system

Abstract

We provide the system. [Solution] The present invention relates to an information management system comprising a customer information management unit, a sales negotiation record management unit, and a generative AI processing unit, which centrally manages customer information and sales negotiation records on a server and uses generative AI to perform tasks such as searching, extracting, summarizing, and analyzing customer information and sales negotiation records, automatically generating proposal materials, and performing trend analysis. Personnel can input instructions for searching, analyzing, and creating materials using natural language from a terminal, and the generative AI analyzes past sales negotiation records and customer trends, providing necessary information and optimal proposal content immediately, thereby improving the efficiency of information management, reducing the workload, enhancing proposal activities, and improving the reliability of information.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method executed by at least one processor, the method comprising the steps of: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence associated with a description related to the character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The problem to be solved by the present invention is that customer information and past negotiation records are dispersedly managed across multiple media such as spreadsheet software, paper media, and notebooks, which makes it difficult for personnel in charge to quickly and accurately search for and extract necessary information, prevents immediate identification of the latest and valid information, undermines the reliability and consistency of information, requires significant time and effort to create proposal materials for customers and utilize past negotiation records, drastically reduces operational efficiency, and causes problems such as increased overtime work, more human errors, and degraded quality of proposal contents. To solve these problems, customer information and negotiation records are centrally managed, and generative AI is used to realize immediate search for necessary information, automatic identification of the latest and valid information, automatic generation of proposal materials, and organization and utilization of past negotiation records, thereby improving the efficiency of information management, reducing operational burdens, advancing proposal activities, and enhancing information reliability. [Means for solving the problem]

[0005] The means for solving the problems according to the present invention comprises a customer information management unit, a sales negotiation record management unit, and a generation AI processing unit. The customer information management unit centrally stores customer information such as unique identification information, name, contact information, affiliated organization, and remarks information for each customer in a database. The sales negotiation record management unit manages multiple sales negotiation records linked to each customer information, and stores sales negotiation identification information, sales negotiation date, sales negotiation summary, sales negotiation status, related document information, etc. for each sales negotiation record. The generation AI processing unit uses a generation AI to process customer information in response to search requests from the person in charge. The system analyzes sales negotiation records, searches for customer information based on keywords such as customer names and organization names, automatically extracts the latest sales negotiation records linked to specified customers, extracts valid sales negotiation records based on negotiation status, automatically generates proposal materials based on customer information and sales negotiation records, and organizes and instantly extracts past sales negotiation records in chronological order. By realizing this series of processes using generative AI-based natural language processing and information extraction technologies, it enables centralized management of customer information and sales negotiation records, faster information retrieval, improved information reliability, more efficient proposal material creation, and effective utilization of past sales negotiation records. [Brief explanation of the drawing]

[0006] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6]This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0007] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0008] First, let's explain the terminology used in the following explanation.

[0009] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0010] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0011] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (for example, hard disks), magnetic tapes, and the like.

[0012] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of 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), and the like.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Further, in the present specification, when three or more items are connected and expressed by "and / or", the same concept as that for "A and / or B" is applied.

[0014] [First Embodiment]

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

[0016] As shown in FIG. 1, the data processing system 10 includes a data processing apparatus 12 and a smart device 14. An example of the data processing apparatus 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of the "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, RAM 30, and 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), and the like.

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, camera 42, and communication I / F 44 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A receives user input via contact of an indicator by detecting the contact of the indicator (for example, a pen, a finger, or the like). The microphone 38B receives user input via voice by detecting the user's voice. A control unit 46A in the processor 46 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, a specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0023] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0024] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0026] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0027] (Example 1)

[0028] The flow of a specific process in Example 1 will now be described. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0029] (Embodiments for carrying out the present invention)

[0030] Embodiments of the present invention will be described in more detail. The system of the present invention is a client-server type information management system consisting of a server and terminals, and includes multiple functional units such as a customer information management unit, a business negotiation record management unit, a generative AI processing unit, a user interface unit, an authentication management unit, a log management unit, and a data backup unit. The functions of each unit, the division of roles between the server and terminals, and the methods of utilizing the generative AI will be comprehensively explained with specific examples.

[0031] The customer information management department is implemented using a relational or NoSQL database on a server, and centrally stores a wide range of information for each customer, including a unique customer ID, name, contact information (phone number, email address), organization name, department, job title, address, industry, transaction start date, contact person name, customer rank, customer attributes (new, existing, important, prospect, etc.), remarks, and tag information. For example, even if a customer has multiple business negotiations with multiple contacts, all the information is linked to a single customer record. Furthermore, it is possible to register multiple contacts and multiple contacts for each customer, and information on different contacts within the same organization, such as "Purchasing Manager at Company A" and "Technical Manager at Company A," can be managed individually.

[0032] The Sales Negotiation Record Management Department manages multiple sales negotiation records linked to each customer's information. Each sales negotiation record stores a variety of information, including negotiation ID, negotiation date, start and end times, negotiation summary, negotiation status (in progress, closed, lost, on hold, following up, etc.), related documents (meeting minutes, quotation, proposal, contract, email history, audio recording, image files, video files, etc.), participant information (internal staff, customer staff), negotiation location (in-person, online, telephone, etc.), negotiation objective, results, next actions, negotiation evaluation score, negotiation challenges, competitor information, negotiation history, and negotiation notes. For example, past sales negotiation records with a particular customer can be displayed in chronological order, and detailed records of each negotiation's content and results, next actions, competitor activities, and customer feedback can be recorded. Furthermore, negotiation records can also record issues that arose during the negotiation, customer requests, price negotiation history, technical questions, and troubleshooting history.

[0033] The generative AI processing unit executes various processes on the server using large-scale language models and generative AI APIs. The generative AI combines diverse AI technologies such as natural language processing, information extraction, summary generation, proposal content generation, data analysis, similar case search, trend analysis, sentiment analysis, keyword extraction, text proofreading, and automated FAQ response. For example, if a user inputs "Summarize the sales negotiation records of Company A for the past year" from their terminal, the generative AI will extract Company A's sales negotiation records in chronological order, summarize the key points, results, challenges, and next actions for each negotiation in natural language, and display it on the terminal. For example, if the user inputs "Extract cases where price negotiations with Company B were difficult," the generative AI will extract descriptions related to price negotiations from Company B's sales negotiation records, summarize the relevant sales negotiation records, and present them.

[0034] Furthermore, generative AI can analyze customer information and sales records across various data, and can handle sophisticated analytical requests such as "extract the proposal with the highest closing rate in the past six months." The generative AI analyzes the contents of sales records, automatically extracting factors that led to successful deals, reasons for lost deals, customer reactions, and competitor activities, and can provide feedback to the person in charge. For example, in response to a question such as "What product did the person in charge at Company C show the most interest in?", the generative AI analyzes past sales records and presents a summary of the relevant product name and the reasons why.

[0035] The automated proposal document generation function uses a generation AI to analyze customer information and past sales negotiation records, extracting customer trends, past transaction history, negotiation results, customer requests and challenges, competitor information, past proposal content, and factors for successful and unsuccessful deals. Based on this, it automatically generates a proposal document containing the most suitable content. For example, if you input "Create a proposal document for Company D," the generation AI will analyze Company D's past sales negotiation records in chronological order, extracting information such as what products and services Company D has shown interest in in the past, what challenges they faced, and what proposals led to successful deals. Based on this information, it automatically generates a template for the proposal document. The generated proposal document will include customer name, company name, latest negotiation date, negotiation summary, summary of past negotiation content, analysis results, recommended proposal content by the generation AI, future action plan, points of differentiation from competitors, solutions to customer challenges, price proposal, and proposed implementation schedule. For example, if Company D has previously experienced delivery delays, a generative AI can extract that information and automatically insert a proposal that includes measures to shorten delivery times.

[0036] Furthermore, generative AI can analyze multiple customer and sales negotiation records across different platforms, and can handle analytical requests such as "extract the most frequent customer requests from the past year," "analyze the main causes of lost deals," and "extract the characteristics of sales representatives with high closing rates." Generative AI can also extract information from unstructured data such as free-text fields in sales negotiation records, meeting minutes, and email histories, providing insights that can be used to improve sales representatives' work and develop sales strategies.

[0037] The user interface is implemented on the terminal side, providing a screen that allows the user to intuitively perform operations such as searching, viewing, editing, adding, deleting customer information and sales records, requesting the generation of proposal materials, and requesting analysis. For example, the dashboard screen can visualize the sales status, closing rate, lost rate, and progress of proposal activities for each customer using graphs and charts. The search screen allows users to narrow down their search using various criteria such as customer name, company name, keywords, sales date, status, contact person name, industry, and region. The sales record details screen offers a variety of functions, including previewing and downloading related documents, playing audio recordings, viewing email history, displaying AI-generated summaries, and registering next actions.

[0038] The authentication management unit is implemented on the server side and sets access permissions for each user, controlling access to customer information and sales records. For example, sales staff can only view and edit information for their assigned customers, while administrators can view and edit information for all customers, allowing for flexible permission management. The log management unit is also implemented on the server side and records the history of all operations, including viewing, editing, deleting, and adding customer information and sales records. This is used for monitoring information leaks and unauthorized access, and for ensuring audit trails. The data backup unit is also implemented on the server side and periodically backs up customer information and sales records, enabling data recovery in the event of a failure.

[0039] In system operation, the terminal side is primarily responsible for user input and information display, while the server side operates with coordinated customer information management, sales negotiation record management, generation AI processing, authentication management, log management, and data backup departments. Input from the terminal is sent to the server, where the generation AI performs various processes and returns the results to the terminal. For example, computationally intensive processes such as automatic generation of proposal documents, summarization of sales negotiation records, and trend analysis are performed on the server side, but simple filtering, display format adjustments, notification functions, and input assistance functions can also be performed on the terminal side.

[0040] For example, if a representative accesses the system from a smartphone or tablet while on the go and registers a sales meeting record via voice input immediately after a meeting with a customer, the generative AI can convert the voice data into text, automatically extract key points, and reflect them in the sales meeting record. For example, if a representative inputs, "Automatically generate an agenda for the next meeting with Company A," the generative AI analyzes past sales meeting records and customer requests, automatically generates an optimal agenda proposal, and displays it on the device. For example, if a representative inputs, "Extract past complaint handling cases for Company B," the generative AI extracts descriptions related to complaint handling from Company B's sales meeting records and email history, summarizes them, and presents them.

[0041] Thus, the embodiments of the present invention realize all processes such as centralized management of customer information and sales negotiation records, information retrieval, extraction, summarization, proposal material generation, trend analysis, and FAQ response using generative AI, while clearly defining the roles of the server and terminal, and comprehensively solving multifaceted issues such as improving the work efficiency of personnel, enhancing the reliability of information, advancing proposal activities, optimizing sales strategies, preventing information leakage, responding to audits, and handling failures.

[0042] (System Configuration)

[0043] The system according to this embodiment comprises a customer information management unit, a business negotiation record management unit, a generation AI processing unit, a user interface unit, an authentication management unit, a log management unit, and a data backup unit. The customer information management unit centrally stores a wide range of information for each customer, including a unique customer ID, name, contact information (telephone number, email address), organization name, department, job title, address, industry, transaction start date, contact person name, customer rank, customer attributes (new, existing, important, prospect, etc.), remarks field, and tag information. For example, even if a customer has conducted multiple business negotiations with multiple contact persons, all information is linked to a single customer record. Furthermore, it is configured to allow registration of multiple contacts and multiple contact persons for each customer, and to manage information on different contact persons within the same organization individually. The customer information management unit can, for example, filter by customer attributes to extract only important customers, create customer lists for specific industries or regions, automatically update customer ranks from past transaction history, and generate target lists for marketing measures based on customer tag information.

[0044] The Sales Record Management Department manages multiple sales records linked to each customer's information. Each sales record includes a variety of information such as sales ID, sales date, start and end times, sales summary, sales status (in progress, closed, lost, on hold, following up, etc.), related documents (meeting minutes, quotation, proposal, contract, email history, audio recording, image files, video files, etc.), participant information (internal staff, customer staff), sales location (in-person, online, telephone, etc.), sales objective, results, next actions, sales evaluation score, sales challenges, competitor information, sales history, and sales notes. The system can store information, for example, displaying a chronological list of past sales negotiation records with a particular customer. It can record details such as the content and outcome of each negotiation, next actions, competitor activities, and customer feedback. Furthermore, the negotiation records can also include issues that arose during the negotiation, customer requests, the history of price negotiations, technical questions, and troubleshooting history. This allows for the extraction of past complaint handling cases from negotiation records, analysis of commonalities in successful deals, recording and classifying the causes of lost deals, and quantitatively evaluating the results and challenges of negotiations.

[0045] The generative AI processing unit executes various processes on the server using large-scale language models and generative AI APIs, combining diverse AI technologies such as natural language processing, information extraction, summary generation, proposal content generation, data analysis, similar case search, trend analysis, sentiment analysis, keyword extraction, text proofreading, and automated FAQ response. For example, if a user inputs "Summarize the sales negotiation records of Company A for the past year" from their terminal, the generative AI can extract Company A's sales negotiation records in chronological order, summarize the key points, results, challenges, and next actions for each negotiation in natural language, and display them on the terminal. Similarly, if the user inputs "Extract cases where price negotiations with Company B were difficult," the generative AI can extract descriptions related to price negotiations from Company B's sales negotiation records, summarize the relevant negotiation records, and present them. Furthermore, the generative AI can analyze customer information and sales records across the board, responding to analysis requests such as "extract the proposals with the highest closing rates in the past six months," "analyze the main reasons for lost deals," and "extract the characteristics of sales representatives with high closing rates." It can also extract information from unstructured data such as free-text fields in sales records, meeting minutes, and email history, providing insights that can be used to improve sales representatives' work and develop sales strategies. Specific examples of prompts required when executing the generative AI processing unit include: "Summarize the sales records of customer A for the past year and extract the main achievements and challenges," "Extract descriptions related to price negotiations from customer B's sales records and summarize the negotiation process and results," "Extract proposals with high closing rates from all sales records of the past six months and analyze their commonalities," "Analyze the sales records of lost deals and list the main reasons for loss," and "Extract the products and services that customer C's representative showed the most interest in and summarize the reasons."

[0046] The user interface is implemented on the terminal side, providing a screen that allows the person in charge to intuitively perform operations such as searching, viewing, editing, adding, deleting customer information and sales record, requesting the generation of proposal materials, and requesting analysis. For example, the dashboard screen can visualize the sales status, closing rate, lost rate, and progress of proposal activities for each customer using graphs and charts. The search screen can narrow down searches using various conditions such as customer name, company name, keywords, sales date, status, person in charge name, industry, and region. The sales record details screen can provide various functions such as previewing and downloading related documents, playing audio recordings, viewing email history, displaying summaries by AI, and registering next actions. For example, if a person in charge accesses the system from a smartphone or tablet while on the go and registers a sales record by voice input immediately after a sales meeting with a customer, the generative AI can convert the voice data into text, automatically extract the key points, and reflect them in the sales record.

[0047] The authentication management system is implemented on the server side, allowing for flexible access control by setting access permissions for each user, and controlling access to customer information and sales records. For example, sales staff can only view and edit information for their assigned customers, while administrators can view and edit information for all customers. For instance, permissions can be automatically set when a new user is added, and permissions can be immediately removed upon transfer or resignation. Furthermore, viewing and editing history for specific customer information and sales records can be recorded, reducing the risk of unauthorized access and information leaks.

[0048] The log management system, implemented on the server side, records the history of all operations, including viewing, editing, deleting, and adding customer information and sales negotiation records. This is used for monitoring information leaks and unauthorized access, and for ensuring audit trails. For example, it can record in detail when, by whom, and what operations were performed on specific customer information, and periodically analyze the logs to detect abnormal operations or suspicious access. For instance, it can issue alerts if a large amount of data is downloaded in a short period of time, or if an employee who does not normally access the system accesses specific customer information.

[0049] The data backup unit is implemented on the server side and regularly backs up customer information and sales negotiation records, enabling data recovery in the event of a failure. For example, it is configured to automatically back up all data every night and retain backup data for the past week, allowing for rapid recovery in the event of data loss or system failure. For example, backup data can be encrypted and stored in secure external storage to protect data even in the event of a disaster.

[0050] As described above, the system according to this embodiment involves the customer information management department, the sales negotiation record management department, the generative AI processing unit, the user interface department, the authentication management department, the log management department, and the data backup department working together to centrally manage customer information and sales negotiation records, and to realize all processes such as information retrieval, extraction, summarization, proposal material generation, trend analysis, and FAQ response using generative AI. By clearly defining the roles of the server and terminal, the system comprehensively solves a wide range of issues, including improving the work efficiency of personnel, enhancing the reliability of information, advancing proposal activities, optimizing sales strategies, preventing information leaks, responding to audits, and handling failures.

[0051] (Implementation Steps)

[0052] Step 1: Register and manage customer information The person in charge enters new customer information through the terminal's user interface and sends it to the customer information management unit on the server. The customer information management unit centrally registers a wide range of information into a database, including customer ID, name, contact information, affiliated organization, department, job title, address, industry, transaction start date, contact person's name, customer rank, customer attributes, remarks, and tag information. For example, it manages multiple contact persons and multiple contacts within the same organization individually, and performs filtering, list creation, and tagging by customer attributes to identify targets for marketing initiatives.

[0053] Step 2: Registering and managing sales negotiation records After a business meeting concludes, the person in charge enters the meeting record from their terminal and sends it to the server's meeting record management department. The meeting record management department stores a variety of information, including meeting ID, meeting date, start and end times, meeting summary, meeting status, related documents (meeting minutes, quotation, proposal, contract, email history, audio recording, image files, etc.), participant information, meeting location, meeting objective, results, next actions, evaluation score, issues, competitor information, history, and notes. For example, it automatically transcribes meeting records from voice input, and also records in detail issues and requests that arose during the meeting, the history of price negotiations, and incident response history.

[0054] Step 3: Information retrieval and extraction using generative AI When a user enters a search request from their terminal, specifying customer names, keywords, negotiation dates, status, etc., the generative AI processing unit analyzes the request using natural language processing on the server, immediately extracts the relevant information from the databases of the Customer Information Management Department and the Negotiation Record Management Department, and sends it back to the terminal. For example, in response to requests such as "Summarize the negotiation records of Company A for the past year," "Extract cases where price negotiations with Company B were difficult," or "Display a list of only successful negotiations with Company C," the generative AI understands the context and extracts and summarizes the relevant information. Specific examples of prompts include "Summarize the negotiation records of customer A for the past year and extract the main achievements and challenges," and "Extract descriptions related to price negotiations from the negotiation records of customer B and summarize the negotiation process and results."

[0055] Step 4: Automatic generation of proposal documents using AI. When a user enters a request such as "Create a proposal document for Company D" from their terminal, the generation AI processing unit analyzes customer information and past sales negotiation records, extracting customer trends, past transaction history, negotiation results, requests, challenges, competitor information, past proposal content, and factors contributing to successful or unsuccessful deals. Based on this, it automatically generates a proposal document containing the most suitable content. The generated proposal document includes customer name, company name, latest negotiation date, negotiation overview, summary of past negotiation content, analysis results, recommended proposal content, future action plan, points of differentiation from competitors, solutions to challenges, price proposal, and proposed implementation schedule. Specific examples of prompt messages include "Analyze the past sales negotiation records of customer D and automatically generate the most suitable proposal document" and "Create a proposal document that takes into account Company D's challenges and requests."

[0056] Step 5: Trend analysis and cross-sectional analysis using generative AI When a representative inputs analysis requests from a terminal, such as "Extract the proposals with the highest closing rates in the past six months," "Analyze the main reasons for lost deals," or "Extract the characteristics of representatives with high closing rates," the generation AI processing unit analyzes the negotiation records across the board, extracting factors for closing deals, factors for losing deals, trends in customer requests, competitor activities, and the performance and characteristics of each representative, and provides this feedback to the terminal. Specific examples of prompts include, "Extract the proposals with the highest closing rates from all negotiation records of the past six months and analyze their commonalities," and "Analyze the negotiation records of lost deals and list the main reasons for losing them."

[0057] Step 6: Information visualization and operation via user interface The user interface on the terminal side visualizes the status of each customer's negotiation, closing rate, lost rate, and progress of proposal activities using graphs and charts. The search screen allows users to narrow down their search using various criteria, and the detailed negotiation record screen offers a variety of functions, including previewing and downloading related documents, playing audio recordings, viewing email history, displaying AI-generated summaries, and registering next actions. For example, a representative can access the system from a smartphone or tablet while on the go, register negotiation records using voice input immediately after a negotiation, and the generating AI can convert the audio data into text, automatically extract key points, and reflect them in the record.

[0058] Step 7: Authentication, Access Control, and Operation Log Management The Authentication Management Department sets access permissions for each person in charge, controlling access to customer information and sales records. For example, sales representatives can only view and edit information for their assigned customers, while administrators can view and edit information for all customers, enabling flexible access control. The Log Management Department records the history of all operations, including viewing, editing, deleting, and adding to customer information and sales records, and uses this information to monitor for information leaks and unauthorized access, and to ensure audit trails. For example, it can record in detail when, by whom, and what operations were performed on specific customer information, allowing for the detection of abnormal operations and suspicious access.

[0059] Step 8: Data Backup and Disaster Recovery The data backup unit regularly backs up customer information and sales records, enabling data recovery in the event of a failure. For example, it automatically backs up all data every night and retains backup data for the past week, allowing for rapid recovery in the event of data loss or system failure. The backup data is encrypted and stored in secure external storage to protect the data even in the event of a disaster.

[0060] (Specific use cases)

[0061] For example, after a sales representative completes an initial meeting with a new customer, they register the new customer information in the customer information management department using the terminal's user interface, entering details such as customer ID, name, contact information, organization, department, position, address, industry, transaction start date, contact person's name, customer rank, customer attributes, remarks, and tag information. Next, they input details such as the meeting ID, meeting date, start and end times, meeting summary, meeting status, related documents (meeting minutes file, quotation, proposal, contract, email history, audio recording, image files, etc.), participant information, meeting location, meeting purpose, results, next actions, evaluation score, issues, competitor information, history, and notes into the meeting record management department. The system also automatically transcribes meeting records via voice input and records details such as issues and requests that arose during the meeting, the history of price negotiations, and incident response history.

[0062] For example, if a representative wants to summarize the past year's sales records for a particular customer and extract the main achievements and challenges, they would input a prompt from their terminal to the generating AI such as, "Summarize the past year's sales records for customer XX and extract the main achievements and challenges." The generating AI processing unit would then extract the relevant sales records chronologically from the databases of the customer information management department and the sales record management department, summarize the key points, achievements, challenges, and next actions for each sales meeting in natural language, and display them on the terminal.

[0063] For example, if a person in charge wants to automatically generate the optimal proposal document for a particular customer, they can input prompts from their terminal to the generation AI such as, "Analyze the past negotiation records of customer XX and automatically generate the optimal proposal document," or "Create a proposal document that takes into account XX's challenges and requests." The generation AI processing unit extracts customer trends, past transaction history, negotiation results, requests, challenges, competitor information, past proposal content, and factors contributing to successful or unsuccessful deals. It then automatically generates a proposal document that includes the customer name, company name, latest negotiation date, negotiation overview, summary of past negotiation content, analysis results, recommended proposal content, future action plan, points of differentiation from competitors, solutions to challenges, price proposal, and proposed implementation schedule, and presents it to the terminal.

[0064] For example, if a sales manager inputs analysis requests from a terminal, such as "I want to extract the proposals with the highest closing rates in the past six months," "I want to analyze the main reasons for lost deals," or "I want to extract the characteristics of sales representatives with high closing rates," they input prompts to the generating AI such as "Extract the proposals with high closing rates from all sales negotiation records of the past six months and analyze the commonalities," "Analyze the sales negotiation records of lost deals and list the main reasons for loss," or "Analyze the sales negotiation records of sales representatives with high closing rates and extract their characteristics." The generating AI processing unit then analyzes the sales negotiation records across the board, extracting factors for closing deals, factors for losing deals, trends in customer requests, competitor trends, and the performance and characteristics of each sales representative, and feeds this information back to the terminal.

[0065] For example, if a representative accesses the system from a smartphone or tablet while out of the office and registers a sales meeting record via voice input immediately after the meeting, they would input a prompt message to the generation AI such as, "Please convert this voice data into text, extract the key points of the meeting, and reflect them in the sales meeting record." The generation AI processing unit would then convert the voice data into text, automatically extract the key points, and reflect them in the sales meeting record.

[0066] For example, if a person in charge wants to extract past complaint handling cases for a particular customer, they would input a prompt to the generation AI such as, "Extract and summarize descriptions related to complaint handling from customer XX's sales records and email history." The generation AI processing unit would then extract descriptions related to complaint handling from the customer's sales records and email history, summarize them, and present them.

[0067] Thus, the system of the present invention uses generative AI to centrally manage customer information and sales negotiation records, and to perform all processes such as information retrieval, extraction, summarization, proposal material generation, trend analysis, and FAQ response. This comprehensively solves a wide range of issues, including improving the work efficiency of personnel, enhancing the reliability of information, advancing proposal activities, optimizing sales strategies, preventing information leaks, complying with audits, and handling system failures.

[0068] (Application Example 1) The flow of a specific process in Application Example 1 will be explained below. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0069] (Embodiments for carrying out the present invention)

[0070] Embodiments for carrying out the present invention will be described in more detail and specifically, including the system configuration and operation examples in the logistics center field. The system of the present invention is equipped with multi-layered functional units such as a shipper information management unit, a shipping record management unit, a generation system AI processing unit, a user interface unit, an authentication management unit, a log management unit, a data backup unit, a notification management unit, an external linkage unit, and a statistical analysis unit, and is implemented in a client-server configuration consisting of a server and terminals.

[0071] The shipper information management department is implemented using a relational or NoSQL database on the server and centrally stores unique shipper IDs, names, contact information (telephone number, email address, fax number), company name, contact person name, transaction start date, transaction terms (contract type, payment terms, delivery terms, etc.), shipper rank (ranking such as A-D), transaction history (transaction amount, number of transactions, items traded), attribute information (important shipper, new shipper, frequent shipper, handles frozen goods, handles hazardous materials, allows night delivery, requires special packaging, etc.), tag information ("caution required," "VIP," "peak season concentrated," etc.), and remarks information (special notes, on-site precautions, past complaints, history of personnel changes, etc.). For example, even if the same shipper has multiple locations or multiple personnel, all information is managed linked to a single shipper record. For example, special attributes and precautions such as "handles frozen goods," "handles hazardous materials," and "allows night delivery" can be assigned as tags to each shipper, allowing on-site personnel to use them for searching and filtering. For example, it's possible to automatically aggregate shipping frequency and transaction value from a shipper's transaction history and automatically update shipper ranks and priorities. For instance, past complaint and request histories of shippers can be accumulated and used for future risk prediction and sales strategy planning.

[0072] The Shipping Records Management Department manages multiple shipping records linked to each shipper's information. Shipping records include: shipping ID, shipping date, shipping details (item, quantity, weight, volume, temperature zone, packaging type, special handling conditions), delivery destination (address, location name, recipient), delivery company (multiple companies handled, evaluation of each company), status (in progress, completed, problem occurred, delayed, canceled, redelivery, etc.), related documents (delivery slip, invoice, photos, videos, email history, inspection records, temperature records, GPS tracking data, etc.), problem details (damage, delay, misdelivery, loss, temperature deviation, quantity shortage, label error, left behind, on-site confusion, etc.), and response history (date and time of occurrence, person in charge, response details, time taken for response, preventative measures, customer notification). The system records details such as the content of the announcement (customer feedback), participant information (field workers, drivers, managers, customer representatives), shipping location (warehouse name, area, lane number, loading berth), shipping purpose (regular delivery, emergency delivery, return, sample shipment, for trade shows, etc.), results (delivery completed, customer evaluation, additional order secured, etc.), next actions (recurrence prevention meeting, on-site training, vendor guidance, customer follow-up, equipment improvement proposals, etc.), evaluation points (on-site evaluation, customer evaluation, AI automated evaluation), competitor information (comparison with other companies, competitor trends, reasons for losing competing projects), and notes (free-form comments from the field, customer requests, on-site improvement proposals, etc.). For example, it can display a list of a shipper's past shipping records in chronological order and record details such as the content and results of each shipment, the occurrence of troubles, response history, and next actions. For example, when a trouble occurs, it also records the type of trouble (damage, delay, misdelivery, loss, etc.), cause, response, recurrence prevention measures, and customer feedback, accumulating a history of trouble responses. For example, shipping records can include on-site photos and videos of the shipping process to preserve evidence of the situation and facilitate future verification. Regarding shipping contents, detailed records of temperature control, packaging methods, and special handling conditions for each item can also be included. Furthermore, the system can automatically compile delivery delay rates and trouble rates for each delivery company, providing valuable information for selecting suppliers and reviewing contracts.

[0073] The generative AI processing unit executes various processes on the server using large-scale language models and generative AI APIs. The generative AI combines diverse AI technologies such as natural language processing, information extraction, summary generation, proposal generation, data analysis, similar case search, trend analysis, risk assessment, keyword extraction, FAQ automated response, speech recognition, and image analysis. For example, if a field staff member inputs "Summarize the trouble cases of Company X over the past year," the generative AI extracts trouble cases from Company X's shipping records and displays a summary of the frequency of occurrence, main causes, countermeasures, and recurrence prevention measures in natural language on the terminal. For example, if the input is "Automatically generate logistics improvement proposals for Company Y," the generative AI analyzes Company Y's past shipping records, trouble history, and transaction trends, and automatically generates specific improvement proposals such as "Increase personnel on days and times with high shipping frequency," "Change the packaging method for specific items," "Review delivery routes where delays frequently occur," "Change packaging materials for items with frequent temperature deviations," and "Strengthen on-site training," and presents them on the terminal. For example, it can handle advanced analytical requests such as "extracting the most common causes of troubles in the past six months," "identifying the characteristics of employees who responded quickly to troubles," "analyzing the commonalities of logistics improvement proposals with high conversion rates," and "comparing the trouble occurrence rates of each delivery company" by analyzing multiple shippers and shipping records across the board. For example, it can automatically compile data such as the time required to resolve a problem, the recurrence rate, and customer satisfaction from the trouble response history, providing insights that can be used for improving on-site operations and training. For example, if an on-site employee accesses the system from a smartphone or tablet while out of the office and registers shipping records and trouble details via voice input immediately after shipment, the generative AI can convert the voice data into text, automatically extract key points, and reflect them in the shipping record. For example, if a manager inputs "Propose future risk reduction measures based on Company Z's past trouble response history," the generative AI will analyze Company Z's past trouble details and countermeasures, and automatically generate and present risk reduction measures such as "reviewing packaging materials," "strengthening pre-shipment inspections," "strengthening cooperation with delivery companies," "thorough on-site training," and "revising the initial response manual in case of trouble." For example, AI can use image analysis technology to automatically detect packaging defects or loading errors from on-site photos and issue alerts as potential problems.

[0074] The user interface is implemented on the terminal side, providing a screen that allows field personnel and managers to intuitively perform operations such as searching, viewing, editing, adding, deleting shipper information and shipping records, requesting the generation of proposal materials, and requesting analysis. For example, the dashboard screen visualizes the shipping status for each shipper, the trouble occurrence rate, the progress of proposal activities, the evaluation of each delivery company, and the work performance of each field worker using graphs and charts. For example, the search screen allows users to narrow down their search using various conditions such as shipper name, company name, keywords, shipping date, status, person in charge, item, delivery destination, delivery company, trouble details, evaluation score, and tags. For example, the detailed shipping record screen provides various functions such as previewing and downloading related documents, viewing field photos and videos, displaying summaries by AI, registering next actions, inputting feedback from the field, and managing the progress of trouble response. For example, field personnel can easily record information using voice input or taking photos, and the AI ​​automatically converts it into text and extracts key points, reducing the burden on field personnel.

[0075] The authentication management unit is implemented on the server side and sets access permissions for each user, controlling access to shipper information and shipping records. For example, field staff can only view and edit information for their assigned shippers, while administrators can view and edit information for all shippers, allowing for flexible permission management. For example, permissions can be automatically set when a new user is added, and permissions can be immediately removed when an employee is transferred or leaves the company. For example, viewing and editing history for specific shipper information and shipping records can be recorded to reduce the risk of unauthorized access and information leakage.

[0076] The log management unit is implemented on the server side and records the history of all operations, including viewing, editing, deleting, and adding to shipper information and shipping records. This is used for monitoring information leaks and unauthorized access, and for ensuring audit trails. For example, it can record in detail when, by whom, and what operations were performed on specific shipper information, and periodically analyze the logs to detect abnormal operations or suspicious access. For instance, it can issue alerts if a large amount of data is downloaded in a short period of time, or if an employee who does not normally access the system accesses specific shipper information.

[0077] The data backup function is implemented on the server side, regularly backing up consignor information and shipping records to enable data recovery in the event of a failure. For example, all data is automatically backed up every night, and the system is configured to retain backup data for the past week, allowing for rapid recovery in the event of data loss or system failure. For example, backup data is encrypted and stored in secure external storage to protect data even in the event of a disaster.

[0078] The notification management department provides real-time notifications to on-site personnel and managers when problems occur or when important actions are required. For example, in the event of a serious problem, an immediate alert is sent to all relevant parties to expedite the initial response. For example, if AI detects signs of trouble, it will alert the on-site manager.

[0079] The External Integration Department integrates with delivery company systems, customer order management systems, inventory management systems, accounting systems, and other systems via APIs to enable automated data transfer and business process automation. For example, it automatically imports delivery completion notifications and delay information from delivery companies and reflects them in shipping records. For example, it automatically registers customer order information in shipper information and shipping records.

[0080] The Statistical Analysis Department aggregates and analyzes big data such as shipper information, shipping records, trouble history, and on-site work performance, and automatically generates reports and dashboards that contribute to on-site improvements and management decisions. For example, it automatically visualizes monthly trouble rate trends, delivery delay rates by delivery company, trouble trends by item, work efficiency by on-site worker, and trends in customer satisfaction, and provides this information to management and on-site supervisors.

[0081] Thus, the embodiments of the present invention realize all processes such as centralized management of shipper information and shipping records, information retrieval, extraction, summarization, proposal material generation, trend analysis, FAQ response, speech recognition, image analysis, external linkage, and statistical analysis using generative AI, while clearly defining the roles of the server and terminal, and comprehensively solving a wide range of issues such as improving the work efficiency of on-site personnel and managers, improving the reliability of information, strengthening troubleshooting capabilities, enhancing proposal activities, accelerating on-site improvements, improving customer satisfaction, preventing information leakage, responding to audits, dealing with failures, and supporting management decisions.

[0082] (System Configuration)

[0083] The system according to this embodiment comprises a shipper information management unit, a shipping record management unit, a generation AI processing unit, a user interface unit, an authentication management unit, a log management unit, a data backup unit, a notification management unit, an external linkage unit, and a statistical analysis unit. The shipper information management unit is implemented using a relational database or NoSQL database on the server and contains a unique shipper ID, name, contact information (telephone number, email address, fax number), company name, contact person name, transaction start date, transaction conditions (contract type, payment terms, delivery conditions, etc.), shipper rank (ranking such as A to D), transaction history (transaction amount, number of transactions, transaction items), attribute information (important shipper, new shipper, frequent shipper, handles frozen goods, handles hazardous materials, can deliver at night, special packaging required, etc.), tag information (caution required, VIP, peak season concentration, etc.), and remarks information (special notes, The system centrally stores information such as on-site precautions, past complaint details, and personnel change history. For example, even if the same shipper has multiple locations or multiple personnel, all information is managed and linked to a single shipper record. Special attributes and precautions, such as handling frozen goods, handling hazardous materials, and nighttime delivery, can be assigned as tags to each shipper, which on-site personnel can use for searching and filtering. For example, it automatically aggregates shipping frequency and transaction amount from the shipper's transaction history, automatically updating shipper rank and priority. For example, it accumulates the shipper's past complaint history and request history, which can be used for future risk prediction and sales strategy planning.

[0084] The Shipping Records Management Department manages multiple shipping records linked to each shipper's information. Each shipping record includes the following information: shipping ID, shipping date, shipping details (item, quantity, weight, volume, temperature zone, packaging type, special handling conditions), delivery destination (address, location name, recipient), delivery company (multiple companies handled, evaluation of each company), status (in progress, completed, trouble occurred, delayed, canceled, redelivery, etc.), related documents (delivery slip, invoice, photos, videos, email history, inspection records, temperature records, GPS tracking data, etc.), trouble details (damage, delay, misdelivery, loss, temperature deviation, quantity shortage, label error, left behind, on-site confusion, etc.), response history (date and time of occurrence, person in charge of response, response content, time taken for response, preventive measures, content reported to customer, customer feedback), participant information (on-site worker, driver, manager, customer representative), shipping location (warehouse name, area, lane number, loading berth), and shipping purpose (regular delivery). Detailed records are kept of items, urgent deliveries, returns, sample shipments, exhibition items, etc., results (delivery completion, customer evaluation, additional order acquisition, etc.), next actions (recurrence prevention meetings, on-site training, vendor guidance, customer follow-up, equipment improvement proposals, etc.), evaluation points (on-site evaluation, customer evaluation, AI automatic evaluation), competitor information (comparison with other companies, competitor trends, reasons for losing competitive deals), and notes (free-form comments from the field, customer requests, on-site improvement proposals, etc.). For example, on-site photos and videos at the time of shipment can be attached to the shipment record to preserve evidence of the on-site situation and be used for later verification. For example, the system automatically compiles the delivery delay rate and trouble rate for each delivery company to be used as a basis for selecting vendors and reviewing contracts. For example, when a trouble occurs, the type of trouble, cause, response, recurrence prevention measures, and customer feedback are also recorded to accumulate a history of trouble response. For example, temperature control, packaging methods, and special handling conditions are also recorded in detail for each item.

[0085] The generative AI processing unit processes large-scale language models and generative AI on the server. Using APIs to perform various processes, the system combines diverse AI technologies such as natural language processing, information extraction, summary generation, proposal generation, data analysis, similar case search, trend analysis, risk assessment, keyword extraction, FAQ automated response, speech recognition, and image analysis. For example, if a field staff member inputs "Summarize the trouble incidents at Company X over the past year," the generative AI extracts trouble incidents from Company X's shipping records and summarizes the frequency of occurrence, main causes, countermeasures, and recurrence prevention measures in natural language, displaying it on the terminal. For example, if the input is "Automatically generate logistics improvement proposals for Company Y," the generative AI analyzes Company Y's past shipping records, trouble history, and transaction trends, and automatically generates and displays specific improvement proposals such as "Increase personnel on days and times with high shipping frequency," "Change the packaging method for specific items," "Review delivery routes where delays frequently occur," "Change packaging materials for items with frequent temperature deviations," and "Strengthen on-site training." For example, by cross-analyzing multiple shippers and shipping records, the system can "Extract the most common causes of troubles in the past six months" and "Extract the characteristics of staff members who responded quickly to troubles." The system can handle advanced analytical requests such as "analyze the commonalities of logistics improvement proposals with high conversion rates" and "compare the trouble occurrence rates for each delivery company." For example, it can automatically collect data such as the time required to resolve a problem, the recurrence rate, and customer satisfaction from the trouble response history, providing insights that can be used for improving on-site operations and training. For example, if a field staff member accesses the system from a smartphone or tablet while out of the office and registers the shipping record and trouble details by voice input immediately after shipment, the generative AI converts the voice data into text, automatically extracts the key points, and reflects them in the shipping record. For example, if a manager inputs "Propose future risk reduction measures based on Company Z's past trouble response history," the generative AI analyzes Company Z's past trouble details and countermeasures, and automatically generates and presents risk reduction measures such as "reviewing packaging materials," "strengthening pre-shipment inspections," "strengthening cooperation with delivery companies," "thorough on-site training," and "revising the initial response manual in case of trouble." For example, the AI ​​can also use image analysis technology to automatically detect packaging defects and loading errors from on-site photos and issue alerts as signs of trouble.Specific examples of prompts to be fed into the generating AI include: "Summarize the trouble incidents that occurred for client X over the past year," "Automatically generate logistics improvement plans for company Y," "Extract delivery routes with frequent delays from all shipping records over the past six months," and "Analyze company Z's trouble response history and propose risk reduction measures."

[0086] The user interface is implemented on the terminal side, providing a screen that allows field staff and managers to intuitively search, view, edit, add, delete shipper information and shipping records, request the generation of proposal materials, and request analysis. For example, the dashboard screen visualizes shipping status for each shipper, trouble occurrence rate, progress of proposal activities, evaluation by delivery company, and work performance for each field worker using graphs and charts. For example, the search screen allows users to narrow down their search using various conditions such as shipper name, company name, keywords, shipping date, status, person in charge, item, delivery destination, delivery company, trouble details, evaluation score, and tags. For example, the detailed shipping record screen provides various functions such as previewing and downloading related documents, viewing field photos and videos, displaying summaries by AI, registering next actions, inputting feedback from the field, and managing the progress of trouble response. For example, field staff can easily record information using voice input or taking photos, and the AI ​​automatically converts this into text and extracts key points, reducing the burden on the field.

[0087] The authentication management unit is implemented on the server side and sets access permissions for each person in charge, controlling access to shipper information and shipping records. For example, field staff can only view and edit information for their assigned shippers, while administrators can view and edit information for all shippers, allowing for flexible permission management. For example, permissions are automatically set when a new person is added, and permissions are immediately removed when a person is transferred or leaves the company. For example, viewing and editing history for specific shipper information and shipping records can be recorded to reduce the risk of unauthorized access and information leakage.

[0088] The log management unit is implemented on the server side and records the history of all operations, including viewing, editing, deleting, and adding to shipper information and shipping records. This is used to monitor for information leaks and unauthorized access, and to ensure audit trails. For example, it records in detail when, by whom, and what operations were performed on specific shipper information, and periodically analyzes the logs to detect abnormal operations or suspicious access. It can also issue alerts, for example, if a large amount of data is downloaded in a short period of time, or if an employee who does not normally access the system accesses specific shipper information.

[0089] The data backup function is implemented on the server side and regularly backs up consignor information and shipping records to enable data recovery in the event of a failure. For example, it automatically backs up all data every night and retains backup data for the past week. For example, it encrypts the backup data and stores it on secure external storage to protect the data even in the event of a disaster.

[0090] The notification management department provides real-time notifications to on-site personnel and managers when problems occur or when important actions are required. For example, in the event of a serious problem, it immediately sends an alert to all relevant parties to expedite the initial response. For example, if AI detects signs of trouble, it alerts the on-site manager.

[0091] The external integration department connects with delivery company systems, customer order management systems, inventory management systems, accounting systems, etc., via APIs to enable automatic data exchange and automation of business processes. For example, it automatically imports delivery completion notifications and delay information from delivery companies and reflects them in shipping records, and automatically registers customer order information in shipper information and shipping records.

[0092] The Statistical Analysis Department aggregates and analyzes big data such as shipper information, shipping records, trouble history, and on-site work performance to automatically generate reports and dashboards that contribute to on-site improvements and management decisions. For example, it automatically visualizes monthly trouble rate trends, delivery delay rates by delivery company, trouble trends by item, work efficiency by on-site worker, and trends in customer satisfaction, and provides this information to management and on-site managers.

[0093] As described above, the system according to this embodiment involves the shipper information management unit, shipping record management unit, generative AI processing unit, user interface unit, authentication management unit, log management unit, data backup unit, notification management unit, external linkage unit, and statistical analysis unit working together to centrally manage shipper information and shipping records, and to realize all processes such as information retrieval, extraction, summarization, proposal material generation, trend analysis, FAQ response, speech recognition, image analysis, external linkage, and statistical analysis using generative AI. By clearly defining the roles of servers and terminals, the system comprehensively solves a wide range of issues, including improving the work efficiency of field staff and managers, improving the reliability of information, strengthening troubleshooting capabilities, enhancing proposal activities, accelerating on-site improvements, improving customer satisfaction, preventing information leaks, responding to audits, handling failures, and supporting management decisions.

[0094] (Implementation Steps)

[0095] Step 1: Register and manage shipper information On-site personnel or managers input new shipper information through the user interface department and send it to the shipper information management department. The shipper information management department centrally registers shipper ID, name, contact information (telephone number, email address, fax number), company name, contact person name, transaction start date, transaction terms, shipper rank, transaction history, attribute information (important shipper, new shipper, handles frozen goods, handles hazardous materials, can deliver at night, etc.), tag information (caution required, VIP, peak season concentrated, etc.), and remarks information (special notes, on-site precautions, past complaint details, personnel change history, etc.) into the database. For example, even if the same shipper has multiple locations or multiple personnel, all information is linked and managed under a single shipper record, special attributes such as handling frozen goods or hazardous materials are assigned as tags for each shipper, shipment frequency and transaction amount are automatically aggregated from the transaction history and the shipper rank is automatically updated, and past complaint history and request history are accumulated and used for risk prediction and sales strategy planning.

[0096] Step 2: Register and manage shipping records After completing the shipping process, the field staff enter the shipping record into the user interface department and send it to the shipping record management department. The shipping record management department records details such as shipping ID, shipping date, shipping contents (item, quantity, weight, volume, temperature zone, packaging type, special handling conditions), delivery destination, shipping company, status, related documents (delivery slip, invoice, photos, videos, email history, inspection records, temperature records, GPS tracking data, etc.), trouble details, response history, participant information, shipping location, shipping purpose, results, next actions, evaluation score, competitor information, and notes. For example, on-site photos and videos of the shipping process can be attached for evidence preservation and verification, delivery delay rates and trouble rates for each shipping company can be automatically compiled and used for vendor selection and contract review, and when troubles occur, the type of trouble, cause, response, preventive measures, and customer feedback are recorded, and temperature control, packaging methods, and special handling conditions are also recorded in detail for each item.

[0097] Step 3: Trouble history summary and extraction using AI generation. When field staff or managers input requests such as "Summarize the trouble incidents of client X over the past year" from a terminal, the generation AI processing unit extracts the relevant trouble history from the shipping record management department's database and displays a summary of the frequency of occurrence, main causes, countermeasures, and recurrence prevention measures in natural language on the terminal. Specific examples of prompts include "Please summarize the trouble incidents of client X over the past year" and "Please extract the trouble response history of company Y and summarize the main countermeasures."

[0098] Step 4: Automatic generation of logistics improvement proposals using AI. When an administrator enters a request such as "Automatically generate logistics improvement plans for Company Y," the generation AI processing unit analyzes Company Y's past shipping records, trouble history, and transaction trends, and automatically generates specific improvement suggestions such as "Increase personnel on days and times with high shipping frequency," "Change the packaging method for specific items," and "Review delivery routes where delays frequently occur," and presents them to the terminal. Specific examples of prompt messages include "Please automatically generate logistics improvement plans for Company Y" and "Analyze past trouble history and propose measures to prevent recurrence."

[0099] Step 5: Cross-sectional trend analysis and risk extraction using generative AI When an administrator inputs an analysis request such as "Extract delivery routes with frequent delays from all shipment records over the past six months" or "Extract the characteristics of employees who responded quickly to problems," the generation AI processing unit analyzes multiple shippers and shipment records across different systems, automatically extracting delivery routes and items with frequent delays and problems, characteristics of employees who respond quickly, and commonalities in logistics improvement proposals with high conversion rates, providing insights that can be used for on-site improvements and sales strategy planning. Specific examples of prompts include "Extract delivery routes with frequent delays from all shipment records over the past six months" and "Extract the characteristics of employees who responded quickly to problems."

[0100] Step 6: Information visualization and operation via user interface The user interface visualizes shipping status and trouble rates for each shipper, progress of proposal activities, evaluations of each delivery company, and work performance of each field worker using graphs and charts. The search screen allows users to narrow down their search using various criteria such as shipper name, company name, keywords, shipping date, status, person in charge, item, delivery destination, delivery company, trouble details, evaluation score, and tags. The detailed shipping record screen offers a variety of functions, including previewing and downloading related documents, viewing on-site photos and videos, displaying AI-generated summaries, registering next actions, inputting feedback from the field, and managing the progress of trouble response.

[0101] Step 7: Authentication, Access Control, and Operation Log Management The Authentication Management Department sets access permissions for each person in charge, controlling access to shipper information and shipping records. Field staff can only view and edit information for their assigned shippers, while administrators can view and edit information for all shippers, enabling flexible access control. The Log Management Department records the history of all operations, including viewing, editing, deleting, and adding to shipper information and shipping records. This is used to monitor for information leaks and unauthorized access, and to ensure audit trails.

[0102] Step 8: Data Backup and Disaster Recovery The data backup unit regularly backs up consignor information and shipping records to enable data recovery in the event of a failure. All data is automatically backed up every night, retaining the past week's worth of backup data. This backup data is encrypted and stored securely on external storage to protect the data even in the event of a disaster.

[0103] Step 9: Notifications, External Integration, and Statistical Analysis The Notification Management Department provides real-time notifications to field personnel and managers when problems occur or when important actions are required, and the AI ​​alerts field managers when it detects signs of trouble. The External Integration Department integrates with delivery company systems, customer order systems, inventory management systems, accounting systems, etc., via APIs to enable automatic data integration and automation of business processes. The Statistical Analysis Department aggregates and analyzes big data such as shipper information, shipping records, trouble history, and field work performance, and automatically generates reports and dashboards that contribute to field improvements and management decisions.

[0104] (Specific use cases)

[0105] For example, in a logistics center, when a field staff member starts a transaction with a new shipper, they register detailed information such as shipper ID, name, contact information, company name, contact person's name, transaction start date, transaction conditions, shipper rank, attribute information, tag information, and remarks information in the shipper information management department via the user interface. For example, if a shipper has special attributes such as handling frozen goods, handling hazardous materials, or being able to deliver at night, these are assigned as tags so that field workers can easily refer to them later when searching or filtering. For example, the shipper's past complaint history and request history are also stored as remarks information and used for future risk prediction and sales strategy planning.

[0106] For example, after completing shipping operations, the field staff member records detailed information from the user interface department to the shipping record management department, including shipping ID, shipping date, item, quantity, weight, volume, temperature zone, packaging type, special handling conditions, delivery destination, shipping carrier, status, delivery slip or invoice, on-site photos or videos, inspection records, temperature records, GPS tracking data, details of the trouble, response history, participant information, shipping location, shipping purpose, results, next actions, evaluation score, competitor information, and notes from the field. For example, on-site photos and videos are attached at the time of shipping to preserve evidence and be used for later verification, and the system automatically compiles delivery delay rates and trouble rates for each shipping carrier to be used as a basis for selecting carriers and reviewing contracts. For example, when a trouble occurs, the system records detailed information such as the type of trouble (damage, delay, misdelivery, loss, temperature deviation, quantity shortage, label error, leftover, on-site confusion, etc.), the cause of the trouble, the response, measures to prevent recurrence, and customer feedback.

[0107] For example, if an administrator sends a prompt from the user interface unit to the generative AI processing unit saying, "Summarize the trouble incidents for client A over the past year," the generative AI extracts the relevant trouble history from the shipping record management unit's database, summarizes the frequency of occurrence, main causes, countermeasures, and preventative measures in natural language, and displays it on the terminal. For example, if a field staff member inputs a prompt saying, "Extract the trouble response history for company B and summarize the main countermeasures," the generative AI analyzes company B's trouble response history, extracts and presents response patterns and effective preventative measures.

[0108] For example, if an administrator prompts "Automatically generate logistics improvement plans for Company C," the generation AI analyzes Company C's past shipping records, trouble history, and transaction trends, and automatically generates specific improvement suggestions such as "Increase personnel on days and times with high shipping frequency," "Change packaging methods for specific items," "Review delivery routes where delays frequently occur," "Change packaging materials for items with frequent temperature deviations," and "Strengthen on-site training," and presents them to the terminal.

[0109] For example, if an administrator prompts, "Please extract delivery routes with frequent delays from all shipping records over the past six months," the generative AI will analyze all shipping records across the board, extract delivery routes and items with a high number of delays, and present this information as a basis for on-site improvements and supplier selection. For example, if an administrator prompts, "Please extract the characteristics of employees who responded quickly to problems," the generative AI will analyze the response history, including the time taken to respond, the content of the response, and customer satisfaction, to extract common behavioral patterns and know-how among employees who responded quickly, providing insights that can be used for on-site training and manual creation.

[0110] For example, if a field staff member accesses the system from a smartphone or tablet while out of the office and records via voice input immediately after shipment, "Packaging damage occurred in today's shipment to Company B; repackaging has been completed on-site," the generative AI converts the voice data into text, extracts keywords such as "packaging damage," "on-site repackaging," and "immediate response," and automatically updates the trouble history.

[0111] Thus, the system of the present invention centrally manages shipper information, shipping records, trouble history, and improvement suggestions, and utilizes generative AI to comprehensively achieve improved work efficiency for on-site staff and managers, enhanced trouble response capabilities, advanced proposal-based sales, faster on-site improvements, and increased customer satisfaction. Specific examples of prompts to be fed into the generative AI include: "Summarize the trouble cases of shipper A over the past year," "Extract the trouble response history of company B and summarize the main countermeasures," "Automatically generate logistics improvement proposals for company C," "Extract delivery routes with frequent delays from all shipping records over the past six months," and "Extract the characteristics of staff members who responded quickly to troubles."

[0112] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0114] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0115] For example, the data collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart device 14 and processes it with the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0116] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0117] [Second Embodiment]

[0118] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0119] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0121] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and communication interface 44 are also connected to the bus 52.

[0122] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0124] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0125] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0126] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0128] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the identification processing unit 290 using these models.

[0129] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is realized by the data processing device 12 and the smart glasses 214. 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".

[0130] (Example 1)

[0131] Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0132] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0133] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] Furthermore, the processing by the data processing system 10 described above is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0135] For example, the data collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart glasses 214 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0136] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0137] [Third Embodiment]

[0138] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0139] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0140] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0141] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, display 343, and communication interface 44 are also connected to the bus 52.

[0142] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0144] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0145] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0146] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0148] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0149] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the headset terminal 314. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0150] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0151] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0152] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0153] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] For example, the data collection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the headset terminal 314 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the headset terminal 314 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0155] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0156] [Fourth Embodiment]

[0157] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0158] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, controlled object 443, and communication interface 44 are also connected to the bus 52.

[0161] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0163] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0164] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0165] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0166] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0167] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0168] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0169] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0170] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0171] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0172] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or external devices, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or external devices.

[0174] For example, the data collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the robot 414 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and controlled object 443 of the robot 414 and the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0175] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0184] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0185] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0186] 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.

[0187] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0188] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using this memory.

[0189] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0190] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0191] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] Furthermore, the following additional information is disclosed regarding the above explanation.

[0195] (Claim 1)

[0196] The system comprises a shipper information management unit, a shipping record management unit, and a generation AI processing unit. The shipper information management unit centrally stores unique identification information, name, contact information, company name, contact person name, transaction start date, transaction terms, shipper rank, transaction history, attribute information, tag information, and remarks information for each shipper in a database. The shipping record management unit links and manages multiple shipping records for each shipper information, and stores various information for each shipping record, such as shipping identification information, shipping date, shipping contents, delivery destination, delivery company, status, related documents, trouble details, response history, participant information, shipping location, shipping purpose, results, next action, evaluation score, competitor information, and memos. The generation AI processing unit This system uses generative AI to analyze shipper information and shipping records in response to search and analysis requests from on-site personnel or managers. It performs tasks such as searching for shipper information based on keywords like shipper name and company name, automatically extracting the latest or ongoing shipping records from specified shippers, extracting trouble details and response history, automatically generating logistics improvement proposals based on shipper information and shipping records, chronologically organizing and immediately extracting past shipping records and trouble history, and automatically generating trend analysis and risk reduction measures by analyzing multiple shippers and shipping records across the board. All of these processes are implemented using natural language processing and information extraction technologies by generative AI. (Claim 2)

[0197] The system according to claim 1, comprising a generation AI processing unit that analyzes trouble details and response history recorded in shipping records, extracts and summarizes the frequency of trouble occurrence, main causes, countermeasures, measures to prevent recurrence, customer feedback, etc., and presents them in natural language upon request from the on-site staff or manager, and further includes a function for automatic text conversion and key point extraction of shipping records and trouble details via voice input. (Claim 3)

[0198] The system according to claim 1, comprising a generation AI processing unit that cross-analyzes shipper information and shipping records, for example, extracting delivery routes and items with frequent delays or problems from all shipping records over the past six months, automatically analyzing the characteristics of personnel who responded quickly to problems and commonalities in logistics improvement proposals with high conversion rates, and automatically generating and presenting insights and risk reduction measures in natural language that can be used for on-site improvements and sales strategy planning. [Explanation of symbols]

[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The system comprises a customer information management unit, a sales negotiation record management unit, and a generative AI processing unit, wherein the customer information management unit stores customer information, including unique identification information, name, contact information, affiliated organization, and remarks information for each customer, in a database; the sales negotiation record management unit manages multiple sales negotiation records linked to each customer information, and stores sales negotiation identification information, sales negotiation date, sales negotiation summary, sales negotiation status, and related document information for each sales negotiation record; and the generative AI processing unit uses generative AI to analyze customer information and sales negotiation records in response to search requests from the person in charge, performing customer information searches based on keywords such as customer name and affiliated organization name, automatic extraction of the latest sales negotiation record from among sales negotiation records linked to a specified customer, extraction of valid sales negotiation records based on sales negotiation status, automatic generation of proposal materials based on customer information and sales negotiation records, and chronological organization and immediate extraction of past sales negotiation records, and the system is characterized in that these series of processes are realized using natural language processing and information extraction technology by generative AI.

2. The system according to claim 1, wherein the generation-based AI processing unit analyzes customer information and negotiation records, automatically analyzes the customer's past negotiation trends and transaction history, and then automatically generates proposal materials containing optimal proposal content for a customer specified by the person in charge, and the proposal materials include the customer's name, organization name, date of the most recent negotiation, negotiation summary, summary and analysis results of past negotiation content, and recommended proposal content by the generation-based AI.

3. The system according to claim 1, wherein the generative AI processing unit organizes customer information and negotiation records in chronological order, and in response to a search request from the person in charge, it immediately extracts and displays in a list all negotiation records related to a specified customer in order of negotiation date or negotiation status, and further has a function to summarize and present the contents of each negotiation record in natural language, and these processes are realized using natural language processing technology by generative AI.

Images