System

Abstract

A system is provided.SOLUTION: The system includes a data collection means for collecting data from a plurality of information sources, a data analysis means for analyzing the collected data and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a retrieval means for inputting customer information and retrieving information in the database, and a proposal material creation means for automatically creating a proposal material based on the retrieved information.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] For many companies, it is extremely important to be able to quickly make effective proposals to address the complex issues facing corporate customers. However, manually collecting and analyzing vast amounts of information and creating appropriate proposal materials takes time and effort, hindering the efficiency and sophistication of sales activities. In particular, because information is frequently updated, it is difficult to make proposals that reflect the latest information. To solve this problem, there is a demand for the introduction of systems that utilize AI. [Means for solving the problem]

[0005] The present invention provides a system that automatically generates proposal materials for customers by collecting and analyzing data from multiple information sources. Specifically, the proposed system includes a data collection means, a data analysis means, a database means, a search means, and a proposal material generation means. The data collection means collects necessary information from external APIs and internal systems, and the data analysis means analyzes that information to extract relevant information. The extracted information is indexed by the database means and stored in a database. When customer information is entered using the search means, information in the database is searched, and the proposal material generation means automatically generates proposal materials based on the search results. This system enables quick and effective proposals, improving the efficiency and sophistication of sales activities.

[0006] A "data collection tool" is a device or system that automatically acquires data from multiple sources.

[0007] "Data analysis means" refers to algorithms or software that analyze acquired data and extract necessary information and meaning.

[0008] "Database creation means" refers to the functions and mechanisms for indexing the analyzed data and storing it in a database.

[0009] A "search tool" is a system or interface that searches a database based on information entered by a user and extracts relevant information.

[0010] "Proposal material generation means" refers to the function or software for automatically creating proposal materials for customers based on the searched information.

[0011] An "external API" is an interface for using data or functions provided by a third party.

[0012] "Internal systems" refer to information systems and applications used within a company.

[0013] "Natural language generation technology" refers to the technology and algorithms that allow computers to automatically generate human language. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The system of the present invention is a tool for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means. This system functions as follows.

[0036] 1. Data Collection Method

[0037] server

[0038] The server collects the necessary data from external APIs (such as industry news sites and SNS APIs) and internal systems (CRM systems, ERP systems, etc.). It collects the latest industry news and competitive information from external APIs, and customer transaction history and past proposal materials from internal systems. This allows important information from both inside and outside the company to be centrally consolidated.

[0039] Specific examples

[0040] Get the latest news about the automotive industry from the Google® News API and past customer transaction history from a CRM system.

[0041] 2. Embodiments of Data Analysis Means

[0042] server

[0043] The server analyzes the collected data using natural language processing (NLP) technology, extracting keywords and important information from the data and analyzing relevance. The analyzed data is then used to generate proposal materials.

[0044] Specific examples

[0045] Keywords such as "fuel efficiency improvement technology" and "electric vehicles" are extracted from the collected news articles.

[0046] 3. Embodiment of database creation means

[0047] server

[0048] The analyzed information is indexed by the database creation means and stored in a database, which allows for efficient data retrieval by the subsequent search means.

[0049] Specific examples

[0050] The extracted keywords and information are added as metadata to each entry in the database.

[0051] 4. Embodiments of Search Means

[0052] Terminal

[0053] Salespeople use terminals to input customer information and perform searches. The server searches the database based on the input customer information and extracts relevant information. The search results are used to generate the next proposal materials.

[0054] Specific examples

[0055] If a salesperson wants to create a proposal for a particular automaker, they enter the name of the automaker and the technology they're interested in.

[0056] 5. Embodiment of Proposal Material Generation Means

[0057] server

[0058] The server automatically generates proposal documents based on the searched information using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to sales representatives.

[0059] Specific examples

[0060] Based on the information on "fuel efficiency improvement technologies" obtained as search results and past success stories, a proposal document is created and output in PDF format.

[0061] As described above, the system of the present invention automates the entire process from data collection to the automatic generation of proposal materials, thereby improving the efficiency and sophistication of sales activities, enabling sales representatives to quickly and effectively make proposals that meet customer needs.

[0062] The processing flow will be explained below.

[0063] Step 1: Data collection

[0064] server

[0065] The server retrieves the necessary data from external APIs (for example, news APIs or SNS APIs) and internal systems (CRM systems or ERP systems). From external APIs, it obtains industry news and competitive information, and from internal systems, it collects customer transaction history and past proposal materials. This data is then stored in temporary storage.

[0066] Step 2: Data analysis

[0067] server

[0068] After collecting the data, the server analyzes it using natural language processing (NLP) technology. Specifically, it tokenizes the collected text data and extracts keywords and important information. This analysis process generates meta-information about the data.

[0069] Step 3: Database creation

[0070] server

[0071] The server indexes the parsed information and stores it in a database, adding related keywords and category information to the database and creating an index for faster response to multiple search queries.

[0072] Step 4: Enter customer information

[0073] User

[0074] A salesperson (user) inputs customer information (for example, company name, industry, technology of interest) from a terminal. This information is used to search the database by the search means.

[0075] Step 5: Database Search

[0076] server

[0077] The server searches the database based on the customer information entered by the user, using SQL queries and full-text search engines to efficiently extract relevant data.

[0078] Step 6: Data Selection

[0079] server

[0080] The search results are then sorted to find the information that best addresses the customer's needs, a process driven by an algorithm that takes into account relevance scores and past ratings data.

[0081] Step 7: Generate a proposal

[0082] server

[0083] The server automatically generates proposal documents based on the selected information using natural language generation (NLG) technology. The generated proposal documents are customized to meet the client's needs and converted into easy-to-read formats (PDF or PPT).

[0084] Step 8: Review and revise your proposal

[0085] Terminal

[0086] The sales representative checks the automatically generated proposal materials on the terminal, corrects the contents of the materials as necessary, and saves them as the final proposal materials.

[0087] Step 9: Submit your proposal

[0088] Terminal

[0089] Once the revisions are complete, the proposal materials are saved in PDF or PPT format and provided to the customer via email or other means.

[0090] Example 1

[0091] 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."

[0092] In the past, making quick and effective proposals to corporate customers to address their challenges required the collection, analysis, database creation, search, and document creation of massive amounts of data, and when sales representatives performed these tasks manually, it was extremely time-consuming and labor-intensive. Furthermore, manual data processing was prone to errors, resulting in inconsistent quality in proposals submitted to customers. This made it difficult to respond quickly to customer needs, reducing the efficiency and effectiveness of sales activities.

[0093] 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.

[0094] In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, and a proposal material generation means for automatically generating proposal materials using natural language generation technology based on the searched information and converting the materials into a predetermined format. This enables sales representatives to process data quickly and accurately and provide high-quality proposal materials to customers in a timely manner.

[0095] "Data collection means" refers to the function of collecting necessary data from multiple sources.

[0096] "Data analysis means" refers to the function of analyzing collected data using natural language processing technology and extracting relevant information.

[0097] "Natural language processing technology" refers to technology for understanding and processing human language, and to technology for extracting keywords and important information in data analysis.

[0098] "Database creation means" refers to the function of indexing the analyzed information and storing it in a database.

[0099] "Search means" refers to the function of entering customer information, searching for information in the database, and extracting the necessary information.

[0100] "Proposal material generation means" refers to a function that automatically generates proposal materials using natural language generation technology based on searched information and converts the materials into a specified format.

[0101] "Natural language generation technology" refers to technology that generates sentences in natural language that is easy for humans to understand based on accumulated data.

[0102] An "external API" refers to an interface for obtaining data from external systems or services.

[0103] "Internal system" refers to a system used within a company for data management and business processing.

[0104] "Database" refers to a collection of data that stores collected and analyzed information and makes it efficiently searchable and accessible.

[0105] The system of the present invention is a tool for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means. This system functions as follows using a server and terminals.

[0106] 1. Data Collection Method

[0107] Server Roles

[0108] The server collects the necessary data from external APIs and internal systems. Specifically, it obtains the latest industry news and competitive information from Google News API and Twitter API, and customer transaction history and past proposal materials from CRM and ERP systems. This allows important internal and external information to be centrally consolidated.

[0109] Specific examples

[0110] The server uses the Google News API to get the latest news about the automotive industry and the API of the company's CRM system to get the transaction history of customer XYZ.

[0111] 2. Embodiments of Data Analysis Means

[0112] Server Roles

[0113] The server analyzes the collected data using natural language processing (NLP) technology, extracting keywords and important information from the data and analyzing their relevance. This organizes the information needed to generate subsequent proposal materials.

[0114] Specific examples

[0115] The server extracts keywords such as "fuel efficiency improvement technology" and "electric vehicles" from the collected news articles, and extracts "top priority projects" and "purchase history" from customer transaction history.

[0116] 3. Embodiment of database creation means

[0117] Server Roles

[0118] The server indexes the parsed information and stores it in a database, with each entry being accompanied by associated metadata and organized for efficient searching.

[0119] Specific examples

[0120] The server stores keywords such as "fuel efficiency technology" and "electric vehicle" as entries in a database, and adds related news articles and transaction history information as metadata.

[0121] 4. Embodiments of Search Means

[0122] Device Role

[0123] The user, a salesperson, uses a terminal to input customer information and perform a search. The server searches the database based on the input information, extracts relevant information, and returns it to the terminal.

[0124] Specific examples

[0125] A salesperson enters "XYZ Motors Co., Ltd." and "electric vehicle" into a search form on a terminal. The server searches the database based on this information, extracts relevant news articles and transaction history information, and sends it back to the terminal.

[0126] 5. Embodiment of Proposal Material Generation Means

[0127] Server Roles

[0128] The server automatically generates proposal documents based on the searched information using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to the sales representatives.

[0129] Specific examples

[0130] The server creates a proposal document based on the latest information on "electric vehicles" from the search results and the customer's transaction history. The created proposal document is converted into PDF format and sent to the sales representative's terminal.

[0131] Prompts based on concrete examples

[0132] Here's an example prompt that can be fed into a generative AI model to generate a proposal:

[0133] Customer information:

[0134] Customer Name: XYZ Automobiles Co., Ltd.

[0135] Technology of interest: Electric vehicles, fuel efficiency improvement technology

[0136] Acquired data:

[0137] Automotive industry news from Google News API

[0138] Past transaction history with XYZ Automotive from internal CRM

[0139] Proposal to generate:

[0140] Title: Proposal for XYZ Motors Co., Ltd.

[0141] Contents:

[0142] Latest trends in the electric vehicle market

[0143] Fuel efficiency improvement technology trends of competitors

[0144] Summary of XYZ Motors' past performance

[0145] The system of the present invention enables salespeople to process data quickly and accurately, and provide high-quality proposal materials to customers in a timely manner.

[0146] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0147] Step 1: Collect data

[0148] server

[0149] The server collects data from multiple sources, such as the latest industry news and competitive information from Google News API and Twitter API, and customer transaction history and past proposal documents from CRM and ERP systems. All of this external and internal data is temporarily stored in storage.

[0150] Input and Output

[0151] Input: External API endpoint, internal system API endpoint

[0152] Output: Collected data from multiple sources (news articles, trading history, etc.)

[0153] Specific actions

[0154] The server queries the Google News API to retrieve the latest news articles related to the automotive industry, and at the same time, uses the CRM system's API to retrieve the transaction history for a specific customer ID. These data are then temporarily stored in storage.

[0155] Step 2: Data analysis

[0156] server

[0157] The server reads the collected data from the storage and analyzes it using natural language processing (NLP) techniques, which extracts keywords and important information from the text and analyzes their relevance. The analysis results are then prepared for the next step.

[0158] Input and Output

[0159] Input: Collected data (news articles, trading history, etc.)

[0160] Output: Analyzed information (keywords, important phrases, relevance)

[0161] Specific actions

[0162] The server reads news articles and uses an NLP engine to extract keywords such as "fuel-efficient technology" and "electric vehicles," while simultaneously extracting important information from customer transaction histories, such as "top priority projects" and "purchase history," and analyzing their relevance.

[0163] Step 3: Store in the database

[0164] server

[0165] The server indexes the parsed information and stores it in a database for efficient searching. Metadata is added to the information to make it easier to find and manage within the database.

[0166] Input and Output

[0167] Input: Analyzed data (keywords, key phrases, relevance)

[0168] Output: Indexed database entries

[0169] Specific actions

[0170] The server stores keywords such as "fuel efficiency technology" and "electric vehicles" along with related news articles and transaction history information in a database, and adds appropriate metadata to each.

[0171] Step 4: Search for data

[0172] Terminal

[0173] A salesperson, who is a user, uses a terminal to input customer information (such as customer name, technology of interest, etc.) into a search form. The server searches the database based on the input information, extracts relevant information, and returns it to the terminal.

[0174] Input and Output

[0175] Input: Customer information (customer name, technology of interest)

[0176] Output: Search results (related news articles, transaction history information)

[0177] Specific actions

[0178] A salesperson enters "XYZ Motors Corporation" and "electric vehicles" into a search form on a terminal. The server retrieves relevant entries from the database and returns relevant news articles and transaction history information to the terminal.

[0179] Step 5: Generate a proposal

[0180] server

[0181] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to the sales representatives.

[0182] Input and Output

[0183] Input: Search results (related news articles, transaction history information)

[0184] Output: Proposal materials (PDF, PPT format)

[0185] Specific actions

[0186] The server creates a proposal document based on the latest information about electric vehicles obtained as a search result and the customer's transaction history. The proposal document is converted into PDF format and sent to the sales representative's terminal.

[0187] (Application example 1)

[0188] 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."

[0189] In conventional sales activities, making quick and effective proposals to corporate customers to address their challenges requires the collection and analysis of vast amounts of information, which takes up a great deal of time and effort. Creating proposal materials also takes time, making it difficult for sales representatives to respond quickly amid their busy schedules. Proposing new production technologies and equipment installations at factories, in particular, requires real-time information gathering and immediate proposals.

[0190] 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.

[0191] In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, and a proposal material generation means for automatically generating proposal materials based on the searched information and displaying them on a visual device. This enables sales representatives to collect and analyze data within the factory in real time and make quick and effective proposals to factory managers and customers.

[0192] A "data collection means" is a device or function that collects necessary data from multiple sources.

[0193] "Data analysis means" refers to a device or function that analyzes collected data and extracts relevant information.

[0194] The "database creation means" is a device or function that indexes the analyzed information and stores it in a database.

[0195] The "search means" is a device or function that inputs customer information and searches for information in the database.

[0196] The "proposal material generating means" is a device or function that automatically generates proposal materials based on the searched information and displays them on a visual device.

[0197] An "External API" is an application programming interface provided over the Internet.

[0198] "Internal systems" are computer systems and software used within a company.

[0199] "Natural language generation technology" is a technology that automatically generates sentences in natural language that are easy for humans to understand.

[0200] A "visual device" is a device for visually displaying information.

[0201] The present invention is a system for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means.

[0202] 1. Data Collection Method

[0203] The server collects the necessary data from external APIs (such as industry news sites and social media APIs) and internal systems (CRM systems, ERP systems, etc.), enabling the latest industry news, competitive information, and customer transaction history to be centrally aggregated.

[0204] As a concrete example, the server uses a news API to get information about the latest factory automation technologies and extracts past transaction history from a CRM system.

[0205] 2. Embodiments of Data Analysis Means

[0206] The server analyzes the collected data using natural language processing (NLP) technology. NLP technology extracts keywords and important information from the data and analyzes their relevance. The analyzed data is then used to generate proposal materials.

[0207] As a specific example, the server extracts keywords such as "automation technology" and "robot introduction" from collected news articles.

[0208] 3. Embodiment of database creation means

[0209] The analyzed information is indexed by the database creation means and stored in a database, which allows for efficient data retrieval by the subsequent search means.

[0210] As a specific example, extracted keywords and information are added as metadata to each entry in the database.

[0211] 4. Embodiments of Search Means

[0212] Salespeople use terminals to input customer information and perform searches. The server searches the database based on the input customer information and extracts relevant information. The search results are used to generate proposal materials.

[0213] As a specific example, when a sales representative prepares a proposal document for a particular automobile manufacturer, he or she inputs the company name and interest in new technologies.

[0214] 5. Embodiment of Proposal Material Generation Means

[0215] The server automatically generates a proposal document based on the searched information using natural language generation (NLG) technology, converts the generated proposal document into PDF or PPT format, and provides it to the sales representative. At the same time, the information is visually displayed via the smart glasses.

[0216] As a specific example, a proposal document is created based on information about "automation technology" obtained from search results and past success stories, and the document is output in PDF format and displayed on a visual device.

[0217] Example prompt sentence:

[0218] "Get the latest competitive information and technology trends related to factory automation technology, and generate and provide proposal materials that best meet the current needs of your factory based on past proposal materials and transaction history."

[0219] In this way, the above-mentioned means realizes more efficient and sophisticated sales activities, and enables salespeople to make proposals that meet customer needs quickly and effectively.

[0220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0221] Step 1:

[0222] The server collects data from external APIs and internal systems. As input, it specifies the URL of the external API or the database of the internal system, and as output, it obtains collected data such as industry news and customer transaction history. Specifically, the server sends HTTP requests to the external API and the internal system, and stores the returned data in temporary files or memory.

[0223] Step 2:

[0224] The server analyzes the collected data using natural language processing (NLP) techniques. It uses the data collected in step 1 as input and extracts keywords and key information as output. Specifically, it uses an NLP library (e.g., spaCy or a natural language toolkit) to extract keywords and phrases from the data and analyze their relationships.

[0225] Step 3:

[0226] The server indexes the parsed information and stores it in a database. It uses the keywords and information extracted in step 2 as input and gets the indexed database entries as output. Specifically, it uses an indexing algorithm to map the keywords and related information to database fields and writes them to the database.

[0227] Step 4:

[0228] A user uses a terminal to input customer information and search for related information. A query such as a customer name or technology interest is used as input, and relevant database entries are obtained as output. Specifically, the server receives the query sent from the terminal, executes the search query against the database, and returns the results to the terminal.

[0229] Step 5:

[0230] The server automatically generates a proposal document based on the searched information and displays it on the visual device. It uses the search results obtained in step 4 as input, and generates a PDF or PPT file of the proposal document as output, which is displayed on the visual device (e.g., smart glasses). Specifically, it uses natural language generation (NLG) technology to compose the proposal document, exports the document in a specified format, and sends the file to the visual device.

[0231] This process allows sales representatives to collect and analyze data in real time within the factory, generating and visually verifying proposals quickly and effectively.

[0232] 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.

[0233] The system of the present invention is a tool for making prompt and effective proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, proposal material generation means, and an emotion engine that recognizes the user's emotions. The specific operation of each means is explained below.

[0234] 1. Data Collection Method

[0235] server

[0236] The server obtains the necessary data from external APIs (e.g., news APIs, SNS APIs) and internal systems (CRM systems, ERP systems). From external APIs, it collects industry news and competitive information, and from internal systems, it obtains customer transaction history and past proposal materials.

[0237] Specific examples

[0238] It uses the Google News API to get the latest automotive industry news and collects transaction history for specific customers from a CRM system.

[0239] 2. Embodiments of Data Analysis Means

[0240] server

[0241] The server analyzes the collected data using natural language processing (NLP) techniques, tokenizing the text data and extracting keywords and important information, which are then used in subsequent processes.

[0242] Specific examples

[0243] The collected news articles are analyzed using NLP technology to extract key keywords such as "electric vehicles" and "fuel efficiency improvement technology."

[0244] 3. Embodiment of database creation means

[0245] server

[0246] The server indexes the analyzed information and stores it in a database, adding related keywords and category information to the database to enable fast and efficient data searches.

[0247] Specific examples

[0248] The extracted keywords and metadata are stored in a database for future searches.

[0249] 4. Embodiments of Search Means

[0250] Terminal

[0251] The salesperson (user) enters customer information into the terminal and performs a search. The server searches the database based on the entered information and extracts relevant information.

[0252] Specific examples

[0253] A sales representative enters the company name and related technical keywords to create a proposal document for a specific automobile manufacturer.

[0254] 5. Embodiment of Proposal Material Generation Means

[0255] server

[0256] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT formats.

[0257] Specific examples

[0258] Based on the search results, a proposal document focusing on "fuel efficiency improvement technologies" is created using NLG technology and output in PDF format.

[0259] 6. Embodiment of Emotion Engine

[0260] server

[0261] The emotion engine analyzes the user's input and operation logs to recognize the user's emotions. The information analyzed by the emotion engine is reflected in the content of the proposal materials.

[0262] Specific examples

[0263] If the emotion engine determines that a salesperson is tired, the system will generate a concise and easy-to-understand sales pitch.

[0264] 7. Review and revise the proposal materials

[0265] Terminal

[0266] The sales representative checks the automatically generated proposal materials on their device, makes any necessary corrections, and saves the corrected materials as the final proposal materials.

[0267] Specific examples

[0268] Review the generated proposal and customize some of the content.

[0269] 8. Providing proposal materials

[0270] Terminal

[0271] Sales representatives save the revised proposal materials in PDF or PPT format and provide them to customers via email or other means.

[0272] As a result, the system of the present invention automates everything from data collection to recognition of customer emotions, enabling the rapid creation and provision of effective proposal materials, thereby improving the efficiency and sophistication of sales activities.

[0273] The processing flow will be explained below.

[0274] Step 1: Data collection

[0275] server

[0276] The server retrieves the necessary data from external APIs (news APIs and SNS APIs) and internal systems (CRM systems and ERP systems). It collects the latest industry information from the news API and customer transaction history and past proposal materials from the internal systems. This data is then stored in temporary storage.

[0277] Specific examples

[0278] Use the Google News API to get the latest news from the automotive industry and collect transaction history for specific customers from your CRM system.

[0279] Step 2: Data analysis

[0280] server

[0281] The collected data is analyzed using natural language processing (NLP) technology. Specifically, the text data is tokenized and keywords and important information are extracted, generating meta-information about the data.

[0282] Specific examples

[0283] Keywords such as "electric vehicles" and "fuel efficiency improvement technology" are extracted from the collected news articles using natural language processing.

[0284] Step 3: Database creation

[0285] server

[0286] The analyzed information is indexed and stored in a database, which involves adding related keywords and category information to the database to create an index that improves the efficiency of data searches.

[0287] Specific examples

[0288] The extracted keywords and metadata are stored for each entry in the database for future searches.

[0289] Step 4: Enter customer information

[0290] User

[0291] Salespeople enter customer information (company name, industry, technology of interest, etc.) into their terminals. This information is used by the server to search the database.

[0292] Specific examples

[0293] To generate proposal materials for a specific automobile manufacturer, a sales representative enters a specific company name and related technical keywords into an input form on the terminal.

[0294] Step 5: Database Search

[0295] server

[0296] The server searches the database based on the customer information entered by the user, using SQL queries and full-text search engines to efficiently extract relevant information.

[0297] Specific examples

[0298] Search for relevant news articles and past proposals in the database based on the company name or keywords entered.

[0299] Step 6: Sentiment Analysis

[0300] server

[0301] The emotion engine analyzes the user's input and operation logs to recognize their emotions. The results of the emotion analysis are then reflected appropriately in the content of the proposal materials.

[0302] Specific examples

[0303] Based on the information entered by the sales representative and the amount of time spent operating the device, the emotion engine detects fatigue and notifies the system.

[0304] Step 7: Data Selection

[0305] server

[0306] The search results are then filtered to best address the customer's needs based on the user's emotional state, using an algorithm that takes into account relevance scores and past ratings data.

[0307] Specific examples

[0308] Taking into account the results of the sentiment analysis, the most relevant data related to "electric vehicles" is selected.

[0309] Step 8: Generate a proposal

[0310] server

[0311] Based on the selected information, proposal materials are automatically generated using natural language generation (NLG) technology. The generated materials are customized to meet the client's needs and converted into PDF or PPT format.

[0312] Specific examples

[0313] Proposal materials are created based on relevant information, and the content is made concise and easy to understand based on sentiment analysis, and then output in PDF format.

[0314] Step 9: Review and revise your proposal

[0315] Terminal

[0316] The sales representative checks the automatically generated proposal documents on the terminal, corrects the contents as necessary, and saves them as the final proposal documents.

[0317] Specific examples

[0318] Review the generated proposal, customize some of the content, and save it as the final version.

[0319] Step 10: Submit your proposal

[0320] Terminal

[0321] Sales representatives save the revised proposal materials in PDF or PPT format and provide them to customers via email or other means.

[0322] Specific examples

[0323] After the revisions are complete, save the proposal document in PDF format and send it to the customer by email.

[0324] Example 2

[0325] 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."

[0326] In conventional proposal document creation systems, each step from data collection and analysis to document generation is often done manually, requiring a great deal of time and effort. It is also difficult to create proposal documents that take customer emotions into account, posing a major challenge to customer satisfaction. To solve these problems and create proposal documents efficiently and effectively, an automated system is needed.

[0327] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information, and a database creation means for indexing the analyzed information and storing it in a database. This automates the entire process from collection to analysis and generation of proposal materials, making it possible to efficiently create high-quality proposal materials. In addition, by using an emotion recognition means, it is possible to create proposal materials that take customer emotions into consideration.

[0328] "Data collection means" refers to the means for obtaining necessary data from multiple sources.

[0329] "Natural language processing technology" is a technology that analyzes collected text data and extracts keywords and important information.

[0330] "Indexing" is the process of creating a data structure that allows the data to be efficiently searched.

[0331] A "database" is a system that stores collected and analyzed data in an organized manner and makes it easy to search and access.

[0332] The "search means" is a means for searching for information in the database based on the customer information entered by the user.

[0333] "Natural language generation technology" is a technology that automatically generates sentences based on searched information.

[0334] The "proposal material generation means" is a means for automatically generating proposal materials using natural language generation technology and converting them into a document format.

[0335] The "emotion recognition means" is a means for analyzing the user's input contents and operation log and recognizing the user's emotions.

[0336] The system of the present invention is a tool for making quick and effective proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, proposal material generation means, and an emotion engine that recognizes user emotions. This makes it possible to automate the creation of proposal materials and to make advanced proposals that take into account the client's emotions. The specific operation of each means is explained below.

[0337] Data collection methods

[0338] server

[0339] The server collects the necessary data from multiple external APIs (e.g., news API, SNS API) and internal systems (e.g., CRM system, ERP system). For example, it uses the Google News API to obtain the latest news in the automotive industry and collects the transaction history of specific customers from the internal CRM system.

[0340] concrete action

[0341] The server starts a scheduled task every morning at 8:00, sends a request to the specified API endpoint, and stores the received data in an internal data store in JSON format.

[0342] Data Analysis Methods

[0343] server

[0344] The server analyzes the collected data using natural language processing (NLP) techniques, specifically using Python NLP libraries (e.g., spaCy, NLTK) to tokenize the text and extract important keywords and information.

[0345] concrete action

[0346] The server analyzes the collected news articles using NLP technology and extracts key keywords such as "electric vehicles" and "fuel efficiency improvement technology."

[0347] Database creation method

[0348] server

[0349] The server indexes the analyzed information and stores it in a database (e.g., ElasticSearch (registered trademark), MySQL (registered trademark), or PostgreSQL), enabling fast and efficient data searches.

[0350] concrete action

[0351] The server stores the extracted keywords and metadata in a database for future searches.

[0352] Search methods

[0353] Terminal

[0354] The sales representative (user) enters specific customer information and keywords into the terminal and performs a search. The server searches the database based on the entered information and extracts relevant information.

[0355] concrete action

[0356] Users access a dedicated search screen and enter a customer name or related technology as search keywords, and the server retrieves the relevant data using an Elasticsearch query.

[0357] Proposal material generation means

[0358] server

[0359] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT formats.

[0360] concrete action

[0361] The server uses Python's NLG libraries (e.g., GPT-3®, Natural Language Toolkit) to generate proposal documents from the search results, which are then converted to PDF or PPT format using Python's ReportLab or pptx libraries.

[0362] Embodiment of Emotion Engine

[0363] server

[0364] The emotion engine analyzes user input and operation logs to recognize the user's emotions, which are reflected in the content of proposal materials.

[0365] concrete action

[0366] The server uses a SaaS-based emotion analysis service (e.g., IBM Watson (registered trademark) Tone Analyzer) to generate an emotion score from operation logs and input data, and adjusts the content and tone of the proposal materials based on that score.

[0367] Specific examples (prompt sentence examples)

[0368] For example, if a salesperson is creating a proposal for a particular car manufacturer, they might use the following prompt:

[0369] "Please create a proposal document that includes the latest news and technological trends about a specific customer's automobile manufacturer. The keywords are 'electric vehicles' and 'fuel efficiency improvement technology.'"

[0370] In this way, the system automates everything from data collection to customer sentiment recognition, enabling efficient creation of high-quality proposal materials and supporting improved sales activities.

[0371] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0372] Program processing flow

[0373] Step 1: Collect data

[0374] server

[0375] The server collects the required data from external APIs (e.g., news APIs, social media APIs) and internal systems (e.g., CRM systems, ERP systems). The input is the API request or an internal database query, and the output is the retrieved data.

[0376] Specific actions

[0377] The server starts a scheduled task every morning at 8:00, sends a request to the Google News API, stores the received JSON data in an internal data store, and simultaneously calls an internal API to retrieve customer transaction history from Salesforce CRM and store it in a database.

[0378] Step 2: Analyze the collected data

[0379] server

[0380] The server analyzes the collected data using natural language processing (NLP) technology. The input is the collected text data, and the output is extracted keywords and important information.

[0381] Specific actions

[0382] The server uses Python NLP libraries (e.g., spaCy, NLTK) to tokenize news articles and extract key keywords such as "electric vehicle" and "fuel-efficient technology." It also performs part-of-speech tagging and named entity extraction.

[0383] Step 3: Indexing and storing data

[0384] server

[0385] The server indexes the parsed information and stores it in a database. The input is the extracted keywords and metadata, and the output is the indexed data.

[0386] Specific actions

[0387] The server uses Elasticsearch to create an index, adding extracted keywords and metadata to the index for future fast searches, and storing the indexed data in a MySQL or PostgreSQL database.

[0388] Step 4: User Search

[0389] Terminal

[0390] Salespeople (users) enter specific customer information and keywords into their terminals to perform searches. The input is the customer name and related technical keywords, and the output is the related information obtained as a result of the search.

[0391] Specific actions

[0392] Users access a dedicated search interface and enter information such as "electric vehicles" or "fuel-efficient technology," and the server executes an Elasticsearch query to quickly retrieve relevant documents and data.

[0393] Step 5: Generate a proposal

[0394] server

[0395] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology. The input is the search results, and the output is the generated proposal documents.

[0396] Specific actions

[0397] The server uses Python's NLG library (e.g., GPT-3, Natural Language Toolkit) to generate proposal documents from the search results, and then converts the documents into PDF or PPT format using Python's ReportLab or pptx library.

[0398] Step 6: Sentiment analysis and material adjustment

[0399] server

[0400] The emotion engine analyzes the user's input and operation log and reflects it in the proposal materials. The input is the user's operation log and input data, and the output is a proposal material based on the user's emotion.

[0401] Specific actions

[0402] The server generates a sentiment score using a SaaS-based sentiment analysis service (e.g., IBM Watson Tone Analyzer), and adjusts the tone and content of the proposal based on the sentiment score.

[0403] Step 7: Review and correct your materials

[0404] Terminal

[0405] The sales representative checks the automatically generated proposal documents on the terminal and makes corrections as necessary. The input is the automatically generated proposal documents, and the output is the corrected and confirmed proposal documents.

[0406] Specific actions

[0407] The user downloads the generated PDF or PPT file, opens it in Adobe Acrobat or Microsoft (registered trademark) PowerPoint, checks the contents, and makes any necessary corrections.

[0408] Step 8: Submit your proposal

[0409] Terminal

[0410] The sales representative saves the revised proposal and provides it to the customer. The input is the revised proposal, and the output is the proposal provided to the customer.

[0411] Specific actions

[0412] The user saves the revised proposal document in a file format and sends it to the customer using an email client (e.g., Microsoft Outlook, Gmail).

[0413] By using the above processing steps, the system of the present invention can efficiently and quickly generate high-quality proposal materials.

[0414] (Application example 2)

[0415] 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."

[0416] In conventional proposal material creation systems, the process from data collection to analysis and generation is often performed partially manually, resulting in problems such as reduced work efficiency. Another problem is that the content of the proposal material does not adapt to the customer's situation or emotions, making it difficult to make effective proposals. The present invention aims to solve these problems by providing a system that automates the creation of proposal materials and adjusts the content based on the customer's emotions.

[0417] The specific processing by the specific 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 data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, a proposal material generation means for automatically generating proposal materials based on the searched information, an emotion engine means for analyzing the customer's input content and operation log and recognizing their emotions, and a material adjustment means for adjusting the content of the proposal materials based on the recognized emotions. This makes it possible to quickly and effectively automate the process of creating proposal materials and provide optimal proposal content tailored to the customer's emotions.

[0418] A "data collection tool" is a tool for collecting data from multiple sources.

[0419] "Data analysis means" refers to means for analyzing collected data and extracting relevant information.

[0420] The "database means" is a means for indexing the analyzed information and storing it in a database.

[0421] The "search means" is a means for inputting customer information and searching for information in the database.

[0422] The "proposal material generating means" is a means for automatically generating proposal materials based on the searched information.

[0423] The "emotion engine means" is a means for analyzing the customer's input contents and operation logs and recognizing emotions.

[0424] The "material adjustment means" is a means for adjusting the content of the proposal materials based on the recognized emotions.

[0425] The system for implementing this invention is based on an application installed on a terminal such as a smartphone or tablet. The system is composed of the following hardware and software.

[0426] Hardware:

[0427] Smartphone (iOS / ANDROID (registered trademark))

[0428] tablet

[0429] Software / Libraries:

[0430] Requests (to communicate with external APIs)

[0431] NLP libraries (e.g. SpaCy)

[0432] Database connection library (e.g. SQLite)

[0433] Natural Language Generation (NLG) toolkits (e.g., GPT-3)

[0434] Emotion recognition engine (e.g. Emotion API)

[0435] The server first uses data collection tools to collect data from multiple sources, including external APIs (e.g., news APIs and social media APIs) and internal systems (CRM and ERP). For example, it uses a news API to collect the latest security news and retrieves the transaction history of a specific customer from a CRM system.

[0436] The server then analyzes the collected data using natural language processing (NLP) technology. The collected text data is tokenized and important keywords and information are extracted. For example, a security-related news article is analyzed to extract key keywords such as "surveillance camera" and "alarm system."

[0437] The collected and analyzed information is indexed using database tools and stored in a database, allowing for fast and efficient data searches.

[0438] When a user enters customer information into a terminal and performs a search, the server searches the database based on that information and extracts relevant information. For example, a user may enter the name of a specific company and related technical keywords to create a security plan for that company.

[0439] Next, the server uses a proposal generation means to automatically generate proposal materials based on the search results using natural language generation (NLG) technology. These materials are output in PDF or PPT format. For example, a proposal material centered on a "surveillance camera system" is created based on the data obtained as search results.

[0440] Furthermore, the server is equipped with an emotion engine that analyzes the user's input and operation logs to recognize their emotions. It also includes a document adjustment mechanism that adjusts the content of the proposal materials based on these emotions. For example, if the user feels that the proposal materials are too detailed and difficult to understand, the system will generate concise and easy-to-understand proposal materials.

[0441] As an example of a specific prompt sentence, the following text is entered:

[0442] "There's too much complicated information and it's hard to understand."

[0443] In this way, the present invention is a system that can quickly and effectively automate the creation of proposal materials and provide optimal proposal content that reflects the user's emotions.

[0444] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0445] Step 1:

[0446] Data collection methods

[0447] The server collects data from multiple sources. It gets the required data from external APIs and internal systems, including news APIs, social media APIs, CRM systems, and ERP systems. For example, it uses a news API to get the latest security news and collects a specific customer's transaction history from a CRM system. The API key and customer ID are used as input, and news data and customer data are obtained as output.

[0448] Step 2:

[0449] Data Analysis Methods

[0450] The server analyzes the collected data using natural language processing (NLP) technology. It tokenizes the collected text data and extracts important keywords and information. An NLP library (such as SpaCy) is used for this analysis. The collected news data and customer data are used as input, and key keywords and important information are obtained as output. Specifically, keywords such as "surveillance camera" and "alarm system" are extracted from the text.

[0451] Step 3:

[0452] Database creation method

[0453] The server indexes the analyzed information and stores it in a database, which allows for fast and efficient data searches. A database connection library (such as SQLite) is used. The analysis results (keywords and important information) are used as input, and the index data stored in the database is obtained as output.

[0454] Step 4:

[0455] Search methods

[0456] The user inputs customer information from the terminal and searches for information in the database. The server searches the database based on this input information and extracts relevant information. Customer information (company name, technical keywords, etc.) is used as input, and search results (related information) are obtained as output. In concrete terms, the user inputs a "specific company name" or "security-related technology."

[0457] Step 5:

[0458] Proposal material generation means

[0459] The server automatically generates proposal documents based on the searched information. It uses natural language generation (NLG) technology to output the proposal documents in PDF or PPT format. An NLG toolkit (e.g., GPT-3) is used. The search results are used as input, and proposal documents (in PDF or PPT format) are obtained as output. Specifically, a proposal document centered on a "surveillance camera system" is created from the search results.

[0460] Step 6:

[0461] Emotion Engine Means

[0462] The server analyzes the customer's input and operation logs to recognize emotions. An emotion recognition engine (e.g., Emotion API) is used. The user's text input and operation logs are used as input, and the recognized emotion is obtained as output. In concrete terms, if the user inputs "There is too much complicated information and it's hard to understand," the server will recognize that the user is "feeling stressed."

[0463] Step 7:

[0464] Material adjustment means

[0465] The server adjusts the content of the presentation materials based on the recognized emotions, which may include simplifying the materials or focusing on key points. The NLG toolkit may be reused. The recognized emotions and presentation materials are used as input, and the adjusted presentation materials are obtained as output. Specifically, for users who are "feeling stressed," a presentation material is generated that restructures the information in a simpler and more understandable way.

[0466] 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.

[0467] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0468] 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.

[0469] [Second embodiment]

[0470] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0471] 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.

[0472] 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).

[0473] 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.

[0474] 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.

[0475] 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).

[0476] 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.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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."

[0482] The system of the present invention is a tool for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means. This system functions as follows.

[0483] 1. Data Collection Method

[0484] server

[0485] The server collects the necessary data from external APIs (such as industry news sites and SNS APIs) and internal systems (CRM systems, ERP systems, etc.). It collects the latest industry news and competitive information from external APIs, and customer transaction history and past proposal materials from internal systems. This allows important information from both inside and outside the company to be centrally consolidated.

[0486] Specific examples

[0487] Get the latest news about the automotive industry from the Google News API and past customer transaction history from your CRM system.

[0488] 2. Embodiments of Data Analysis Means

[0489] server

[0490] The server analyzes the collected data using natural language processing (NLP) technology, extracting keywords and important information from the data and analyzing relevance. The analyzed data is then used to generate proposal materials.

[0491] Specific examples

[0492] Keywords such as "fuel efficiency improvement technology" and "electric vehicles" are extracted from the collected news articles.

[0493] 3. Embodiment of database creation means

[0494] server

[0495] The analyzed information is indexed by the database creation means and stored in a database, which allows for efficient data retrieval by the subsequent search means.

[0496] Specific examples

[0497] The extracted keywords and information are added as metadata to each entry in the database.

[0498] 4. Embodiments of Search Means

[0499] Terminal

[0500] Salespeople use terminals to input customer information and perform searches. The server searches the database based on the input customer information and extracts relevant information. The search results are used to generate the next proposal materials.

[0501] Specific examples

[0502] If a salesperson wants to create a proposal for a particular automaker, they enter the name of the automaker and the technology they're interested in.

[0503] 5. Embodiment of Proposal Material Generation Means

[0504] server

[0505] The server automatically generates proposal documents based on the searched information using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to sales representatives.

[0506] Specific examples

[0507] Based on the information on "fuel efficiency improvement technologies" obtained as search results and past success stories, a proposal document is created and output in PDF format.

[0508] As described above, the system of the present invention automates the entire process from data collection to the automatic generation of proposal materials, thereby improving the efficiency and sophistication of sales activities, enabling sales representatives to quickly and effectively make proposals that meet customer needs.

[0509] The processing flow will be explained below.

[0510] Step 1: Data collection

[0511] server

[0512] The server retrieves the necessary data from external APIs (for example, news APIs or SNS APIs) and internal systems (CRM systems or ERP systems). From external APIs, it obtains industry news and competitive information, and from internal systems, it collects customer transaction history and past proposal materials. This data is then stored in temporary storage.

[0513] Step 2: Data analysis

[0514] server

[0515] After collecting the data, the server analyzes it using natural language processing (NLP) technology. Specifically, it tokenizes the collected text data and extracts keywords and important information. This analysis process generates meta-information about the data.

[0516] Step 3: Database creation

[0517] server

[0518] The server indexes the parsed information and stores it in a database, adding related keywords and category information to the database and creating an index for faster response to multiple search queries.

[0519] Step 4: Enter customer information

[0520] User

[0521] A salesperson (user) inputs customer information (for example, company name, industry, technology of interest) from a terminal. This information is used to search the database by the search means.

[0522] Step 5: Database Search

[0523] server

[0524] The server searches the database based on the customer information entered by the user, using SQL queries and full-text search engines to efficiently extract relevant data.

[0525] Step 6: Data Selection

[0526] server

[0527] The search results are then sorted to find the information that best addresses the customer's needs, a process driven by an algorithm that takes into account relevance scores and past ratings data.

[0528] Step 7: Generate a proposal

[0529] server

[0530] The server automatically generates proposal documents based on the selected information using natural language generation (NLG) technology. The generated proposal documents are customized to meet the client's needs and converted into easy-to-read formats (PDF or PPT).

[0531] Step 8: Review and revise your proposal

[0532] Terminal

[0533] The sales representative checks the automatically generated proposal materials on the terminal, corrects the contents of the materials as necessary, and saves them as the final proposal materials.

[0534] Step 9: Submit your proposal

[0535] Terminal

[0536] Once the revisions are complete, the proposal materials are saved in PDF or PPT format and provided to the customer via email or other means.

[0537] Example 1

[0538] 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."

[0539] In the past, making quick and effective proposals to corporate customers to address their challenges required the collection, analysis, database creation, search, and document creation of massive amounts of data, and when sales representatives performed these tasks manually, it was extremely time-consuming and labor-intensive. Furthermore, manual data processing was prone to errors, resulting in inconsistent quality in proposals submitted to customers. This made it difficult to respond quickly to customer needs, reducing the efficiency and effectiveness of sales activities.

[0540] 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.

[0541] In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, and a proposal material generation means for automatically generating proposal materials using natural language generation technology based on the searched information and converting the materials into a predetermined format. This enables sales representatives to process data quickly and accurately and provide high-quality proposal materials to customers in a timely manner.

[0542] "Data collection means" refers to the function of collecting necessary data from multiple sources.

[0543] "Data analysis means" refers to the function of analyzing collected data using natural language processing technology and extracting relevant information.

[0544] "Natural language processing technology" refers to technology for understanding and processing human language, and to technology for extracting keywords and important information in data analysis.

[0545] "Database creation means" refers to the function of indexing the analyzed information and storing it in a database.

[0546] "Search means" refers to the function of entering customer information, searching for information in the database, and extracting the necessary information.

[0547] "Proposal material generation means" refers to a function that automatically generates proposal materials using natural language generation technology based on searched information and converts the materials into a specified format.

[0548] "Natural language generation technology" refers to technology that generates sentences in natural language that is easy for humans to understand based on accumulated data.

[0549] An "external API" refers to an interface for obtaining data from external systems or services.

[0550] "Internal system" refers to a system used within a company for data management and business processing.

[0551] "Database" refers to a collection of data that stores collected and analyzed information and makes it efficiently searchable and accessible.

[0552] The system of the present invention is a tool for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means. This system functions as follows using a server and terminals.

[0553] 1. Data Collection Method

[0554] Server Roles

[0555] The server collects the necessary data from external APIs and internal systems. Specifically, it obtains the latest industry news and competitive information from Google News API and Twitter API, and customer transaction history and past proposal materials from CRM and ERP systems. This allows important internal and external information to be centrally consolidated.

[0556] Specific examples

[0557] The server uses the Google News API to get the latest news about the automotive industry and the API of the company's CRM system to get the transaction history of customer XYZ.

[0558] 2. Embodiments of Data Analysis Means

[0559] Server Roles

[0560] The server analyzes the collected data using natural language processing (NLP) technology, extracting keywords and important information from the data and analyzing their relevance. This organizes the information needed to generate subsequent proposal materials.

[0561] Specific examples

[0562] The server extracts keywords such as "fuel efficiency improvement technology" and "electric vehicles" from the collected news articles, and extracts "top priority projects" and "purchase history" from customer transaction history.

[0563] 3. Embodiment of database creation means

[0564] Server Roles

[0565] The server indexes the parsed information and stores it in a database, with each entry being accompanied by associated metadata and organized for efficient searching.

[0566] Specific examples

[0567] The server stores keywords such as "fuel efficiency technology" and "electric vehicle" as entries in a database, and adds related news articles and transaction history information as metadata.

[0568] 4. Embodiments of Search Means

[0569] Device Role

[0570] The user, a salesperson, uses a terminal to input customer information and perform a search. The server searches the database based on the input information, extracts relevant information, and returns it to the terminal.

[0571] Specific examples

[0572] A salesperson enters "XYZ Motors Co., Ltd." and "electric vehicle" into a search form on a terminal. The server searches the database based on this information, extracts relevant news articles and transaction history information, and sends it back to the terminal.

[0573] 5. Embodiment of Proposal Material Generation Means

[0574] Server Roles

[0575] The server automatically generates proposal documents based on the searched information using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to the sales representatives.

[0576] Specific examples

[0577] The server creates a proposal document based on the latest information on "electric vehicles" from the search results and the customer's transaction history. The created proposal document is converted into PDF format and sent to the sales representative's terminal.

[0578] Prompts based on concrete examples

[0579] Here's an example prompt that can be fed into a generative AI model to generate a proposal:

[0580] Customer information:

[0581] Customer Name: XYZ Automobiles Co., Ltd.

[0582] Technology of interest: Electric vehicles, fuel efficiency improvement technology

[0583] Acquired data:

[0584] Automotive industry news from Google News API

[0585] Past transaction history with XYZ Automotive from internal CRM

[0586] Proposal to generate:

[0587] Title: Proposal for XYZ Motors Co., Ltd.

[0588] Contents:

[0589] Latest trends in the electric vehicle market

[0590] Fuel efficiency improvement technology trends of competitors

[0591] Summary of XYZ Motors' past performance

[0592] The system of the present invention enables salespeople to process data quickly and accurately, and provide high-quality proposal materials to customers in a timely manner.

[0593] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0594] Step 1: Collect data

[0595] server

[0596] The server collects data from multiple sources, such as the latest industry news and competitive information from Google News API and Twitter API, and customer transaction history and past proposal documents from CRM and ERP systems. All of this external and internal data is temporarily stored in storage.

[0597] Input and Output

[0598] Input: External API endpoint, internal system API endpoint

[0599] Output: Collected data from multiple sources (news articles, trading history, etc.)

[0600] Specific actions

[0601] The server queries the Google News API to retrieve the latest news articles related to the automotive industry, and at the same time, uses the CRM system's API to retrieve the transaction history for a specific customer ID. These data are then temporarily stored in storage.

[0602] Step 2: Data analysis

[0603] server

[0604] The server reads the collected data from the storage and analyzes it using natural language processing (NLP) techniques, which extracts keywords and important information from the text and analyzes their relevance. The analysis results are then prepared for the next step.

[0605] Input and Output

[0606] Input: Collected data (news articles, trading history, etc.)

[0607] Output: Analyzed information (keywords, important phrases, relevance)

[0608] Specific actions

[0609] The server reads news articles and uses an NLP engine to extract keywords such as "fuel-efficient technology" and "electric vehicles," while simultaneously extracting important information from customer transaction histories, such as "top priority projects" and "purchase history," and analyzing their relevance.

[0610] Step 3: Store in the database

[0611] server

[0612] The server indexes the parsed information and stores it in a database for efficient searching. Metadata is added to the information to make it easier to find and manage within the database.

[0613] Input and Output

[0614] Input: Analyzed data (keywords, key phrases, relevance)

[0615] Output: Indexed database entries

[0616] Specific actions

[0617] The server stores keywords such as "fuel efficiency technology" and "electric vehicles" along with related news articles and transaction history information in a database, and adds appropriate metadata to each.

[0618] Step 4: Search for data

[0619] Terminal

[0620] A salesperson, who is a user, uses a terminal to input customer information (such as customer name, technology of interest, etc.) into a search form. The server searches the database based on the input information, extracts relevant information, and returns it to the terminal.

[0621] Input and Output

[0622] Input: Customer information (customer name, technology of interest)

[0623] Output: Search results (related news articles, transaction history information)

[0624] Specific actions

[0625] A salesperson enters "XYZ Motors Corporation" and "electric vehicles" into a search form on a terminal. The server retrieves relevant entries from the database and returns relevant news articles and transaction history information to the terminal.

[0626] Step 5: Generate a proposal

[0627] server

[0628] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to the sales representatives.

[0629] Input and Output

[0630] Input: Search results (related news articles, transaction history information)

[0631] Output: Proposal materials (PDF, PPT format)

[0632] Specific actions

[0633] The server creates a proposal document based on the latest information about electric vehicles obtained as a search result and the customer's transaction history. The proposal document is converted into PDF format and sent to the sales representative's terminal.

[0634] (Application example 1)

[0635] 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."

[0636] In conventional sales activities, making quick and effective proposals to corporate customers to address their challenges requires the collection and analysis of vast amounts of information, which takes up a great deal of time and effort. Creating proposal materials also takes time, making it difficult for sales representatives to respond quickly amid their busy schedules. Proposing new production technologies and equipment installations at factories, in particular, requires real-time information gathering and immediate proposals.

[0637] 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.

[0638] In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, and a proposal material generation means for automatically generating proposal materials based on the searched information and displaying them on a visual device. This enables sales representatives to collect and analyze data within the factory in real time and make quick and effective proposals to factory managers and customers.

[0639] A "data collection means" is a device or function that collects necessary data from multiple sources.

[0640] "Data analysis means" refers to a device or function that analyzes collected data and extracts relevant information.

[0641] The "database creation means" is a device or function that indexes the analyzed information and stores it in a database.

[0642] The "search means" is a device or function that inputs customer information and searches for information in the database.

[0643] The "proposal material generating means" is a device or function that automatically generates proposal materials based on the searched information and displays them on a visual device.

[0644] An "External API" is an application programming interface provided over the Internet.

[0645] "Internal systems" are computer systems and software used within a company.

[0646] "Natural language generation technology" is a technology that automatically generates sentences in natural language that are easy for humans to understand.

[0647] A "visual device" is a device for visually displaying information.

[0648] The present invention is a system for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means.

[0649] 1. Data Collection Method

[0650] The server collects the necessary data from external APIs (such as industry news sites and social media APIs) and internal systems (CRM systems, ERP systems, etc.), enabling the latest industry news, competitive information, and customer transaction history to be centrally aggregated.

[0651] As a concrete example, the server uses a news API to get information about the latest factory automation technologies and extracts past transaction history from a CRM system.

[0652] 2. Embodiments of Data Analysis Means

[0653] The server analyzes the collected data using natural language processing (NLP) technology. NLP technology extracts keywords and important information from the data and analyzes their relevance. The analyzed data is then used to generate proposal materials.

[0654] As a specific example, the server extracts keywords such as "automation technology" and "robot introduction" from collected news articles.

[0655] 3. Embodiment of database creation means

[0656] The analyzed information is indexed by the database creation means and stored in a database, which allows for efficient data retrieval by the subsequent search means.

[0657] As a specific example, extracted keywords and information are added as metadata to each entry in the database.

[0658] 4. Embodiments of Search Means

[0659] Salespeople use terminals to input customer information and perform searches. The server searches the database based on the input customer information and extracts relevant information. The search results are used to generate proposal materials.

[0660] As a specific example, when a sales representative prepares a proposal document for a particular automobile manufacturer, he or she inputs the company name and interest in new technologies.

[0661] 5. Embodiment of Proposal Material Generation Means

[0662] The server automatically generates a proposal document based on the searched information using natural language generation (NLG) technology, converts the generated proposal document into PDF or PPT format, and provides it to the sales representative. At the same time, the information is visually displayed via the smart glasses.

[0663] As a specific example, a proposal document is created based on information about "automation technology" obtained from search results and past success stories, and the document is output in PDF format and displayed on a visual device.

[0664] Example prompt sentence:

[0665] "Get the latest competitive information and technology trends related to factory automation technology, and generate and provide proposal materials that best meet the current needs of your factory based on past proposal materials and transaction history."

[0666] In this way, the above-mentioned means realizes more efficient and sophisticated sales activities, and enables salespeople to make proposals that meet customer needs quickly and effectively.

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1:

[0669] The server collects data from external APIs and internal systems. As input, it specifies the URL of the external API or the database of the internal system, and as output, it obtains collected data such as industry news and customer transaction history. Specifically, the server sends HTTP requests to the external API and the internal system, and stores the returned data in temporary files or memory.

[0670] Step 2:

[0671] The server analyzes the collected data using natural language processing (NLP) techniques. It uses the data collected in step 1 as input and extracts keywords and key information as output. Specifically, it uses an NLP library (e.g., spaCy or a natural language toolkit) to extract keywords and phrases from the data and analyze their relationships.

[0672] Step 3:

[0673] The server indexes the parsed information and stores it in a database. It uses the keywords and information extracted in step 2 as input and gets the indexed database entries as output. Specifically, it uses an indexing algorithm to map the keywords and related information to database fields and writes them to the database.

[0674] Step 4:

[0675] A user uses a terminal to input customer information and search for related information. A query such as a customer name or technology interest is used as input, and relevant database entries are obtained as output. Specifically, the server receives the query sent from the terminal, executes the search query against the database, and returns the results to the terminal.

[0676] Step 5:

[0677] The server automatically generates a proposal document based on the searched information and displays it on the visual device. It uses the search results obtained in step 4 as input, and generates a PDF or PPT file of the proposal document as output, which is displayed on the visual device (e.g., smart glasses). Specifically, it uses natural language generation (NLG) technology to compose the proposal document, exports the document in a specified format, and sends the file to the visual device.

[0678] This process allows sales representatives to collect and analyze data in real time within the factory, generating and visually verifying proposals quickly and effectively.

[0679] 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.

[0680] The system of the present invention is a tool for making prompt and effective proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, proposal material generation means, and an emotion engine that recognizes the user's emotions. The specific operation of each means is explained below.

[0681] 1. Data Collection Method

[0682] server

[0683] The server obtains the necessary data from external APIs (e.g., news APIs, SNS APIs) and internal systems (CRM systems, ERP systems). From external APIs, it collects industry news and competitive information, and from internal systems, it obtains customer transaction history and past proposal materials.

[0684] Specific examples

[0685] It uses the Google News API to get the latest automotive industry news and collects transaction history for specific customers from a CRM system.

[0686] 2. Embodiments of Data Analysis Means

[0687] server

[0688] The server analyzes the collected data using natural language processing (NLP) techniques, tokenizing the text data and extracting keywords and important information, which are then used in subsequent processes.

[0689] Specific examples

[0690] The collected news articles are analyzed using NLP technology to extract key keywords such as "electric vehicles" and "fuel efficiency improvement technology."

[0691] 3. Embodiment of database creation means

[0692] server

[0693] The server indexes the analyzed information and stores it in a database, adding related keywords and category information to the database to enable fast and efficient data searches.

[0694] Specific examples

[0695] The extracted keywords and metadata are stored in a database for future searches.

[0696] 4. Embodiments of Search Means

[0697] Terminal

[0698] The salesperson (user) enters customer information into the terminal and performs a search. The server searches the database based on the entered information and extracts relevant information.

[0699] Specific examples

[0700] A sales representative enters the company name and related technical keywords to create a proposal document for a specific automobile manufacturer.

[0701] 5. Embodiment of Proposal Material Generation Means

[0702] server

[0703] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT formats.

[0704] Specific examples

[0705] Based on the search results, a proposal document focusing on "fuel efficiency improvement technologies" is created using NLG technology and output in PDF format.

[0706] 6. Embodiment of Emotion Engine

[0707] server

[0708] The emotion engine analyzes the user's input and operation logs to recognize the user's emotions. The information analyzed by the emotion engine is reflected in the content of the proposal materials.

[0709] Specific examples

[0710] If the emotion engine determines that a salesperson is tired, the system will generate a concise and easy-to-understand sales pitch.

[0711] 7. Review and revise the proposal materials

[0712] Terminal

[0713] The sales representative checks the automatically generated proposal materials on their device, makes any necessary corrections, and saves the corrected materials as the final proposal materials.

[0714] Specific examples

[0715] Review the generated proposal and customize some of the content.

[0716] 8. Providing proposal materials

[0717] Terminal

[0718] Sales representatives save the revised proposal materials in PDF or PPT format and provide them to customers via email or other means.

[0719] As a result, the system of the present invention automates everything from data collection to recognition of customer emotions, enabling the rapid creation and provision of effective proposal materials, thereby improving the efficiency and sophistication of sales activities.

[0720] The processing flow will be explained below.

[0721] Step 1: Data collection

[0722] server

[0723] The server retrieves the necessary data from external APIs (news APIs and SNS APIs) and internal systems (CRM systems and ERP systems). It collects the latest industry information from the news API and customer transaction history and past proposal materials from the internal systems. This data is then stored in temporary storage.

[0724] Specific examples

[0725] Use the Google News API to get the latest news from the automotive industry and collect transaction history for specific customers from your CRM system.

[0726] Step 2: Data analysis

[0727] server

[0728] The collected data is analyzed using natural language processing (NLP) technology. Specifically, the text data is tokenized and keywords and important information are extracted, generating meta-information about the data.

[0729] Specific examples

[0730] Keywords such as "electric vehicles" and "fuel efficiency improvement technology" are extracted from the collected news articles using natural language processing.

[0731] Step 3: Database creation

[0732] server

[0733] The analyzed information is indexed and stored in a database, which involves adding related keywords and category information to the database to create an index that improves the efficiency of data searches.

[0734] Specific examples

[0735] The extracted keywords and metadata are stored for each entry in the database for future searches.

[0736] Step 4: Enter customer information

[0737] User

[0738] Salespeople enter customer information (company name, industry, technology of interest, etc.) into their terminals. This information is used by the server to search the database.

[0739] Specific examples

[0740] To generate proposal materials for a specific automobile manufacturer, a sales representative enters a specific company name and related technical keywords into an input form on the terminal.

[0741] Step 5: Database Search

[0742] server

[0743] The server searches the database based on the customer information entered by the user, using SQL queries and full-text search engines to efficiently extract relevant information.

[0744] Specific examples

[0745] Search for relevant news articles and past proposals in the database based on the company name or keywords entered.

[0746] Step 6: Sentiment Analysis

[0747] server

[0748] The emotion engine analyzes the user's input and operation logs to recognize their emotions. The results of the emotion analysis are then reflected appropriately in the content of the proposal materials.

[0749] Specific examples

[0750] Based on the information entered by the sales representative and the amount of time spent operating the device, the emotion engine detects fatigue and notifies the system.

[0751] Step 7: Data Selection

[0752] server

[0753] The search results are then filtered to best address the customer's needs based on the user's emotional state, using an algorithm that takes into account relevance scores and past ratings data.

[0754] Specific examples

[0755] Taking into account the results of the sentiment analysis, the most relevant data related to "electric vehicles" is selected.

[0756] Step 8: Generate a proposal

[0757] server

[0758] Based on the selected information, proposal materials are automatically generated using natural language generation (NLG) technology. The generated materials are customized to meet the client's needs and converted into PDF or PPT format.

[0759] Specific examples

[0760] Proposal materials are created based on relevant information, and the content is made concise and easy to understand based on sentiment analysis, and then output in PDF format.

[0761] Step 9: Review and revise your proposal

[0762] Terminal

[0763] The sales representative checks the automatically generated proposal documents on the terminal, corrects the contents as necessary, and saves them as the final proposal documents.

[0764] Specific examples

[0765] Review the generated proposal, customize some of the content, and save it as the final version.

[0766] Step 10: Submit your proposal

[0767] Terminal

[0768] Sales representatives save the revised proposal materials in PDF or PPT format and provide them to customers via email or other means.

[0769] Specific examples

[0770] After the revisions are complete, save the proposal document in PDF format and send it to the customer by email.

[0771] Example 2

[0772] 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."

[0773] In conventional proposal document creation systems, each step from data collection and analysis to document generation is often done manually, requiring a great deal of time and effort. It is also difficult to create proposal documents that take customer emotions into account, posing a major challenge to customer satisfaction. To solve these problems and create proposal documents efficiently and effectively, an automated system is needed.

[0774] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information, and a database creation means for indexing the analyzed information and storing it in a database. This automates the entire process from collection to analysis and generation of proposal materials, making it possible to efficiently create high-quality proposal materials. In addition, by using an emotion recognition means, it is possible to create proposal materials that take customer emotions into consideration.

[0775] "Data collection means" refers to the means for obtaining necessary data from multiple sources.

[0776] "Natural language processing technology" is a technology that analyzes collected text data and extracts keywords and important information.

[0777] "Indexing" is the process of creating a data structure that allows the data to be efficiently searched.

[0778] A "database" is a system that stores collected and analyzed data in an organized manner and makes it easy to search and access.

[0779] The "search means" is a means for searching for information in the database based on the customer information entered by the user.

[0780] "Natural language generation technology" is a technology that automatically generates sentences based on searched information.

[0781] The "proposal material generation means" is a means for automatically generating proposal materials using natural language generation technology and converting them into a document format.

[0782] The "emotion recognition means" is a means for analyzing the user's input contents and operation log and recognizing the user's emotions.

[0783] The system of the present invention is a tool for making quick and effective proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, proposal material generation means, and an emotion engine that recognizes user emotions. This makes it possible to automate the creation of proposal materials and to make advanced proposals that take into account the client's emotions. The specific operation of each means is explained below.

[0784] Data collection methods

[0785] server

[0786] The server collects the necessary data from multiple external APIs (e.g., news API, SNS API) and internal systems (e.g., CRM system, ERP system). For example, it uses the Google News API to obtain the latest news in the automotive industry and collects the transaction history of specific customers from the internal CRM system.

[0787] concrete action

[0788] The server starts a scheduled task every morning at 8:00, sends a request to the specified API endpoint, and stores the received data in an internal data store in JSON format.

[0789] Data Analysis Methods

[0790] server

[0791] The server analyzes the collected data using natural language processing (NLP) techniques, specifically using Python NLP libraries (e.g., spaCy, NLTK) to tokenize the text and extract important keywords and information.

[0792] concrete action

[0793] The server analyzes the collected news articles using NLP technology and extracts key keywords such as "electric vehicles" and "fuel efficiency improvement technology."

[0794] Database creation method

[0795] server

[0796] The server indexes the parsed information and stores it in a database (e.g., Elasticsearch, MySQL, PostgreSQL), allowing for fast and efficient data retrieval.

[0797] concrete action

[0798] The server stores the extracted keywords and metadata in a database for future searches.

[0799] Search methods

[0800] Terminal

[0801] The sales representative (user) enters specific customer information and keywords into the terminal and performs a search. The server searches the database based on the entered information and extracts relevant information.

[0802] concrete action

[0803] Users access a dedicated search screen and enter a customer name or related technology as search keywords, and the server retrieves the relevant data using an Elasticsearch query.

[0804] Proposal material generation means

[0805] server

[0806] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT formats.

[0807] concrete action

[0808] The server uses Python's NLG libraries (e.g., GPT-3, Natural Language Toolkit) to generate proposal documents from the search results, which are then converted to PDF or PPT format using Python's ReportLab or pptx libraries.

[0809] Embodiment of Emotion Engine

[0810] server

[0811] The emotion engine analyzes user input and operation logs to recognize the user's emotions, which are reflected in the content of proposal materials.

[0812] concrete action

[0813] The server uses a SaaS-based emotion analysis service (e.g., IBM Watson Tone Analyzer) to generate an emotion score from operation logs and input data, and adjusts the content and tone of the proposal materials based on that score.

[0814] Specific examples (prompt sentence examples)

[0815] For example, if a salesperson is creating a proposal for a particular car manufacturer, they might use the following prompt:

[0816] "Please create a proposal document that includes the latest news and technological trends about a specific customer's automobile manufacturer. The keywords are 'electric vehicles' and 'fuel efficiency improvement technology.'"

[0817] In this way, the system automates everything from data collection to customer sentiment recognition, enabling efficient creation of high-quality proposal materials and supporting improved sales activities.

[0818] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0819] Program processing flow

[0820] Step 1: Collect data

[0821] server

[0822] The server collects the required data from external APIs (e.g., news APIs, social media APIs) and internal systems (e.g., CRM systems, ERP systems). The input is the API request or an internal database query, and the output is the retrieved data.

[0823] Specific actions

[0824] The server starts a scheduled task every morning at 8:00, sends a request to the Google News API, stores the received JSON data in an internal data store, and simultaneously calls an internal API to retrieve customer transaction history from Salesforce CRM and store it in a database.

[0825] Step 2: Analyze the collected data

[0826] server

[0827] The server analyzes the collected data using natural language processing (NLP) technology. The input is the collected text data, and the output is extracted keywords and important information.

[0828] Specific actions

[0829] The server uses Python NLP libraries (e.g., spaCy, NLTK) to tokenize news articles and extract key keywords such as "electric vehicle" and "fuel-efficient technology." It also performs part-of-speech tagging and named entity extraction.

[0830] Step 3: Indexing and storing data

[0831] server

[0832] The server indexes the parsed information and stores it in a database. The input is the extracted keywords and metadata, and the output is the indexed data.

[0833] Specific actions

[0834] The server uses Elasticsearch to create an index, adding extracted keywords and metadata to the index for future fast searches, and storing the indexed data in a MySQL or PostgreSQL database.

[0835] Step 4: User Search

[0836] Terminal

[0837] Salespeople (users) enter specific customer information and keywords into their terminals to perform searches. The input is the customer name and related technical keywords, and the output is the related information obtained as a result of the search.

[0838] Specific actions

[0839] Users access a dedicated search interface and enter information such as "electric vehicles" or "fuel-efficient technology," and the server executes an Elasticsearch query to quickly retrieve relevant documents and data.

[0840] Step 5: Generate a proposal

[0841] server

[0842] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology. The input is the search results, and the output is the generated proposal documents.

[0843] Specific actions

[0844] The server uses Python's NLG library (e.g., GPT-3, Natural Language Toolkit) to generate proposal documents from the search results, and then converts the documents into PDF or PPT format using Python's ReportLab or pptx library.

[0845] Step 6: Sentiment analysis and material adjustment

[0846] server

[0847] The emotion engine analyzes the user's input and operation log and reflects it in the proposal materials. The input is the user's operation log and input data, and the output is a proposal material based on the user's emotion.

[0848] Specific actions

[0849] The server generates a sentiment score using a SaaS-based sentiment analysis service (e.g., IBM Watson Tone Analyzer), and adjusts the tone and content of the proposal based on the sentiment score.

[0850] Step 7: Review and correct your materials

[0851] Terminal

[0852] The sales representative checks the automatically generated proposal documents on the terminal and makes corrections as necessary. The input is the automatically generated proposal documents, and the output is the corrected and confirmed proposal documents.

[0853] Specific actions

[0854] Users can download the generated PDF or PPT file, open it in Adobe Acrobat or Microsoft PowerPoint, review the contents, and make any necessary corrections.

[0855] Step 8: Submit your proposal

[0856] Terminal

[0857] The sales representative saves the revised proposal and provides it to the customer. The input is the revised proposal, and the output is the proposal provided to the customer.

[0858] Specific actions

[0859] The user saves the revised proposal document in a file format and sends it to the customer using an email client (e.g., Microsoft Outlook, Gmail).

[0860] By using the above processing steps, the system of the present invention can efficiently and quickly generate high-quality proposal materials.

[0861] (Application example 2)

[0862] 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."

[0863] In conventional proposal material creation systems, the process from data collection to analysis and generation is often performed partially manually, resulting in problems such as reduced work efficiency. Another problem is that the content of the proposal material does not adapt to the customer's situation or emotions, making it difficult to make effective proposals. The present invention aims to solve these problems by providing a system that automates the creation of proposal materials and adjusts the content based on the customer's emotions.

[0864] The specific processing by the specific 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 data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, a proposal material generation means for automatically generating proposal materials based on the searched information, an emotion engine means for analyzing the customer's input content and operation log and recognizing their emotions, and a material adjustment means for adjusting the content of the proposal materials based on the recognized emotions. This makes it possible to quickly and effectively automate the process of creating proposal materials and provide optimal proposal content tailored to the customer's emotions.

[0865] A "data collection tool" is a tool for collecting data from multiple sources.

[0866] "Data analysis means" refers to means for analyzing collected data and extracting relevant information.

[0867] The "database means" is a means for indexing the analyzed information and storing it in a database.

[0868] The "search means" is a means for inputting customer information and searching for information in the database.

[0869] The "proposal material generating means" is a means for automatically generating proposal materials based on the searched information.

[0870] The "emotion engine means" is a means for analyzing the customer's input contents and operation logs and recognizing emotions.

[0871] The "material adjustment means" is a means for adjusting the content of the proposal materials based on the recognized emotions.

[0872] The system for implementing this invention is based on an application installed on a terminal such as a smartphone or tablet. The system is composed of the following hardware and software.

[0873] Hardware:

[0874] Smartphone (iOS / Android)

[0875] tablet

[0876] Software / Libraries:

[0877] Requests (to communicate with external APIs)

[0878] NLP libraries (e.g. SpaCy)

[0879] Database connection library (e.g. SQLite)

[0880] Natural Language Generation (NLG) toolkits (e.g., GPT-3)

[0881] Emotion recognition engine (e.g. Emotion API)

[0882] The server first uses data collection tools to collect data from multiple sources, including external APIs (e.g., news APIs and social media APIs) and internal systems (CRM and ERP). For example, it uses a news API to collect the latest security news and retrieves the transaction history of a specific customer from a CRM system.

[0883] The server then analyzes the collected data using natural language processing (NLP) technology. The collected text data is tokenized and important keywords and information are extracted. For example, a security-related news article is analyzed to extract key keywords such as "surveillance camera" and "alarm system."

[0884] The collected and analyzed information is indexed using database tools and stored in a database, allowing for fast and efficient data searches.

[0885] When a user enters customer information into a terminal and performs a search, the server searches the database based on that information and extracts relevant information. For example, a user may enter the name of a specific company and related technical keywords to create a security plan for that company.

[0886] Next, the server uses a proposal generation means to automatically generate proposal materials based on the search results using natural language generation (NLG) technology. These materials are output in PDF or PPT format. For example, a proposal material centered on a "surveillance camera system" is created based on the data obtained as search results.

[0887] Furthermore, the server is equipped with an emotion engine that analyzes the user's input and operation logs to recognize their emotions. It also includes a document adjustment mechanism that adjusts the content of the proposal materials based on these emotions. For example, if the user feels that the proposal materials are too detailed and difficult to understand, the system will generate concise and easy-to-understand proposal materials.

[0888] As an example of a specific prompt sentence, the following text is entered:

[0889] "There's too much complicated information and it's hard to understand."

[0890] In this way, the present invention is a system that can quickly and effectively automate the creation of proposal materials and provide optimal proposal content that reflects the user's emotions.

[0891] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0892] Step 1:

[0893] Data collection methods

[0894] The server collects data from multiple sources. It gets the required data from external APIs and internal systems, including news APIs, social media APIs, CRM systems, and ERP systems. For example, it uses a news API to get the latest security news and collects a specific customer's transaction history from a CRM system. The API key and customer ID are used as input, and news data and customer data are obtained as output.

[0895] Step 2:

[0896] Data Analysis Methods

[0897] The server analyzes the collected data using natural language processing (NLP) technology. It tokenizes the collected text data and extracts important keywords and information. An NLP library (such as SpaCy) is used for this analysis. The collected news data and customer data are used as input, and key keywords and important information are obtained as output. Specifically, keywords such as "surveillance camera" and "alarm system" are extracted from the text.

[0898] Step 3:

[0899] Database creation method

[0900] The server indexes the analyzed information and stores it in a database, which allows for fast and efficient data searches. A database connection library (such as SQLite) is used. The analysis results (keywords and important information) are used as input, and the index data stored in the database is obtained as output.

[0901] Step 4:

[0902] Search methods

[0903] The user inputs customer information from the terminal and searches for information in the database. The server searches the database based on this input information and extracts relevant information. Customer information (company name, technical keywords, etc.) is used as input, and search results (related information) are obtained as output. In concrete terms, the user inputs a "specific company name" or "security-related technology."

[0904] Step 5:

[0905] Proposal material generation means

[0906] The server automatically generates proposal documents based on the searched information. It uses natural language generation (NLG) technology to output the proposal documents in PDF or PPT format. An NLG toolkit (e.g., GPT-3) is used. The search results are used as input, and proposal documents (in PDF or PPT format) are obtained as output. Specifically, a proposal document centered on a "surveillance camera system" is created from the search results.

[0907] Step 6:

[0908] Emotion Engine Means

[0909] The server analyzes the customer's input and operation logs to recognize emotions. An emotion recognition engine (e.g., Emotion API) is used. The user's text input and operation logs are used as input, and the recognized emotion is obtained as output. In concrete terms, if the user inputs "There is too much complicated information and it's hard to understand," the server will recognize that the user is "feeling stressed."

[0910] Step 7:

[0911] Material adjustment means

[0912] The server adjusts the content of the presentation materials based on the recognized emotions, which may include simplifying the materials or focusing on key points. The NLG toolkit may be reused. The recognized emotions and presentation materials are used as input, and the adjusted presentation materials are obtained as output. Specifically, for users who are "feeling stressed," a presentation material is generated that restructures the information in a simpler and more understandable way.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] [Third embodiment]

[0917] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0918] 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.

[0919] 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).

[0920] 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.

[0921] 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.

[0922] 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).

[0923] 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.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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."

[0929] The system of the present invention is a tool for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means. This system functions as follows.

[0930] 1. Data Collection Method

[0931] server

[0932] The server collects the necessary data from external APIs (such as industry news sites and SNS APIs) and internal systems (CRM systems, ERP systems, etc.). It collects the latest industry news and competitive information from external APIs, and customer transaction history and past proposal materials from internal systems. This allows important information from both inside and outside the company to be centrally consolidated.

[0933] Specific examples

[0934] Get the latest news about the automotive industry from the Google News API and past customer transaction history from your CRM system.

[0935] 2. Embodiments of Data Analysis Means

[0936] server

[0937] The server analyzes the collected data using natural language processing (NLP) technology, extracting keywords and important information from the data and analyzing relevance. The analyzed data is then used to generate proposal materials.

[0938] Specific examples

[0939] Keywords such as "fuel efficiency improvement technology" and "electric vehicles" are extracted from the collected news articles.

[0940] 3. Embodiment of database creation means

[0941] server

[0942] The analyzed information is indexed by the database creation means and stored in a database, which allows for efficient data retrieval by the subsequent search means.

[0943] Specific examples

[0944] The extracted keywords and information are added as metadata to each entry in the database.

[0945] 4. Embodiments of Search Means

[0946] Terminal

[0947] Salespeople use terminals to input customer information and perform searches. The server searches the database based on the input customer information and extracts relevant information. The search results are used to generate the next proposal materials.

[0948] Specific examples

[0949] If a salesperson wants to create a proposal for a particular automaker, they enter the name of the automaker and the technology they're interested in.

[0950] 5. Embodiment of Proposal Material Generation Means

[0951] server

[0952] The server automatically generates proposal documents based on the searched information using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to sales representatives.

[0953] Specific examples

[0954] Based on the information on "fuel efficiency improvement technologies" obtained as search results and past success stories, a proposal document is created and output in PDF format.

[0955] As described above, the system of the present invention automates the entire process from data collection to the automatic generation of proposal materials, thereby improving the efficiency and sophistication of sales activities, enabling sales representatives to quickly and effectively make proposals that meet customer needs.

[0956] The processing flow will be explained below.

[0957] Step 1: Data collection

[0958] server

[0959] The server retrieves the necessary data from external APIs (for example, news APIs or SNS APIs) and internal systems (CRM systems or ERP systems). From external APIs, it obtains industry news and competitive information, and from internal systems, it collects customer transaction history and past proposal materials. This data is then stored in temporary storage.

[0960] Step 2: Data analysis

[0961] server

[0962] After collecting the data, the server analyzes it using natural language processing (NLP) technology. Specifically, it tokenizes the collected text data and extracts keywords and important information. This analysis process generates meta-information about the data.

[0963] Step 3: Database creation

[0964] server

[0965] The server indexes the parsed information and stores it in a database, adding related keywords and category information to the database and creating an index for faster response to multiple search queries.

[0966] Step 4: Enter customer information

[0967] User

[0968] A salesperson (user) inputs customer information (for example, company name, industry, technology of interest) from a terminal. This information is used to search the database by the search means.

[0969] Step 5: Database Search

[0970] server

[0971] The server searches the database based on the customer information entered by the user, using SQL queries and full-text search engines to efficiently extract relevant data.

[0972] Step 6: Data Selection

[0973] server

[0974] The search results are then sorted to find the information that best addresses the customer's needs, a process driven by an algorithm that takes into account relevance scores and past ratings data.

[0975] Step 7: Generate a proposal

[0976] server

[0977] The server automatically generates proposal documents based on the selected information using natural language generation (NLG) technology. The generated proposal documents are customized to meet the client's needs and converted into easy-to-read formats (PDF or PPT).

[0978] Step 8: Review and revise your proposal

[0979] Terminal

[0980] The sales representative checks the automatically generated proposal materials on the terminal, corrects the contents of the materials as necessary, and saves them as the final proposal materials.

[0981] Step 9: Submit your proposal

[0982] Terminal

[0983] Once the revisions are complete, the proposal materials are saved in PDF or PPT format and provided to the customer via email or other means.

[0984] Example 1

[0985] 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."

[0986] In the past, making quick and effective proposals to corporate customers to address their challenges required the collection, analysis, database creation, search, and document creation of massive amounts of data, and when sales representatives performed these tasks manually, it was extremely time-consuming and labor-intensive. Furthermore, manual data processing was prone to errors, resulting in inconsistent quality in proposals submitted to customers. This made it difficult to respond quickly to customer needs, reducing the efficiency and effectiveness of sales activities.

[0987] 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.

[0988] In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, and a proposal material generation means for automatically generating proposal materials using natural language generation technology based on the searched information and converting the materials into a predetermined format. This enables sales representatives to process data quickly and accurately and provide high-quality proposal materials to customers in a timely manner.

[0989] "Data collection means" refers to the function of collecting necessary data from multiple sources.

[0990] "Data analysis means" refers to the function of analyzing collected data using natural language processing technology and extracting relevant information.

[0991] "Natural language processing technology" refers to technology for understanding and processing human language, and to technology for extracting keywords and important information in data analysis.

[0992] "Database creation means" refers to the function of indexing the analyzed information and storing it in a database.

[0993] "Search means" refers to the function of entering customer information, searching for information in the database, and extracting the necessary information.

[0994] "Proposal material generation means" refers to a function that automatically generates proposal materials using natural language generation technology based on searched information and converts the materials into a specified format.

[0995] "Natural language generation technology" refers to technology that generates sentences in natural language that is easy for humans to understand based on accumulated data.

[0996] An "external API" refers to an interface for obtaining data from external systems or services.

[0997] "Internal system" refers to a system used within a company for data management and business processing.

[0998] "Database" refers to a collection of data that stores collected and analyzed information and makes it efficiently searchable and accessible.

[0999] The system of the present invention is a tool for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means. This system functions as follows using a server and terminals.

[1000] 1. Data Collection Method

[1001] Server Roles

[1002] The server collects the necessary data from external APIs and internal systems. Specifically, it obtains the latest industry news and competitive information from Google News API and Twitter API, and customer transaction history and past proposal materials from CRM and ERP systems. This allows important internal and external information to be centrally consolidated.

[1003] Specific examples

[1004] The server uses the Google News API to get the latest news about the automotive industry and the API of the company's CRM system to get the transaction history of customer XYZ.

[1005] 2. Embodiments of Data Analysis Means

[1006] Server Roles

[1007] The server analyzes the collected data using natural language processing (NLP) technology, extracting keywords and important information from the data and analyzing their relevance. This organizes the information needed to generate subsequent proposal materials.

[1008] Specific examples

[1009] The server extracts keywords such as "fuel efficiency improvement technology" and "electric vehicles" from the collected news articles, and extracts "top priority projects" and "purchase history" from customer transaction history.

[1010] 3. Embodiment of database creation means

[1011] Server Roles

[1012] The server indexes the parsed information and stores it in a database, with each entry being accompanied by associated metadata and organized for efficient searching.

[1013] Specific examples

[1014] The server stores keywords such as "fuel efficiency technology" and "electric vehicle" as entries in a database, and adds related news articles and transaction history information as metadata.

[1015] 4. Embodiments of Search Means

[1016] Device Role

[1017] The user, a salesperson, uses a terminal to input customer information and perform a search. The server searches the database based on the input information, extracts relevant information, and returns it to the terminal.

[1018] Specific examples

[1019] A salesperson enters "XYZ Motors Co., Ltd." and "electric vehicle" into a search form on a terminal. The server searches the database based on this information, extracts relevant news articles and transaction history information, and sends it back to the terminal.

[1020] 5. Embodiment of Proposal Material Generation Means

[1021] Server Roles

[1022] The server automatically generates proposal documents based on the searched information using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to the sales representatives.

[1023] Specific examples

[1024] The server creates a proposal document based on the latest information on "electric vehicles" from the search results and the customer's transaction history. The created proposal document is converted into PDF format and sent to the sales representative's terminal.

[1025] Prompts based on concrete examples

[1026] Here's an example prompt that can be fed into a generative AI model to generate a proposal:

[1027] Customer information:

[1028] Customer Name: XYZ Automobiles Co., Ltd.

[1029] Technology of interest: Electric vehicles, fuel efficiency improvement technology

[1030] Acquired data:

[1031] Automotive industry news from Google News API

[1032] Past transaction history with XYZ Automotive from internal CRM

[1033] Proposal to generate:

[1034] Title: Proposal for XYZ Motors Co., Ltd.

[1035] Contents:

[1036] Latest trends in the electric vehicle market

[1037] Fuel efficiency improvement technology trends of competitors

[1038] Summary of XYZ Motors' past performance

[1039] The system of the present invention enables salespeople to process data quickly and accurately, and provide high-quality proposal materials to customers in a timely manner.

[1040] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1041] Step 1: Collect data

[1042] server

[1043] The server collects data from multiple sources, such as the latest industry news and competitive information from Google News API and Twitter API, and customer transaction history and past proposal documents from CRM and ERP systems. All of this external and internal data is temporarily stored in storage.

[1044] Input and Output

[1045] Input: External API endpoint, internal system API endpoint

[1046] Output: Collected data from multiple sources (news articles, trading history, etc.)

[1047] Specific actions

[1048] The server queries the Google News API to retrieve the latest news articles related to the automotive industry, and at the same time, uses the CRM system's API to retrieve the transaction history for a specific customer ID. These data are then temporarily stored in storage.

[1049] Step 2: Data analysis

[1050] server

[1051] The server reads the collected data from the storage and analyzes it using natural language processing (NLP) techniques, which extracts keywords and important information from the text and analyzes their relevance. The analysis results are then prepared for the next step.

[1052] Input and Output

[1053] Input: Collected data (news articles, trading history, etc.)

[1054] Output: Analyzed information (keywords, important phrases, relevance)

[1055] Specific actions

[1056] The server reads news articles and uses an NLP engine to extract keywords such as "fuel-efficient technology" and "electric vehicles," while simultaneously extracting important information from customer transaction histories, such as "top priority projects" and "purchase history," and analyzing their relevance.

[1057] Step 3: Store in the database

[1058] server

[1059] The server indexes the parsed information and stores it in a database for efficient searching. Metadata is added to the information to make it easier to find and manage within the database.

[1060] Input and Output

[1061] Input: Analyzed data (keywords, key phrases, relevance)

[1062] Output: Indexed database entries

[1063] Specific actions

[1064] The server stores keywords such as "fuel efficiency technology" and "electric vehicles" along with related news articles and transaction history information in a database, and adds appropriate metadata to each.

[1065] Step 4: Search for data

[1066] Terminal

[1067] A salesperson, who is a user, uses a terminal to input customer information (such as customer name, technology of interest, etc.) into a search form. The server searches the database based on the input information, extracts relevant information, and returns it to the terminal.

[1068] Input and Output

[1069] Input: Customer information (customer name, technology of interest)

[1070] Output: Search results (related news articles, transaction history information)

[1071] Specific actions

[1072] A salesperson enters "XYZ Motors Corporation" and "electric vehicles" into a search form on a terminal. The server retrieves relevant entries from the database and returns relevant news articles and transaction history information to the terminal.

[1073] Step 5: Generate a proposal

[1074] server

[1075] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to the sales representatives.

[1076] Input and Output

[1077] Input: Search results (related news articles, transaction history information)

[1078] Output: Proposal materials (PDF, PPT format)

[1079] Specific actions

[1080] The server creates a proposal document based on the latest information about electric vehicles obtained as a search result and the customer's transaction history. The proposal document is converted into PDF format and sent to the sales representative's terminal.

[1081] (Application example 1)

[1082] 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."

[1083] In conventional sales activities, making quick and effective proposals to corporate customers to address their challenges requires the collection and analysis of vast amounts of information, which takes up a great deal of time and effort. Creating proposal materials also takes time, making it difficult for sales representatives to respond quickly amid their busy schedules. Proposing new production technologies and equipment installations at factories, in particular, requires real-time information gathering and immediate proposals.

[1084] 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.

[1085] In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, and a proposal material generation means for automatically generating proposal materials based on the searched information and displaying them on a visual device. This enables sales representatives to collect and analyze data within the factory in real time and make quick and effective proposals to factory managers and customers.

[1086] A "data collection means" is a device or function that collects necessary data from multiple sources.

[1087] "Data analysis means" refers to a device or function that analyzes collected data and extracts relevant information.

[1088] The "database creation means" is a device or function that indexes the analyzed information and stores it in a database.

[1089] The "search means" is a device or function that inputs customer information and searches for information in the database.

[1090] The "proposal material generating means" is a device or function that automatically generates proposal materials based on the searched information and displays them on a visual device.

[1091] An "External API" is an application programming interface provided over the Internet.

[1092] "Internal systems" are computer systems and software used within a company.

[1093] "Natural language generation technology" is a technology that automatically generates sentences in natural language that are easy for humans to understand.

[1094] A "visual device" is a device for visually displaying information.

[1095] The present invention is a system for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means.

[1096] 1. Data Collection Method

[1097] The server collects the necessary data from external APIs (such as industry news sites and social media APIs) and internal systems (CRM systems, ERP systems, etc.), enabling the latest industry news, competitive information, and customer transaction history to be centrally aggregated.

[1098] As a concrete example, the server uses a news API to get information about the latest factory automation technologies and extracts past transaction history from a CRM system.

[1099] 2. Embodiments of Data Analysis Means

[1100] The server analyzes the collected data using natural language processing (NLP) technology. NLP technology extracts keywords and important information from the data and analyzes their relevance. The analyzed data is then used to generate proposal materials.

[1101] As a specific example, the server extracts keywords such as "automation technology" and "robot introduction" from collected news articles.

[1102] 3. Embodiment of database creation means

[1103] The analyzed information is indexed by the database creation means and stored in a database, which allows for efficient data retrieval by the subsequent search means.

[1104] As a specific example, extracted keywords and information are added as metadata to each entry in the database.

[1105] 4. Embodiments of Search Means

[1106] Salespeople use terminals to input customer information and perform searches. The server searches the database based on the input customer information and extracts relevant information. The search results are used to generate proposal materials.

[1107] As a specific example, when a sales representative prepares a proposal document for a particular automobile manufacturer, he or she inputs the company name and interest in new technologies.

[1108] 5. Embodiment of Proposal Material Generation Means

[1109] The server automatically generates a proposal document based on the searched information using natural language generation (NLG) technology, converts the generated proposal document into PDF or PPT format, and provides it to the sales representative. At the same time, the information is visually displayed via the smart glasses.

[1110] As a specific example, a proposal document is created based on information about "automation technology" obtained from search results and past success stories, and the document is output in PDF format and displayed on a visual device.

[1111] Example prompt sentence:

[1112] "Get the latest competitive information and technology trends related to factory automation technology, and generate and provide proposal materials that best meet the current needs of your factory based on past proposal materials and transaction history."

[1113] In this way, the above-mentioned means realizes more efficient and sophisticated sales activities, and enables salespeople to make proposals that meet customer needs quickly and effectively.

[1114] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1115] Step 1:

[1116] The server collects data from external APIs and internal systems. As input, it specifies the URL of the external API or the database of the internal system, and as output, it obtains collected data such as industry news and customer transaction history. Specifically, the server sends HTTP requests to the external API and the internal system, and stores the returned data in temporary files or memory.

[1117] Step 2:

[1118] The server analyzes the collected data using natural language processing (NLP) techniques. It uses the data collected in step 1 as input and extracts keywords and key information as output. Specifically, it uses an NLP library (e.g., spaCy or a natural language toolkit) to extract keywords and phrases from the data and analyze their relationships.

[1119] Step 3:

[1120] The server indexes the parsed information and stores it in a database. It uses the keywords and information extracted in step 2 as input and gets the indexed database entries as output. Specifically, it uses an indexing algorithm to map the keywords and related information to database fields and writes them to the database.

[1121] Step 4:

[1122] A user uses a terminal to input customer information and search for related information. A query such as a customer name or technology interest is used as input, and relevant database entries are obtained as output. Specifically, the server receives the query sent from the terminal, executes the search query against the database, and returns the results to the terminal.

[1123] Step 5:

[1124] The server automatically generates a proposal document based on the searched information and displays it on the visual device. It uses the search results obtained in step 4 as input, and generates a PDF or PPT file of the proposal document as output, which is displayed on the visual device (e.g., smart glasses). Specifically, it uses natural language generation (NLG) technology to compose the proposal document, exports the document in a specified format, and sends the file to the visual device.

[1125] This process allows sales representatives to collect and analyze data in real time within the factory, generating and visually verifying proposals quickly and effectively.

[1126] 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.

[1127] The system of the present invention is a tool for making prompt and effective proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, proposal material generation means, and an emotion engine that recognizes the user's emotions. The specific operation of each means is explained below.

[1128] 1. Data Collection Method

[1129] server

[1130] The server obtains the necessary data from external APIs (e.g., news APIs, SNS APIs) and internal systems (CRM systems, ERP systems). From external APIs, it collects industry news and competitive information, and from internal systems, it obtains customer transaction history and past proposal materials.

[1131] Specific examples

[1132] It uses the Google News API to get the latest automotive industry news and collects transaction history for specific customers from a CRM system.

[1133] 2. Embodiments of Data Analysis Means

[1134] server

[1135] The server analyzes the collected data using natural language processing (NLP) techniques, tokenizing the text data and extracting keywords and important information, which are then used in subsequent processes.

[1136] Specific examples

[1137] The collected news articles are analyzed using NLP technology to extract key keywords such as "electric vehicles" and "fuel efficiency improvement technology."

[1138] 3. Embodiment of database creation means

[1139] server

[1140] The server indexes the analyzed information and stores it in a database, adding related keywords and category information to the database to enable fast and efficient data searches.

[1141] Specific examples

[1142] The extracted keywords and metadata are stored in a database for future searches.

[1143] 4. Embodiments of Search Means

[1144] Terminal

[1145] The salesperson (user) enters customer information into the terminal and performs a search. The server searches the database based on the entered information and extracts relevant information.

[1146] Specific examples

[1147] A sales representative enters the company name and related technical keywords to create a proposal document for a specific automobile manufacturer.

[1148] 5. Embodiment of Proposal Material Generation Means

[1149] server

[1150] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT formats.

[1151] Specific examples

[1152] Based on the search results, a proposal document focusing on "fuel efficiency improvement technologies" is created using NLG technology and output in PDF format.

[1153] 6. Embodiment of Emotion Engine

[1154] server

[1155] The emotion engine analyzes the user's input and operation logs to recognize the user's emotions. The information analyzed by the emotion engine is reflected in the content of the proposal materials.

[1156] Specific examples

[1157] If the emotion engine determines that a salesperson is tired, the system will generate a concise and easy-to-understand sales pitch.

[1158] 7. Review and revise the proposal materials

[1159] Terminal

[1160] The sales representative checks the automatically generated proposal materials on their device, makes any necessary corrections, and saves the corrected materials as the final proposal materials.

[1161] Specific examples

[1162] Review the generated proposal and customize some of the content.

[1163] 8. Providing proposal materials

[1164] Terminal

[1165] Sales representatives save the revised proposal materials in PDF or PPT format and provide them to customers via email or other means.

[1166] As a result, the system of the present invention automates everything from data collection to recognition of customer emotions, enabling the rapid creation and provision of effective proposal materials, thereby improving the efficiency and sophistication of sales activities.

[1167] The processing flow will be explained below.

[1168] Step 1: Data collection

[1169] server

[1170] The server retrieves the necessary data from external APIs (news APIs and SNS APIs) and internal systems (CRM systems and ERP systems). It collects the latest industry information from the news API and customer transaction history and past proposal materials from the internal systems. This data is then stored in temporary storage.

[1171] Specific examples

[1172] Use the Google News API to get the latest news from the automotive industry and collect transaction history for specific customers from your CRM system.

[1173] Step 2: Data analysis

[1174] server

[1175] The collected data is analyzed using natural language processing (NLP) technology. Specifically, the text data is tokenized and keywords and important information are extracted, generating meta-information about the data.

[1176] Specific examples

[1177] Keywords such as "electric vehicles" and "fuel efficiency improvement technology" are extracted from the collected news articles using natural language processing.

[1178] Step 3: Database creation

[1179] server

[1180] The analyzed information is indexed and stored in a database, which involves adding related keywords and category information to the database to create an index that improves the efficiency of data searches.

[1181] Specific examples

[1182] The extracted keywords and metadata are stored for each entry in the database for future searches.

[1183] Step 4: Enter customer information

[1184] User

[1185] Salespeople enter customer information (company name, industry, technology of interest, etc.) into their terminals. This information is used by the server to search the database.

[1186] Specific examples

[1187] To generate proposal materials for a specific automobile manufacturer, a sales representative enters a specific company name and related technical keywords into an input form on the terminal.

[1188] Step 5: Database Search

[1189] server

[1190] The server searches the database based on the customer information entered by the user, using SQL queries and full-text search engines to efficiently extract relevant information.

[1191] Specific examples

[1192] Search for relevant news articles and past proposals in the database based on the company name or keywords entered.

[1193] Step 6: Sentiment Analysis

[1194] server

[1195] The emotion engine analyzes the user's input and operation logs to recognize their emotions. The results of the emotion analysis are then reflected appropriately in the content of the proposal materials.

[1196] Specific examples

[1197] Based on the information entered by the sales representative and the amount of time spent operating the device, the emotion engine detects fatigue and notifies the system.

[1198] Step 7: Data Selection

[1199] server

[1200] The search results are then filtered to best address the customer's needs based on the user's emotional state, using an algorithm that takes into account relevance scores and past ratings data.

[1201] Specific examples

[1202] Taking into account the results of the sentiment analysis, the most relevant data related to "electric vehicles" is selected.

[1203] Step 8: Generate a proposal

[1204] server

[1205] Based on the selected information, proposal materials are automatically generated using natural language generation (NLG) technology. The generated materials are customized to meet the client's needs and converted into PDF or PPT format.

[1206] Specific examples

[1207] Proposal materials are created based on relevant information, and the content is made concise and easy to understand based on sentiment analysis, and then output in PDF format.

[1208] Step 9: Review and revise your proposal

[1209] Terminal

[1210] The sales representative checks the automatically generated proposal documents on the terminal, corrects the contents as necessary, and saves them as the final proposal documents.

[1211] Specific examples

[1212] Review the generated proposal, customize some of the content, and save it as the final version.

[1213] Step 10: Submit your proposal

[1214] Terminal

[1215] Sales representatives save the revised proposal materials in PDF or PPT format and provide them to customers via email or other means.

[1216] Specific examples

[1217] After the revisions are complete, save the proposal document in PDF format and send it to the customer by email.

[1218] Example 2

[1219] 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."

[1220] In conventional proposal document creation systems, each step from data collection and analysis to document generation is often done manually, requiring a great deal of time and effort. It is also difficult to create proposal documents that take customer emotions into account, posing a major challenge to customer satisfaction. To solve these problems and create proposal documents efficiently and effectively, an automated system is needed.

[1221] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information, and a database creation means for indexing the analyzed information and storing it in a database. This automates the entire process from collection to analysis and generation of proposal materials, making it possible to efficiently create high-quality proposal materials. In addition, by using an emotion recognition means, it is possible to create proposal materials that take customer emotions into consideration.

[1222] "Data collection means" refers to the means for obtaining necessary data from multiple sources.

[1223] "Natural language processing technology" is a technology that analyzes collected text data and extracts keywords and important information.

[1224] "Indexing" is the process of creating a data structure that allows the data to be efficiently searched.

[1225] A "database" is a system that stores collected and analyzed data in an organized manner and makes it easy to search and access.

[1226] The "search means" is a means for searching for information in the database based on the customer information entered by the user.

[1227] "Natural language generation technology" is a technology that automatically generates sentences based on searched information.

[1228] The "proposal material generation means" is a means for automatically generating proposal materials using natural language generation technology and converting them into a document format.

[1229] The "emotion recognition means" is a means for analyzing the user's input contents and operation log and recognizing the user's emotions.

[1230] The system of the present invention is a tool for making quick and effective proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, proposal material generation means, and an emotion engine that recognizes user emotions. This makes it possible to automate the creation of proposal materials and to make advanced proposals that take into account the client's emotions. The specific operation of each means is explained below.

[1231] Data collection methods

[1232] server

[1233] The server collects the necessary data from multiple external APIs (e.g., news API, SNS API) and internal systems (e.g., CRM system, ERP system). For example, it uses the Google News API to obtain the latest news in the automotive industry and collects the transaction history of specific customers from the internal CRM system.

[1234] concrete action

[1235] The server starts a scheduled task every morning at 8:00, sends a request to the specified API endpoint, and stores the received data in an internal data store in JSON format.

[1236] Data Analysis Methods

[1237] server

[1238] The server analyzes the collected data using natural language processing (NLP) techniques, specifically using Python NLP libraries (e.g., spaCy, NLTK) to tokenize the text and extract important keywords and information.

[1239] concrete action

[1240] The server analyzes the collected news articles using NLP technology and extracts key keywords such as "electric vehicles" and "fuel efficiency improvement technology."

[1241] Database creation method

[1242] server

[1243] The server indexes the parsed information and stores it in a database (e.g., Elasticsearch, MySQL, PostgreSQL), allowing for fast and efficient data retrieval.

[1244] concrete action

[1245] The server stores the extracted keywords and metadata in a database for future searches.

[1246] Search methods

[1247] Terminal

[1248] The sales representative (user) enters specific customer information and keywords into the terminal and performs a search. The server searches the database based on the entered information and extracts relevant information.

[1249] concrete action

[1250] Users access a dedicated search screen and enter a customer name or related technology as search keywords, and the server retrieves the relevant data using an Elasticsearch query.

[1251] Proposal material generation means

[1252] server

[1253] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT formats.

[1254] concrete action

[1255] The server uses Python's NLG libraries (e.g., GPT-3, Natural Language Toolkit) to generate proposal documents from the search results, which are then converted to PDF or PPT format using Python's ReportLab or pptx libraries.

[1256] Embodiment of Emotion Engine

[1257] server

[1258] The emotion engine analyzes user input and operation logs to recognize the user's emotions, which are reflected in the content of proposal materials.

[1259] concrete action

[1260] The server uses a SaaS-based emotion analysis service (e.g., IBM Watson Tone Analyzer) to generate an emotion score from operation logs and input data, and adjusts the content and tone of the proposal materials based on that score.

[1261] Specific examples (prompt sentence examples)

[1262] For example, if a salesperson is creating a proposal for a particular car manufacturer, they might use the following prompt:

[1263] "Please create a proposal document that includes the latest news and technological trends about a specific customer's automobile manufacturer. The keywords are 'electric vehicles' and 'fuel efficiency improvement technology.'"

[1264] In this way, the system automates everything from data collection to customer sentiment recognition, enabling efficient creation of high-quality proposal materials and supporting improved sales activities.

[1265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1266] Program processing flow

[1267] Step 1: Collect data

[1268] server

[1269] The server collects the required data from external APIs (e.g., news APIs, social media APIs) and internal systems (e.g., CRM systems, ERP systems). The input is the API request or an internal database query, and the output is the retrieved data.

[1270] Specific actions

[1271] The server starts a scheduled task every morning at 8:00, sends a request to the Google News API, stores the received JSON data in an internal data store, and simultaneously calls an internal API to retrieve customer transaction history from Salesforce CRM and store it in a database.

[1272] Step 2: Analyze the collected data

[1273] server

[1274] The server analyzes the collected data using natural language processing (NLP) technology. The input is the collected text data, and the output is extracted keywords and important information.

[1275] Specific actions

[1276] The server uses Python NLP libraries (e.g., spaCy, NLTK) to tokenize news articles and extract key keywords such as "electric vehicle" and "fuel-efficient technology." It also performs part-of-speech tagging and named entity extraction.

[1277] Step 3: Indexing and storing data

[1278] server

[1279] The server indexes the parsed information and stores it in a database. The input is the extracted keywords and metadata, and the output is the indexed data.

[1280] Specific actions

[1281] The server uses Elasticsearch to create an index, adding extracted keywords and metadata to the index for future fast searches, and storing the indexed data in a MySQL or PostgreSQL database.

[1282] Step 4: User Search

[1283] Terminal

[1284] Salespeople (users) enter specific customer information and keywords into their terminals to perform searches. The input is the customer name and related technical keywords, and the output is the related information obtained as a result of the search.

[1285] Specific actions

[1286] Users access a dedicated search interface and enter information such as "electric vehicles" or "fuel-efficient technology," and the server executes an Elasticsearch query to quickly retrieve relevant documents and data.

[1287] Step 5: Generate a proposal

[1288] server

[1289] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology. The input is the search results, and the output is the generated proposal documents.

[1290] Specific actions

[1291] The server uses Python's NLG library (e.g., GPT-3, Natural Language Toolkit) to generate proposal documents from the search results, and then converts the documents into PDF or PPT format using Python's ReportLab or pptx library.

[1292] Step 6: Sentiment analysis and material adjustment

[1293] server

[1294] The emotion engine analyzes the user's input and operation log and reflects it in the proposal materials. The input is the user's operation log and input data, and the output is a proposal material based on the user's emotion.

[1295] Specific actions

[1296] The server generates a sentiment score using a SaaS-based sentiment analysis service (e.g., IBM Watson Tone Analyzer), and adjusts the tone and content of the proposal based on the sentiment score.

[1297] Step 7: Review and correct your materials

[1298] Terminal

[1299] The sales representative checks the automatically generated proposal documents on the terminal and makes corrections as necessary. The input is the automatically generated proposal documents, and the output is the corrected and confirmed proposal documents.

[1300] Specific actions

[1301] Users can download the generated PDF or PPT file, open it in Adobe Acrobat or Microsoft PowerPoint, review the contents, and make any necessary corrections.

[1302] Step 8: Submit your proposal

[1303] Terminal

[1304] The sales representative saves the revised proposal and provides it to the customer. The input is the revised proposal, and the output is the proposal provided to the customer.

[1305] Specific actions

[1306] The user saves the revised proposal document in a file format and sends it to the customer using an email client (e.g., Microsoft Outlook, Gmail).

[1307] By using the above processing steps, the system of the present invention can efficiently and quickly generate high-quality proposal materials.

[1308] (Application example 2)

[1309] 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."

[1310] In conventional proposal material creation systems, the process from data collection to analysis and generation is often performed partially manually, resulting in problems such as reduced work efficiency. Another problem is that the content of the proposal material does not adapt to the customer's situation or emotions, making it difficult to make effective proposals. The present invention aims to solve these problems by providing a system that automates the creation of proposal materials and adjusts the content based on the customer's emotions.

[1311] The specific processing by the specific 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 data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, a proposal material generation means for automatically generating proposal materials based on the searched information, an emotion engine means for analyzing the customer's input content and operation log and recognizing their emotions, and a material adjustment means for adjusting the content of the proposal materials based on the recognized emotions. This makes it possible to quickly and effectively automate the process of creating proposal materials and provide optimal proposal content tailored to the customer's emotions.

[1312] A "data collection tool" is a tool for collecting data from multiple sources.

[1313] "Data analysis means" refers to means for analyzing collected data and extracting relevant information.

[1314] The "database means" is a means for indexing the analyzed information and storing it in a database.

[1315] The "search means" is a means for inputting customer information and searching for information in the database.

[1316] The "proposal material generating means" is a means for automatically generating proposal materials based on the searched information.

[1317] The "emotion engine means" is a means for analyzing the customer's input contents and operation logs and recognizing emotions.

[1318] The "material adjustment means" is a means for adjusting the content of the proposal materials based on the recognized emotions.

[1319] The system for implementing this invention is based on an application installed on a terminal such as a smartphone or tablet. The system is composed of the following hardware and software.

[1320] Hardware:

[1321] Smartphone (iOS / Android)

[1322] tablet

[1323] Software / Libraries:

[1324] Requests (to communicate with external APIs)

[1325] NLP libraries (e.g. SpaCy)

[1326] Database connection library (e.g. SQLite)

[1327] Natural Language Generation (NLG) toolkits (e.g., GPT-3)

[1328] Emotion recognition engine (e.g. Emotion API)

[1329] The server first uses data collection tools to collect data from multiple sources, including external APIs (e.g., news APIs and social media APIs) and internal systems (CRM and ERP). For example, it uses a news API to collect the latest security news and retrieves the transaction history of a specific customer from a CRM system.

[1330] The server then analyzes the collected data using natural language processing (NLP) technology. The collected text data is tokenized and important keywords and information are extracted. For example, a security-related news article is analyzed to extract key keywords such as "surveillance camera" and "alarm system."

[1331] The collected and analyzed information is indexed using database tools and stored in a database, allowing for fast and efficient data searches.

[1332] When a user enters customer information into a terminal and performs a search, the server searches the database based on that information and extracts relevant information. For example, a user may enter the name of a specific company and related technical keywords to create a security plan for that company.

[1333] Next, the server uses a proposal generation means to automatically generate proposal materials based on the search results using natural language generation (NLG) technology. These materials are output in PDF or PPT format. For example, a proposal material centered on a "surveillance camera system" is created based on the data obtained as search results.

[1334] Furthermore, the server is equipped with an emotion engine that analyzes the user's input and operation logs to recognize their emotions. It also includes a document adjustment mechanism that adjusts the content of the proposal materials based on these emotions. For example, if the user feels that the proposal materials are too detailed and difficult to understand, the system will generate concise and easy-to-understand proposal materials.

[1335] As an example of a specific prompt sentence, the following text is entered:

[1336] "There's too much complicated information and it's hard to understand."

[1337] In this way, the present invention is a system that can quickly and effectively automate the creation of proposal materials and provide optimal proposal content that reflects the user's emotions.

[1338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1339] Step 1:

[1340] Data collection methods

[1341] The server collects data from multiple sources. It gets the required data from external APIs and internal systems, including news APIs, social media APIs, CRM systems, and ERP systems. For example, it uses a news API to get the latest security news and collects a specific customer's transaction history from a CRM system. The API key and customer ID are used as input, and news data and customer data are obtained as output.

[1342] Step 2:

[1343] Data Analysis Methods

[1344] The server analyzes the collected data using natural language processing (NLP) technology. It tokenizes the collected text data and extracts important keywords and information. An NLP library (such as SpaCy) is used for this analysis. The collected news data and customer data are used as input, and key keywords and important information are obtained as output. Specifically, keywords such as "surveillance camera" and "alarm system" are extracted from the text.

[1345] Step 3:

[1346] Database creation method

[1347] The server indexes the analyzed information and stores it in a database, which allows for fast and efficient data searches. A database connection library (such as SQLite) is used. The analysis results (keywords and important information) are used as input, and the index data stored in the database is obtained as output.

[1348] Step 4:

[1349] Search methods

[1350] The user inputs customer information from the terminal and searches for information in the database. The server searches the database based on this input information and extracts relevant information. Customer information (company name, technical keywords, etc.) is used as input, and search results (related information) are obtained as output. In concrete terms, the user inputs a "specific company name" or "security-related technology."

[1351] Step 5:

[1352] Proposal material generation means

[1353] The server automatically generates proposal documents based on the searched information. It uses natural language generation (NLG) technology to output the proposal documents in PDF or PPT format. An NLG toolkit (e.g., GPT-3) is used. The search results are used as input, and proposal documents (in PDF or PPT format) are obtained as output. Specifically, a proposal document centered on a "surveillance camera system" is created from the search results.

[1354] Step 6:

[1355] Emotion Engine Means

[1356] The server analyzes the customer's input and operation logs to recognize emotions. An emotion recognition engine (e.g., Emotion API) is used. The user's text input and operation logs are used as input, and the recognized emotion is obtained as output. In concrete terms, if the user inputs "There is too much complicated information and it's hard to understand," the server will recognize that the user is "feeling stressed."

[1357] Step 7:

[1358] Material adjustment means

[1359] The server adjusts the content of the presentation materials based on the recognized emotions, which may include simplifying the materials or focusing on key points. The NLG toolkit may be reused. The recognized emotions and presentation materials are used as input, and the adjusted presentation materials are obtained as output. Specifically, for users who are "feeling stressed," a presentation material is generated that restructures the information in a simpler and more understandable way.

[1360] 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.

[1361] 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.

[1362] 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.

[1363] [Fourth embodiment]

[1364] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1365] 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.

[1366] 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).

[1367] 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.

[1368] 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.

[1369] 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).

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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."

[1377] The system of the present invention is a tool for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means. This system functions as follows.

[1378] 1. Data Collection Method

[1379] server

[1380] The server collects the necessary data from external APIs (such as industry news sites and SNS APIs) and internal systems (CRM systems, ERP systems, etc.). It collects the latest industry news and competitive information from external APIs, and customer transaction history and past proposal materials from internal systems. This allows important information from both inside and outside the company to be centrally consolidated.

[1381] Specific examples

[1382] Get the latest news about the automotive industry from the Google News API and past customer transaction history from your CRM system.

[1383] 2. Embodiments of Data Analysis Means

[1384] server

[1385] The server analyzes the collected data using natural language processing (NLP) technology, extracting keywords and important information from the data and analyzing relevance. The analyzed data is then used to generate proposal materials.

[1386] Specific examples

[1387] Keywords such as "fuel efficiency improvement technology" and "electric vehicles" are extracted from the collected news articles.

[1388] 3. Embodiment of database creation means

[1389] server

[1390] The analyzed information is indexed by the database creation means and stored in a database, which allows for efficient data retrieval by the subsequent search means.

[1391] Specific examples

[1392] The extracted keywords and information are added as metadata to each entry in the database.

[1393] 4. Embodiments of Search Means

[1394] Terminal

[1395] Salespeople use terminals to input customer information and perform searches. The server searches the database based on the input customer information and extracts relevant information. The search results are used to generate the next proposal materials.

[1396] Specific examples

[1397] If a salesperson wants to create a proposal for a particular automaker, they enter the name of the automaker and the technology they're interested in.

[1398] 5. Embodiment of Proposal Material Generation Means

[1399] server

[1400] The server automatically generates proposal documents based on the searched information using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to sales representatives.

[1401] Specific examples

[1402] Based on the information on "fuel efficiency improvement technologies" obtained as search results and past success stories, a proposal document is created and output in PDF format.

[1403] As described above, the system of the present invention automates the entire process from data collection to the automatic generation of proposal materials, thereby improving the efficiency and sophistication of sales activities, enabling sales representatives to quickly and effectively make proposals that meet customer needs.

[1404] The processing flow will be explained below.

[1405] Step 1: Data collection

[1406] server

[1407] The server retrieves the necessary data from external APIs (for example, news APIs or SNS APIs) and internal systems (CRM systems or ERP systems). From external APIs, it obtains industry news and competitive information, and from internal systems, it collects customer transaction history and past proposal materials. This data is then stored in temporary storage.

[1408] Step 2: Data analysis

[1409] server

[1410] After collecting the data, the server analyzes it using natural language processing (NLP) technology. Specifically, it tokenizes the collected text data and extracts keywords and important information. This analysis process generates meta-information about the data.

[1411] Step 3: Database creation

[1412] server

[1413] The server indexes the parsed information and stores it in a database, adding related keywords and category information to the database and creating an index for faster response to multiple search queries.

[1414] Step 4: Enter customer information

[1415] User

[1416] A salesperson (user) inputs customer information (for example, company name, industry, technology of interest) from a terminal. This information is used to search the database by the search means.

[1417] Step 5: Database Search

[1418] server

[1419] The server searches the database based on the customer information entered by the user, using SQL queries and full-text search engines to efficiently extract relevant data.

[1420] Step 6: Data Selection

[1421] server

[1422] The search results are then sorted to find the information that best addresses the customer's needs, a process driven by an algorithm that takes into account relevance scores and past ratings data.

[1423] Step 7: Generate a proposal

[1424] server

[1425] The server automatically generates proposal documents based on the selected information using natural language generation (NLG) technology. The generated proposal documents are customized to meet the client's needs and converted into easy-to-read formats (PDF or PPT).

[1426] Step 8: Review and revise your proposal

[1427] Terminal

[1428] The sales representative checks the automatically generated proposal materials on the terminal, corrects the contents of the materials as necessary, and saves them as the final proposal materials.

[1429] Step 9: Submit your proposal

[1430] Terminal

[1431] Once the revisions are complete, the proposal materials are saved in PDF or PPT format and provided to the customer via email or other means.

[1432] Example 1

[1433] 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."

[1434] In the past, making quick and effective proposals to corporate customers to address their challenges required the collection, analysis, database creation, search, and document creation of massive amounts of data, and when sales representatives performed these tasks manually, it was extremely time-consuming and labor-intensive. Furthermore, manual data processing was prone to errors, resulting in inconsistent quality in proposals submitted to customers. This made it difficult to respond quickly to customer needs, reducing the efficiency and effectiveness of sales activities.

[1435] 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.

[1436] In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, and a proposal material generation means for automatically generating proposal materials using natural language generation technology based on the searched information and converting the materials into a predetermined format. This enables sales representatives to process data quickly and accurately and provide high-quality proposal materials to customers in a timely manner.

[1437] "Data collection means" refers to the function of collecting necessary data from multiple sources.

[1438] "Data analysis means" refers to the function of analyzing collected data using natural language processing technology and extracting relevant information.

[1439] "Natural language processing technology" refers to technology for understanding and processing human language, and to technology for extracting keywords and important information in data analysis.

[1440] "Database creation means" refers to the function of indexing the analyzed information and storing it in a database.

[1441] "Search means" refers to the function of entering customer information, searching for information in the database, and extracting the necessary information.

[1442] "Proposal material generation means" refers to a function that automatically generates proposal materials using natural language generation technology based on searched information and converts the materials into a specified format.

[1443] "Natural language generation technology" refers to technology that generates sentences in natural language that is easy for humans to understand based on accumulated data.

[1444] An "external API" refers to an interface for obtaining data from external systems or services.

[1445] "Internal system" refers to a system used within a company for data management and business processing.

[1446] "Database" refers to a collection of data that stores collected and analyzed information and makes it efficiently searchable and accessible.

[1447] The system of the present invention is a tool for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means. This system functions as follows using a server and terminals.

[1448] 1. Data Collection Method

[1449] Server Roles

[1450] The server collects the necessary data from external APIs and internal systems. Specifically, it obtains the latest industry news and competitive information from Google News API and Twitter API, and customer transaction history and past proposal materials from CRM and ERP systems. This allows important internal and external information to be centrally consolidated.

[1451] Specific examples

[1452] The server uses the Google News API to get the latest news about the automotive industry and the API of the company's CRM system to get the transaction history of customer XYZ.

[1453] 2. Embodiments of Data Analysis Means

[1454] Server Roles

[1455] The server analyzes the collected data using natural language processing (NLP) technology, extracting keywords and important information from the data and analyzing their relevance. This organizes the information needed to generate subsequent proposal materials.

[1456] Specific examples

[1457] The server extracts keywords such as "fuel efficiency improvement technology" and "electric vehicles" from the collected news articles, and extracts "top priority projects" and "purchase history" from customer transaction history.

[1458] 3. Embodiment of database creation means

[1459] Server Roles

[1460] The server indexes the parsed information and stores it in a database, with each entry being accompanied by associated metadata and organized for efficient searching.

[1461] Specific examples

[1462] The server stores keywords such as "fuel efficiency technology" and "electric vehicle" as entries in a database, and adds related news articles and transaction history information as metadata.

[1463] 4. Embodiments of Search Means

[1464] Device Role

[1465] The user, a salesperson, uses a terminal to input customer information and perform a search. The server searches the database based on the input information, extracts relevant information, and returns it to the terminal.

[1466] Specific examples

[1467] A salesperson enters "XYZ Motors Co., Ltd." and "electric vehicle" into a search form on a terminal. The server searches the database based on this information, extracts relevant news articles and transaction history information, and sends it back to the terminal.

[1468] 5. Embodiment of Proposal Material Generation Means

[1469] Server Roles

[1470] The server automatically generates proposal documents based on the searched information using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to the sales representatives.

[1471] Specific examples

[1472] The server creates a proposal document based on the latest information on "electric vehicles" from the search results and the customer's transaction history. The created proposal document is converted into PDF format and sent to the sales representative's terminal.

[1473] Prompts based on concrete examples

[1474] Here's an example prompt that can be fed into a generative AI model to generate a proposal:

[1475] Customer information:

[1476] Customer Name: XYZ Automobiles Co., Ltd.

[1477] Technology of interest: Electric vehicles, fuel efficiency improvement technology

[1478] Acquired data:

[1479] Automotive industry news from Google News API

[1480] Past transaction history with XYZ Automotive from internal CRM

[1481] Proposal to generate:

[1482] Title: Proposal for XYZ Motors Co., Ltd.

[1483] Contents:

[1484] Latest trends in the electric vehicle market

[1485] Fuel efficiency improvement technology trends of competitors

[1486] Summary of XYZ Motors' past performance

[1487] The system of the present invention enables salespeople to process data quickly and accurately, and provide high-quality proposal materials to customers in a timely manner.

[1488] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1489] Step 1: Collect data

[1490] server

[1491] The server collects data from multiple sources, such as the latest industry news and competitive information from Google News API and Twitter API, and customer transaction history and past proposal documents from CRM and ERP systems. All of this external and internal data is temporarily stored in storage.

[1492] Input and Output

[1493] Input: External API endpoint, internal system API endpoint

[1494] Output: Collected data from multiple sources (news articles, trading history, etc.)

[1495] Specific actions

[1496] The server queries the Google News API to retrieve the latest news articles related to the automotive industry, and at the same time, uses the CRM system's API to retrieve the transaction history for a specific customer ID. These data are then temporarily stored in storage.

[1497] Step 2: Data analysis

[1498] server

[1499] The server reads the collected data from the storage and analyzes it using natural language processing (NLP) techniques, which extracts keywords and important information from the text and analyzes their relevance. The analysis results are then prepared for the next step.

[1500] Input and Output

[1501] Input: Collected data (news articles, trading history, etc.)

[1502] Output: Analyzed information (keywords, important phrases, relevance)

[1503] Specific actions

[1504] The server reads news articles and uses an NLP engine to extract keywords such as "fuel-efficient technology" and "electric vehicles," while simultaneously extracting important information from customer transaction histories, such as "top priority projects" and "purchase history," and analyzing their relevance.

[1505] Step 3: Store in the database

[1506] server

[1507] The server indexes the parsed information and stores it in a database for efficient searching. Metadata is added to the information to make it easier to find and manage within the database.

[1508] Input and Output

[1509] Input: Analyzed data (keywords, key phrases, relevance)

[1510] Output: Indexed database entries

[1511] Specific actions

[1512] The server stores keywords such as "fuel efficiency technology" and "electric vehicles" along with related news articles and transaction history information in a database, and adds appropriate metadata to each.

[1513] Step 4: Search for data

[1514] Terminal

[1515] A salesperson, who is a user, uses a terminal to input customer information (such as customer name, technology of interest, etc.) into a search form. The server searches the database based on the input information, extracts relevant information, and returns it to the terminal.

[1516] Input and Output

[1517] Input: Customer information (customer name, technology of interest)

[1518] Output: Search results (related news articles, transaction history information)

[1519] Specific actions

[1520] A salesperson enters "XYZ Motors Corporation" and "electric vehicles" into a search form on a terminal. The server retrieves relevant entries from the database and returns relevant news articles and transaction history information to the terminal.

[1521] Step 5: Generate a proposal

[1522] server

[1523] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT format and provided to the sales representatives.

[1524] Input and Output

[1525] Input: Search results (related news articles, transaction history information)

[1526] Output: Proposal materials (PDF, PPT format)

[1527] Specific actions

[1528] The server creates a proposal document based on the latest information about electric vehicles obtained as a search result and the customer's transaction history. The proposal document is converted into PDF format and sent to the sales representative's terminal.

[1529] (Application example 1)

[1530] 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."

[1531] In conventional sales activities, making quick and effective proposals to corporate customers to address their challenges requires the collection and analysis of vast amounts of information, which takes up a great deal of time and effort. Creating proposal materials also takes time, making it difficult for sales representatives to respond quickly amid their busy schedules. Proposing new production technologies and equipment installations at factories, in particular, requires real-time information gathering and immediate proposals.

[1532] 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.

[1533] In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, and a proposal material generation means for automatically generating proposal materials based on the searched information and displaying them on a visual device. This enables sales representatives to collect and analyze data within the factory in real time and make quick and effective proposals to factory managers and customers.

[1534] A "data collection means" is a device or function that collects necessary data from multiple sources.

[1535] "Data analysis means" refers to a device or function that analyzes collected data and extracts relevant information.

[1536] The "database creation means" is a device or function that indexes the analyzed information and stores it in a database.

[1537] The "search means" is a device or function that inputs customer information and searches for information in the database.

[1538] The "proposal material generating means" is a device or function that automatically generates proposal materials based on the searched information and displays them on a visual device.

[1539] An "External API" is an application programming interface provided over the Internet.

[1540] "Internal systems" are computer systems and software used within a company.

[1541] "Natural language generation technology" is a technology that automatically generates sentences in natural language that are easy for humans to understand.

[1542] A "visual device" is a device for visually displaying information.

[1543] The present invention is a system for quickly and effectively making proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, and proposal material generation means.

[1544] 1. Data Collection Method

[1545] The server collects the necessary data from external APIs (such as industry news sites and social media APIs) and internal systems (CRM systems, ERP systems, etc.), enabling the latest industry news, competitive information, and customer transaction history to be centrally aggregated.

[1546] As a concrete example, the server uses a news API to get information about the latest factory automation technologies and extracts past transaction history from a CRM system.

[1547] 2. Embodiments of Data Analysis Means

[1548] The server analyzes the collected data using natural language processing (NLP) technology. NLP technology extracts keywords and important information from the data and analyzes their relevance. The analyzed data is then used to generate proposal materials.

[1549] As a specific example, the server extracts keywords such as "automation technology" and "robot introduction" from collected news articles.

[1550] 3. Embodiment of database creation means

[1551] The analyzed information is indexed by the database creation means and stored in a database, which allows for efficient data retrieval by the subsequent search means.

[1552] As a specific example, extracted keywords and information are added as metadata to each entry in the database.

[1553] 4. Embodiments of Search Means

[1554] Salespeople use terminals to input customer information and perform searches. The server searches the database based on the input customer information and extracts relevant information. The search results are used to generate proposal materials.

[1555] As a specific example, when a sales representative prepares a proposal document for a particular automobile manufacturer, he or she inputs the company name and interest in new technologies.

[1556] 5. Embodiment of Proposal Material Generation Means

[1557] The server automatically generates a proposal document based on the searched information using natural language generation (NLG) technology, converts the generated proposal document into PDF or PPT format, and provides it to the sales representative. At the same time, the information is visually displayed via the smart glasses.

[1558] As a specific example, a proposal document is created based on information about "automation technology" obtained from search results and past success stories, and the document is output in PDF format and displayed on a visual device.

[1559] Example prompt sentence:

[1560] "Get the latest competitive information and technology trends related to factory automation technology, and generate and provide proposal materials that best meet the current needs of your factory based on past proposal materials and transaction history."

[1561] In this way, the above-mentioned means realizes more efficient and sophisticated sales activities, and enables salespeople to make proposals that meet customer needs quickly and effectively.

[1562] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1563] Step 1:

[1564] The server collects data from external APIs and internal systems. As input, it specifies the URL of the external API or the database of the internal system, and as output, it obtains collected data such as industry news and customer transaction history. Specifically, the server sends HTTP requests to the external API and the internal system, and stores the returned data in temporary files or memory.

[1565] Step 2:

[1566] The server analyzes the collected data using natural language processing (NLP) techniques. It uses the data collected in step 1 as input and extracts keywords and key information as output. Specifically, it uses an NLP library (e.g., spaCy or a natural language toolkit) to extract keywords and phrases from the data and analyze their relationships.

[1567] Step 3:

[1568] The server indexes the parsed information and stores it in a database. It uses the keywords and information extracted in step 2 as input and gets the indexed database entries as output. Specifically, it uses an indexing algorithm to map the keywords and related information to database fields and writes them to the database.

[1569] Step 4:

[1570] A user uses a terminal to input customer information and search for related information. A query such as a customer name or technology interest is used as input, and relevant database entries are obtained as output. Specifically, the server receives the query sent from the terminal, executes the search query against the database, and returns the results to the terminal.

[1571] Step 5:

[1572] The server automatically generates a proposal document based on the searched information and displays it on the visual device. It uses the search results obtained in step 4 as input, and generates a PDF or PPT file of the proposal document as output, which is displayed on the visual device (e.g., smart glasses). Specifically, it uses natural language generation (NLG) technology to compose the proposal document, exports the document in a specified format, and sends the file to the visual device.

[1573] This process allows sales representatives to collect and analyze data in real time within the factory, generating and visually verifying proposals quickly and effectively.

[1574] 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.

[1575] The system of the present invention is a tool for making prompt and effective proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, proposal material generation means, and an emotion engine that recognizes the user's emotions. The specific operation of each means is explained below.

[1576] 1. Data Collection Method

[1577] server

[1578] The server obtains the necessary data from external APIs (e.g., news APIs, SNS APIs) and internal systems (CRM systems, ERP systems). From external APIs, it collects industry news and competitive information, and from internal systems, it obtains customer transaction history and past proposal materials.

[1579] Specific examples

[1580] It uses the Google News API to get the latest automotive industry news and collects transaction history for specific customers from a CRM system.

[1581] 2. Embodiments of Data Analysis Means

[1582] server

[1583] The server analyzes the collected data using natural language processing (NLP) techniques, tokenizing the text data and extracting keywords and important information, which are then used in subsequent processes.

[1584] Specific examples

[1585] The collected news articles are analyzed using NLP technology to extract key keywords such as "electric vehicles" and "fuel efficiency improvement technology."

[1586] 3. Embodiment of database creation means

[1587] server

[1588] The server indexes the analyzed information and stores it in a database, adding related keywords and category information to the database to enable fast and efficient data searches.

[1589] Specific examples

[1590] The extracted keywords and metadata are stored in a database for future searches.

[1591] 4. Embodiments of Search Means

[1592] Terminal

[1593] The salesperson (user) enters customer information into the terminal and performs a search. The server searches the database based on the entered information and extracts relevant information.

[1594] Specific examples

[1595] A sales representative enters the company name and related technical keywords to create a proposal document for a specific automobile manufacturer.

[1596] 5. Embodiment of Proposal Material Generation Means

[1597] server

[1598] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT formats.

[1599] Specific examples

[1600] Based on the search results, a proposal document focusing on "fuel efficiency improvement technologies" is created using NLG technology and output in PDF format.

[1601] 6. Embodiment of Emotion Engine

[1602] server

[1603] The emotion engine analyzes the user's input and operation logs to recognize the user's emotions. The information analyzed by the emotion engine is reflected in the content of the proposal materials.

[1604] Specific examples

[1605] If the emotion engine determines that a salesperson is tired, the system will generate a concise and easy-to-understand sales pitch.

[1606] 7. Review and revise the proposal materials

[1607] Terminal

[1608] The sales representative checks the automatically generated proposal materials on their device, makes any necessary corrections, and saves the corrected materials as the final proposal materials.

[1609] Specific examples

[1610] Review the generated proposal and customize some of the content.

[1611] 8. Providing proposal materials

[1612] Terminal

[1613] Sales representatives save the revised proposal materials in PDF or PPT format and provide them to customers via email or other means.

[1614] As a result, the system of the present invention automates everything from data collection to recognition of customer emotions, enabling the rapid creation and provision of effective proposal materials, thereby improving the efficiency and sophistication of sales activities.

[1615] The processing flow will be explained below.

[1616] Step 1: Data collection

[1617] server

[1618] The server retrieves the necessary data from external APIs (news APIs and SNS APIs) and internal systems (CRM systems and ERP systems). It collects the latest industry information from the news API and customer transaction history and past proposal materials from the internal systems. This data is then stored in temporary storage.

[1619] Specific examples

[1620] Use the Google News API to get the latest news from the automotive industry and collect transaction history for specific customers from your CRM system.

[1621] Step 2: Data analysis

[1622] server

[1623] The collected data is analyzed using natural language processing (NLP) technology. Specifically, the text data is tokenized and keywords and important information are extracted, generating meta-information about the data.

[1624] Specific examples

[1625] Keywords such as "electric vehicles" and "fuel efficiency improvement technology" are extracted from the collected news articles using natural language processing.

[1626] Step 3: Database creation

[1627] server

[1628] The analyzed information is indexed and stored in a database, which involves adding related keywords and category information to the database to create an index that improves the efficiency of data searches.

[1629] Specific examples

[1630] The extracted keywords and metadata are stored for each entry in the database for future searches.

[1631] Step 4: Enter customer information

[1632] User

[1633] Salespeople enter customer information (company name, industry, technology of interest, etc.) into their terminals. This information is used by the server to search the database.

[1634] Specific examples

[1635] To generate proposal materials for a specific automobile manufacturer, a sales representative enters a specific company name and related technical keywords into an input form on the terminal.

[1636] Step 5: Database Search

[1637] server

[1638] The server searches the database based on the customer information entered by the user, using SQL queries and full-text search engines to efficiently extract relevant information.

[1639] Specific examples

[1640] Search for relevant news articles and past proposals in the database based on the company name or keywords entered.

[1641] Step 6: Sentiment Analysis

[1642] server

[1643] The emotion engine analyzes the user's input and operation logs to recognize their emotions. The results of the emotion analysis are then reflected appropriately in the content of the proposal materials.

[1644] Specific examples

[1645] Based on the information entered by the sales representative and the amount of time spent operating the device, the emotion engine detects fatigue and notifies the system.

[1646] Step 7: Data Selection

[1647] server

[1648] The search results are then filtered to best address the customer's needs based on the user's emotional state, using an algorithm that takes into account relevance scores and past ratings data.

[1649] Specific examples

[1650] Taking into account the results of the sentiment analysis, the most relevant data related to "electric vehicles" is selected.

[1651] Step 8: Generate a proposal

[1652] server

[1653] Based on the selected information, proposal materials are automatically generated using natural language generation (NLG) technology. The generated materials are customized to meet the client's needs and converted into PDF or PPT format.

[1654] Specific examples

[1655] Proposal materials are created based on relevant information, and the content is made concise and easy to understand based on sentiment analysis, and then output in PDF format.

[1656] Step 9: Review and revise your proposal

[1657] Terminal

[1658] The sales representative checks the automatically generated proposal documents on the terminal, corrects the contents as necessary, and saves them as the final proposal documents.

[1659] Specific examples

[1660] Review the generated proposal, customize some of the content, and save it as the final version.

[1661] Step 10: Submit your proposal

[1662] Terminal

[1663] Sales representatives save the revised proposal materials in PDF or PPT format and provide them to customers via email or other means.

[1664] Specific examples

[1665] After the revisions are complete, save the proposal document in PDF format and send it to the customer by email.

[1666] Example 2

[1667] 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."

[1668] In conventional proposal document creation systems, each step from data collection and analysis to document generation is often done manually, requiring a great deal of time and effort. It is also difficult to create proposal documents that take customer emotions into account, posing a major challenge to customer satisfaction. To solve these problems and create proposal documents efficiently and effectively, an automated system is needed.

[1669] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information, and a database creation means for indexing the analyzed information and storing it in a database. This automates the entire process from collection to analysis and generation of proposal materials, making it possible to efficiently create high-quality proposal materials. In addition, by using an emotion recognition means, it is possible to create proposal materials that take customer emotions into consideration.

[1670] "Data collection means" refers to the means for obtaining necessary data from multiple sources.

[1671] "Natural language processing technology" is a technology that analyzes collected text data and extracts keywords and important information.

[1672] "Indexing" is the process of creating a data structure that allows the data to be efficiently searched.

[1673] A "database" is a system that stores collected and analyzed data in an organized manner and makes it easy to search and access.

[1674] The "search means" is a means for searching for information in the database based on the customer information entered by the user.

[1675] "Natural language generation technology" is a technology that automatically generates sentences based on searched information.

[1676] The "proposal material generation means" is a means for automatically generating proposal materials using natural language generation technology and converting them into a document format.

[1677] The "emotion recognition means" is a means for analyzing the user's input contents and operation log and recognizing the user's emotions.

[1678] The system of the present invention is a tool for making quick and effective proposals to corporate clients for their problems, and includes data collection means, data analysis means, database creation means, search means, proposal material generation means, and an emotion engine that recognizes user emotions. This makes it possible to automate the creation of proposal materials and to make advanced proposals that take into account the client's emotions. The specific operation of each means is explained below.

[1679] Data collection methods

[1680] server

[1681] The server collects the necessary data from multiple external APIs (e.g., news API, SNS API) and internal systems (e.g., CRM system, ERP system). For example, it uses the Google News API to obtain the latest news in the automotive industry and collects the transaction history of specific customers from the internal CRM system.

[1682] concrete action

[1683] The server starts a scheduled task every morning at 8:00, sends a request to the specified API endpoint, and stores the received data in an internal data store in JSON format.

[1684] Data Analysis Methods

[1685] server

[1686] The server analyzes the collected data using natural language processing (NLP) techniques, specifically using Python NLP libraries (e.g., spaCy, NLTK) to tokenize the text and extract important keywords and information.

[1687] concrete action

[1688] The server analyzes the collected news articles using NLP technology and extracts key keywords such as "electric vehicles" and "fuel efficiency improvement technology."

[1689] Database creation method

[1690] server

[1691] The server indexes the parsed information and stores it in a database (e.g., Elasticsearch, MySQL, PostgreSQL), allowing for fast and efficient data retrieval.

[1692] concrete action

[1693] The server stores the extracted keywords and metadata in a database for future searches.

[1694] Search methods

[1695] Terminal

[1696] The sales representative (user) enters specific customer information and keywords into the terminal and performs a search. The server searches the database based on the entered information and extracts relevant information.

[1697] concrete action

[1698] Users access a dedicated search screen and enter a customer name or related technology as search keywords, and the server retrieves the relevant data using an Elasticsearch query.

[1699] Proposal material generation means

[1700] server

[1701] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology, which are then converted into PDF or PPT formats.

[1702] concrete action

[1703] The server uses Python's NLG libraries (e.g., GPT-3, Natural Language Toolkit) to generate proposal documents from the search results, which are then converted to PDF or PPT format using Python's ReportLab or pptx libraries.

[1704] Embodiment of Emotion Engine

[1705] server

[1706] The emotion engine analyzes user input and operation logs to recognize the user's emotions, which are reflected in the content of proposal materials.

[1707] concrete action

[1708] The server uses a SaaS-based emotion analysis service (e.g., IBM Watson Tone Analyzer) to generate an emotion score from operation logs and input data, and adjusts the content and tone of the proposal materials based on that score.

[1709] Specific examples (prompt sentence examples)

[1710] For example, if a salesperson is creating a proposal for a particular car manufacturer, they might use the following prompt:

[1711] "Please create a proposal document that includes the latest news and technological trends about a specific customer's automobile manufacturer. The keywords are 'electric vehicles' and 'fuel efficiency improvement technology.'"

[1712] In this way, the system automates everything from data collection to customer sentiment recognition, enabling efficient creation of high-quality proposal materials and supporting improved sales activities.

[1713] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1714] Program processing flow

[1715] Step 1: Collect data

[1716] server

[1717] The server collects the required data from external APIs (e.g., news APIs, social media APIs) and internal systems (e.g., CRM systems, ERP systems). The input is the API request or an internal database query, and the output is the retrieved data.

[1718] Specific actions

[1719] The server starts a scheduled task every morning at 8:00, sends a request to the Google News API, stores the received JSON data in an internal data store, and simultaneously calls an internal API to retrieve customer transaction history from Salesforce CRM and store it in a database.

[1720] Step 2: Analyze the collected data

[1721] server

[1722] The server analyzes the collected data using natural language processing (NLP) technology. The input is the collected text data, and the output is extracted keywords and important information.

[1723] Specific actions

[1724] The server uses Python NLP libraries (e.g., spaCy, NLTK) to tokenize news articles and extract key keywords such as "electric vehicle" and "fuel-efficient technology." It also performs part-of-speech tagging and named entity extraction.

[1725] Step 3: Indexing and storing data

[1726] server

[1727] The server indexes the parsed information and stores it in a database. The input is the extracted keywords and metadata, and the output is the indexed data.

[1728] Specific actions

[1729] The server uses Elasticsearch to create an index, adding extracted keywords and metadata to the index for future fast searches, and storing the indexed data in a MySQL or PostgreSQL database.

[1730] Step 4: User Search

[1731] Terminal

[1732] Salespeople (users) enter specific customer information and keywords into their terminals to perform searches. The input is the customer name and related technical keywords, and the output is the related information obtained as a result of the search.

[1733] Specific actions

[1734] Users access a dedicated search interface and enter information such as "electric vehicles" or "fuel-efficient technology," and the server executes an Elasticsearch query to quickly retrieve relevant documents and data.

[1735] Step 5: Generate a proposal

[1736] server

[1737] The server automatically generates proposal documents based on the search results using natural language generation (NLG) technology. The input is the search results, and the output is the generated proposal documents.

[1738] Specific actions

[1739] The server uses Python's NLG library (e.g., GPT-3, Natural Language Toolkit) to generate proposal documents from the search results, and then converts the documents into PDF or PPT format using Python's ReportLab or pptx library.

[1740] Step 6: Sentiment analysis and material adjustment

[1741] server

[1742] The emotion engine analyzes the user's input and operation log and reflects it in the proposal materials. The input is the user's operation log and input data, and the output is a proposal material based on the user's emotion.

[1743] Specific actions

[1744] The server generates a sentiment score using a SaaS-based sentiment analysis service (e.g., IBM Watson Tone Analyzer), and adjusts the tone and content of the proposal based on the sentiment score.

[1745] Step 7: Review and correct your materials

[1746] Terminal

[1747] The sales representative checks the automatically generated proposal documents on the terminal and makes corrections as necessary. The input is the automatically generated proposal documents, and the output is the corrected and confirmed proposal documents.

[1748] Specific actions

[1749] Users can download the generated PDF or PPT file, open it in Adobe Acrobat or Microsoft PowerPoint, review the contents, and make any necessary corrections.

[1750] Step 8: Submit your proposal

[1751] Terminal

[1752] The sales representative saves the revised proposal and provides it to the customer. The input is the revised proposal, and the output is the proposal provided to the customer.

[1753] Specific actions

[1754] The user saves the revised proposal document in a file format and sends it to the customer using an email client (e.g., Microsoft Outlook, Gmail).

[1755] By using the above processing steps, the system of the present invention can efficiently and quickly generate high-quality proposal materials.

[1756] (Application example 2)

[1757] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1758] In conventional proposal material creation systems, the process from data collection to analysis and generation is often performed partially manually, resulting in problems such as reduced work efficiency. Another problem is that the content of the proposal material does not adapt to the customer's situation or emotions, making it difficult to make effective proposals. The present invention aims to solve these problems by providing a system that automates the creation of proposal materials and adjusts the content based on the customer's emotions.

[1759] The specific processing by the specific 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 data collection means for collecting data from multiple information sources, a data analysis means for analyzing the collected data and extracting relevant information, a database creation means for indexing the analyzed information and storing it in a database, a search means for inputting customer information and searching for information in the database, a proposal material generation means for automatically generating proposal materials based on the searched information, an emotion engine means for analyzing the customer's input content and operation log and recognizing their emotions, and a material adjustment means for adjusting the content of the proposal materials based on the recognized emotions. This makes it possible to quickly and effectively automate the process of creating proposal materials and provide optimal proposal content tailored to the customer's emotions.

[1760] A "data collection tool" is a tool for collecting data from multiple sources.

[1761] "Data analysis means" refers to means for analyzing collected data and extracting relevant information.

[1762] The "database means" is a means for indexing the analyzed information and storing it in a database.

[1763] The "search means" is a means for inputting customer information and searching for information in the database.

[1764] The "proposal material generating means" is a means for automatically generating proposal materials based on the searched information.

[1765] The "emotion engine means" is a means for analyzing the customer's input contents and operation logs and recognizing emotions.

[1766] The "material adjustment means" is a means for adjusting the content of the proposal materials based on the recognized emotions.

[1767] The system for implementing this invention is based on an application installed on a terminal such as a smartphone or tablet. The system is composed of the following hardware and software.

[1768] Hardware:

[1769] Smartphone (iOS / Android)

[1770] tablet

[1771] Software / Libraries:

[1772] Requests (to communicate with external APIs)

[1773] NLP libraries (e.g. SpaCy)

[1774] Database connection library (e.g. SQLite)

[1775] Natural Language Generation (NLG) toolkits (e.g., GPT-3)

[1776] Emotion recognition engine (e.g. Emotion API)

[1777] The server first uses data collection tools to collect data from multiple sources, including external APIs (e.g., news APIs and social media APIs) and internal systems (CRM and ERP). For example, it uses a news API to collect the latest security news and retrieves the transaction history of a specific customer from a CRM system.

[1778] The server then analyzes the collected data using natural language processing (NLP) technology. The collected text data is tokenized and important keywords and information are extracted. For example, a security-related news article is analyzed to extract key keywords such as "surveillance camera" and "alarm system."

[1779] The collected and analyzed information is indexed using database tools and stored in a database, allowing for fast and efficient data searches.

[1780] When a user enters customer information into a terminal and performs a search, the server searches the database based on that information and extracts relevant information. For example, a user may enter the name of a specific company and related technical keywords to create a security plan for that company.

[1781] Next, the server uses a proposal generation means to automatically generate proposal materials based on the search results using natural language generation (NLG) technology. These materials are output in PDF or PPT format. For example, a proposal material centered on a "surveillance camera system" is created based on the data obtained as search results.

[1782] Furthermore, the server is equipped with an emotion engine that analyzes the user's input and operation logs to recognize their emotions. It also includes a document adjustment mechanism that adjusts the content of the proposal materials based on these emotions. For example, if the user feels that the proposal materials are too detailed and difficult to understand, the system will generate concise and easy-to-understand proposal materials.

[1783] As an example of a specific prompt sentence, the following text is entered:

[1784] "There's too much complicated information and it's hard to understand."

[1785] In this way, the present invention is a system that can quickly and effectively automate the creation of proposal materials and provide optimal proposal content that reflects the user's emotions.

[1786] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1787] Step 1:

[1788] Data collection methods

[1789] The server collects data from multiple sources. It gets the required data from external APIs and internal systems, including news APIs, social media APIs, CRM systems, and ERP systems. For example, it uses a news API to get the latest security news and collects a specific customer's transaction history from a CRM system. The API key and customer ID are used as input, and news data and customer data are obtained as output.

[1790] Step 2:

[1791] Data Analysis Methods

[1792] The server analyzes the collected data using natural language processing (NLP) technology. It tokenizes the collected text data and extracts important keywords and information. An NLP library (such as SpaCy) is used for this analysis. The collected news data and customer data are used as input, and key keywords and important information are obtained as output. Specifically, keywords such as "surveillance camera" and "alarm system" are extracted from the text.

[1793] Step 3:

[1794] Database creation method

[1795] The server indexes the analyzed information and stores it in a database, which allows for fast and efficient data searches. A database connection library (such as SQLite) is used. The analysis results (keywords and important information) are used as input, and the index data stored in the database is obtained as output.

[1796] Step 4:

[1797] Search methods

[1798] The user inputs customer information from the terminal and searches for information in the database. The server searches the database based on this input information and extracts relevant information. Customer information (company name, technical keywords, etc.) is used as input, and search results (related information) are obtained as output. In concrete terms, the user inputs a "specific company name" or "security-related technology."

[1799] Step 5:

[1800] Proposal material generation means

[1801] The server automatically generates proposal documents based on the searched information. It uses natural language generation (NLG) technology to output the proposal documents in PDF or PPT format. An NLG toolkit (e.g., GPT-3) is used. The search results are used as input, and proposal documents (in PDF or PPT format) are obtained as output. Specifically, a proposal document centered on a "surveillance camera system" is created from the search results.

[1802] Step 6:

[1803] Emotion Engine Means

[1804] The server analyzes the customer's input and operation logs to recognize emotions. An emotion recognition engine (e.g., Emotion API) is used. The user's text input and operation logs are used as input, and the recognized emotion is obtained as output. In concrete terms, if the user inputs "There is too much complicated information and it's hard to understand," the server will recognize that the user is "feeling stressed."

[1805] Step 7:

[1806] Material adjustment means

[1807] The server adjusts the content of the presentation materials based on the recognized emotions, which may include simplifying the materials or focusing on key points. The NLG toolkit may be reused. The recognized emotions and presentation materials are used as input, and the adjusted presentation materials are obtained as output. Specifically, for users who are "feeling stressed," a presentation material is generated that restructures the information in a simpler and more understandable way.

[1808] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1809] 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.

[1810] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1811] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1812] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1813] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1814] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1815] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1816] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1817] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1818] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1819] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1820] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1821] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1822] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1823] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1824] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1825] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1826] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1827] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1828] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1829] The following is further disclosed regarding the above embodiment.

[1830] (Claim 1)

[1831] a data collection means for collecting data from multiple sources;

[1832] a data analysis means for analyzing the collected data and extracting relevant information;

[1833] a database creation means for indexing the analyzed information and storing it in a database;

[1834] A search means for inputting customer information and searching for information in the database;

[1835] a proposal material generating means for automatically generating a proposal material based on the searched information;

[1836] A system including:

[1837] (Claim 2)

[1838] 10. The system of claim 1, wherein the information sources include external APIs and internal systems.

[1839] (Claim 3)

[1840] 2. The system according to claim 1, wherein natural language generation technology is used to automatically generate proposal materials.

[1841] "Example 1"

[1842] (Claim 1)

[1843] a data collection means for collecting data from multiple sources;

[1844] a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information;

[1845] a database creation means for indexing the analyzed information and storing it in a database;

[1846] A search means for entering customer information to search for information in the database;

[1847] a proposal material generation means for automatically generating proposal materials using natural language generation technology based on the searched information and converting the materials into a predetermined format;

[1848] A system including:

[1849] (Claim 2)

[1850] 10. The system of claim 1, wherein the information sources include external APIs and internal systems.

[1851] (Claim 3)

[1852] The system according to claim 1, characterized in that in addition to automatically generating proposal materials, the system converts the proposal materials into PDF or PPT format.

[1853] "Application Example 1"

[1854] (Claim 1)

[1855] a data collection means for collecting data from multiple sources;

[1856] a data analysis means for analyzing the collected data and extracting relevant information;

[1857] a database creation means for indexing the analyzed information and storing it in a database;

[1858] A search means for inputting customer information and searching for information in the database;

[1859] a proposal material generating means for automatically generating a proposal material based on the searched information and displaying the proposal material on a visual device;

[1860] A system including:

[1861] (Claim 2)

[1862] 10. The system of claim 1, wherein the information sources include external APIs and internal systems.

[1863] (Claim 3)

[1864] 2. The system according to claim 1, wherein natural language generation technology is used to automatically generate proposal materials.

[1865] "Example 2: Combining Emotion Engines"

[1866] (Claim 1)

[1867] a data collection means for collecting data from multiple sources;

[1868] a data analysis means for analyzing the collected data using natural language processing technology and extracting relevant information;

[1869] a database creation means for indexing the analyzed information and storing it in a database;

[1870] A search means for searching for information in a database based on customer information input by a user;

[1871] a proposal material generation means for automatically generating proposal materials based on the searched information using natural language generation technology and converting the materials into a document format;

[1872] An emotion recognition means for analyzing the input contents and operation logs of the user to recognize emotions and reflect them in the content of the proposal materials;

[1873] A system including:

[1874] (Claim 2)

[1875] 10. The system of claim 1, wherein the information sources include external application program interfaces and in-house systems.

[1876] (Claim 3)

[1877] 2. The system according to claim 1, wherein the searched information is output in document form using natural language generation technology.

[1878] "Application example 2 when combining emotion engines"

[1879] (Claim 1)

[1880] a data collection means for collecting data from multiple sources;

[1881] a data analysis means for analyzing the collected data and extracting relevant information;

[1882] a database creation means for indexing the analyzed information and storing it in a database;

[1883] A search means for inputting customer information and searching for information in the database;

[1884] a proposal material generating means for automatically generating a proposal material based on the searched information;

[1885] An emotion engine means for analyzing customer input contents and operation logs and recognizing emotions;

[1886] a material adjustment means for adjusting the content of the proposal material based on the recognized emotion;

[1887] A system including:

[1888] (Claim 2)

[1889] 10. The system of claim 1, wherein the information sources include external APIs and internal systems.

[1890] (Claim 3)

[1891] 2. The system according to claim 1, wherein natural language generation technology is used to automatically generate proposal materials. [Explanation of symbols]

[1892] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a data collection means for collecting data from multiple sources; a data analysis means for analyzing the collected data and extracting relevant information; a database creation means for indexing the analyzed information and storing it in a database; A search means for inputting customer information and searching for information in the database; a proposal material generating means for automatically generating a proposal material based on the searched information; A system including:

2. 10. The system of claim 1, wherein the information sources include external APIs and in-house systems.

3. 2. The system according to claim 1, wherein the automatic generation of the proposal materials uses natural language generation technology.

Images