect industry data such as the latest trends, issues, and success stories from the industry information database. The input is a data request for a specific industry, and the output is the latest information and statistical data for that industry. This allows you to understand the trends and major issues of the entire industry.

[0224] Step 3:

[0225] The server uses web scraping technology to collect publicly available information from companies, such as IR reports, press releases, and recruitment information, from official company websites and financial information sites. The input is the company name and URL, and the output is the collected, publicly available information from the company. This allows us to understand the company's current situation and future strategies.

[0226] Step 4:

[0227] The server uses a means of collecting product information to obtain product information such as the features, benefits, and use cases of the proposed product from an internal database or product personnel. The input is the product name and product category, and the output is detailed information about the product. This allows the benefits and use cases of the proposed product to be clarified.

[0228] Step 5:

[0229] The server consolidates the various data collected above and stores it in a centralized database. The inputs are data sets of customer information, industry data, company public information, and product information, and the output is an integrated database. This allows for smooth data access and analysis.

[0230] Step 6:

[0231] The server extracts data points useful to sales from the integrated database. Specifically, it extracts data points such as customer growth strategies, industry trends, and past purchase history. The input is a query from the integrated database, and the output is a list of useful data points. This allows efficient extraction of only the important information.

[0232] Step 7:

[0233] The server analyzes the collected and integrated information using natural language processing (NLP) algorithms. The input is a dataset from the integrated database, and the output is the analysis results (e.g., the company's needs and challenges). This allows for the extraction of meaningful information from unstructured data.

[0234] Step 8:

[0235] The server automatically generates hypothesis proposals using a generative AI model based on the analysis results. The input is the analysis results and prompt text, and the output is an automatically generated hypothesis proposal. Input data is supplied to the generative AI model using the prompt text, and appropriate hypothesis proposals are generated from customer information and industry data.

[0236] Step 9:

[0237] The server inserts specific application examples into the generated hypothesis proposal. The input is a hypothesis proposal and an application example, and the output is a hypothesis proposal including an application example. This makes the proposal more specific and persuasive.

[0238] Step 10:

[0239] The server displays the generated hypothetical proposal on the sales representative's terminal. The input is the final hypothetical proposal, and the output is a proposal that can be viewed on the terminal. The sales representative checks the proposal content, edits and saves it as necessary, and completes the final proposal. This is expected to improve the quality of proposals, increase the order rate, and make sales activities more efficient.

[0240] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0241] This invention relates to a system that supports the formulation of hypothetical proposals in field sales. It is characterized by collecting, integrating, and analyzing customer information, industry data, public company information, and product information, and automatically generating and outputting high-quality hypothetical proposals based on that information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the proposals can be further improved. Below, we will explain the system's program processing and provide concrete examples.

[0242] System program processing

[0243] 1. Data Collection:

[0244] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[0245] The server collects information on the latest trends, challenges, and success stories related to manufacturing from industry information databases, including specific industry reports, research papers, and industry news.

[0246] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from companies' official websites and financial information sites. In this step, the contents of the latest IR reports and press releases are imported in text format.

[0247] The server obtains product information such as the features, advantages, and application examples of the proposed product (e.g., production management software) from an internal database or from product personnel.

[0248] 2. Data integration and analysis:

[0249] The server integrates the various data collected above into a centralized database that compiles customer information, industry information, company disclosures, and product information.

[0250] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[0251] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges, analyzing IR reports and press releases to extract specific needs such as "the need to expand production capacity."

[0252] 3. Hypothesis proposal generation:

[0253] Based on the collected, integrated, and analyzed data, the server automatically generates a hypothetical proposal optimized for each customer, including the customer's specific challenges, industry trends, and the benefits of the proposed product.

[0254] The server inserts specific application examples into the generated hypothetical proposal. For example, it adds a specific example such as "Through the implementation example at another company B, production efficiency is expected to improve by XX%."

[0255] 4. Use of Emotion Engine:

[0256] The server runs an emotion engine that recognizes emotions from the user's voice and text input. The engine analyzes the tone of the voice and the text content to identify the user's emotions (e.g., excitement, interest, impatience, etc.).

[0257] The server adjusts the suggestions based on the perceived emotion, for example, increasing emphasis in the suggestions if the user is excited, or simplifying the suggestions if the user is impatient.

[0258] 5. Hypothesis proposal output:

[0259] The server outputs the generated and edited hypothesis proposal to the sales representative's device (e.g., PC or tablet), where a preview of the proposal is displayed.

[0260] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[0261] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[0262] Specific examples

[0263] Situation: Creating a hypothetical proposal for client company C

[0264] Client Company C: Major pharmaceutical company

[0265] Suggested product: Research management software

[0266] 1. Data Collection:

[0267] The server obtains the past transaction history and contact history of customer company C from the SFA system, thereby understanding company C's basic information and business negotiation history.

[0268] The server collects the latest trends and issues related to the pharmaceutical industry from an industry information database. For example, it collects trend information on "Accelerating drug development using AI."

[0269] The server retrieves IR reports and recruitment information for Company C from official websites and financial information sites, thereby understanding Company C's recent activities and growth strategies.

[0270] The server retrieves the features and benefits of its research management software from an internal database.

[0271] 2. Data integration and analysis:

[0272] The server consolidates the collected data into a centralized database, providing consolidated data on Company C's growth strategies and the latest trends in the industry.

[0273] Based on the IR report, the server analyzes that "improving the efficiency of new drug development projects is important."

[0274] 3. Hypothesis proposal generation:

[0275] The server automatically generates a hypothesis proposal such as, "Company C is trying to streamline its new drug development projects, and by introducing research management software, the development period will be shortened by XX%."

[0276] Past application examples will also be added, and specific examples such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%" will be inserted into the proposal.

[0277] 4. Use of Emotion Engine:

[0278] When the user makes a voice input, the server uses an emotion engine to recognize the user's emotion.

[0279] For example, if a user speaks in a bright tone, the system recognizes that emotion as "excitement" and adjusts the suggestions it presents to be more detailed and emphasized.

[0280] Conversely, if the user speaks in a tired tone, the system will recognize that emotion as "impatience" and adjust the suggestions to be concise and summarized.

[0281] 5. Hypothesis proposal output:

[0282] The server displays the generated hypothesis proposal on the sales representative's PC.

[0283] The user (sales representative) checks the proposal contents, edits them as necessary, and completes the final proposal.

[0284] The completed proposal is saved by the server in the client's folder for later use.

[0285] In this way, the HYPOS system can quickly create high-quality hypothetical proposals and adjust the proposal content based on the user's emotions, allowing it to provide customers with optimal proposals that meet their specific needs. This is expected to improve the quality of proposals, increase order rates, and streamline sales activities.

[0286] The processing flow will be explained below.

[0287] Step 1:

[0288] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[0289] Step 2:

[0290] The server connects to an industry information database to collect information on the latest trends, challenges, and success stories related to the pharmaceutical industry, including specific industry reports, research papers, and industry news.

[0291] Step 3:

[0292] The server uses web scraping technology to obtain public information about the company (e.g., IR reports, press releases, and recruitment information) from the company's official website and financial information site. In this step, the contents of the latest IR reports and press releases are captured in text format.

[0293] Step 4:

[0294] The server retrieves product information such as features, benefits, and application examples of the proposed product (e.g., research management software) from an internal database or product personnel.

[0295] Step 5:

[0296] The server consolidates the various data collected into a centralized database that includes customer information, industry information, company disclosures, and product information.

[0297] Step 6:

[0298] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[0299] Step 7:

[0300] The server uses natural language processing (NLP) algorithms to analyze the needs and challenges of companies, analyzing IR reports and press releases to extract specific needs such as "improving the efficiency of new drug development projects is important."

[0301] Step 8:

[0302] Based on the collected, integrated, and analyzed data, the server automatically generates a hypothetical proposal optimized for each company, including the customer's specific challenges, industry trends, and the benefits of the proposed product.

[0303] Step 9:

[0304] The server inserts specific application examples into the generated hypothesis proposals, for example, adding a specific example such as "Through implementation examples at other pharmaceutical companies, development time was shortened by XX%."

[0305] Step 10:

[0306] The server runs an emotion engine that recognizes emotions from the user's voice and text input. The engine analyzes the tone of the voice and the text content to identify the user's emotions (e.g., excitement, interest, impatience, etc.).

[0307] Step 11:

[0308] The server adjusts the suggestions based on the perceived emotion, for example, increasing emphasis in the suggestions if the user is excited, or simplifying the suggestions if the user is impatient.

[0309] Step 12:

[0310] The server outputs the generated and edited hypothesis proposal to the sales representative's device (e.g., PC or tablet), where a preview of the proposal is displayed.

[0311] Step 13:

[0312] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[0313] Step 14:

[0314] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[0315] In this way, the HYPOS system can quickly create high-quality hypothetical proposals and adjust the proposal content based on the user's emotions, thereby providing customers with optimal proposals that meet their specific needs. This is expected to improve the quality of proposals, increase order rates, and streamline sales activities.

[0316] Example 2

[0317] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0318] In traditional field sales, it was difficult to properly collect and integrate customer information, industry data, public information, and product information, and then quickly generate high-quality hypothetical proposals based on that information. It was also difficult to incorporate user sentiment into these proposals, resulting in problems with not being able to provide optimal proposals that fully meet the user's needs. Furthermore, the lack of a means to efficiently analyze the collected information often led to a decline in the quality of proposals and the efficiency of sales activities.

[0319] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0320] In this invention, the server includes means for collecting customer information, means for collecting industry data, means for collecting public company information, means for collecting product information, means for integrating the collected information and storing information from multiple data sources in an integrated database, means for analyzing the collected text data using a natural language processing algorithm to identify company needs and issues, means for automatically generating a hypothesis proposal using a generative AI model based on the analysis results, means for inserting specific application examples into the generated hypothesis proposal, means for outputting the collected proposal content, means for using an emotion engine that recognizes user emotions from voice input or text input and adjusting the hypothesis proposal content based on the recognized emotions, and means for editing the output hypothesis proposal on a user terminal and saving it as a final proposal. This makes it possible to integrate customer information, industry data, etc., quickly create high-quality hypothesis proposals, and make proposals that reflect user emotions.

[0321] "Means for collecting customer information" refers to devices and methods for collecting past transaction history, sales activity records, and basic information about customer companies.

[0322] "Industry data collection means" are devices or methods for collecting information on the latest trends, issues, success stories, etc. related to a particular industry.

[0323] "Means for collecting public information about companies" refers to devices and methods for extracting public information such as IR reports, press releases, and recruitment information from official company websites and financial information sites.

[0324] "Means for collecting product information" refers to devices and methods for collecting information such as the product's features, advantages, and application examples.

[0325] "Means for integrating collected information and storing information from multiple data sources in an integrated database" refers to a device or method for centrally managing information obtained from different data sources and storing it in a relational database.

[0326] "Means for analyzing collected text data using natural language processing algorithms to identify a company's needs and issues" refers to devices and methods for analyzing text data using natural language processing technology and extracting a company's specific needs and issues.

[0327] "Means for automatically generating hypothesis proposals using a generative AI model based on analysis results" refers to devices and methods for automatically generating hypothesis proposals using an artificial intelligence model based on the results of data analysis.

[0328] The "means for inserting a specific application example into the generated hypothesis proposal" refers to a device or method for adding a past application example to the generated hypothesis proposal.

[0329] The "means for outputting collected proposal contents" refers to a device or method for displaying or outputting the generated and edited proposal contents on the user's terminal.

[0330] "Means for using an emotion engine that recognizes a user's emotion from a voice input or text input, and adjusting the content of a hypothetical proposal based on the recognized emotion" refers to a device or method for analyzing a user's voice or text, identifying the emotion, and adjusting the content of a hypothetical proposal based on the emotion.

[0331] The "means for editing the output hypothetical proposal on the user terminal and saving it as a final proposal" refers to a device or method that allows a user to edit the output hypothetical proposal and save it as a final proposal.

[0332] This invention relates to a system that supports the formulation of hypothetical proposals in field sales, and is characterized by the fact that it collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates and outputs high-quality hypothetical proposals based on this information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the proposal content can be further improved.

[0333] Data collection

[0334] 1. Collection of Customer Information:

[0335] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history. Specifically, an API request is generated and retrieved using the HTTP protocol.

[0336] 2. Industry data collection:

[0337] The server collects information on the latest trends, challenges, and success stories related to the manufacturing industry from an industry information database, and accesses API endpoints to obtain the required data.

[0338] 3. Collecting public company information:

[0339] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from official corporate websites and financial information sites, analyzing the HTML structure and extracting text data.

[0340] 4. Product Information Collection:

[0341] The server executes SQL queries to retrieve product information (features, benefits, application examples) from the internal database, resulting in detailed product information for the proposed product.

[0342] Data Integration and Analysis

[0343] 1. Data integration:

[0344] The server consolidates the collected data into a centralized database. The information obtained from different data sources is stored in a relational database, and table relationships are established.

[0345] 2. Extracting useful data points:

[0346] The server runs SQL queries to extract useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[0347] 3. Analyzing needs using natural language processing:

[0348] The server uses NLP algorithms to analyze the collected text data and identify the company's needs and challenges. For example, it tokenizes the text of an IR report and extracts specific keywords and phrases.

[0349] Generate hypothesis proposals

[0350] 1. Automatic generation of hypothesis proposals:

[0351] The server generates hypothesis proposals optimized for each customer based on the analyzed data. The proposals are automatically generated using a generative AI model. For example, the server generates a proposal such as, "Company C is striving to streamline its new drug development projects, and introducing research management software will shorten development time by XX%."

[0352] 2. Insert application example:

[0353] The server inserts past application examples into the proposal, providing a concrete example such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%."

[0354] Use of emotion engine

[0355] 1. User Emotion Recognition:

[0356] The server converts the user's voice input into text using a speech recognition API and analyzes it using an emotion engine. For example, the voice input "I'm very interested in this proposal" can be recognized as "excited."

[0357] 2. Adjusting the proposal:

[0358] The server tailors its suggestions based on the perceived emotion: more detailed and emphatic if excited, and more concise if impatient.

[0359] Hypothesis proposal output

[0360] 1. Hypothesis proposal display:

[0361] The server outputs the generated and edited hypothetical proposal to the sales representative's terminal, which displays a preview of the proposal content.

[0362] 2. User edits:

[0363] The user (salesperson) checks the output hypothetical proposal and edits it as necessary, specifically adjusting the customer name and details of the proposal.

[0364] 3. Save the Final Proposal:

[0365] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[0366] Specific examples

[0367] Situation: Creating a hypothetical proposal for client company C

[0368] Client Company C: Major pharmaceutical company

[0369] Suggested product: Research management software

[0370] 1. Data Collection:

[0371] The server obtains the past transaction history and contact history of customer company C from the SFA system, thereby understanding company C's basic information and business negotiation history.

[0372] The server collects the latest trends and issues related to the pharmaceutical industry from an industry information database. For example, it collects trend information on "Accelerating drug development using AI."

[0373] The server retrieves IR reports and recruitment information for Company C from official websites and financial information sites, thereby understanding Company C's recent activities and growth strategies.

[0374] The server retrieves the features and benefits of its research management software from an internal database.

[0375] 2. Data integration and analysis:

[0376] The server consolidates the collected data into a centralized database, providing consolidated data on Company C's growth strategies and the latest trends in the industry.

[0377] Based on the IR report, the server analyzes that "improving the efficiency of new drug development projects is important."

[0378] 3. Hypothesis proposal generation:

[0379] The server automatically generates a hypothesis proposal such as, "Company C is trying to streamline its new drug development projects, and by introducing research management software, the development period will be shortened by XX%."

[0380] Past application examples will also be added, and specific examples such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%" will be inserted into the proposal.

[0381] 4. Use of Emotion Engine:

[0382] When the user makes a voice input, the server uses an emotion engine to recognize the user's emotion.

[0383] For example, if a user speaks in a bright tone, the system recognizes that emotion as "excitement" and adjusts the suggestions it presents to be more detailed and emphasized.

[0384] Conversely, if the user speaks in a tired tone, the system will recognize that emotion as "impatience" and adjust the suggestions to be concise and summarized.

[0385] 5. Hypothesis proposal output:

[0386] The server displays the generated hypothesis proposal on the sales representative's PC.

[0387] The user (sales representative) checks the proposal contents, edits them as necessary, and completes the final proposal.

[0388] The completed proposal is saved by the server in the customer folder for later use.

[0389] Prompt Sentence Examples

[0390] "What kind of research management software would you recommend for Client Company C's new drug development project?"

[0391] "Please tell me the proposal based on Company C's IR report."

[0392] "Give me an example of how you adjusted your proposal to take into account the salesperson's emotions."

[0393] In this way, the system can quickly and effectively create high-quality hypothetical proposals and provide proposals that reflect the user's emotions. As a result, the quality of proposals can be improved, leading to an increase in order acceptance rates and more efficient sales activities.

[0394] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0395] Step 1: Gather customer information

[0396] Input: The customer company ID is entered from the SFA system's API.

[0397] Specific operation: The server sends an HTTP request via the SFA system's API to obtain past transaction history, sales activity records, and basic information about the client company.

[0398] Data processing: Parse the received data in JSON format and extract and format the customer name, location, industry, transaction history, and contact history.

[0399] Output: Formatted customer information data is saved to temporary storage.

[0400] Step 2: Collect industry data

[0401] Input: The name of a specific industry (e.g., manufacturing) is entered.

[0402] What it does: The server accesses the API of an industry information database and sends a request to retrieve the latest trends, issues, and success stories.

[0403] Data processing: Compiling acquired information and formatting industry reports, research papers, and industry news into text format.

[0404] Output: The formatted industry data is saved to temporary storage.

[0405] Step 3: Gather public company information

[0406] Input: Enter the URL of the target company's official website or financial information site.

[0407] Specific operation: The server uses web scraping technology to obtain HTML pages and extracts IR reports, press releases, and recruitment information using BeautifulSoup and other tools.

[0408] Data processing: Structure the text data extracted from HTML and organize the necessary information.

[0409] Output: The formatted public information data is saved to temporary storage.

[0410] Step 4: Gather product information

[0411] Input: The name of the proposed product (e.g., production management software) is entered.

[0412] What happens: The server runs SQL queries against an internal database to search and retrieve product features, benefits, and use cases.

[0413] Data processing: Formatting the results of SQL queries into text and organizing product information.

[0414] Output: Formatted product information is saved to temporary storage.

[0415] Step 5: Integrate the data

[0416] Input: Customer information, industry data, public information, and product information collected at each step are entered.

[0417] What happens next: The server consolidates this information into a unified database, creating relationships between the database tables to create the consolidated data.

[0418] Data processing: Normalize data and remove redundancies.

[0419] Output: Consolidated data stored in a centralized database.

[0420] Step 6: Extract useful data points

[0421] Input: The integrated database is input.

[0422] What it does: The server runs SQL queries to extract specific data points, such as company growth strategies, current industry trends, or past purchase history.

[0423] Data processing: Aggregating extracted data and shaping it into a meaningful dataset.

[0424] Output: A useful dataset extracted.

[0425] Step 7: Analyze needs using natural language processing

[0426] Input: The extracted dataset is input.

[0427] What it does: The server uses NLP algorithms to analyze text data, such as a company's investor relations report, to tokenize it and extract key keywords and phrases.

[0428] Data processing: Using the results analyzed by NLP algorithms to identify the needs and challenges of the company.

[0429] Output: Identified needs and challenges.

[0430] Step 8: Automatic generation of hypotheses

[0431] Input: Identified needs and challenges are entered.

[0432] Specific operation: The server uses a generative AI model (e.g., GPT-3) to automatically generate hypothesis proposals based on identified needs and challenges.

[0433] Data processing: The proposed text is arranged in a natural format and converted into output data.

[0434] Output: Auto-generated hypothesis proposals.

[0435] Step 9: Inserting application examples

[0436] Input: The automatically generated hypothesis proposal is entered.

[0437] Specific operation: The server searches for relevant cases from a database of past application cases and inserts them into the automatically generated proposal text.

[0438] Data processing: Properly combine the proposal and examples to edit it into a more specific and persuasive proposal.

[0439] Output: A hypothetical proposal with concrete application examples inserted.

[0440] Step 10: Use the Emotion Engine

[0441] Input: User voice or text input is entered.

[0442] How it works: The server converts speech into text using a speech recognition API, analyzes it using an emotion engine, and adjusts the suggestions based on the analysis results.

[0443] Data processing: Adjust the details and summary of the suggestion based on the user's emotions (e.g., excitement, impatience).

[0444] Output: The adjusted proposal.

[0445] Step 11: Output of hypothesis proposals

[0446] Input: The adjusted hypothesis proposal is entered.

[0447] Specific operations: The server displays the adjusted hypothesis proposal on the terminal, and the terminal displays the proposal content via a user interface.

[0448] Data processing: Formatting the proposal for display on the screen.

[0449] Output: The proposed hypotheses displayed in the user interface.

[0450] Step 12: User Editing

[0451] Input: A GUI is entered that allows the user to edit the displayed hypothesis proposal.

[0452] Specific operation: The user (salesperson) edits the proposal on the terminal, specifically by correcting the company name and numerical data through the input form.

[0453] Data processing: Update the database in real time to save edits.

[0454] Output: Edited hypothesis proposal.

[0455] Step 13: Save your final proposal

[0456] Input: The edited hypothesis proposal is entered.

[0457] Specific operation: The user saves the edited hypothetical proposal as a final proposal. The server saves the final proposal in PDF format in the customer folder.

[0458] Data processing: Organizing the saved proposals systematically and setting up indexes for future use.

[0459] Output: The final proposal is saved in the customer folder.

[0460] (Application example 2)

[0461] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0462] In today's customer service environment, it is difficult for store clerks to recommend products that are appropriate for each individual customer. To solve this problem, store clerks need to instantly understand a customer's past purchase history and preference data, and then make optimal product recommendations based on the customer's current emotional state. However, relying solely on human intervention makes it difficult to respond quickly and accurately, and it is difficult to expect improved customer satisfaction or increased sales.

[0463] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for collecting customer information, a means for collecting industry data, a means for collecting public company information, a means for collecting product information, a means for integrating and analyzing the collected information, a means for automatically generating hypothetical proposals based on the analysis results, a means for recognizing the user's emotions and adjusting the proposal content, and a means for outputting the generated hypothetical proposals. This enables store clerks to make optimal product proposals to customers in real time through the smart glasses.

[0464] "Means of collecting customer information" refers to functions for obtaining basic information about customers, purchase history, preference data, etc.

[0465] "Means for collecting industry data" is a function for collecting information such as trends, challenges, and success stories related to a specific industry.

[0466] "Means for collecting public information about companies" refers to functions for obtaining public information such as IR reports and press releases from official company websites and financial information sites.

[0467] "Means of collecting product information" refers to a function for obtaining information about the features, advantages, and application examples of your company's products.

[0468] "Means for integrating and analyzing collected information" refers to a function for integrating data obtained from multiple sources into a centralized database and analyzing it.

[0469] The "means for automatically generating hypothesis proposals based on analysis results" is a function for automatically generating optimal hypothesis proposals based on the integrated data.

[0470] The "means for recognizing the user's emotions and adjusting the content of suggestions" is a function for analyzing the user's voice and facial expressions to recognize their emotions and change the content of suggestions accordingly.

[0471] The "means for outputting the generated hypothesis proposal" is a function for finally displaying or providing the generated hypothesis proposal.

[0472] This invention is a system that uses smart glasses to support store clerks in real time in making optimal product recommendations when serving customers. This system integrates and analyzes customer information, industry data, public company information, and product information, and is characterized by recognizing the user's emotions and adjusting the content of recommendations accordingly.

[0473] The server has means for collecting customer information (e.g., acquiring customers' past purchase history and preference data), means for collecting industry data (e.g., collecting trends and success stories in a particular industry), means for collecting public information about companies (e.g., acquiring public information from official websites and financial information sites), and means for collecting product information (e.g., acquiring the features and benefits of a company's products).

[0474] The server then integrates the collected information and analyzes it using a natural language processing algorithm. Based on the analysis results, it automatically generates a hypothesis proposal, which is then accompanied by specific application examples. Furthermore, to recognize the user's emotions, the server utilizes an emotion engine that recognizes emotions from the camera and voice inputs installed in the smart glasses. This engine analyzes the tone of voice and facial expressions to recognize the user's emotions.

[0475] For example, when a user serves a customer through smart glasses, the server analyzes the customer's information in real time, generates optimal product recommendations based on that information, and displays them on the smart glasses' display. At the same time, the server analyzes the user's voice and facial expressions and adjusts the recommendations according to their emotions.

[0476] The following software and hardware are mainly used for program processing:

[0477] Smart glasses: Capture customer faces and analyze images

[0478] FER library: Used for emotion recognition processing

[0479] TfidfVectorizer: Used to analyze customer and product data

[0480] KMeans clustering: used to select the best product

[0481] pyttsx3: Used for audio output

[0482] This system allows store clerks to use the smart glasses to make product recommendations in real time based on the customer's needs and emotions. For example, if a customer is looking for a relaxing effect, the server will suggest "aromatherapy oil with a relaxing effect" based on past preference data and product information. Furthermore, if the user's emotion is recognized as "excitement," the server will display the recommendation in more detail and with more emphasis.

[0483] Here is an example prompt:

[0484] Prompt statement:

[0485] To make product recommendations, you will suggest the best products based on customer preferences and product data, and adjust the recommendations based on customer sentiment.

[0486] Customer ID: 12345

[0487] Customer preference: Relaxing aromatherapy

[0488] Product information: Lavender essential oil (relaxing effect), Citrus mixed oil (energizing effect)

[0489] As a result, efficient and accurate product suggestions can be made when dealing with customers in physical stores.

[0490] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0491] Step 1:

[0492] The server executes the steps to collect customer information through API. In this step, it obtains the customer's past purchase history and preference data. Specifically, it sends an API request to obtain customer data and stores it in a database. The input is the customer ID, and the output is customer information.

[0493] Step 2:

[0494] The server executes the industry data collection process. It collects information on trends, issues, and success stories related to a specific industry from an industry information database. In this step, industry-related data is acquired and integrated into the database. The input is the industry name and related keywords, and the output is industry data.

[0495] Step 3:

[0496] The server runs a method to collect public information about companies. It uses web scraping technology to obtain public information such as IR reports and press releases from official websites and financial information sites. The input is the company name and related URLs, and the output is the company's public information.

[0497] Step 4:

[0498] The server executes the process of collecting information about the company's products, such as their features, benefits, and application examples, from the company's database. The input is the product ID and product name, and the output is the product information.

[0499] Step 5:

[0500] The server then integrates the collected information and analyzes it using natural language processing algorithms. This step involves extracting and analyzing data points from multiple sources stored in an integrated database. The input is the integrated database, and the output is the analysis results.

[0501] Step 6:

[0502] The server executes a means to automatically generate hypothetical proposals based on the analysis results. Specifically, it identifies the optimal product that meets the customer's needs and generates hypothetical proposals based on that. It uses NLP algorithms and clustering technology to select the optimal product and generate hypothetical proposals. The input is the analysis results, and the output is hypothetical proposals.

[0503] Step 7:

[0504] The server recognizes the user's emotions and performs processing to adjust the suggestions according to those emotions. It uses the camera and voice inputs installed in the smart glasses to recognize emotions using an emotion engine. The input is image and voice data from the smart glasses, and the output is the recognized emotion.

[0505] Step 8:

[0506] The server adjusts the content of the hypothesis proposal according to the emotion and generates the final proposal. If the user is excited, the proposal is adjusted to be more detailed and emphasized, and if the user is impatient, the proposal is made brief. The input is the recognized emotion and the hypothesis proposal, and the output is the adjusted hypothesis proposal.

[0507] Step 9:

[0508] The server executes a means for outputting the generated hypothesis proposal, and displays the adjusted hypothesis proposal on the display of the smart glasses so that the user can confirm its content. The input is the adjusted hypothesis proposal, and the output is the proposal content displayed on the smart glasses.

[0509] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0510] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0511] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0512] [Second embodiment]

[0513] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0514] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0515] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0516] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0517] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0518] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0519] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0520] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0521] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0522] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0523] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0524] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0525] This invention relates to a system that supports the creation of hypothetical proposals in field sales, and it collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates and outputs high-quality hypothetical proposals based on that information. Below, we will explain the system's program processing and provide concrete examples.

[0526] System program processing

[0527] 1. Data Collection:

[0528] The server retrieves sales data from the SFA system, which refers to records of past transactions and sales activities related to client companies.

[0529] The server collects the latest trends, challenges, success stories, and other information related to manufacturing from an industry information database.

[0530] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from companies' official websites and financial information sites.

[0531] The server obtains product information such as the features, advantages, and application examples of the proposed product from an internal database or from product personnel.

[0532] 2. Data integration and analysis:

[0533] The server integrates the various data collected above into a centralized database.

[0534] The server extracts sales-useful data points (e.g., growth strategies, industry trends, past purchase history, etc.) from the integrated database.

[0535] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges.

[0536] 3. Hypothesis proposal generation:

[0537] The server automatically generates hypothesis proposals optimized for each customer based on the collected, integrated, and analyzed data.

[0538] The hypothetical proposal includes the customer's specific challenges, industry trends, and the benefits of the proposed product.

[0539] 4. Hypothesis proposal output:

[0540] The server outputs the generated hypothesis proposal to the sales representative's terminal (e.g., PC or tablet).

[0541] The sales representative checks the proposal on the terminal, edits and saves it as necessary, and completes the final proposal.

[0542] Specific examples

[0543] Situation: Creating a hypothetical proposal for client company A

[0544] Customer Company A: Medium-sized manufacturing company

[0545] Proposed product: Production management software

[0546] 1. Data Collection:

[0547] The server obtains the past transaction history and contact history of customer company A from the SFA system.

[0548] The server collects the latest trends and issues related to manufacturing from an industry information database.

[0549] The server retrieves Company A's IR report and recent news articles from its official website and financial information sites.

[0550] The server retrieves product information such as the features and application examples of the production management software from the company's internal database.

[0551] 2. Data integration and analysis:

[0552] The server integrates the collected data into a centralized database and extracts data points related to client company A's growth strategy and the latest trends in the manufacturing industry.

[0553] The server analyzes the details of Company A's new capital investment from the IR report and determines the applicability of production management software.

[0554] 3. Hypothesis proposal generation:

[0555] The server automatically generates hypothetical proposals such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%."

[0556] Proposals will include concrete examples of application (e.g., success stories from other manufacturing companies).

[0557] 4. Hypothesis proposal output:

[0558] The server displays the generated hypothesis proposal on the sales representative's terminal.

[0559] The user (sales representative) checks the proposal contents, edits them as necessary, and creates a proposal document.

[0560] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[0561] The processing flow will be explained below.

[0562] Step 1:

[0563] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[0564] Step 2:

[0565] The server connects to an industry information database to gather information on the latest trends, challenges, and success stories related to the target industry (e.g., manufacturing), including specific industry reports, research papers, and industry news.

[0566] Step 3:

[0567] The server uses web scraping technology to obtain public information about the company (e.g., IR reports, press releases, and recruitment information) from the company's official website and financial information site. In this step, the contents of the latest IR reports and press releases are captured in text format.

[0568] Step 4:

[0569] The server obtains product information such as the features, advantages, and application examples of the proposed product (e.g., production management software) from an internal database or from product personnel.

[0570] Step 5:

[0571] The server consolidates the various data collected into a centralized database that includes customer information, industry information, company disclosures, and product information.

[0572] Step 6:

[0573] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[0574] Step 7:

[0575] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges, analyzing IR reports and press releases to extract specific needs such as "the need to expand production capacity."

[0576] Step 8:

[0577] The server automatically generates a hypothesis proposal based on the analysis results. For example, it creates a proposal such as, "Company A will expand its production capacity by introducing production management software, which will reduce annual costs by XX%."

[0578] Step 9:

[0579] The server inserts specific application examples into the generated hypothesis proposal. For example, it adds a specific example such as "Through the implementation example at another company B, an improvement in production efficiency of XX% is expected."

[0580] Step 10:

[0581] The server outputs the generated and edited hypothesis proposal to the sales representative's device (PC, smartphone, tablet, etc.), where a preview of the proposal is displayed.

[0582] Step 11:

[0583] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[0584] Step 12:

[0585] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[0586] In this way, the HYPOS system quickly creates high-quality hypothetical proposals and provides them to customers based on their specific needs, which is expected to improve the quality of proposals, increase order acceptance rates, and streamline sales activities.

[0587] Example 1

[0588] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0589] In the past, the creation of hypothesis proposals in field sales required manual collection, integration, and analysis of information from a wide variety of data sources, which resulted in inefficiency and a lack of accuracy. Furthermore, the speed and consistency of proposal creation by individual sales representatives was also an issue. As a result, the quality of proposals declined, making it difficult to improve conversion rates.

[0590] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0591] In this invention, the server includes means for acquiring customer information, means for acquiring industry data, means for acquiring public company information, means for acquiring product information, means for integrating the acquired information into a centralized database, means for analyzing the integrated information, means for analyzing company needs and issues using a natural language processing algorithm, means for automatically generating a hypothesis proposal based on the analysis results using a generation AI model, and means for outputting the generated hypothesis proposal to a user's terminal. This automates the proposal creation process and makes it possible to provide hypothesis proposals quickly and with high accuracy.

[0592] 1. "Customer Information" means information related to a customer company regarding its business activities and transaction history.

[0593] 2. "Industry Data" means information about trends, challenges, success stories, and other information related to a particular industry sector.

[0594] 3. "Public corporate information" refers to information officially published by a company, such as IR reports, press releases, and recruitment information.

[0595] 4. "Product Information" means information about the features, benefits, applications, etc. of the products offered.

[0596] 5. "Means of collection" refers to the technical methods and devices used to automatically collect the required information from each data source.

[0597] 6. A "centralized database" is a database that uniformly manages and stores information collected from multiple data sources.

[0598] 7. "Integration means" means the technical methods or devices used to aggregate data collected from different sources into a centralized database.

[0599] 8. “Analytical tools” refers to algorithms or devices used to analyze collected and integrated data and extract useful data points or patterns.

[0600] 9. "Natural language processing algorithm" refers to a technical method for analyzing text data and understanding its meaning and intent.

[0601] 10. "Generative AI model" refers to a model that uses artificial intelligence technology to automatically generate hypotheses and proposals for specific problems.

[0602] 11. "User Device" refers to a device, such as a computer or tablet, used by a sales representative.

[0603] 12. "Output means" refers to the technical methods or devices for displaying the generated hypothesis proposals on the user's terminal or saving them as a file.

[0604] This invention is a system that supports the creation of hypothetical proposals in field sales, collecting, integrating, and analyzing customer information, industry data, public company information, and product information, and automatically generating and outputting high-quality hypothetical proposals based on that information. To implement this system, the following hardware and software are used to process and calculate data.

[0605] Hardware used

[0606] Server: A server equipped with a high-performance processor and large memory capacity, which allows for efficient processing and analysis of large amounts of data.

[0607] Device: PC or tablet used by sales representatives. These devices are used to check, edit, and save hypothesis proposals.

[0608] Software used

[0609] SFA system: Manage customer information using the SalesForce Automation system.

[0610] Industry Information Database: A database that provides industry data such as trends and issues related to the manufacturing industry.

[0611] Web scraping software: BeautifulSoup, Selenium, and other similar software are used to automatically collect publicly available information from companies.

[0612] Natural Language Processing (NLP) algorithms: Used to analyze text data and understand a company's needs and challenges.

[0613] Generative AI model: Uses generative models such as GPT-4 to automatically generate hypothesis proposals.

[0614] Data processing and calculation

[0615] Data collection: The server collects various data using the SFA system, industry information database, and web scraping. It obtains customer information, industry data, company public information, and product information, and automatically collects data from each data source.

[0616] Data integration: The server integrates the collected data into a centralized database, unifying data of different formats and content.

[0617] Data analysis: The server analyzes the integrated data using natural language processing algorithms to extract the company's needs and challenges, and then uses a generative AI model to generate hypothesis proposals based on the data.

[0618] Proposal output: The server outputs the generated hypothetical proposal to the sales representative's terminal. The sales representative checks the proposal content on the terminal and edits and saves it as necessary.

[0619] Specific examples

[0620] Situation: Creating a hypothetical proposal for client company A

[0621] Customer Company A: Medium-sized manufacturing company

[0622] Proposed product: Production management software

[0623] 1. Data Collection:

[0624] The server obtains the past transaction history and contact history of customer company A from the SFA system.

[0625] The server collects the latest trends and issues related to manufacturing from an industry information database.

[0626] The server retrieves Company A's IR report and recent news articles from its official website and financial information sites.

[0627] The server retrieves product information such as the features and application examples of the production management software from the company's internal database.

[0628] 2. Data integration and analysis:

[0629] The server integrates the collected data into a centralized database and extracts data points related to client company A's growth strategy and the latest trends in the manufacturing industry.

[0630] The server analyzes the details of Company A's new capital investment from the IR report and determines the applicability of production management software.

[0631] 3. Hypothesis proposal generation:

[0632] The server automatically generates hypothetical proposals such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%." The proposals include specific application examples (e.g., success stories from other manufacturing companies).

[0633] 4. Hypothesis proposal output:

[0634] The server displays the generated hypothetical proposal on the sales representative's terminal. The user (sales representative) checks the proposal content, edits it as necessary, and creates a proposal.

[0635] Prompt Sentence Examples

[0636] Example 1: Data collection for customer company A

[0637] "Collect information about Client Company A's past transaction history, the latest industry trends, public information about the company, and the features of its production management software. Please explain the source of each information and how you obtained it."

[0638] Example 2: Generating hypothesis proposals

[0639] "Generate a hypothetical proposal for Client Company A, including the cost reduction effects of introducing production management software. Please also consider detailed information about new capital investment."

[0640] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[0641] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0642] System program processing flow

[0643] Step 1: Gather customer information

[0644] Specific operation: The server obtains customer information from the SFA system via API.

[0645] Input: Basic information such as customer company A's ID and name

[0646] Data processing / calculation: By calling the API, records of past transactions and sales activities of client company A are obtained and converted into a database format.

[0647] Output: Saved in the database as "Customer A_Transaction Data".

[0648] Step 2: Gather industry information

[0649] Specific operations: The server executes queries against an industry information database to gather the required information.

[0650] Input: Query criteria related to manufacturing industry

[0651] Data processing / calculation: Extract the latest trends, challenges, and success stories in the manufacturing industry from the query results, convert them into a format, and store them in a database.

[0652] Output: Saved in the database as "Manufacturing_Trend_Data".

[0653] Step 3: Gather public company information

[0654] Specific operations: The server uses web scraping software to collect information from official company websites and financial information sites.

[0655] Input: URL of Company A's official website or financial information site

[0656] Data processing / calculation: Analyze the HTML structure of web pages, extract IR reports, press releases, and recruitment information, convert them into text format, and analyze them to extract important information.

[0657] Output: Saved in the database as "Company A_Public Information".

[0658] Step 4: Gather product information

[0659] Specific operation: The server accesses the company's internal database to obtain information such as the features, benefits, and application examples of the production management software.

[0660] Input: Query terms related to production management software

[0661] Data processing / calculation: Extract product information through database queries, convert it into the appropriate format and store it.

[0662] Output: Saved as "Production Management Software_Features" data.

[0663] Step 5: Integrate the data

[0664] Specific operation: The server consolidates all the data collected above into a centralized database.

[0665] Input: "Customer A_Transaction Data", "Manufacturing Industry_Trend Data", "Company A_Public Information", "Production Management Software_Features"

[0666] Data processing / calculation: Each dataset is converted into a unified format and integrated into a centralized database.

[0667] Output: All data stored in a consolidated database.

[0668] Step 6: Analyze the data

[0669] What it does: The server extracts useful data points from the aggregated data and analyzes them using natural language processing algorithms.

[0670] Input: All data in the integrated database

[0671] Data processing / calculation: Execute natural language processing algorithms to analyze and extract corporate needs and issues.

[0672] Output: Saved as "Company A_Needs Analysis Results".

[0673] Step 7: Generate hypothesis proposals

[0674] Specific operation: The server automatically generates hypothesis proposals using a generative AI model.

[0675] Input: "Company A_Needs Analysis Results" and other integrated data

[0676] Data processing / computation: Using a generative AI model (e.g., GPT-4), generate hypothesis proposals based on the analyzed data.

[0677] Output: Saved as "Hypothesis Proposal".

[0678] Step 8: Output of hypothesis proposals

[0679] Specific operation: The server displays the generated hypothesis proposal on the sales representative's terminal.

[0680] Input: "Hypothesis Proposal"

[0681] Data processing / calculation: Convert the data format into a format suitable for the device used by the sales representative and transfer it.

[0682] Output: The proposal is displayed on the sales representative's terminal.

[0683] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[0684] (Application example 1)

[0685] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0686] In field sales, generating optimal hypothesis proposals for each customer quickly and with high quality is extremely time-consuming, placing a heavy burden on sales representatives. Furthermore, there is a lack of an integrated system for effectively collecting and analyzing customer information and industry data to make accurate proposals, making it difficult to improve order rates and streamline sales activities.

[0687] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0688] In this invention, the server includes means for collecting customer information, means for collecting industry data, means for collecting public company information, means for collecting product information, means for integrating and analyzing the collected information, means for automatically generating a hypothetical proposal based on the analysis results, means for outputting the generated hypothetical proposal, means for generating an appropriate hypothetical proposal from the customer information and industry data using a generative AI model, and means for supplying input data to the generative AI model using prompt statements. This makes it possible to effectively collect and analyze customer information and industry data and quickly generate individually optimized hypothetical proposals.

[0689] "Customer information" refers to data relating to a customer, including past transaction history, contact history, purchasing trends, and the like.

[0690] "Industry Data" is data that includes statistics, trends, challenges, success stories, etc. related to a particular industry.

[0691] "Corporate public information" refers to information such as IR reports, press releases, and recruitment information that is officially released by a company.

[0692] "Product information" is detailed data about a product, such as its features, benefits, and application examples.

[0693] "Collection" is the act of gathering necessary data and information from various sources.

[0694] "Integration" is the act of centralizing multiple collected data.

[0695] "Analysis" is the act of using collected and integrated data to derive specific patterns and meanings.

[0696] A "hypothetical proposal" is a proposal that automatically generates solutions and strategies proposed to address customer issues and needs.

[0697] A "generative AI model" is an algorithm or system that uses artificial intelligence to process data and generate new information or suggestions.

[0698] A "prompt" is a document or text that instructs the input data for a generative AI model.

[0699] A "natural language processing algorithm" is an algorithm for analyzing and understanding human language, and is a technology used to analyze collected information.

[0700] This invention is a system that collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates high-quality hypothesis proposals based on that information. This system is composed of three main players: a server, a terminal, and a user.

[0701] The server first collects customer information. This is done by retrieving past transaction history and contact history from the SFA system. Industry data is also collected, and the latest trends, issues, and success stories are retrieved from industry information databases. Next, publicly available company information is obtained using web scraping technology. Specifically, IR reports, press releases, and recruitment information are collected from official company websites and financial information sites. Product information such as the features, benefits, and application examples of the proposed product is also obtained from internal databases and product personnel.

[0702] The server integrates the various collected data into a centralized database. From this integrated database, the server extracts data points useful for sales, such as customer growth strategies, industry trends, and past purchase history. The server also uses natural language processing (NLP) algorithms to analyze the needs and challenges of companies.

[0703] Next, a hypothesis proposal is automatically generated based on the analysis results. During this process, a generative AI model is utilized to generate appropriate hypothesis proposals from customer information and industry data. Input data is provided to the generative AI model using prompt statements. The generated hypothesis proposal includes the customer's specific challenges, industry trends, and the benefits of the proposed product, and also includes specific application examples.

[0704] The generated hypothetical proposal is output from the server to the sales representative's device (e.g., PC or tablet), where the sales representative can check the proposal content, edit and save it as necessary, and complete the final proposal.

[0705] The implementation of this system uses the following specific hardware and software: A PC or tablet is used as the hardware, and Python 3.x, the requests library (to process HTTP requests), BeautifulSoup (for web scraping), pandas (for data manipulation), and scikit-learn (a machine learning library).

[0706] As a specific example, consider the case of creating a hypothetical proposal for Client Company A. Client Company A is a mid-sized manufacturing company, and the proposed product is production management software. The server obtains Client Company A's past transaction history and contact history from the SFA system, and collects the latest trends and issues related to the manufacturing industry from an industry information database. In addition, it obtains Company A's IR reports and recent news articles from official websites and financial information sites, and obtains product information such as the features and application examples of the production management software from an internal database. By integrating and analyzing this data, a hypothetical proposal is automatically generated, such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%."

[0707] An example of a prompt is, "Please generate a hypothesis proposal that corresponds to the latest industry trends based on the autonomous driving products that client company A has purchased in the past." By inputting this prompt into the generative AI model, it is possible to generate an optimal hypothesis proposal.

[0708] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0709] Step 1:

[0710] The server uses the means for collecting customer information to obtain sales data from the SFA system. Specifically, it obtains records of past transactions and sales activities related to the client company. The input is the customer's ID and name, and the output is detailed data on past transaction history and sales activities. This allows the server to understand the customer's purchasing patterns and areas of interest.

[0711] Step 2:

[0712] The server uses the industry data collection means to collect industry data such as the latest trends, issues, and success stories from the industry information database. The input is a data request for a specific industry, and the output is the latest information and statistical data for that industry. This allows you to understand the trends and major issues of the entire industry.

[0713] Step 3:

[0714] The server uses web scraping technology to collect publicly available information from companies, such as IR reports, press releases, and recruitment information, from official company websites and financial information sites. The input is the company name and URL, and the output is the collected, publicly available information from the company. This allows us to understand the company's current situation and future strategies.

[0715] Step 4:

[0716] The server uses a means of collecting product information to obtain product information such as the features, benefits, and use cases of the proposed product from an internal database or product personnel. The input is the product name and product category, and the output is detailed information about the product. This allows the benefits and use cases of the proposed product to be clarified.

[0717] Step 5:

[0718] The server consolidates the various data collected above and stores it in a centralized database. The inputs are data sets of customer information, industry data, company public information, and product information, and the output is an integrated database. This allows for smooth data access and analysis.

[0719] Step 6:

[0720] The server extracts data points useful to sales from the integrated database. Specifically, it extracts data points such as customer growth strategies, industry trends, and past purchase history. The input is a query from the integrated database, and the output is a list of useful data points. This allows efficient extraction of only the important information.

[0721] Step 7:

[0722] The server analyzes the collected and integrated information using natural language processing (NLP) algorithms. The input is a dataset from the integrated database, and the output is the analysis results (e.g., the company's needs and challenges). This allows for the extraction of meaningful information from unstructured data.

[0723] Step 8:

[0724] The server automatically generates hypothesis proposals using a generative AI model based on the analysis results. The input is the analysis results and prompt text, and the output is an automatically generated hypothesis proposal. Input data is supplied to the generative AI model using the prompt text, and appropriate hypothesis proposals are generated from customer information and industry data.

[0725] Step 9:

[0726] The server inserts specific application examples into the generated hypothesis proposal. The input is a hypothesis proposal and an application example, and the output is a hypothesis proposal including an application example. This makes the proposal more specific and persuasive.

[0727] Step 10:

[0728] The server displays the generated hypothetical proposal on the sales representative's terminal. The input is the final hypothetical proposal, and the output is a proposal that can be viewed on the terminal. The sales representative checks the proposal content, edits and saves it as necessary, and completes the final proposal. This is expected to improve the quality of proposals, increase the order rate, and make sales activities more efficient.

[0729] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0730] This invention relates to a system that supports the formulation of hypothetical proposals in field sales. It is characterized by collecting, integrating, and analyzing customer information, industry data, public company information, and product information, and automatically generating and outputting high-quality hypothetical proposals based on that information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the proposals can be further improved. Below, we will explain the system's program processing and provide concrete examples.

[0731] System program processing

[0732] 1. Data Collection:

[0733] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[0734] The server collects information on the latest trends, challenges, and success stories related to manufacturing from industry information databases, including specific industry reports, research papers, and industry news.

[0735] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from companies' official websites and financial information sites. In this step, the contents of the latest IR reports and press releases are imported in text format.

[0736] The server obtains product information such as the features, advantages, and application examples of the proposed product (e.g., production management software) from an internal database or from product personnel.

[0737] 2. Data integration and analysis:

[0738] The server integrates the various data collected above into a centralized database that compiles customer information, industry information, company disclosures, and product information.

[0739] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[0740] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges, analyzing IR reports and press releases to extract specific needs such as "the need to expand production capacity."

[0741] 3. Hypothesis proposal generation:

[0742] Based on the collected, integrated, and analyzed data, the server automatically generates a hypothetical proposal optimized for each customer, including the customer's specific challenges, industry trends, and the benefits of the proposed product.

[0743] The server inserts specific application examples into the generated hypothetical proposal. For example, it adds a specific example such as "Through the implementation example at another company B, production efficiency is expected to improve by XX%."

[0744] 4. Use of Emotion Engine:

[0745] The server runs an emotion engine that recognizes emotions from the user's voice and text input. The engine analyzes the tone of the voice and the text content to identify the user's emotions (e.g., excitement, interest, impatience, etc.).

[0746] The server adjusts the suggestions based on the perceived emotion, for example, increasing emphasis in the suggestions if the user is excited, or simplifying the suggestions if the user is impatient.

[0747] 5. Hypothesis proposal output:

[0748] The server outputs the generated and edited hypothesis proposal to the sales representative's device (e.g., PC or tablet), where a preview of the proposal is displayed.

[0749] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[0750] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[0751] Specific examples

[0752] Situation: Creating a hypothetical proposal for client company C

[0753] Client Company C: Major pharmaceutical company

[0754] Suggested product: Research management software

[0755] 1. Data Collection:

[0756] The server obtains the past transaction history and contact history of customer company C from the SFA system, thereby understanding company C's basic information and business negotiation history.

[0757] The server collects the latest trends and issues related to the pharmaceutical industry from an industry information database. For example, it collects trend information on "Accelerating drug development using AI."

[0758] The server retrieves IR reports and recruitment information for Company C from official websites and financial information sites, thereby understanding Company C's recent activities and growth strategies.

[0759] The server retrieves the features and benefits of its research management software from an internal database.

[0760] 2. Data integration and analysis:

[0761] The server consolidates the collected data into a centralized database, providing consolidated data on Company C's growth strategies and the latest trends in the industry.

[0762] Based on the IR report, the server analyzes that "improving the efficiency of new drug development projects is important."

[0763] 3. Hypothesis proposal generation:

[0764] The server automatically generates a hypothesis proposal such as, "Company C is trying to streamline its new drug development projects, and by introducing research management software, the development period will be shortened by XX%."

[0765] Past application examples will also be added, and specific examples such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%" will be inserted into the proposal.

[0766] 4. Use of Emotion Engine:

[0767] When the user makes a voice input, the server uses an emotion engine to recognize the user's emotion.

[0768] For example, if a user speaks in a bright tone, the system recognizes that emotion as "excitement" and adjusts the suggestions it presents to be more detailed and emphasized.

[0769] Conversely, if the user speaks in a tired tone, the system will recognize that emotion as "impatience" and adjust the suggestions to be concise and summarized.

[0770] 5. Hypothesis proposal output:

[0771] The server displays the generated hypothesis proposal on the sales representative's PC.

[0772] The user (sales representative) checks the proposal contents, edits them as necessary, and completes the final proposal.

[0773] The completed proposal is saved by the server in the client's folder for later use.

[0774] In this way, the HYPOS system can quickly create high-quality hypothetical proposals and adjust the proposal content based on the user's emotions, allowing it to provide customers with optimal proposals that meet their specific needs. This is expected to improve the quality of proposals, increase order rates, and streamline sales activities.

[0775] The processing flow will be explained below.

[0776] Step 1:

[0777] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[0778] Step 2:

[0779] The server connects to an industry information database to collect information on the latest trends, challenges, and success stories related to the pharmaceutical industry, including specific industry reports, research papers, and industry news.

[0780] Step 3:

[0781] The server uses web scraping technology to obtain public information about the company (e.g., IR reports, press releases, and recruitment information) from the company's official website and financial information site. In this step, the contents of the latest IR reports and press releases are captured in text format.

[0782] Step 4:

[0783] The server retrieves product information such as features, benefits, and application examples of the proposed product (e.g., research management software) from an internal database or product personnel.

[0784] Step 5:

[0785] The server consolidates the various data collected into a centralized database that includes customer information, industry information, company disclosures, and product information.

[0786] Step 6:

[0787] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[0788] Step 7:

[0789] The server uses natural language processing (NLP) algorithms to analyze the needs and challenges of companies, analyzing IR reports and press releases to extract specific needs such as "improving the efficiency of new drug development projects is important."

[0790] Step 8:

[0791] Based on the collected, integrated, and analyzed data, the server automatically generates a hypothetical proposal optimized for each company, including the customer's specific challenges, industry trends, and the benefits of the proposed product.

[0792] Step 9:

[0793] The server inserts specific application examples into the generated hypothesis proposals, for example, adding a specific example such as "Through implementation examples at other pharmaceutical companies, development time was shortened by XX%."

[0794] Step 10:

[0795] The server runs an emotion engine that recognizes emotions from the user's voice and text input. The engine analyzes the tone of the voice and the text content to identify the user's emotions (e.g., excitement, interest, impatience, etc.).

[0796] Step 11:

[0797] The server adjusts the suggestions based on the perceived emotion, for example, increasing emphasis in the suggestions if the user is excited, or simplifying the suggestions if the user is impatient.

[0798] Step 12:

[0799] The server outputs the generated and edited hypothesis proposal to the sales representative's device (e.g., PC or tablet), where a preview of the proposal is displayed.

[0800] Step 13:

[0801] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[0802] Step 14:

[0803] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[0804] In this way, the HYPOS system can quickly create high-quality hypothetical proposals and adjust the proposal content based on the user's emotions, thereby providing customers with optimal proposals that meet their specific needs. This is expected to improve the quality of proposals, increase order rates, and streamline sales activities.

[0805] Example 2

[0806] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0807] In traditional field sales, it was difficult to properly collect and integrate customer information, industry data, public information, and product information, and then quickly generate high-quality hypothetical proposals based on that information. It was also difficult to incorporate user sentiment into these proposals, resulting in problems with not being able to provide optimal proposals that fully meet the user's needs. Furthermore, the lack of a means to efficiently analyze the collected information often led to a decline in the quality of proposals and the efficiency of sales activities.

[0808] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0809] In this invention, the server includes means for collecting customer information, means for collecting industry data, means for collecting public company information, means for collecting product information, means for integrating the collected information and storing information from multiple data sources in an integrated database, means for analyzing the collected text data using a natural language processing algorithm to identify company needs and issues, means for automatically generating a hypothesis proposal using a generative AI model based on the analysis results, means for inserting specific application examples into the generated hypothesis proposal, means for outputting the collected proposal content, means for using an emotion engine that recognizes user emotions from voice input or text input and adjusting the hypothesis proposal content based on the recognized emotions, and means for editing the output hypothesis proposal on a user terminal and saving it as a final proposal. This makes it possible to integrate customer information, industry data, etc., quickly create high-quality hypothesis proposals, and make proposals that reflect user emotions.

[0810] "Means for collecting customer information" refers to devices and methods for collecting past transaction history, sales activity records, and basic information about customer companies.

[0811] "Industry data collection means" are devices or methods for collecting information on the latest trends, issues, success stories, etc. related to a particular industry.

[0812] "Means for collecting public information about companies" refers to devices and methods for extracting public information such as IR reports, press releases, and recruitment information from official company websites and financial information sites.

[0813] "Means for collecting product information" refers to devices and methods for collecting information such as the product's features, advantages, and application examples.

[0814] "Means for integrating collected information and storing information from multiple data sources in an integrated database" refers to a device or method for centrally managing information obtained from different data sources and storing it in a relational database.

[0815] "Means for analyzing collected text data using natural language processing algorithms to identify a company's needs and issues" refers to devices and methods for analyzing text data using natural language processing technology and extracting a company's specific needs and issues.

[0816] "Means for automatically generating hypothesis proposals using a generative AI model based on analysis results" refers to devices and methods for automatically generating hypothesis proposals using an artificial intelligence model based on the results of data analysis.

[0817] The "means for inserting a specific application example into the generated hypothesis proposal" refers to a device or method for adding a past application example to the generated hypothesis proposal.

[0818] The "means for outputting collected proposal contents" refers to a device or method for displaying or outputting the generated and edited proposal contents on the user's terminal.

[0819] "Means for using an emotion engine that recognizes a user's emotion from a voice input or text input, and adjusting the content of a hypothetical proposal based on the recognized emotion" refers to a device or method for analyzing a user's voice or text, identifying the emotion, and adjusting the content of a hypothetical proposal based on the emotion.

[0820] The "means for editing the output hypothetical proposal on the user terminal and saving it as a final proposal" refers to a device or method that allows a user to edit the output hypothetical proposal and save it as a final proposal.

[0821] This invention relates to a system that supports the formulation of hypothetical proposals in field sales, and is characterized by the fact that it collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates and outputs high-quality hypothetical proposals based on this information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the proposal content can be further improved.

[0822] Data collection

[0823] 1. Collection of Customer Information:

[0824] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history. Specifically, an API request is generated and retrieved using the HTTP protocol.

[0825] 2. Industry data collection:

[0826] The server collects information on the latest trends, challenges, and success stories related to the manufacturing industry from an industry information database, and accesses API endpoints to obtain the required data.

[0827] 3. Collecting public company information:

[0828] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from official corporate websites and financial information sites, analyzing the HTML structure and extracting text data.

[0829] 4. Product Information Collection:

[0830] The server executes SQL queries to retrieve product information (features, benefits, application examples) from the internal database, resulting in detailed product information for the proposed product.

[0831] Data Integration and Analysis

[0832] 1. Data integration:

[0833] The server consolidates the collected data into a centralized database. The information obtained from different data sources is stored in a relational database, and table relationships are established.

[0834] 2. Extracting useful data points:

[0835] The server runs SQL queries to extract useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[0836] 3. Analyzing needs using natural language processing:

[0837] The server uses NLP algorithms to analyze the collected text data and identify the company's needs and challenges. For example, it tokenizes the text of an IR report and extracts specific keywords and phrases.

[0838] Generate hypothesis proposals

[0839] 1. Automatic generation of hypothesis proposals:

[0840] The server generates hypothesis proposals optimized for each customer based on the analyzed data. The proposals are automatically generated using a generative AI model. For example, the server generates a proposal such as, "Company C is striving to streamline its new drug development projects, and introducing research management software will shorten development time by XX%."

[0841] 2. Insert application example:

[0842] The server inserts past application examples into the proposal, providing a concrete example such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%."

[0843] Use of emotion engine

[0844] 1. User Emotion Recognition:

[0845] The server converts the user's voice input into text using a speech recognition API and analyzes it using an emotion engine. For example, the voice input "I'm very interested in this proposal" can be recognized as "excited."

[0846] 2. Adjusting the proposal:

[0847] The server tailors its suggestions based on the perceived emotion: more detailed and emphatic if excited, and more concise if impatient.

[0848] Hypothesis proposal output

[0849] 1. Hypothesis proposal display:

[0850] The server outputs the generated and edited hypothetical proposal to the sales representative's terminal, which displays a preview of the proposal content.

[0851] 2. User edits:

[0852] The user (salesperson) checks the output hypothetical proposal and edits it as necessary, specifically adjusting the customer name and details of the proposal.

[0853] 3. Save the Final Proposal:

[0854] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[0855] Specific examples

[0856] Situation: Creating a hypothetical proposal for client company C

[0857] Client Company C: Major pharmaceutical company

[0858] Suggested product: Research management software

[0859] 1. Data Collection:

[0860] The server obtains the past transaction history and contact history of customer company C from the SFA system, thereby understanding company C's basic information and business negotiation history.

[0861] The server collects the latest trends and issues related to the pharmaceutical industry from an industry information database. For example, it collects trend information on "Accelerating drug development using AI."

[0862] The server retrieves IR reports and recruitment information for Company C from official websites and financial information sites, thereby understanding Company C's recent activities and growth strategies.

[0863] The server retrieves the features and benefits of its research management software from an internal database.

[0864] 2. Data integration and analysis:

[0865] The server consolidates the collected data into a centralized database, providing consolidated data on Company C's growth strategies and the latest trends in the industry.

[0866] Based on the IR report, the server analyzes that "improving the efficiency of new drug development projects is important."

[0867] 3. Hypothesis proposal generation:

[0868] The server automatically generates a hypothesis proposal such as, "Company C is trying to streamline its new drug development projects, and by introducing research management software, the development period will be shortened by XX%."

[0869] Past application examples will also be added, and specific examples such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%" will be inserted into the proposal.

[0870] 4. Use of Emotion Engine:

[0871] When the user makes a voice input, the server uses an emotion engine to recognize the user's emotion.

[0872] For example, if a user speaks in a bright tone, the system recognizes that emotion as "excitement" and adjusts the suggestions it presents to be more detailed and emphasized.

[0873] Conversely, if the user speaks in a tired tone, the system will recognize that emotion as "impatience" and adjust the suggestions to be concise and summarized.

[0874] 5. Hypothesis proposal output:

[0875] The server displays the generated hypothesis proposal on the sales representative's PC.

[0876] The user (sales representative) checks the proposal contents, edits them as necessary, and completes the final proposal.

[0877] The completed proposal is saved by the server in the customer folder for later use.

[0878] Prompt Sentence Examples

[0879] "What kind of research management software would you recommend for Client Company C's new drug development project?"

[0880] "Please tell me the proposal based on Company C's IR report."

[0881] "Give me an example of how you adjusted your proposal to take into account the salesperson's emotions."

[0882] In this way, the system can quickly and effectively create high-quality hypothetical proposals and provide proposals that reflect the user's emotions. As a result, the quality of proposals can be improved, leading to an increase in order acceptance rates and more efficient sales activities.

[0883] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0884] Step 1: Gather customer information

[0885] Input: The customer company ID is entered from the SFA system's API.

[0886] Specific operation: The server sends an HTTP request via the SFA system's API to obtain past transaction history, sales activity records, and basic information about the client company.

[0887] Data processing: Parse the received data in JSON format and extract and format the customer name, location, industry, transaction history, and contact history.

[0888] Output: Formatted customer information data is saved to temporary storage.

[0889] Step 2: Collect industry data

[0890] Input: The name of a specific industry (e.g., manufacturing) is entered.

[0891] What it does: The server accesses the API of an industry information database and sends a request to retrieve the latest trends, issues, and success stories.

[0892] Data processing: Compiling acquired information and formatting industry reports, research papers, and industry news into text format.

[0893] Output: The formatted industry data is saved to temporary storage.

[0894] Step 3: Gather public company information

[0895] Input: Enter the URL of the target company's official website or financial information site.

[0896] Specific operation: The server uses web scraping technology to obtain HTML pages and extracts IR reports, press releases, and recruitment information using BeautifulSoup and other tools.

[0897] Data processing: Structure the text data extracted from HTML and organize the necessary information.

[0898] Output: The formatted public information data is saved to temporary storage.

[0899] Step 4: Gather product information

[0900] Input: The name of the proposed product (e.g., production management software) is entered.

[0901] What happens: The server runs SQL queries against an internal database to search and retrieve product features, benefits, and use cases.

[0902] Data processing: Formatting the results of SQL queries into text and organizing product information.

[0903] Output: Formatted product information is saved to temporary storage.

[0904] Step 5: Integrate the data

[0905] Input: Customer information, industry data, public information, and product information collected at each step are entered.

[0906] What happens next: The server consolidates this information into a unified database, creating relationships between the database tables to create the consolidated data.

[0907] Data processing: Normalize data and remove redundancies.

[0908] Output: Consolidated data stored in a centralized database.

[0909] Step 6: Extract useful data points

[0910] Input: The integrated database is input.

[0911] What it does: The server runs SQL queries to extract specific data points, such as company growth strategies, current industry trends, or past purchase history.

[0912] Data processing: Aggregating extracted data and shaping it into a meaningful dataset.

[0913] Output: A useful dataset extracted.

[0914] Step 7: Analyze needs using natural language processing

[0915] Input: The extracted dataset is input.

[0916] What it does: The server uses NLP algorithms to analyze text data, such as a company's investor relations report, to tokenize it and extract key keywords and phrases.

[0917] Data processing: Using the results analyzed by NLP algorithms to identify the needs and challenges of the company.

[0918] Output: Identified needs and challenges.

[0919] Step 8: Automatic generation of hypotheses

[0920] Input: Identified needs and challenges are entered.

[0921] Specific operation: The server uses a generative AI model (e.g., GPT-3) to automatically generate hypothesis proposals based on identified needs and challenges.

[0922] Data processing: The proposed text is arranged in a natural format and converted into output data.

[0923] Output: Auto-generated hypothesis proposals.

[0924] Step 9: Inserting application examples

[0925] Input: The automatically generated hypothesis proposal is entered.

[0926] Specific operation: The server searches for relevant cases from a database of past application cases and inserts them into the automatically generated proposal text.

[0927] Data processing: Properly combine the proposal and examples to edit it into a more specific and persuasive proposal.

[0928] Output: A hypothetical proposal with concrete application examples inserted.

[0929] Step 10: Use the Emotion Engine

[0930] Input: User voice or text input is entered.

[0931] How it works: The server converts speech into text using a speech recognition API, analyzes it using an emotion engine, and adjusts the suggestions based on the analysis results.

[0932] Data processing: Adjust the details and summary of the suggestion based on the user's emotions (e.g., excitement, impatience).

[0933] Output: The adjusted proposal.

[0934] Step 11: Output of hypothesis proposals

[0935] Input: The adjusted hypothesis proposal is entered.

[0936] Specific operations: The server displays the adjusted hypothesis proposal on the terminal, and the terminal displays the proposal content via a user interface.

[0937] Data processing: Formatting the proposal for display on the screen.

[0938] Output: The proposed hypotheses displayed in the user interface.

[0939] Step 12: User Editing

[0940] Input: A GUI is entered that allows the user to edit the displayed hypothesis proposal.

[0941] Specific operation: The user (salesperson) edits the proposal on the terminal, specifically by correcting the company name and numerical data through the input form.

[0942] Data processing: Update the database in real time to save edits.

[0943] Output: Edited hypothesis proposal.

[0944] Step 13: Save your final proposal

[0945] Input: The edited hypothesis proposal is entered.

[0946] Specific operation: The user saves the edited hypothetical proposal as a final proposal. The server saves the final proposal in PDF format in the customer folder.

[0947] Data processing: Organizing the saved proposals systematically and setting up indexes for future use.

[0948] Output: The final proposal is saved in the customer folder.

[0949] (Application example 2)

[0950] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0951] In today's customer service environment, it is difficult for store clerks to recommend products that are appropriate for each individual customer. To solve this problem, store clerks need to instantly understand a customer's past purchase history and preference data, and then make optimal product recommendations based on the customer's current emotional state. However, relying solely on human intervention makes it difficult to respond quickly and accurately, and it is difficult to expect improved customer satisfaction or increased sales.

[0952] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for collecting customer information, a means for collecting industry data, a means for collecting public company information, a means for collecting product information, a means for integrating and analyzing the collected information, a means for automatically generating hypothetical proposals based on the analysis results, a means for recognizing the user's emotions and adjusting the proposal content, and a means for outputting the generated hypothetical proposals. This enables store clerks to make optimal product proposals to customers in real time through the smart glasses.

[0953] "Means of collecting customer information" refers to functions for obtaining basic information about customers, purchase history, preference data, etc.

[0954] "Means for collecting industry data" is a function for collecting information such as trends, challenges, and success stories related to a specific industry.

[0955] "Means for collecting public information about companies" refers to functions for obtaining public information such as IR reports and press releases from official company websites and financial information sites.

[0956] "Means of collecting product information" refers to a function for obtaining information about the features, advantages, and application examples of your company's products.

[0957] "Means for integrating and analyzing collected information" refers to a function for integrating data obtained from multiple sources into a centralized database and analyzing it.

[0958] The "means for automatically generating hypothesis proposals based on analysis results" is a function for automatically generating optimal hypothesis proposals based on the integrated data.

[0959] The "means for recognizing the user's emotions and adjusting the content of suggestions" is a function for analyzing the user's voice and facial expressions to recognize their emotions and change the content of suggestions accordingly.

[0960] The "means for outputting the generated hypothesis proposal" is a function for finally displaying or providing the generated hypothesis proposal.

[0961] This invention is a system that uses smart glasses to support store clerks in real time in making optimal product recommendations when serving customers. This system integrates and analyzes customer information, industry data, public company information, and product information, and is characterized by recognizing the user's emotions and adjusting the content of recommendations accordingly.

[0962] The server has means for collecting customer information (e.g., acquiring customers' past purchase history and preference data), means for collecting industry data (e.g., collecting trends and success stories in a particular industry), means for collecting public information about companies (e.g., acquiring public information from official websites and financial information sites), and means for collecting product information (e.g., acquiring the features and benefits of a company's products).

[0963] The server then integrates the collected information and analyzes it using a natural language processing algorithm. Based on the analysis results, it automatically generates a hypothesis proposal, which is then accompanied by specific application examples. Furthermore, to recognize the user's emotions, the server utilizes an emotion engine that recognizes emotions from the camera and voice inputs installed in the smart glasses. This engine analyzes the tone of voice and facial expressions to recognize the user's emotions.

[0964] For example, when a user serves a customer through smart glasses, the server analyzes the customer's information in real time, generates optimal product recommendations based on that information, and displays them on the smart glasses' display. At the same time, the server analyzes the user's voice and facial expressions and adjusts the recommendations according to their emotions.

[0965] The following software and hardware are mainly used for program processing:

[0966] Smart glasses: Capture customer faces and analyze images

[0967] FER library: Used for emotion recognition processing

[0968] TfidfVectorizer: Used to analyze customer and product data

[0969] KMeans clustering: used to select the best product

[0970] pyttsx3: Used for audio output

[0971] This system allows store clerks to use the smart glasses to make product recommendations in real time based on the customer's needs and emotions. For example, if a customer is looking for a relaxing effect, the server will suggest "aromatherapy oil with a relaxing effect" based on past preference data and product information. Furthermore, if the user's emotion is recognized as "excitement," the server will display the recommendation in more detail and with more emphasis.

[0972] Here is an example prompt:

[0973] Prompt statement:

[0974] To make product recommendations, you will suggest the best products based on customer preferences and product data, and adjust the recommendations based on customer sentiment.

[0975] Customer ID: 12345

[0976] Customer preference: Relaxing aromatherapy

[0977] Product information: Lavender essential oil (relaxing effect), Citrus mixed oil (energizing effect)

[0978] As a result, efficient and accurate product suggestions can be made when dealing with customers in physical stores.

[0979] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0980] Step 1:

[0981] The server executes the steps to collect customer information through API. In this step, it obtains the customer's past purchase history and preference data. Specifically, it sends an API request to obtain customer data and stores it in a database. The input is the customer ID, and the output is customer information.

[0982] Step 2:

[0983] The server executes the industry data collection process. It collects information on trends, issues, and success stories related to a specific industry from an industry information database. In this step, industry-related data is acquired and integrated into the database. The input is the industry name and related keywords, and the output is industry data.

[0984] Step 3:

[0985] The server runs a method to collect public information about companies. It uses web scraping technology to obtain public information such as IR reports and press releases from official websites and financial information sites. The input is the company name and related URLs, and the output is the company's public information.

[0986] Step 4:

[0987] The server executes the process of collecting information about the company's products, such as their features, benefits, and application examples, from the company's database. The input is the product ID and product name, and the output is the product information.

[0988] Step 5:

[0989] The server then integrates the collected information and analyzes it using natural language processing algorithms. This step involves extracting and analyzing data points from multiple sources stored in an integrated database. The input is the integrated database, and the output is the analysis results.

[0990] Step 6:

[0991] The server executes a means to automatically generate hypothetical proposals based on the analysis results. Specifically, it identifies the optimal product that meets the customer's needs and generates hypothetical proposals based on that. It uses NLP algorithms and clustering technology to select the optimal product and generate hypothetical proposals. The input is the analysis results, and the output is hypothetical proposals.

[0992] Step 7:

[0993] The server recognizes the user's emotions and performs processing to adjust the suggestions according to those emotions. It uses the camera and voice inputs installed in the smart glasses to recognize emotions using an emotion engine. The input is image and voice data from the smart glasses, and the output is the recognized emotion.

[0994] Step 8:

[0995] The server adjusts the content of the hypothesis proposal according to the emotion and generates the final proposal. If the user is excited, the proposal is adjusted to be more detailed and emphasized, and if the user is impatient, the proposal is made brief. The input is the recognized emotion and the hypothesis proposal, and the output is the adjusted hypothesis proposal.

[0996] Step 9:

[0997] The server executes a means for outputting the generated hypothesis proposal, and displays the adjusted hypothesis proposal on the display of the smart glasses so that the user can confirm its content. The input is the adjusted hypothesis proposal, and the output is the proposal content displayed on the smart glasses.

[0998] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0999] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1000] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1001] [Third embodiment]

[1002] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1003] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1004] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1005] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1006] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1007] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1008] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1009] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1010] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1011] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1012] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1013] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1014] This invention relates to a system that supports the creation of hypothetical proposals in field sales, and it collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates and outputs high-quality hypothetical proposals based on that information. Below, we will explain the system's program processing and provide concrete examples.

[1015] System program processing

[1016] 1. Data Collection:

[1017] The server retrieves sales data from the SFA system, which refers to records of past transactions and sales activities related to client companies.

[1018] The server collects the latest trends, challenges, success stories, and other information related to manufacturing from an industry information database.

[1019] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from companies' official websites and financial information sites.

[1020] The server obtains product information such as the features, advantages, and application examples of the proposed product from an internal database or from product personnel.

[1021] 2. Data integration and analysis:

[1022] The server integrates the various data collected above into a centralized database.

[1023] The server extracts sales-useful data points (e.g., growth strategies, industry trends, past purchase history, etc.) from the integrated database.

[1024] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges.

[1025] 3. Hypothesis proposal generation:

[1026] The server automatically generates hypothesis proposals optimized for each customer based on the collected, integrated, and analyzed data.

[1027] The hypothetical proposal includes the customer's specific challenges, industry trends, and the benefits of the proposed product.

[1028] 4. Hypothesis proposal output:

[1029] The server outputs the generated hypothesis proposal to the sales representative's terminal (e.g., PC or tablet).

[1030] The sales representative checks the proposal on the terminal, edits and saves it as necessary, and completes the final proposal.

[1031] Specific examples

[1032] Situation: Creating a hypothetical proposal for client company A

[1033] Customer Company A: Medium-sized manufacturing company

[1034] Proposed product: Production management software

[1035] 1. Data Collection:

[1036] The server obtains the past transaction history and contact history of customer company A from the SFA system.

[1037] The server collects the latest trends and issues related to manufacturing from an industry information database.

[1038] The server retrieves Company A's IR report and recent news articles from its official website and financial information sites.

[1039] The server retrieves product information such as the features and application examples of the production management software from the company's internal database.

[1040] 2. Data integration and analysis:

[1041] The server integrates the collected data into a centralized database and extracts data points related to client company A's growth strategy and the latest trends in the manufacturing industry.

[1042] The server analyzes the details of Company A's new capital investment from the IR report and determines the applicability of production management software.

[1043] 3. Hypothesis proposal generation:

[1044] The server automatically generates hypothetical proposals such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%."

[1045] Proposals will include concrete examples of application (e.g., success stories from other manufacturing companies).

[1046] 4. Hypothesis proposal output:

[1047] The server displays the generated hypothesis proposal on the sales representative's terminal.

[1048] The user (sales representative) checks the proposal contents, edits them as necessary, and creates a proposal document.

[1049] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[1050] The processing flow will be explained below.

[1051] Step 1:

[1052] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[1053] Step 2:

[1054] The server connects to an industry information database to gather information on the latest trends, challenges, and success stories related to the target industry (e.g., manufacturing), including specific industry reports, research papers, and industry news.

[1055] Step 3:

[1056] The server uses web scraping technology to obtain public information about the company (e.g., IR reports, press releases, and recruitment information) from the company's official website and financial information site. In this step, the contents of the latest IR reports and press releases are captured in text format.

[1057] Step 4:

[1058] The server obtains product information such as the features, advantages, and application examples of the proposed product (e.g., production management software) from an internal database or from product personnel.

[1059] Step 5:

[1060] The server consolidates the various data collected into a centralized database that includes customer information, industry information, company disclosures, and product information.

[1061] Step 6:

[1062] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[1063] Step 7:

[1064] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges, analyzing IR reports and press releases to extract specific needs such as "the need to expand production capacity."

[1065] Step 8:

[1066] The server automatically generates a hypothesis proposal based on the analysis results. For example, it creates a proposal such as, "Company A will expand its production capacity by introducing production management software, which will reduce annual costs by XX%."

[1067] Step 9:

[1068] The server inserts specific application examples into the generated hypothesis proposal. For example, it adds a specific example such as "Through the implementation example at another company B, an improvement in production efficiency of XX% is expected."

[1069] Step 10:

[1070] The server outputs the generated and edited hypothesis proposal to the sales representative's device (PC, smartphone, tablet, etc.), where a preview of the proposal is displayed.

[1071] Step 11:

[1072] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[1073] Step 12:

[1074] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[1075] In this way, the HYPOS system quickly creates high-quality hypothetical proposals and provides them to customers based on their specific needs, which is expected to improve the quality of proposals, increase order acceptance rates, and streamline sales activities.

[1076] Example 1

[1077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1078] In the past, the creation of hypothesis proposals in field sales required manual collection, integration, and analysis of information from a wide variety of data sources, which resulted in inefficiency and a lack of accuracy. Furthermore, the speed and consistency of proposal creation by individual sales representatives was also an issue. As a result, the quality of proposals declined, making it difficult to improve conversion rates.

[1079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1080] In this invention, the server includes means for acquiring customer information, means for acquiring industry data, means for acquiring public company information, means for acquiring product information, means for integrating the acquired information into a centralized database, means for analyzing the integrated information, means for analyzing company needs and issues using a natural language processing algorithm, means for automatically generating a hypothesis proposal based on the analysis results using a generation AI model, and means for outputting the generated hypothesis proposal to a user's terminal. This automates the proposal creation process and makes it possible to provide hypothesis proposals quickly and with high accuracy.

[1081] 1. "Customer Information" means information related to a customer company regarding its business activities and transaction history.

[1082] 2. "Industry Data" means information about trends, challenges, success stories, and other information related to a particular industry sector.

[1083] 3. "Public corporate information" refers to information officially published by a company, such as IR reports, press releases, and recruitment information.

[1084] 4. "Product Information" means information about the features, benefits, applications, etc. of the products offered.

[1085] 5. "Means of collection" refers to the technical methods and devices used to automatically collect the required information from each data source.

[1086] 6. A "centralized database" is a database that uniformly manages and stores information collected from multiple data sources.

[1087] 7. "Integration means" means the technical methods or devices used to aggregate data collected from different sources into a centralized database.

[1088] 8. “Analytical tools” refers to algorithms or devices used to analyze collected and integrated data and extract useful data points or patterns.

[1089] 9. "Natural language processing algorithm" refers to a technical method for analyzing text data and understanding its meaning and intent.

[1090] 10. "Generative AI model" refers to a model that uses artificial intelligence technology to automatically generate hypotheses and proposals for specific problems.

[1091] 11. "User Device" refers to a device, such as a computer or tablet, used by a sales representative.

[1092] 12. "Output means" refers to the technical methods or devices for displaying the generated hypothesis proposals on the user's terminal or saving them as a file.

[1093] This invention is a system that supports the creation of hypothetical proposals in field sales, collecting, integrating, and analyzing customer information, industry data, public company information, and product information, and automatically generating and outputting high-quality hypothetical proposals based on that information. To implement this system, the following hardware and software are used to process and calculate data.

[1094] Hardware used

[1095] Server: A server equipped with a high-performance processor and large memory capacity, which allows for efficient processing and analysis of large amounts of data.

[1096] Device: PC or tablet used by sales representatives. These devices are used to check, edit, and save hypothesis proposals.

[1097] Software used

[1098] SFA system: Manage customer information using the SalesForce Automation system.

[1099] Industry Information Database: A database that provides industry data such as trends and issues related to the manufacturing industry.

[1100] Web scraping software: BeautifulSoup, Selenium, and other similar software are used to automatically collect publicly available information from companies.

[1101] Natural Language Processing (NLP) algorithms: Used to analyze text data and understand a company's needs and challenges.

[1102] Generative AI model: Uses generative models such as GPT-4 to automatically generate hypothesis proposals.

[1103] Data processing and calculation

[1104] Data collection: The server collects various data using the SFA system, industry information database, and web scraping. It obtains customer information, industry data, company public information, and product information, and automatically collects data from each data source.

[1105] Data integration: The server integrates the collected data into a centralized database, unifying data of different formats and content.

[1106] Data analysis: The server analyzes the integrated data using natural language processing algorithms to extract the company's needs and challenges, and then uses a generative AI model to generate hypothesis proposals based on the data.

[1107] Proposal output: The server outputs the generated hypothetical proposal to the sales representative's terminal. The sales representative checks the proposal content on the terminal and edits and saves it as necessary.

[1108] Specific examples

[1109] Situation: Creating a hypothetical proposal for client company A

[1110] Customer Company A: Medium-sized manufacturing company

[1111] Proposed product: Production management software

[1112] 1. Data Collection:

[1113] The server obtains the past transaction history and contact history of customer company A from the SFA system.

[1114] The server collects the latest trends and issues related to manufacturing from an industry information database.

[1115] The server retrieves Company A's IR report and recent news articles from its official website and financial information sites.

[1116] The server retrieves product information such as the features and application examples of the production management software from the company's internal database.

[1117] 2. Data integration and analysis:

[1118] The server integrates the collected data into a centralized database and extracts data points related to client company A's growth strategy and the latest trends in the manufacturing industry.

[1119] The server analyzes the details of Company A's new capital investment from the IR report and determines the applicability of production management software.

[1120] 3. Hypothesis proposal generation:

[1121] The server automatically generates hypothetical proposals such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%." The proposals include specific application examples (e.g., success stories from other manufacturing companies).

[1122] 4. Hypothesis proposal output:

[1123] The server displays the generated hypothetical proposal on the sales representative's terminal. The user (sales representative) checks the proposal content, edits it as necessary, and creates a proposal.

[1124] Prompt Sentence Examples

[1125] Example 1: Data collection for customer company A

[1126] "Collect information about Client Company A's past transaction history, the latest industry trends, public information about the company, and the features of its production management software. Please explain the source of each information and how you obtained it."

[1127] Example 2: Generating hypothesis proposals

[1128] "Generate a hypothetical proposal for Client Company A, including the cost reduction effects of introducing production management software. Please also consider detailed information about new capital investment."

[1129] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[1130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1131] System program processing flow

[1132] Step 1: Gather customer information

[1133] Specific operation: The server obtains customer information from the SFA system via API.

[1134] Input: Basic information such as customer company A's ID and name

[1135] Data processing / calculation: By calling the API, records of past transactions and sales activities of client company A are obtained and converted into a database format.

[1136] Output: Saved in the database as "Customer A_Transaction Data".

[1137] Step 2: Gather industry information

[1138] Specific operations: The server executes queries against an industry information database to gather the required information.

[1139] Input: Query criteria related to manufacturing industry

[1140] Data processing / calculation: Extract the latest trends, challenges, and success stories in the manufacturing industry from the query results, convert them into a format, and store them in a database.

[1141] Output: Saved in the database as "Manufacturing_Trend_Data".

[1142] Step 3: Gather public company information

[1143] Specific operations: The server uses web scraping software to collect information from official company websites and financial information sites.

[1144] Input: URL of Company A's official website or financial information site

[1145] Data processing / calculation: Analyze the HTML structure of web pages, extract IR reports, press releases, and recruitment information, convert them into text format, and analyze them to extract important information.

[1146] Output: Saved in the database as "Company A_Public Information".

[1147] Step 4: Gather product information

[1148] Specific operation: The server accesses the company's internal database to obtain information such as the features, benefits, and application examples of the production management software.

[1149] Input: Query terms related to production management software

[1150] Data processing / calculation: Extract product information through database queries, convert it into the appropriate format and store it.

[1151] Output: Saved as "Production Management Software_Features" data.

[1152] Step 5: Integrate the data

[1153] Specific operation: The server consolidates all the data collected above into a centralized database.

[1154] Input: "Customer A_Transaction Data", "Manufacturing Industry_Trend Data", "Company A_Public Information", "Production Management Software_Features"

[1155] Data processing / calculation: Each dataset is converted into a unified format and integrated into a centralized database.

[1156] Output: All data stored in a consolidated database.

[1157] Step 6: Analyze the data

[1158] What it does: The server extracts useful data points from the aggregated data and analyzes them using natural language processing algorithms.

[1159] Input: All data in the integrated database

[1160] Data processing / calculation: Execute natural language processing algorithms to analyze and extract corporate needs and issues.

[1161] Output: Saved as "Company A_Needs Analysis Results".

[1162] Step 7: Generate hypothesis proposals

[1163] Specific operation: The server automatically generates hypothesis proposals using a generative AI model.

[1164] Input: "Company A_Needs Analysis Results" and other integrated data

[1165] Data processing / computation: Using a generative AI model (e.g., GPT-4), generate hypothesis proposals based on the analyzed data.

[1166] Output: Saved as "Hypothesis Proposal".

[1167] Step 8: Output of hypothesis proposals

[1168] Specific operation: The server displays the generated hypothesis proposal on the sales representative's terminal.

[1169] Input: "Hypothesis Proposal"

[1170] Data processing / calculation: Convert the data format into a format suitable for the device used by the sales representative and transfer it.

[1171] Output: The proposal is displayed on the sales representative's terminal.

[1172] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[1173] (Application example 1)

[1174] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1175] In field sales, generating optimal hypothesis proposals for each customer quickly and with high quality is extremely time-consuming, placing a heavy burden on sales representatives. Furthermore, there is a lack of an integrated system for effectively collecting and analyzing customer information and industry data to make accurate proposals, making it difficult to improve order rates and streamline sales activities.

[1176] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1177] In this invention, the server includes means for collecting customer information, means for collecting industry data, means for collecting public company information, means for collecting product information, means for integrating and analyzing the collected information, means for automatically generating a hypothetical proposal based on the analysis results, means for outputting the generated hypothetical proposal, means for generating an appropriate hypothetical proposal from the customer information and industry data using a generative AI model, and means for supplying input data to the generative AI model using prompt statements. This makes it possible to effectively collect and analyze customer information and industry data and quickly generate individually optimized hypothetical proposals.

[1178] "Customer information" refers to data relating to a customer, including past transaction history, contact history, purchasing trends, and the like.

[1179] "Industry Data" is data that includes statistics, trends, challenges, success stories, etc. related to a particular industry.

[1180] "Corporate public information" refers to information such as IR reports, press releases, and recruitment information that is officially released by a company.

[1181] "Product information" is detailed data about a product, such as its features, benefits, and application examples.

[1182] "Collection" is the act of gathering necessary data and information from various sources.

[1183] "Integration" is the act of centralizing multiple collected data.

[1184] "Analysis" is the act of using collected and integrated data to derive specific patterns and meanings.

[1185] A "hypothetical proposal" is a proposal that automatically generates solutions and strategies proposed to address customer issues and needs.

[1186] A "generative AI model" is an algorithm or system that uses artificial intelligence to process data and generate new information or suggestions.

[1187] A "prompt" is a document or text that instructs the input data for a generative AI model.

[1188] A "natural language processing algorithm" is an algorithm for analyzing and understanding human language, and is a technology used to analyze collected information.

[1189] This invention is a system that collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates high-quality hypothesis proposals based on that information. This system is composed of three main players: a server, a terminal, and a user.

[1190] The server first collects customer information. This is done by retrieving past transaction history and contact history from the SFA system. Industry data is also collected, and the latest trends, issues, and success stories are retrieved from industry information databases. Next, publicly available company information is obtained using web scraping technology. Specifically, IR reports, press releases, and recruitment information are collected from official company websites and financial information sites. Product information such as the features, benefits, and application examples of the proposed product is also obtained from internal databases and product personnel.

[1191] The server integrates the various collected data into a centralized database. From this integrated database, the server extracts data points useful for sales, such as customer growth strategies, industry trends, and past purchase history. The server also uses natural language processing (NLP) algorithms to analyze the needs and challenges of companies.

[1192] Next, a hypothesis proposal is automatically generated based on the analysis results. During this process, a generative AI model is utilized to generate appropriate hypothesis proposals from customer information and industry data. Input data is provided to the generative AI model using prompt statements. The generated hypothesis proposal includes the customer's specific challenges, industry trends, and the benefits of the proposed product, and also includes specific application examples.

[1193] The generated hypothetical proposal is output from the server to the sales representative's device (e.g., PC or tablet), where the sales representative can check the proposal content, edit and save it as necessary, and complete the final proposal.

[1194] The implementation of this system uses the following specific hardware and software: A PC or tablet is used as the hardware, and Python 3.x, the requests library (to process HTTP requests), BeautifulSoup (for web scraping), pandas (for data manipulation), and scikit-learn (a machine learning library).

[1195] As a specific example, consider the case of creating a hypothetical proposal for Client Company A. Client Company A is a mid-sized manufacturing company, and the proposed product is production management software. The server obtains Client Company A's past transaction history and contact history from the SFA system, and collects the latest trends and issues related to the manufacturing industry from an industry information database. In addition, it obtains Company A's IR reports and recent news articles from official websites and financial information sites, and obtains product information such as the features and application examples of the production management software from an internal database. By integrating and analyzing this data, a hypothetical proposal is automatically generated, such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%."

[1196] An example of a prompt is, "Please generate a hypothesis proposal that corresponds to the latest industry trends based on the autonomous driving products that client company A has purchased in the past." By inputting this prompt into the generative AI model, it is possible to generate an optimal hypothesis proposal.

[1197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1198] Step 1:

[1199] The server uses the means for collecting customer information to obtain sales data from the SFA system. Specifically, it obtains records of past transactions and sales activities related to the client company. The input is the customer's ID and name, and the output is detailed data on past transaction history and sales activities. This allows the server to understand the customer's purchasing patterns and areas of interest.

[1200] Step 2:

[1201] The server uses the industry data collection means to collect industry data such as the latest trends, issues, and success stories from the industry information database. The input is a data request for a specific industry, and the output is the latest information and statistical data for that industry. This allows you to understand the trends and major issues of the entire industry.

[1202] Step 3:

[1203] The server uses web scraping technology to collect publicly available information from companies, such as IR reports, press releases, and recruitment information, from official company websites and financial information sites. The input is the company name and URL, and the output is the collected, publicly available information from the company. This allows us to understand the company's current situation and future strategies.

[1204] Step 4:

[1205] The server uses a means of collecting product information to obtain product information such as the features, benefits, and use cases of the proposed product from an internal database or product personnel. The input is the product name and product category, and the output is detailed information about the product. This allows the benefits and use cases of the proposed product to be clarified.

[1206] Step 5:

[1207] The server consolidates the various data collected above and stores it in a centralized database. The inputs are data sets of customer information, industry data, company public information, and product information, and the output is an integrated database. This allows for smooth data access and analysis.

[1208] Step 6:

[1209] The server extracts data points useful to sales from the integrated database. Specifically, it extracts data points such as customer growth strategies, industry trends, and past purchase history. The input is a query from the integrated database, and the output is a list of useful data points. This allows efficient extraction of only the important information.

[1210] Step 7:

[1211] The server analyzes the collected and integrated information using natural language processing (NLP) algorithms. The input is a dataset from the integrated database, and the output is the analysis results (e.g., the company's needs and challenges). This allows for the extraction of meaningful information from unstructured data.

[1212] Step 8:

[1213] The server automatically generates hypothesis proposals using a generative AI model based on the analysis results. The input is the analysis results and prompt text, and the output is an automatically generated hypothesis proposal. Input data is supplied to the generative AI model using the prompt text, and appropriate hypothesis proposals are generated from customer information and industry data.

[1214] Step 9:

[1215] The server inserts specific application examples into the generated hypothesis proposal. The input is a hypothesis proposal and an application example, and the output is a hypothesis proposal including an application example. This makes the proposal more specific and persuasive.

[1216] Step 10:

[1217] The server displays the generated hypothetical proposal on the sales representative's terminal. The input is the final hypothetical proposal, and the output is a proposal that can be viewed on the terminal. The sales representative checks the proposal content, edits and saves it as necessary, and completes the final proposal. This is expected to improve the quality of proposals, increase the order rate, and make sales activities more efficient.

[1218] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1219] This invention relates to a system that supports the formulation of hypothetical proposals in field sales. It is characterized by collecting, integrating, and analyzing customer information, industry data, public company information, and product information, and automatically generating and outputting high-quality hypothetical proposals based on that information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the proposals can be further improved. Below, we will explain the system's program processing and provide concrete examples.

[1220] System program processing

[1221] 1. Data Collection:

[1222] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[1223] The server collects information on the latest trends, challenges, and success stories related to manufacturing from industry information databases, including specific industry reports, research papers, and industry news.

[1224] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from companies' official websites and financial information sites. In this step, the contents of the latest IR reports and press releases are imported in text format.

[1225] The server obtains product information such as the features, advantages, and application examples of the proposed product (e.g., production management software) from an internal database or from product personnel.

[1226] 2. Data integration and analysis:

[1227] The server integrates the various data collected above into a centralized database that compiles customer information, industry information, company disclosures, and product information.

[1228] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[1229] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges, analyzing IR reports and press releases to extract specific needs such as "the need to expand production capacity."

[1230] 3. Hypothesis proposal generation:

[1231] Based on the collected, integrated, and analyzed data, the server automatically generates a hypothetical proposal optimized for each customer, including the customer's specific challenges, industry trends, and the benefits of the proposed product.

[1232] The server inserts specific application examples into the generated hypothetical proposal. For example, it adds a specific example such as "Through the implementation example at another company B, production efficiency is expected to improve by XX%."

[1233] 4. Use of Emotion Engine:

[1234] The server runs an emotion engine that recognizes emotions from the user's voice and text input. The engine analyzes the tone of the voice and the text content to identify the user's emotions (e.g., excitement, interest, impatience, etc.).

[1235] The server adjusts the suggestions based on the perceived emotion, for example, increasing emphasis in the suggestions if the user is excited, or simplifying the suggestions if the user is impatient.

[1236] 5. Hypothesis proposal output:

[1237] The server outputs the generated and edited hypothesis proposal to the sales representative's device (e.g., PC or tablet), where a preview of the proposal is displayed.

[1238] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[1239] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[1240] Specific examples

[1241] Situation: Creating a hypothetical proposal for client company C

[1242] Client Company C: Major pharmaceutical company

[1243] Suggested product: Research management software

[1244] 1. Data Collection:

[1245] The server obtains the past transaction history and contact history of customer company C from the SFA system, thereby understanding company C's basic information and business negotiation history.

[1246] The server collects the latest trends and issues related to the pharmaceutical industry from an industry information database. For example, it collects trend information on "Accelerating drug development using AI."

[1247] The server retrieves IR reports and recruitment information for Company C from official websites and financial information sites, thereby understanding Company C's recent activities and growth strategies.

[1248] The server retrieves the features and benefits of its research management software from an internal database.

[1249] 2. Data integration and analysis:

[1250] The server consolidates the collected data into a centralized database, providing consolidated data on Company C's growth strategies and the latest trends in the industry.

[1251] Based on the IR report, the server analyzes that "improving the efficiency of new drug development projects is important."

[1252] 3. Hypothesis proposal generation:

[1253] The server automatically generates a hypothesis proposal such as, "Company C is trying to streamline its new drug development projects, and by introducing research management software, the development period will be shortened by XX%."

[1254] Past application examples will also be added, and specific examples such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%" will be inserted into the proposal.

[1255] 4. Use of Emotion Engine:

[1256] When the user makes a voice input, the server uses an emotion engine to recognize the user's emotion.

[1257] For example, if a user speaks in a bright tone, the system recognizes that emotion as "excitement" and adjusts the suggestions it presents to be more detailed and emphasized.

[1258] Conversely, if the user speaks in a tired tone, the system will recognize that emotion as "impatience" and adjust the suggestions to be concise and summarized.

[1259] 5. Hypothesis proposal output:

[1260] The server displays the generated hypothesis proposal on the sales representative's PC.

[1261] The user (sales representative) checks the proposal contents, edits them as necessary, and completes the final proposal.

[1262] The completed proposal is saved by the server in the client's folder for later use.

[1263] In this way, the HYPOS system can quickly create high-quality hypothetical proposals and adjust the proposal content based on the user's emotions, allowing it to provide customers with optimal proposals that meet their specific needs. This is expected to improve the quality of proposals, increase order rates, and streamline sales activities.

[1264] The processing flow will be explained below.

[1265] Step 1:

[1266] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[1267] Step 2:

[1268] The server connects to an industry information database to collect information on the latest trends, challenges, and success stories related to the pharmaceutical industry, including specific industry reports, research papers, and industry news.

[1269] Step 3:

[1270] The server uses web scraping technology to obtain public information about the company (e.g., IR reports, press releases, and recruitment information) from the company's official website and financial information site. In this step, the contents of the latest IR reports and press releases are captured in text format.

[1271] Step 4:

[1272] The server retrieves product information such as features, benefits, and application examples of the proposed product (e.g., research management software) from an internal database or product personnel.

[1273] Step 5:

[1274] The server consolidates the various data collected into a centralized database that includes customer information, industry information, company disclosures, and product information.

[1275] Step 6:

[1276] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[1277] Step 7:

[1278] The server uses natural language processing (NLP) algorithms to analyze the needs and challenges of companies, analyzing IR reports and press releases to extract specific needs such as "improving the efficiency of new drug development projects is important."

[1279] Step 8:

[1280] Based on the collected, integrated, and analyzed data, the server automatically generates a hypothetical proposal optimized for each company, including the customer's specific challenges, industry trends, and the benefits of the proposed product.

[1281] Step 9:

[1282] The server inserts specific application examples into the generated hypothesis proposals, for example, adding a specific example such as "Through implementation examples at other pharmaceutical companies, development time was shortened by XX%."

[1283] Step 10:

[1284] The server runs an emotion engine that recognizes emotions from the user's voice and text input. The engine analyzes the tone of the voice and the text content to identify the user's emotions (e.g., excitement, interest, impatience, etc.).

[1285] Step 11:

[1286] The server adjusts the suggestions based on the perceived emotion, for example, increasing emphasis in the suggestions if the user is excited, or simplifying the suggestions if the user is impatient.

[1287] Step 12:

[1288] The server outputs the generated and edited hypothesis proposal to the sales representative's device (e.g., PC or tablet), where a preview of the proposal is displayed.

[1289] Step 13:

[1290] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[1291] Step 14:

[1292] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[1293] In this way, the HYPOS system can quickly create high-quality hypothetical proposals and adjust the proposal content based on the user's emotions, thereby providing customers with optimal proposals that meet their specific needs. This is expected to improve the quality of proposals, increase order rates, and streamline sales activities.

[1294] Example 2

[1295] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1296] In traditional field sales, it was difficult to properly collect and integrate customer information, industry data, public information, and product information, and then quickly generate high-quality hypothetical proposals based on that information. It was also difficult to incorporate user sentiment into these proposals, resulting in problems with not being able to provide optimal proposals that fully meet the user's needs. Furthermore, the lack of a means to efficiently analyze the collected information often led to a decline in the quality of proposals and the efficiency of sales activities.

[1297] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1298] In this invention, the server includes means for collecting customer information, means for collecting industry data, means for collecting public company information, means for collecting product information, means for integrating the collected information and storing information from multiple data sources in an integrated database, means for analyzing the collected text data using a natural language processing algorithm to identify company needs and issues, means for automatically generating a hypothesis proposal using a generative AI model based on the analysis results, means for inserting specific application examples into the generated hypothesis proposal, means for outputting the collected proposal content, means for using an emotion engine that recognizes user emotions from voice input or text input and adjusting the hypothesis proposal content based on the recognized emotions, and means for editing the output hypothesis proposal on a user terminal and saving it as a final proposal. This makes it possible to integrate customer information, industry data, etc., quickly create high-quality hypothesis proposals, and make proposals that reflect user emotions.

[1299] "Means for collecting customer information" refers to devices and methods for collecting past transaction history, sales activity records, and basic information about customer companies.

[1300] "Industry data collection means" are devices or methods for collecting information on the latest trends, issues, success stories, etc. related to a particular industry.

[1301] "Means for collecting public information about companies" refers to devices and methods for extracting public information such as IR reports, press releases, and recruitment information from official company websites and financial information sites.

[1302] "Means for collecting product information" refers to devices and methods for collecting information such as the product's features, advantages, and application examples.

[1303] "Means for integrating collected information and storing information from multiple data sources in an integrated database" refers to a device or method for centrally managing information obtained from different data sources and storing it in a relational database.

[1304] "Means for analyzing collected text data using natural language processing algorithms to identify a company's needs and issues" refers to devices and methods for analyzing text data using natural language processing technology and extracting a company's specific needs and issues.

[1305] "Means for automatically generating hypothesis proposals using a generative AI model based on analysis results" refers to devices and methods for automatically generating hypothesis proposals using an artificial intelligence model based on the results of data analysis.

[1306] The "means for inserting a specific application example into the generated hypothesis proposal" refers to a device or method for adding a past application example to the generated hypothesis proposal.

[1307] The "means for outputting collected proposal contents" refers to a device or method for displaying or outputting the generated and edited proposal contents on the user's terminal.

[1308] "Means for using an emotion engine that recognizes a user's emotion from a voice input or text input, and adjusting the content of a hypothetical proposal based on the recognized emotion" refers to a device or method for analyzing a user's voice or text, identifying the emotion, and adjusting the content of a hypothetical proposal based on the emotion.

[1309] The "means for editing the output hypothetical proposal on the user terminal and saving it as a final proposal" refers to a device or method that allows a user to edit the output hypothetical proposal and save it as a final proposal.

[1310] This invention relates to a system that supports the formulation of hypothetical proposals in field sales, and is characterized by the fact that it collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates and outputs high-quality hypothetical proposals based on this information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the proposal content can be further improved.

[1311] Data collection

[1312] 1. Collection of Customer Information:

[1313] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history. Specifically, an API request is generated and retrieved using the HTTP protocol.

[1314] 2. Industry data collection:

[1315] The server collects information on the latest trends, challenges, and success stories related to the manufacturing industry from an industry information database, and accesses API endpoints to obtain the required data.

[1316] 3. Collecting public company information:

[1317] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from official corporate websites and financial information sites, analyzing the HTML structure and extracting text data.

[1318] 4. Product Information Collection:

[1319] The server executes SQL queries to retrieve product information (features, benefits, application examples) from the internal database, resulting in detailed product information for the proposed product.

[1320] Data Integration and Analysis

[1321] 1. Data integration:

[1322] The server consolidates the collected data into a centralized database. The information obtained from different data sources is stored in a relational database, and table relationships are established.

[1323] 2. Extracting useful data points:

[1324] The server runs SQL queries to extract useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[1325] 3. Analyzing needs using natural language processing:

[1326] The server uses NLP algorithms to analyze the collected text data and identify the company's needs and challenges. For example, it tokenizes the text of an IR report and extracts specific keywords and phrases.

[1327] Generate hypothesis proposals

[1328] 1. Automatic generation of hypothesis proposals:

[1329] The server generates hypothesis proposals optimized for each customer based on the analyzed data. The proposals are automatically generated using a generative AI model. For example, the server generates a proposal such as, "Company C is striving to streamline its new drug development projects, and introducing research management software will shorten development time by XX%."

[1330] 2. Insert application example:

[1331] The server inserts past application examples into the proposal, providing a concrete example such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%."

[1332] Use of emotion engine

[1333] 1. User Emotion Recognition:

[1334] The server converts the user's voice input into text using a speech recognition API and analyzes it using an emotion engine. For example, the voice input "I'm very interested in this proposal" can be recognized as "excited."

[1335] 2. Adjusting the proposal:

[1336] The server tailors its suggestions based on the perceived emotion: more detailed and emphatic if excited, and more concise if impatient.

[1337] Hypothesis proposal output

[1338] 1. Hypothesis proposal display:

[1339] The server outputs the generated and edited hypothetical proposal to the sales representative's terminal, which displays a preview of the proposal content.

[1340] 2. User edits:

[1341] The user (salesperson) checks the output hypothetical proposal and edits it as necessary, specifically adjusting the customer name and details of the proposal.

[1342] 3. Save the Final Proposal:

[1343] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[1344] Specific examples

[1345] Situation: Creating a hypothetical proposal for client company C

[1346] Client Company C: Major pharmaceutical company

[1347] Suggested product: Research management software

[1348] 1. Data Collection:

[1349] The server obtains the past transaction history and contact history of customer company C from the SFA system, thereby understanding company C's basic information and business negotiation history.

[1350] The server collects the latest trends and issues related to the pharmaceutical industry from an industry information database. For example, it collects trend information on "Accelerating drug development using AI."

[1351] The server retrieves IR reports and recruitment information for Company C from official websites and financial information sites, thereby understanding Company C's recent activities and growth strategies.

[1352] The server retrieves the features and benefits of its research management software from an internal database.

[1353] 2. Data integration and analysis:

[1354] The server consolidates the collected data into a centralized database, providing consolidated data on Company C's growth strategies and the latest trends in the industry.

[1355] Based on the IR report, the server analyzes that "improving the efficiency of new drug development projects is important."

[1356] 3. Hypothesis proposal generation:

[1357] The server automatically generates a hypothesis proposal such as, "Company C is trying to streamline its new drug development projects, and by introducing research management software, the development period will be shortened by XX%."

[1358] Past application examples will also be added, and specific examples such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%" will be inserted into the proposal.

[1359] 4. Use of Emotion Engine:

[1360] When the user makes a voice input, the server uses an emotion engine to recognize the user's emotion.

[1361] For example, if a user speaks in a bright tone, the system recognizes that emotion as "excitement" and adjusts the suggestions it presents to be more detailed and emphasized.

[1362] Conversely, if the user speaks in a tired tone, the system will recognize that emotion as "impatience" and adjust the suggestions to be concise and summarized.

[1363] 5. Hypothesis proposal output:

[1364] The server displays the generated hypothesis proposal on the sales representative's PC.

[1365] The user (sales representative) checks the proposal contents, edits them as necessary, and completes the final proposal.

[1366] The completed proposal is saved by the server in the customer folder for later use.

[1367] Prompt Sentence Examples

[1368] "What kind of research management software would you recommend for Client Company C's new drug development project?"

[1369] "Please tell me the proposal based on Company C's IR report."

[1370] "Give me an example of how you adjusted your proposal to take into account the salesperson's emotions."

[1371] In this way, the system can quickly and effectively create high-quality hypothetical proposals and provide proposals that reflect the user's emotions. As a result, the quality of proposals can be improved, leading to an increase in order acceptance rates and more efficient sales activities.

[1372] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1373] Step 1: Gather customer information

[1374] Input: The customer company ID is entered from the SFA system's API.

[1375] Specific operation: The server sends an HTTP request via the SFA system's API to obtain past transaction history, sales activity records, and basic information about the client company.

[1376] Data processing: Parse the received data in JSON format and extract and format the customer name, location, industry, transaction history, and contact history.

[1377] Output: Formatted customer information data is saved to temporary storage.

[1378] Step 2: Collect industry data

[1379] Input: The name of a specific industry (e.g., manufacturing) is entered.

[1380] What it does: The server accesses the API of an industry information database and sends a request to retrieve the latest trends, issues, and success stories.

[1381] Data processing: Compiling acquired information and formatting industry reports, research papers, and industry news into text format.

[1382] Output: The formatted industry data is saved to temporary storage.

[1383] Step 3: Gather public company information

[1384] Input: Enter the URL of the target company's official website or financial information site.

[1385] Specific operation: The server uses web scraping technology to obtain HTML pages and extracts IR reports, press releases, and recruitment information using BeautifulSoup and other tools.

[1386] Data processing: Structure the text data extracted from HTML and organize the necessary information.

[1387] Output: The formatted public information data is saved to temporary storage.

[1388] Step 4: Gather product information

[1389] Input: The name of the proposed product (e.g., production management software) is entered.

[1390] What happens: The server runs SQL queries against an internal database to search and retrieve product features, benefits, and use cases.

[1391] Data processing: Formatting the results of SQL queries into text and organizing product information.

[1392] Output: Formatted product information is saved to temporary storage.

[1393] Step 5: Integrate the data

[1394] Input: Customer information, industry data, public information, and product information collected at each step are entered.

[1395] What happens next: The server consolidates this information into a unified database, creating relationships between the database tables to create the consolidated data.

[1396] Data processing: Normalize data and remove redundancies.

[1397] Output: Consolidated data stored in a centralized database.

[1398] Step 6: Extract useful data points

[1399] Input: The integrated database is input.

[1400] What it does: The server runs SQL queries to extract specific data points, such as company growth strategies, current industry trends, or past purchase history.

[1401] Data processing: Aggregating extracted data and shaping it into a meaningful dataset.

[1402] Output: A useful dataset extracted.

[1403] Step 7: Analyze needs using natural language processing

[1404] Input: The extracted dataset is input.

[1405] What it does: The server uses NLP algorithms to analyze text data, such as a company's investor relations report, to tokenize it and extract key keywords and phrases.

[1406] Data processing: Using the results analyzed by NLP algorithms to identify the needs and challenges of the company.

[1407] Output: Identified needs and challenges.

[1408] Step 8: Automatic generation of hypotheses

[1409] Input: Identified needs and challenges are entered.

[1410] Specific operation: The server uses a generative AI model (e.g., GPT-3) to automatically generate hypothesis proposals based on identified needs and challenges.

[1411] Data processing: The proposed text is arranged in a natural format and converted into output data.

[1412] Output: Auto-generated hypothesis proposals.

[1413] Step 9: Inserting application examples

[1414] Input: The automatically generated hypothesis proposal is entered.

[1415] Specific operation: The server searches for relevant cases from a database of past application cases and inserts them into the automatically generated proposal text.

[1416] Data processing: Properly combine the proposal and examples to edit it into a more specific and persuasive proposal.

[1417] Output: A hypothetical proposal with concrete application examples inserted.

[1418] Step 10: Use the Emotion Engine

[1419] Input: User voice or text input is entered.

[1420] How it works: The server converts speech into text using a speech recognition API, analyzes it using an emotion engine, and adjusts the suggestions based on the analysis results.

[1421] Data processing: Adjust the details and summary of the suggestion based on the user's emotions (e.g., excitement, impatience).

[1422] Output: The adjusted proposal.

[1423] Step 11: Output of hypothesis proposals

[1424] Input: The adjusted hypothesis proposal is entered.

[1425] Specific operations: The server displays the adjusted hypothesis proposal on the terminal, and the terminal displays the proposal content via a user interface.

[1426] Data processing: Formatting the proposal for display on the screen.

[1427] Output: The proposed hypotheses displayed in the user interface.

[1428] Step 12: User Editing

[1429] Input: A GUI is entered that allows the user to edit the displayed hypothesis proposal.

[1430] Specific operation: The user (salesperson) edits the proposal on the terminal, specifically by correcting the company name and numerical data through the input form.

[1431] Data processing: Update the database in real time to save edits.

[1432] Output: Edited hypothesis proposal.

[1433] Step 13: Save your final proposal

[1434] Input: The edited hypothesis proposal is entered.

[1435] Specific operation: The user saves the edited hypothetical proposal as a final proposal. The server saves the final proposal in PDF format in the customer folder.

[1436] Data processing: Organizing the saved proposals systematically and setting up indexes for future use.

[1437] Output: The final proposal is saved in the customer folder.

[1438] (Application example 2)

[1439] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1440] In today's customer service environment, it is difficult for store clerks to recommend products that are appropriate for each individual customer. To solve this problem, store clerks need to instantly understand a customer's past purchase history and preference data, and then make optimal product recommendations based on the customer's current emotional state. However, relying solely on human intervention makes it difficult to respond quickly and accurately, and it is difficult to expect improved customer satisfaction or increased sales.

[1441] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for collecting customer information, a means for collecting industry data, a means for collecting public company information, a means for collecting product information, a means for integrating and analyzing the collected information, a means for automatically generating hypothetical proposals based on the analysis results, a means for recognizing the user's emotions and adjusting the proposal content, and a means for outputting the generated hypothetical proposals. This enables store clerks to make optimal product proposals to customers in real time through the smart glasses.

[1442] "Means of collecting customer information" refers to functions for obtaining basic information about customers, purchase history, preference data, etc.

[1443] "Means for collecting industry data" is a function for collecting information such as trends, challenges, and success stories related to a specific industry.

[1444] "Means for collecting public information about companies" refers to functions for obtaining public information such as IR reports and press releases from official company websites and financial information sites.

[1445] "Means of collecting product information" refers to a function for obtaining information about the features, advantages, and application examples of your company's products.

[1446] "Means for integrating and analyzing collected information" refers to a function for integrating data obtained from multiple sources into a centralized database and analyzing it.

[1447] The "means for automatically generating hypothesis proposals based on analysis results" is a function for automatically generating optimal hypothesis proposals based on the integrated data.

[1448] The "means for recognizing the user's emotions and adjusting the content of suggestions" is a function for analyzing the user's voice and facial expressions to recognize their emotions and change the content of suggestions accordingly.

[1449] The "means for outputting the generated hypothesis proposal" is a function for finally displaying or providing the generated hypothesis proposal.

[1450] This invention is a system that uses smart glasses to support store clerks in real time in making optimal product recommendations when serving customers. This system integrates and analyzes customer information, industry data, public company information, and product information, and is characterized by recognizing the user's emotions and adjusting the content of recommendations accordingly.

[1451] The server has means for collecting customer information (e.g., acquiring customers' past purchase history and preference data), means for collecting industry data (e.g., collecting trends and success stories in a particular industry), means for collecting public information about companies (e.g., acquiring public information from official websites and financial information sites), and means for collecting product information (e.g., acquiring the features and benefits of a company's products).

[1452] The server then integrates the collected information and analyzes it using a natural language processing algorithm. Based on the analysis results, it automatically generates a hypothesis proposal, which is then accompanied by specific application examples. Furthermore, to recognize the user's emotions, the server utilizes an emotion engine that recognizes emotions from the camera and voice inputs installed in the smart glasses. This engine analyzes the tone of voice and facial expressions to recognize the user's emotions.

[1453] For example, when a user serves a customer through smart glasses, the server analyzes the customer's information in real time, generates optimal product recommendations based on that information, and displays them on the smart glasses' display. At the same time, the server analyzes the user's voice and facial expressions and adjusts the recommendations according to their emotions.

[1454] The following software and hardware are mainly used for program processing:

[1455] Smart glasses: Capture customer faces and analyze images

[1456] FER library: Used for emotion recognition processing

[1457] TfidfVectorizer: Used to analyze customer and product data

[1458] KMeans clustering: used to select the best product

[1459] pyttsx3: Used for audio output

[1460] This system allows store clerks to use the smart glasses to make product recommendations in real time based on the customer's needs and emotions. For example, if a customer is looking for a relaxing effect, the server will suggest "aromatherapy oil with a relaxing effect" based on past preference data and product information. Furthermore, if the user's emotion is recognized as "excitement," the server will display the recommendation in more detail and with more emphasis.

[1461] Here is an example prompt:

[1462] Prompt statement:

[1463] To make product recommendations, you will suggest the best products based on customer preferences and product data, and adjust the recommendations based on customer sentiment.

[1464] Customer ID: 12345

[1465] Customer preference: Relaxing aromatherapy

[1466] Product information: Lavender essential oil (relaxing effect), Citrus mixed oil (energizing effect)

[1467] As a result, efficient and accurate product suggestions can be made when dealing with customers in physical stores.

[1468] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1469] Step 1:

[1470] The server executes the steps to collect customer information through API. In this step, it obtains the customer's past purchase history and preference data. Specifically, it sends an API request to obtain customer data and stores it in a database. The input is the customer ID, and the output is customer information.

[1471] Step 2:

[1472] The server executes the industry data collection process. It collects information on trends, issues, and success stories related to a specific industry from an industry information database. In this step, industry-related data is acquired and integrated into the database. The input is the industry name and related keywords, and the output is industry data.

[1473] Step 3:

[1474] The server runs a method to collect public information about companies. It uses web scraping technology to obtain public information such as IR reports and press releases from official websites and financial information sites. The input is the company name and related URLs, and the output is the company's public information.

[1475] Step 4:

[1476] The server executes the process of collecting information about the company's products, such as their features, benefits, and application examples, from the company's database. The input is the product ID and product name, and the output is the product information.

[1477] Step 5:

[1478] The server then integrates the collected information and analyzes it using natural language processing algorithms. This step involves extracting and analyzing data points from multiple sources stored in an integrated database. The input is the integrated database, and the output is the analysis results.

[1479] Step 6:

[1480] The server executes a means to automatically generate hypothetical proposals based on the analysis results. Specifically, it identifies the optimal product that meets the customer's needs and generates hypothetical proposals based on that. It uses NLP algorithms and clustering technology to select the optimal product and generate hypothetical proposals. The input is the analysis results, and the output is hypothetical proposals.

[1481] Step 7:

[1482] The server recognizes the user's emotions and performs processing to adjust the suggestions according to those emotions. It uses the camera and voice inputs installed in the smart glasses to recognize emotions using an emotion engine. The input is image and voice data from the smart glasses, and the output is the recognized emotion.

[1483] Step 8:

[1484] The server adjusts the content of the hypothesis proposal according to the emotion and generates the final proposal. If the user is excited, the proposal is adjusted to be more detailed and emphasized, and if the user is impatient, the proposal is made brief. The input is the recognized emotion and the hypothesis proposal, and the output is the adjusted hypothesis proposal.

[1485] Step 9:

[1486] The server executes a means for outputting the generated hypothesis proposal, and displays the adjusted hypothesis proposal on the display of the smart glasses so that the user can confirm its content. The input is the adjusted hypothesis proposal, and the output is the proposal content displayed on the smart glasses.

[1487] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1488] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1489] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1490] [Fourth embodiment]

[1491] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1492] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1493] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1494] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1495] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1496] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1497] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1498] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1499] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1500] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1501] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1502] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1503] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1504] This invention relates to a system that supports the creation of hypothetical proposals in field sales, and it collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates and outputs high-quality hypothetical proposals based on that information. Below, we will explain the system's program processing and provide concrete examples.

[1505] System program processing

[1506] 1. Data Collection:

[1507] The server retrieves sales data from the SFA system, which refers to records of past transactions and sales activities related to client companies.

[1508] The server collects the latest trends, challenges, success stories, and other information related to manufacturing from an industry information database.

[1509] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from companies' official websites and financial information sites.

[1510] The server obtains product information such as the features, advantages, and application examples of the proposed product from an internal database or from product personnel.

[1511] 2. Data integration and analysis:

[1512] The server integrates the various data collected above into a centralized database.

[1513] The server extracts sales-useful data points (e.g., growth strategies, industry trends, past purchase history, etc.) from the integrated database.

[1514] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges.

[1515] 3. Hypothesis proposal generation:

[1516] The server automatically generates hypothesis proposals optimized for each customer based on the collected, integrated, and analyzed data.

[1517] The hypothetical proposal includes the customer's specific challenges, industry trends, and the benefits of the proposed product.

[1518] 4. Hypothesis proposal output:

[1519] The server outputs the generated hypothesis proposal to the sales representative's terminal (e.g., PC or tablet).

[1520] The sales representative checks the proposal on the terminal, edits and saves it as necessary, and completes the final proposal.

[1521] Specific examples

[1522] Situation: Creating a hypothetical proposal for client company A

[1523] Customer Company A: Medium-sized manufacturing company

[1524] Proposed product: Production management software

[1525] 1. Data Collection:

[1526] The server obtains the past transaction history and contact history of customer company A from the SFA system.

[1527] The server collects the latest trends and issues related to manufacturing from an industry information database.

[1528] The server retrieves Company A's IR report and recent news articles from its official website and financial information sites.

[1529] The server retrieves product information such as the features and application examples of the production management software from the company's internal database.

[1530] 2. Data integration and analysis:

[1531] The server integrates the collected data into a centralized database and extracts data points related to client company A's growth strategy and the latest trends in the manufacturing industry.

[1532] The server analyzes the details of Company A's new capital investment from the IR report and determines the applicability of production management software.

[1533] 3. Hypothesis proposal generation:

[1534] The server automatically generates hypothetical proposals such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%."

[1535] Proposals will include concrete examples of application (e.g., success stories from other manufacturing companies).

[1536] 4. Hypothesis proposal output:

[1537] The server displays the generated hypothesis proposal on the sales representative's terminal.

[1538] The user (sales representative) checks the proposal contents, edits them as necessary, and creates a proposal document.

[1539] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[1540] The processing flow will be explained below.

[1541] Step 1:

[1542] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[1543] Step 2:

[1544] The server connects to an industry information database to gather information on the latest trends, challenges, and success stories related to the target industry (e.g., manufacturing), including specific industry reports, research papers, and industry news.

[1545] Step 3:

[1546] The server uses web scraping technology to obtain public information about the company (e.g., IR reports, press releases, and recruitment information) from the company's official website and financial information site. In this step, the contents of the latest IR reports and press releases are captured in text format.

[1547] Step 4:

[1548] The server obtains product information such as the features, advantages, and application examples of the proposed product (e.g., production management software) from an internal database or from product personnel.

[1549] Step 5:

[1550] The server consolidates the various data collected into a centralized database that includes customer information, industry information, company disclosures, and product information.

[1551] Step 6:

[1552] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[1553] Step 7:

[1554] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges, analyzing IR reports and press releases to extract specific needs such as "the need to expand production capacity."

[1555] Step 8:

[1556] The server automatically generates a hypothesis proposal based on the analysis results. For example, it creates a proposal such as, "Company A will expand its production capacity by introducing production management software, which will reduce annual costs by XX%."

[1557] Step 9:

[1558] The server inserts specific application examples into the generated hypothesis proposal. For example, it adds a specific example such as "Through the implementation example at another company B, an improvement in production efficiency of XX% is expected."

[1559] Step 10:

[1560] The server outputs the generated and edited hypothesis proposal to the sales representative's device (PC, smartphone, tablet, etc.), where a preview of the proposal is displayed.

[1561] Step 11:

[1562] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[1563] Step 12:

[1564] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[1565] In this way, the HYPOS system quickly creates high-quality hypothetical proposals and provides them to customers based on their specific needs, which is expected to improve the quality of proposals, increase order acceptance rates, and streamline sales activities.

[1566] Example 1

[1567] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1568] In the past, the creation of hypothesis proposals in field sales required manual collection, integration, and analysis of information from a wide variety of data sources, which resulted in inefficiency and a lack of accuracy. Furthermore, the speed and consistency of proposal creation by individual sales representatives was also an issue. As a result, the quality of proposals declined, making it difficult to improve conversion rates.

[1569] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1570] In this invention, the server includes means for acquiring customer information, means for acquiring industry data, means for acquiring public company information, means for acquiring product information, means for integrating the acquired information into a centralized database, means for analyzing the integrated information, means for analyzing company needs and issues using a natural language processing algorithm, means for automatically generating a hypothesis proposal based on the analysis results using a generation AI model, and means for outputting the generated hypothesis proposal to a user's terminal. This automates the proposal creation process and makes it possible to provide hypothesis proposals quickly and with high accuracy.

[1571] 1. "Customer Information" means information related to a customer company regarding its business activities and transaction history.

[1572] 2. "Industry Data" means information about trends, challenges, success stories, and other information related to a particular industry sector.

[1573] 3. "Public corporate information" refers to information officially published by a company, such as IR reports, press releases, and recruitment information.

[1574] 4. "Product Information" means information about the features, benefits, applications, etc. of the products offered.

[1575] 5. "Means of collection" refers to the technical methods and devices used to automatically collect the required information from each data source.

[1576] 6. A "centralized database" is a database that uniformly manages and stores information collected from multiple data sources.

[1577] 7. "Integration means" means the technical methods or devices used to aggregate data collected from different sources into a centralized database.

[1578] 8. “Analytical tools” refers to algorithms or devices used to analyze collected and integrated data and extract useful data points or patterns.

[1579] 9. "Natural language processing algorithm" refers to a technical method for analyzing text data and understanding its meaning and intent.

[1580] 10. "Generative AI model" refers to a model that uses artificial intelligence technology to automatically generate hypotheses and proposals for specific problems.

[1581] 11. "User Device" refers to a device, such as a computer or tablet, used by a sales representative.

[1582] 12. "Output means" refers to the technical methods or devices for displaying the generated hypothesis proposals on the user's terminal or saving them as a file.

[1583] This invention is a system that supports the creation of hypothetical proposals in field sales, collecting, integrating, and analyzing customer information, industry data, public company information, and product information, and automatically generating and outputting high-quality hypothetical proposals based on that information. To implement this system, the following hardware and software are used to process and calculate data.

[1584] Hardware used

[1585] Server: A server equipped with a high-performance processor and large memory capacity, which allows for efficient processing and analysis of large amounts of data.

[1586] Device: PC or tablet used by sales representatives. These devices are used to check, edit, and save hypothesis proposals.

[1587] Software used

[1588] SFA system: Manage customer information using the SalesForce Automation system.

[1589] Industry Information Database: A database that provides industry data such as trends and issues related to the manufacturing industry.

[1590] Web scraping software: BeautifulSoup, Selenium, and other similar software are used to automatically collect publicly available information from companies.

[1591] Natural Language Processing (NLP) algorithms: Used to analyze text data and understand a company's needs and challenges.

[1592] Generative AI model: Uses generative models such as GPT-4 to automatically generate hypothesis proposals.

[1593] Data processing and calculation

[1594] Data collection: The server collects various data using the SFA system, industry information database, and web scraping. It obtains customer information, industry data, company public information, and product information, and automatically collects data from each data source.

[1595] Data integration: The server integrates the collected data into a centralized database, unifying data of different formats and content.

[1596] Data analysis: The server analyzes the integrated data using natural language processing algorithms to extract the company's needs and challenges, and then uses a generative AI model to generate hypothesis proposals based on the data.

[1597] Proposal output: The server outputs the generated hypothetical proposal to the sales representative's terminal. The sales representative checks the proposal content on the terminal and edits and saves it as necessary.

[1598] Specific examples

[1599] Situation: Creating a hypothetical proposal for client company A

[1600] Customer Company A: Medium-sized manufacturing company

[1601] Proposed product: Production management software

[1602] 1. Data Collection:

[1603] The server obtains the past transaction history and contact history of customer company A from the SFA system.

[1604] The server collects the latest trends and issues related to manufacturing from an industry information database.

[1605] The server retrieves Company A's IR report and recent news articles from its official website and financial information sites.

[1606] The server retrieves product information such as the features and application examples of the production management software from the company's internal database.

[1607] 2. Data integration and analysis:

[1608] The server integrates the collected data into a centralized database and extracts data points related to client company A's growth strategy and the latest trends in the manufacturing industry.

[1609] The server analyzes the details of Company A's new capital investment from the IR report and determines the applicability of production management software.

[1610] 3. Hypothesis proposal generation:

[1611] The server automatically generates hypothetical proposals such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%." The proposals include specific application examples (e.g., success stories from other manufacturing companies).

[1612] 4. Hypothesis proposal output:

[1613] The server displays the generated hypothetical proposal on the sales representative's terminal. The user (sales representative) checks the proposal content, edits it as necessary, and creates a proposal.

[1614] Prompt Sentence Examples

[1615] Example 1: Data collection for customer company A

[1616] "Collect information about Client Company A's past transaction history, the latest industry trends, public information about the company, and the features of its production management software. Please explain the source of each information and how you obtained it."

[1617] Example 2: Generating hypothesis proposals

[1618] "Generate a hypothetical proposal for Client Company A, including the cost reduction effects of introducing production management software. Please also consider detailed information about new capital investment."

[1619] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[1620] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1621] System program processing flow

[1622] Step 1: Gather customer information

[1623] Specific operation: The server obtains customer information from the SFA system via API.

[1624] Input: Basic information such as customer company A's ID and name

[1625] Data processing / calculation: By calling the API, records of past transactions and sales activities of client company A are obtained and converted into a database format.

[1626] Output: Saved in the database as "Customer A_Transaction Data".

[1627] Step 2: Gather industry information

[1628] Specific operations: The server executes queries against an industry information database to gather the required information.

[1629] Input: Query criteria related to manufacturing industry

[1630] Data processing / calculation: Extract the latest trends, challenges, and success stories in the manufacturing industry from the query results, convert them into a format, and store them in a database.

[1631] Output: Saved in the database as "Manufacturing_Trend_Data".

[1632] Step 3: Gather public company information

[1633] Specific operations: The server uses web scraping software to collect information from official company websites and financial information sites.

[1634] Input: URL of Company A's official website or financial information site

[1635] Data processing / calculation: Analyze the HTML structure of web pages, extract IR reports, press releases, and recruitment information, convert them into text format, and analyze them to extract important information.

[1636] Output: Saved in the database as "Company A_Public Information".

[1637] Step 4: Gather product information

[1638] Specific operation: The server accesses the company's internal database to obtain information such as the features, benefits, and application examples of the production management software.

[1639] Input: Query terms related to production management software

[1640] Data processing / calculation: Extract product information through database queries, convert it into the appropriate format and store it.

[1641] Output: Saved as "Production Management Software_Features" data.

[1642] Step 5: Integrate the data

[1643] Specific operation: The server consolidates all the data collected above into a centralized database.

[1644] Input: "Customer A_Transaction Data", "Manufacturing Industry_Trend Data", "Company A_Public Information", "Production Management Software_Features"

[1645] Data processing / calculation: Each dataset is converted into a unified format and integrated into a centralized database.

[1646] Output: All data stored in a consolidated database.

[1647] Step 6: Analyze the data

[1648] What it does: The server extracts useful data points from the aggregated data and analyzes them using natural language processing algorithms.

[1649] Input: All data in the integrated database

[1650] Data processing / calculation: Execute natural language processing algorithms to analyze and extract corporate needs and issues.

[1651] Output: Saved as "Company A_Needs Analysis Results".

[1652] Step 7: Generate hypothesis proposals

[1653] Specific operation: The server automatically generates hypothesis proposals using a generative AI model.

[1654] Input: "Company A_Needs Analysis Results" and other integrated data

[1655] Data processing / computation: Using a generative AI model (e.g., GPT-4), generate hypothesis proposals based on the analyzed data.

[1656] Output: Saved as "Hypothesis Proposal".

[1657] Step 8: Output of hypothesis proposals

[1658] Specific operation: The server displays the generated hypothesis proposal on the sales representative's terminal.

[1659] Input: "Hypothesis Proposal"

[1660] Data processing / calculation: Convert the data format into a format suitable for the device used by the sales representative and transfer it.

[1661] Output: The proposal is displayed on the sales representative's terminal.

[1662] In this way, high-quality hypothetical proposals can be created quickly and provided to meet the specific needs of customers. This system is expected to improve the quality of proposals, increase the rate of orders, and make sales activities more efficient.

[1663] (Application example 1)

[1664] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1665] In field sales, generating optimal hypothesis proposals for each customer quickly and with high quality is extremely time-consuming, placing a heavy burden on sales representatives. Furthermore, there is a lack of an integrated system for effectively collecting and analyzing customer information and industry data to make accurate proposals, making it difficult to improve order rates and streamline sales activities.

[1666] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1667] In this invention, the server includes means for collecting customer information, means for collecting industry data, means for collecting public company information, means for collecting product information, means for integrating and analyzing the collected information, means for automatically generating a hypothetical proposal based on the analysis results, means for outputting the generated hypothetical proposal, means for generating an appropriate hypothetical proposal from the customer information and industry data using a generative AI model, and means for supplying input data to the generative AI model using prompt statements. This makes it possible to effectively collect and analyze customer information and industry data and quickly generate individually optimized hypothetical proposals.

[1668] "Customer information" refers to data relating to a customer, including past transaction history, contact history, purchasing trends, and the like.

[1669] "Industry Data" is data that includes statistics, trends, challenges, success stories, etc. related to a particular industry.

[1670] "Corporate public information" refers to information such as IR reports, press releases, and recruitment information that is officially released by a company.

[1671] "Product information" is detailed data about a product, such as its features, benefits, and application examples.

[1672] "Collection" is the act of gathering necessary data and information from various sources.

[1673] "Integration" is the act of centralizing multiple collected data.

[1674] "Analysis" is the act of using collected and integrated data to derive specific patterns and meanings.

[1675] A "hypothetical proposal" is a proposal that automatically generates solutions and strategies proposed to address customer issues and needs.

[1676] A "generative AI model" is an algorithm or system that uses artificial intelligence to process data and generate new information or suggestions.

[1677] A "prompt" is a document or text that instructs the input data for a generative AI model.

[1678] A "natural language processing algorithm" is an algorithm for analyzing and understanding human language, and is a technology used to analyze collected information.

[1679] This invention is a system that collects, integrates, and analyzes customer information, industry data, public company information, and product information, and automatically generates high-quality hypothesis proposals based on that information. This system is composed of three main players: a server, a terminal, and a user.

[1680] The server first collects customer information. This is done by retrieving past transaction history and contact history from the SFA system. Industry data is also collected, and the latest trends, issues, and success stories are retrieved from industry information databases. Next, publicly available company information is obtained using web scraping technology. Specifically, IR reports, press releases, and recruitment information are collected from official company websites and financial information sites. Product information such as the features, benefits, and application examples of the proposed product is also obtained from internal databases and product personnel.

[1681] The server integrates the various collected data into a centralized database. From this integrated database, the server extracts data points useful for sales, such as customer growth strategies, industry trends, and past purchase history. The server also uses natural language processing (NLP) algorithms to analyze the needs and challenges of companies.

[1682] Next, a hypothesis proposal is automatically generated based on the analysis results. During this process, a generative AI model is utilized to generate appropriate hypothesis proposals from customer information and industry data. Input data is provided to the generative AI model using prompt statements. The generated hypothesis proposal includes the customer's specific challenges, industry trends, and the benefits of the proposed product, and also includes specific application examples.

[1683] The generated hypothetical proposal is output from the server to the sales representative's device (e.g., PC or tablet), where the sales representative can check the proposal content, edit and save it as necessary, and complete the final proposal.

[1684] The implementation of this system uses the following specific hardware and software: A PC or tablet is used as the hardware, and Python 3.x, the requests library (to process HTTP requests), BeautifulSoup (for web scraping), pandas (for data manipulation), and scikit-learn (a machine learning library).

[1685] As a specific example, consider the case of creating a hypothetical proposal for Client Company A. Client Company A is a mid-sized manufacturing company, and the proposed product is production management software. The server obtains Client Company A's past transaction history and contact history from the SFA system, and collects the latest trends and issues related to the manufacturing industry from an industry information database. In addition, it obtains Company A's IR reports and recent news articles from official websites and financial information sites, and obtains product information such as the features and application examples of the production management software from an internal database. By integrating and analyzing this data, a hypothetical proposal is automatically generated, such as, "Company A is planning to expand its production capacity, and by introducing production management software, annual cost reduction effects are expected to be XX%."

[1686] An example of a prompt is, "Please generate a hypothesis proposal that corresponds to the latest industry trends based on the autonomous driving products that client company A has purchased in the past." By inputting this prompt into the generative AI model, it is possible to generate an optimal hypothesis proposal.

[1687] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1688] Step 1:

[1689] The server uses the means for collecting customer information to obtain sales data from the SFA system. Specifically, it obtains records of past transactions and sales activities related to the client company. The input is the customer's ID and name, and the output is detailed data on past transaction history and sales activities. This allows the server to understand the customer's purchasing patterns and areas of interest.

[1690] Step 2:

[1691] The server uses the industry data collection means to collect industry data such as the latest trends, issues, and success stories from the industry information database. The input is a data request for a specific industry, and the output is the latest information and statistical data for that industry. This allows you to understand the trends and major issues of the entire industry.

[1692] Step 3:

[1693] The server uses web scraping technology to collect publicly available information from companies, such as IR reports, press releases, and recruitment information, from official company websites and financial information sites. The input is the company name and URL, and the output is the collected, publicly available information from the company. This allows us to understand the company's current situation and future strategies.

[1694] Step 4:

[1695] The server uses a means of collecting product information to obtain product information such as the features, benefits, and use cases of the proposed product from an internal database or product personnel. The input is the product name and product category, and the output is detailed information about the product. This allows the benefits and use cases of the proposed product to be clarified.

[1696] Step 5:

[1697] The server consolidates the various data collected above and stores it in a centralized database. The inputs are data sets of customer information, industry data, company public information, and product information, and the output is an integrated database. This allows for smooth data access and analysis.

[1698] Step 6:

[1699] The server extracts data points useful to sales from the integrated database. Specifically, it extracts data points such as customer growth strategies, industry trends, and past purchase history. The input is a query from the integrated database, and the output is a list of useful data points. This allows efficient extraction of only the important information.

[1700] Step 7:

[1701] The server analyzes the collected and integrated information using natural language processing (NLP) algorithms. The input is a dataset from the integrated database, and the output is the analysis results (e.g., the company's needs and challenges). This allows for the extraction of meaningful information from unstructured data.

[1702] Step 8:

[1703] The server automatically generates hypothesis proposals using a generative AI model based on the analysis results. The input is the analysis results and prompt text, and the output is an automatically generated hypothesis proposal. Input data is supplied to the generative AI model using the prompt text, and appropriate hypothesis proposals are generated from customer information and industry data.

[1704] Step 9:

[1705] The server inserts specific application examples into the generated hypothesis proposal. The input is a hypothesis proposal and an application example, and the output is a hypothesis proposal including an application example. This makes the proposal more specific and persuasive.

[1706] Step 10:

[1707] The server displays the generated hypothetical proposal on the sales representative's terminal. The input is the final hypothetical proposal, and the output is a proposal that can be viewed on the terminal. The sales representative checks the proposal content, edits and saves it as necessary, and completes the final proposal. This is expected to improve the quality of proposals, increase the order rate, and make sales activities more efficient.

[1708] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1709] This invention relates to a system that supports the formulation of hypothetical proposals in field sales. It is characterized by collecting, integrating, and analyzing customer information, industry data, public company information, and product information, and automatically generating and outputting high-quality hypothetical proposals based on that information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the quality of the proposals can be further improved. Below, we will explain the system's program processing and provide concrete examples.

[1710] System program processing

[1711] 1. Data Collection:

[1712] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[1713] The server collects information on the latest trends, challenges, and success stories related to manufacturing from industry information databases, including specific industry reports, research papers, and industry news.

[1714] The server uses web scraping technology to obtain public information such as IR reports, press releases, and recruitment information from companies' official websites and financial information sites. In this step, the contents of the latest IR reports and press releases are imported in text format.

[1715] The server obtains product information such as the features, advantages, and application examples of the proposed product (e.g., production management software) from an internal database or from product personnel.

[1716] 2. Data integration and analysis:

[1717] The server integrates the various data collected above into a centralized database that compiles customer information, industry information, company disclosures, and product information.

[1718] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[1719] The server uses natural language processing (NLP) algorithms to analyze a company's needs and challenges, analyzing IR reports and press releases to extract specific needs such as "the need to expand production capacity."

[1720] 3. Hypothesis proposal generation:

[1721] Based on the collected, integrated, and analyzed data, the server automatically generates a hypothetical proposal optimized for each customer, including the customer's specific challenges, industry trends, and the benefits of the proposed product.

[1722] The server inserts specific application examples into the generated hypothetical proposal. For example, it adds a specific example such as "Through the implementation example at another company B, production efficiency is expected to improve by XX%."

[1723] 4. Use of Emotion Engine:

[1724] The server runs an emotion engine that recognizes emotions from the user's voice and text input. The engine analyzes the tone of the voice and the text content to identify the user's emotions (e.g., excitement, interest, impatience, etc.).

[1725] The server adjusts the suggestions based on the perceived emotion, for example, increasing emphasis in the suggestions if the user is excited, or simplifying the suggestions if the user is impatient.

[1726] 5. Hypothesis proposal output:

[1727] The server outputs the generated and edited hypothesis proposal to the sales representative's device (e.g., PC or tablet), where a preview of the proposal is displayed.

[1728] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[1729] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[1730] Specific examples

[1731] Situation: Creating a hypothetical proposal for client company C

[1732] Client Company C: Major pharmaceutical company

[1733] Suggested product: Research management software

[1734] 1. Data Collection:

[1735] The server obtains the past transaction history and contact history of customer company C from the SFA system, thereby understanding company C's basic information and business negotiation history.

[1736] The server collects the latest trends and issues related to the pharmaceutical industry from an industry information database. For example, it collects trend information on "Accelerating drug development using AI."

[1737] The server retrieves IR reports and recruitment information for Company C from official websites and financial information sites, thereby understanding Company C's recent activities and growth strategies.

[1738] The server retrieves the features and benefits of its research management software from an internal database.

[1739] 2. Data integration and analysis:

[1740] The server consolidates the collected data into a centralized database, providing consolidated data on Company C's growth strategies and the latest trends in the industry.

[1741] Based on the IR report, the server analyzes that "improving the efficiency of new drug development projects is important."

[1742] 3. Hypothesis proposal generation:

[1743] The server automatically generates a hypothesis proposal such as, "Company C is trying to streamline its new drug development projects, and by introducing research management software, the development period will be shortened by XX%."

[1744] Past application examples will also be added, and specific examples such as "By introducing this at another pharmaceutical company D, development time was reduced by XX%" will be inserted into the proposal.

[1745] 4. Use of Emotion Engine:

[1746] When the user makes a voice input, the server uses an emotion engine to recognize the user's emotion.

[1747] For example, if a user speaks in a bright tone, the system recognizes that emotion as "excitement" and adjusts the suggestions it presents to be more detailed and emphasized.

[1748] Conversely, if the user speaks in a tired tone, the system will recognize that emotion as "impatience" and adjust the suggestions to be concise and summarized.

[1749] 5. Hypothesis proposal output:

[1750] The server displays the generated hypothesis proposal on the sales representative's PC.

[1751] The user (sales representative) checks the proposal contents, edits them as necessary, and completes the final proposal.

[1752] The completed proposal is saved by the server in the client's folder for later use.

[1753] In this way, the HYPOS system can quickly create high-quality hypothetical proposals and adjust the proposal content based on the user's emotions, allowing it to provide customers with optimal proposals that meet their specific needs. This is expected to improve the quality of proposals, increase order rates, and streamline sales activities.

[1754] The processing flow will be explained below.

[1755] Step 1:

[1756] The server retrieves past transaction history and sales activity records for client companies through the SFA system's API. This data includes basic customer information (company name, location, industry), transaction history, and contact history.

[1757] Step 2:

[1758] The server connects to an industry information database to collect information on the latest trends, challenges, and success stories related to the pharmaceutical industry, including specific industry reports, research papers, and industry news.

[1759] Step 3:

[1760] The server uses web scraping technology to obtain public information about the company (e.g., IR reports, press releases, and recruitment information) from the company's official website and financial information site. In this step, the contents of the latest IR reports and press releases are captured in text format.

[1761] Step 4:

[1762] The server retrieves product information such as features, benefits, and application examples of the proposed product (e.g., research management software) from an internal database or product personnel.

[1763] Step 5:

[1764] The server consolidates the various data collected into a centralized database that includes customer information, industry information, company disclosures, and product information.

[1765] Step 6:

[1766] The server extracts useful data points from the integrated database, such as identifying a company's growth strategy, current industry trends, and past purchase history.

[1767] Step 7:

[1768] The server uses natural language processing (NLP) algorithms to analyze the needs and challenges of companies, analyzing IR reports and press releases to extract specific needs such as "improving the efficiency of new drug development projects is important."

[1769] Step 8:

[1770] Based on the collected, integrated, and analyzed data, the server automatically generates a hypothetical proposal optimized for each company, including the customer's specific challenges, industry trends, and the benefits of the proposed product.

[1771] Step 9:

[1772] The server inserts specific application examples into the generated hypothesis proposals, for example, adding a specific example such as "Through implementation examples at other pharmaceutical companies, development time was shortened by XX%."

[1773] Step 10:

[1774] The server runs an emotion engine that recognizes emotions from the user's voice and text input. The engine analyzes the tone of the voice and the text content to identify the user's emotions (e.g., excitement, interest, impatience, etc.).

[1775] Step 11:

[1776] The server adjusts the suggestions based on the perceived emotion, for example, increasing emphasis in the suggestions if the user is excited, or simplifying the suggestions if the user is impatient.

[1777] Step 12:

[1778] The server outputs the generated and edited hypothesis proposal to the sales representative's device (e.g., PC or tablet), where a preview of the proposal is displayed.

[1779] Step 13:

[1780] The user (sales representative) checks the output hypothetical proposal and edits it as necessary, including adjusting the specific customer names and other details.

[1781] Step 14:

[1782] The user saves the edited proposal as a final proposal. The server stores the saved proposal in the client folder and manages it for future use.

[1783] In this way, the HYPOS system can quickly create high-quality hypothetical proposals and adjust the proposal content based on the user's emotions, thereby providing customers with optimal proposals that meet their specific needs. This is expected to improve the quality of proposals, increase order rates, and streamline sales activities.

[1784] Example 2

[1785] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1786] In traditional field sales, it was difficult to properly collect and integrate customer information, industry data, public information, and product information, and then quickly generate high-quality hypothetical proposals based on that information. It was also difficult to incorporate user sentiment into these proposals, resulting in problems with not being able to provide optimal proposals that fully meet the user's needs. Furthermore, the lack of a means to efficiently analyze the collected information often led to a decline in the quality of proposals and the efficiency of sales activities.

[1787] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1788] In this invention, the server includes means for collecting customer information, means for collecting industry data, means for collecting public company information, means for collecting product information, means for integrating the collected information and storing information from multiple data sources in an integrated database, means for analyzing the collected text data using a natural language processing algorithm to identify company needs and issues, means for automatically generating a hypothesis proposal using a generative AI model based on the analysis results, means for inserting specific application examples into the generated hypothesis proposal, means for outputting the collected proposal content, means for using an emotion engine that recognizes user emotions from voice input or text input and adjusting the hypothesis proposal content based on the recognized emotions, and means for editing the output hypothesis proposal on a user terminal and saving it as a final proposal. This makes it possible to integrate customer information, industry data, etc., quickly create high-quality hypothesis proposals, and make proposals that reflect user emotions.

[1789] "Means for collecting customer information" refers to devices and methods for collecting past transaction history, sales activity records, and basic information about customer companies.

[1790] "Industry data collection means" are devices or methods for collecting information on the latest trends, issues, success stories, etc. related to a particular industry.

[1791] "Means for collecting public information about companies" refers to devices and methods for extracting public information such as IR reports, press releases, and recruitment information from official company websites and financial information sites.

[1792] "Me...

Claims

1. A means of collecting customer information; a means of collecting industry data; means of collecting public information about companies; a means for collecting product information; A means of integrating and analyzing the collected information; and A means for automatically generating hypothesis proposals based on the analysis results; A means for outputting the generated hypothesis proposal; A system including:

2. 10. The system of claim 1, further comprising means for analyzing the collected information using a natural language processing algorithm.

3. 2. The system according to claim 1, further comprising means for inserting specific application examples into the hypothetical proposals generated based on the analysis results.

Images