system

Abstract

We provide the system. [Solution] The present invention relates to a system that, in response to inquiries received by corporate sales representatives from customers, utilizes a dedicated generative AI agent for each product to automatically generate product overviews, pricing information, case studies, FAQs, interview questions, and proposal strategies based on the content of the inquiries, and provides them to the sales representatives immediately. The system comprises an inquiry reception department, a product information management department, and a generative AI response department. Based on the latest information updated by product managers, the generative AI automatically generates optimal proposals, quotations, case studies, FAQs, and interview questions, significantly reducing the effort previously required for internal coordination and information gathering, and simultaneously achieving increased efficiency in sales activities and improved proposal quality.

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 relating to a 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 this invention aims to solve is that corporate sales representatives often lack sufficient specialized knowledge and up-to-date information on each product, making it difficult to provide immediate answers and proposals to customer inquiries. As a result, they have to repeatedly consult with internal product managers and communicate via various tools, leading to long lead times of 1-2 business days for initial proposals, quotation creation, case studies, and FAQ responses, hindering prompt customer service and faster negotiation speeds. Furthermore, because corporate sales representatives cannot immediately provide optimal proposal strategies and information to meet customer needs, it can lead to decreased customer satisfaction, reduced proposal accuracy, and overall inefficiency in sales activities. This presents a challenge that includes the obsolescence of information due to product managers' inability to share the latest information, case studies, price revisions, and FAQ additions with the sales team in a timely manner, as well as the resulting information gap in the sales field. Therefore, the aim is to solve these problems and enable corporate sales representatives to use product-specific generative AI agents to instantly and automatically generate proposals, quotations, case studies, FAQs, interview points, and proposal strategies based on the latest and most optimal information in response to customer inquiries. This will enable rapid and high-quality responses to customers, while significantly reducing the effort required for internal coordination and information gathering, thereby simultaneously achieving overall efficiency in sales activities and improved proposal quality. [Means for solving the problem]

[0005] As a means of solving the problem, we have built a system comprising: an inquiry reception department where corporate sales representatives input inquiries received from customers; a product information management department that receives and stores the latest overviews, pricing information, case studies, frequently asked questions, and interview items for each product from product managers as they come in; and a generative AI response department that uses the inquiry content received from the inquiry reception department and the information stored in the product information management department to activate generative AI, which automatically generates the optimal product overview, pricing information, case studies, FAQs, interview items, and proposal policies according to the inquiry content, and provides them to corporate sales representatives immediately. This means that corporate sales representatives can use a generative AI agent dedicated to each product to respond to customer inquiries, and automatically generate proposals, quotations, case studies, FAQs, interview items, and proposal policies based on the latest and most optimal information, enabling a rapid and high-quality response to customers, while also significantly reducing the effort required for internal coordination and information gathering, thereby simultaneously achieving increased efficiency in overall sales activities and improved proposal quality. [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 the non-volatile storage device include a flash memory (SSD (Solid State Drive)), a magnetic disk (for example, a hard disk), a magnetic tape, 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. In addition, in the present specification, when three or more matters are expressed by being connected with "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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network), 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, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, the camera 42, and the 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 inputs. The touch panel 38A detects contact of an indicator (for example, a pen, a finger, or the like), thereby receiving a user input by the contact of the indicator. The microphone 38B detects a user's voice, thereby receiving a voice-based user input. 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] An embodiment of the present invention is a system that, in response to inquiries received by corporate sales representatives from customers, utilizes a dedicated generative AI agent for each product to automatically generate product overviews, pricing information, case studies, frequently asked questions, interview topics, and proposal strategies based on the content of the inquiries, and provides them to the corporate sales representatives immediately. In this embodiment, the system mainly consists of a server and terminals, and the functions of each part are divided as follows.

[0031] First, an inquiry reception system will be implemented on the terminals used by corporate sales representatives. This system will operate on terminals such as PCs, tablets, and smartphones, and will provide a user interface for sales representatives to input inquiries received from customers. For example, sales representatives can input specific requests and questions from customers on their terminals, such as "I would like a proposal to reduce the cost of cloud services," "I would like to know about examples of strengthening the security of network services," or "I would like to know about examples of implementing business efficiency improvements using AI." A variety of input methods will be available, including text input, voice input, selection input, and file attachments, and it will also be possible to upload requirements definition documents and RFPs (Requests for Proposals) received from customers directly.

[0032] The submitted inquiry content is sent to the server via the network. The server side implements a product information management unit and a generation-based AI response unit. The product information management unit receives the latest overview, pricing information, case studies, FAQs, and interview questions for each product from product managers as they come in, and stores and manages them in a database. For example, when a product manager adds a new case study, reflects price revision information, or updates an FAQ, they can register and update the information in the product information management unit on the server via a dedicated management screen or API. This ensures that the latest information is always available to the AI ​​response unit. Furthermore, the product information management unit can manage multiple versions for each product, store past case studies and pricing history, and maintain information on relevant laws, regulations, and industry standards. For example, it can also manage version upgrade information for cloud services, the addition of new options for network services, and the algorithm update history for AI products.

[0033] The generative AI response unit operates the generative AI using the inquiry content sent from the inquiry reception unit and the information stored in the product information management unit. The generative AI used includes large-scale language models and generative AI fine-tuned for specific applications. For example, if the inquiry is "I would like a proposal for reducing the cost of cloud services," the generative AI extracts an overview of the cloud service, pricing information, past cost reduction examples, FAQs, and interview questions from the product information management unit. It then analyzes the keyword "cost reduction" in the inquiry and automatically generates a proposal strategy that prioritizes cost efficiency. Furthermore, the generative AI dynamically combines information of high customer interest, such as "implementation examples at competitors," "comparison of initial costs and running costs," and "differences from other cloud services," to generate proposals and quotations that sales representatives can directly present to customers.

[0034] Furthermore, the generative AI automatically extracts and presents interview questions based on the content of the inquiry. For example, for a cloud service proposal, it would select and present the most suitable interview items for each product, such as "number of planned users," "existing system configuration," and "desired implementation timing," while for a network service, it would select items such as "number of locations," "required bandwidth," and "operational structure." This allows sales representatives to efficiently collect additional information from customers, improving the accuracy of future proposals. Moreover, the interview questions are customized by the AI ​​based on past sales history and information from similar cases, according to the customer's industry, size, and requirements. For example, for a manufacturing customer, more specific interview items such as "number of production sites" and "need for integration with existing production management systems" are automatically added, while for a financial customer, items such as "data protection requirements" and "audit compliance" are automatically added.

[0035] Furthermore, the generative AI can select the most relevant case studies and FAQs from multiple sources and automatically incorporate them into proposals and responses. For example, it can extract the most suitable case studies according to the industry and requirements, such as "IoT infrastructure implementation case studies in manufacturing," "nationwide VPN implementation case studies in the financial industry," and "operational efficiency improvement case studies in the retail industry," enabling proposals tailored to the customer's interests and challenges. It can also automatically generate answers to FAQs, such as "support system," "security measures," and "differences from competitors," based on customer questions. Moreover, the AI ​​learns from past FAQ answer history and customer feedback to generate even more accurate answers.

[0036] The generated proposals, quotations, case studies, FAQs, interview questions, and proposal policies are sent from the server to the terminal and immediately displayed on the sales representative's terminal. The sales representative can not only present this information to the customer as is, but can also edit parts of it or ask additional questions as needed. For example, if a sales representative enters "I would like to know about case studies of business efficiency improvements using AI" at a customer site, the generation AI retrieves the latest case studies, pricing information, and FAQs for AI-related products from the product information management department, and automatically generates a proposal by combining "case studies of business efficiency improvements through AI implementation in a major logistics company," "cost reduction effects of AI implementation," and "example schedule until implementation," and can also present interview questions such as "current business processes," "objectives of AI implementation," and "budget scale."

[0037] Furthermore, when a product manager registers new case studies or price revision information, the product information management department immediately reflects this information in the generation-based AI response unit, allowing sales representatives to always make proposals based on the latest information. For example, in the event of a price revision, the generation-based AI automatically generates a quote reflecting the new price, and can also automatically generate explanatory text including comparisons with past prices and reasons for price increases or decreases.

[0038] Furthermore, generative AI can handle inquiries that span multiple products. For example, even for complex inquiries such as "I would like a proposal that combines cloud services and network services," it can integrate information from each product and automatically generate optimal combination proposals or cross-sell suggestions. For instance, if network bandwidth needs to be increased due to the introduction of cloud services, the AI ​​will combine pricing, case studies, and FAQs for both products to generate a comprehensive proposal.

[0039] Furthermore, the generative AI can also refer to the sales representative's past sales history and customer attribute information, automatically generating personalized proposals such as, "This type of proposal was effective for customers who made similar inquiries in the past," or "This customer previously emphasized security, so we will include security enhancements this time as well." In addition, the AI ​​automatically adjusts the format and expression of proposals, generating optimal documents according to the customer's role and interests, such as "summary documents for management," "detailed explanations for field staff," and "technical specifications for engineers."

[0040] Thus, in this embodiment of the present invention, the inquiry reception unit is implemented on the terminal side, while the product information management unit and the generation-based AI response unit are implemented on the server side. This configuration minimizes the load on the terminal side while enabling advanced information generation processing using a powerful generation-based AI on the server side. This allows corporate sales representatives to automatically generate high-quality proposals, quotations, case studies, FAQs, interview items, and proposal policies immediately in response to diverse and complex inquiries from customers, thereby simultaneously improving customer satisfaction and streamlining sales activities.

[0041] Furthermore, for example, if a sales representative is offline at a customer's site, it is possible to temporarily use past proposal examples and FAQs cached on the terminal, and then synchronize them with the server-side generative AI response unit after returning online, ensuring that the latest information is always reflected. The generative AI can also handle multiple languages, so for example, it can automatically generate proposals and FAQs in English, Chinese, etc., in response to inquiries from overseas customers. In addition, the AI ​​can learn from customer feedback and sales negotiation results, and can continuously improve the accuracy of proposals and customer satisfaction.

[0042] Thus, the embodiment of the present invention implements the inquiry reception unit on the terminal side and the product information management unit and the generation-based AI response unit on the server side, with the generation-based AI at its core. This creates an extremely practical and scalable system that enables corporate sales representatives to quickly and accurately generate proposals, quotations, case studies, FAQs, interview items, and proposal policies based on the latest and most optimal information in response to all customer inquiries, thereby achieving overall efficiency in sales activities and a fundamental improvement in proposal quality.

[0043] (System Configuration)

[0044] The system according to this embodiment comprises an inquiry reception unit, a product information management unit, a generation-based AI response unit, a user interface unit, an information update management unit, a history management unit, and a security management unit. The inquiry reception unit has a function for corporate sales representatives to input the content of inquiries received from customers, and operates on terminals such as PCs, tablets, and smartphones, providing various input methods such as text input, voice input, selection input, and file attachment. For example, a sales representative can input text such as "I would like a proposal for cost reduction of cloud services," or voice input such as "Please tell me about examples of business efficiency improvements using AI," or upload requirements definition documents and requests for proposals received from customers as files. The inquiry reception unit also has an automatic completion function for input content and a function to search for similar cases from past inquiry history, and provides support such as "presenting the content of similar inquiries in the past as a reference" and "suggesting relevant FAQs and examples during input."

[0045] The Product Information Management Department has the function of receiving the latest overviews, pricing information, case studies, FAQs, and interview questions for each product from product managers as they come in, and storing and managing them in a database. For example, when a product manager adds a new case study, they can register detailed information such as "Cloud service implementation case study for the manufacturing industry" or "Network service implementation case study for the financial industry" from a dedicated management screen. In addition, if there is a price revision, information such as "Monthly fee for cloud service changed from 100,000 yen to 120,000 yen" or "Initial fee for network service reduced from 50,000 yen to 30,000 yen" can be reflected immediately. FAQ updates can also be registered as needed, including "Changes to support system," "Addition of new security measures," and "Addition of questions regarding differences from other companies' services." Furthermore, interview questions such as "Number of planned users," "Existing system configuration," "Desired implementation period," "Number of locations," "Required bandwidth," and "Operational structure" can be flexibly managed, differing for each product. The Product Information Management Department also stores past version control information, legal and industry standard information, and related technical documents and manuals. For example, it centrally manages "cloud service version upgrade history," "network service new option addition history," and "AI product algorithm update history."

[0046] The Generative AI Response Unit uses the inquiry content sent from the Inquiry Reception Unit and the information stored in the Product Information Management Unit to activate the Generative AI and automatically generate the optimal product overview, pricing information, case studies, FAQs, interview questions, and proposal strategies according to the inquiry content. For example, if a sales representative inputs "I would like a proposal for cost reduction of cloud services," the Generative AI extracts the cloud service overview, latest pricing, past cost reduction case studies, FAQs, and interview questions from the Product Information Management Unit, analyzes the keyword "cost reduction," and automatically generates a proposal strategy that prioritizes cost efficiency. Furthermore, the Generative AI dynamically combines information of high interest to the customer, such as "case studies from competitors," "comparison of initial costs and running costs," and "differences from other cloud services," to generate proposals and estimates that sales representatives can present directly to customers. Furthermore, the generative AI automatically extracts and presents interview questions based on the inquiry. For example, for cloud service proposals, it might ask for "number of planned users," "existing system configuration," and "desired implementation timeline." For network services, it might ask for "number of locations," "required bandwidth," and "operational structure." The AI ​​selects the most appropriate interview items for each product and presents them to the sales representative. In addition, the generative AI can select the most relevant case studies and FAQs from multiple sources and automatically incorporate them into proposals and responses. For example, it can extract the most suitable case studies according to the industry and requirements, such as "IoT infrastructure implementation case studies in manufacturing," "nationwide VPN implementation case studies in the financial industry," and "business efficiency improvement case studies in the retail industry," enabling proposals tailored to the customer's interests and challenges. It can also automatically generate answers to FAQs, such as "support system," "security measures," and "differences from competitors," based on customer questions. The generative AI learns from past FAQ answer history and customer feedback to generate even more accurate answers. A concrete example of a prompt message to be fed into a generative AI is: "Based on the following information, please create a proposal that prioritizes cost reduction of cloud services. Customer industry: Manufacturing, Number of planned users: 200, Existing system: On-premise server, Desired implementation period: Within 3 months. Please also refer to past implementation cases and FAQs."Examples include, "Please automatically generate a proposal and interview questions for the financial industry based on examples of network service security enhancements, including the latest pricing information and support system."

[0047] The user interface section provides screens and operating systems for sales representatives to use the system on their terminals, and includes a variety of interfaces such as inquiry input screens, proposal display screens, FAQ viewing screens, interview item presentation screens, and past sales history search screens. For example, sales representatives can use tablets at customer sites to view and edit proposals on the spot, search FAQs in real time, and input interview items while reviewing them together with the customer. Furthermore, the user interface section can customize the displayed content according to the sales representative's authority and usage history, and can automatically display the most suitable documents according to the customer's position and interests, such as "summary materials for management," "detailed explanations for field staff," and "technical specifications for engineers."

[0048] The Information Update Management Department provides functions for product managers and administrators to register and update new information in the Product Information Management Department. It centrally manages all information updates, such as adding new products, changing specifications for existing products, revising prices, adding case studies, updating FAQs, and reviewing interview items. For example, if a product manager adds information about a new version release of an AI product, adds a new option to a cloud service, or adds a case study of troubleshooting for a network service, these changes are immediately reflected through the Information Update Management Department. The Information Update Management Department also includes features such as update history management, a rollback function to previous versions, and an approval workflow for update content.

[0049] The History Management Department manages inquiry history, proposal history, FAQ viewing history, and interview information collection history for each sales representative and customer in chronological order. For example, it analyzes and visualizes "what kinds of inquiries the same customer has made in the past," "which proposals led to successful deals," and "which FAQs are frequently referenced." This allows sales representatives to conduct more effective sales activities by referring to past success and failure cases. The History Management Department is also used for AI-powered sales negotiation analysis, customer trend analysis, and optimization of sales activities.

[0050] The Security Management Department has functions to ensure the information security of the entire system, such as authentication and authorization of sales and product personnel, encryption of communications, data access control, prevention of information leaks, and recording of audit logs. For example, it addresses all security risks, such as multi-factor authentication when sales personnel access the system from terminals, management of access rights to product information, masking of customer information, and detection of unauthorized access from external sources. The Security Management Department can also operate in compliance with laws, regulations, and industry standards, and can handle industries that require high security requirements, such as the financial and medical industries.

[0051] Thus, the system according to this embodiment organically links the inquiry reception unit, product information management unit, generation-based AI response unit, user interface unit, information update management unit, history management unit, and security management unit, enabling corporate sales representatives to automatically generate high-quality proposals, quotations, case studies, FAQs, interview items, and proposal policies in real time, even in response to diverse and complex inquiries from customers, thereby achieving overall efficiency in sales activities and a fundamental improvement in proposal quality.

[0052] (Implementation Steps)

[0053] Step 1: Enter and submit inquiry details. Corporate sales representatives input customer inquiries into a user interface on their terminals. A variety of input methods are available, including text input, voice input, selection input, and file attachments. For example, they can enter specific requests such as "I would like a proposal for reducing cloud service costs" or "I would like to hear examples of business efficiency improvements using AI," and they can also upload files such as requirements definitions and requests for proposals received from customers. The inquiry reception system also features automatic completion of input content and suggests similar cases based on past inquiry history.

[0054] Step 2: Acquisition and management of product information The server-side product information management unit receives the latest product overviews, pricing information, case studies, FAQs, and interview data from product managers as needed, and stores and manages them in a database. For example, when a product manager adds a new case study, reflects price revisions, or updates FAQs, they register and update the information through a dedicated management screen or API. Furthermore, version control, legal and regulatory information, and related technical documents are also managed centrally.

[0055] Step 3: Automatic response generation by generation AI The generation AI response unit operates using the inquiry content sent from the inquiry reception unit and the information stored in the product information management unit. The generation AI analyzes keywords and customer attributes in the inquiry content and automatically generates the optimal product overview, pricing information, case studies, FAQs, interview questions, and proposal strategy. For example, if the proposal is for cost reduction of cloud services, it will create a proposal document by combining case studies, price comparisons, and FAQs that emphasize cost efficiency. Specific examples of prompts to be fed into the generation AI include: "Please create a proposal document emphasizing cost reduction of cloud services based on the following information. Customer industry: manufacturing, planned number of users: 200, existing system: on-premise server, desired implementation period: within 3 months. Please also refer to past case studies and FAQs." and "Please automatically generate a proposal document and interview questions for the financial industry based on a case study of strengthening network service security. Please also include the latest pricing information and support system." The AI ​​selects the most relevant information from multiple case studies and FAQs and automatically incorporates it into the proposal document and response.

[0056] Step 4: Presenting and editing information for sales representatives. The AI-generated proposals, price quotes, case studies, FAQs, interview questions, and proposal strategies are automatically sent from the server to the sales representative's terminal and displayed immediately. Sales representatives can not only present this information to customers as is, but also edit parts of it or ask additional questions as needed. For example, they can adjust the wording of the proposal or add or delete interview questions according to customer requests.

[0057] Step 5: Customer Service & Feedback Collection Sales representatives use proposals, FAQs, and interview questions generated by AI to conduct business negotiations with customers, and input any additional requests or feedback from customers into the system. The feedback is recorded in the history management department and used for AI learning and improving the accuracy of future proposals. For example, if a customer makes additional requests such as "I want to know the detailed breakdown of the price" or "I want comparative materials with other companies," this information will also be reflected in the generation of future proposals.

[0058] Step 6: Updating and maintaining product information Product managers and administrators can, through the Information Update Management Department, add new products, modify specifications of existing products, revise prices, add case studies, update FAQs, and review interview topics as needed. Examples include "adding information on new AI product version releases," "adding new options for cloud services," and "adding network service incident response case studies." These updates are immediately reflected in the Product Information Management Department and the Generative AI Response Department, allowing sales representatives to always make proposals based on the latest information.

[0059] (Specific use cases)

[0060] For example, if a corporate sales representative receives an inquiry from a customer stating, "We want to refresh our business systems using cloud services, but we would like a proposal that prioritizes cost reduction," the sales representative would input "We would like a proposal for cost reduction using cloud services" into the inquiry reception unit on their terminal. The inquiry reception unit sends the input to the server's generation AI response unit, which then generates a prompt message for the generation AI while referring to the latest overview of cloud services, pricing information, past implementation cases, FAQs, and interview items stored in the product information management unit. A concrete example of such a prompt message would be: "Based on the following information, create a proposal that prioritizes cost reduction using cloud services. Customer industry: manufacturing, planned number of users: 200, existing system: on-premise server, desired implementation period: within 3 months. Please also refer to past implementation cases and FAQs." The AI ​​combines this prompt text with information extracted from the product information management department's database to automatically generate a proposal that includes an overview of the cost-reduction-focused cloud service, the latest pricing plans, case studies of cost reduction through cloud migration in the manufacturing industry, frequently asked questions and their answers, and information gathered through interviews such as "planned number of users," "existing system configuration," and "desired implementation timeframe." The generated proposal is immediately displayed on the sales representative's terminal, allowing them to present it directly to the customer, edit parts of the content as needed, or ask additional questions.

[0061] For example, if a customer requests to know about "case studies of network service security enhancements," the sales representative would input "Please provide case studies of network service security enhancements." The generation AI response unit extracts the latest overview of network services, pricing, implementation examples in high-security industries such as finance and healthcare, FAQs, and interview questions from the product information management unit, and prompts the generation AI with the message, "Based on case studies of network service security enhancements, automatically generate a proposal and interview questions for the financial industry. Include the latest pricing information and support system." The generation AI combines information such as "case studies of security enhancements through nationwide VPN implementation," "encrypted communication provided as standard," "immediate remote support in case of failure," and "security audit compliance" to automatically generate a proposal and interview questions, which are then immediately displayed on the sales representative's terminal.

[0062] For example, if a customer requests to know about case studies of AI-driven business efficiency improvements, the sales representative would input, "Please provide case studies and proposals for AI-driven business efficiency improvements." The generation AI response unit extracts the latest overview, pricing, AI implementation case studies in industries such as logistics and retail, FAQs, and interview questions for AI-related products from the product information management unit, and prompts the generation AI with the message, "Based on case studies of AI-driven business efficiency improvements, automatically generate a proposal and interview questions for the logistics industry. Include cost reduction effects from AI implementation and an example schedule for implementation." The generation AI combines information such as "case studies of reduced work time through AI implementation," "inventory management optimization using AI," "example schedule for implementation," "objectives of AI implementation," "current business processes," and "budget size" to automatically generate a proposal and interview questions, which are immediately displayed on the sales representative's terminal.

[0063] For example, if a customer requests a proposal combining cloud services and network services, the sales representative would input "Request a proposal combining cloud services and network services." The generation AI response unit extracts the latest overview, pricing, combined implementation case studies, FAQs, and interview questions for both products from the product information management unit, and provides the generation AI with a prompt message such as, "Create a proposal combining cloud services and network services. Customer industry: retail, 20 locations nationwide, planned number of users: 500, existing system: on-premise server, desired implementation period: within 6 months. Refer to combined implementation case studies and FAQs as well." The generation AI then automatically generates a proposal and interview questions by combining information such as "simultaneous proposal for cloud migration and network bandwidth enhancement," "VPN implementation case studies at nationwide locations," "security measures for cloud services," "price simulation for combined proposals," "number of locations," "required bandwidth," and "existing system configuration," and immediately displays them on the sales representative's terminal.

[0064] Thus, the system of the present invention provides the sales representative with the most suitable prompt text for the AI ​​based on the content of the inquiry and customer attributes in response to various inquiries received from customers. Based on the latest information from the product information management department, it automatically generates proposals, quotations, case studies, FAQs, interview items, proposal policies, etc., enabling the sales representative to immediately provide high-quality proposals to customers.

[0065] (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."

[0066] (Embodiments for carrying out the present invention)

[0067] The embodiment of the present invention provides a system that enables extremely high-level on-site support for logistics center operations. To address the diverse operational challenges, troubles, requests for operational improvements, and immediate on-site decision-making needs faced daily by on-site personnel and managers, a dedicated generative AI agent is assigned to each business process. The system automatically generates optimal standard work procedures, troubleshooting measures, past improvement examples, FAQs, interview items, and custom advice in response to the inquiry content and provides them to on-site personnel and managers. In this embodiment, the system mainly consists of a server and on-site terminals. On-site terminals include personal computers, tablets, smartphones, wearable devices, voice input devices, AR glasses, handheld terminals, etc., and are used directly by on-site personnel and managers. The server side implements a business process information management unit and a generative AI response unit.

[0068] The inquiry reception unit operates on field terminals and provides a variety of user interfaces for field staff and managers to input inquiries related to their work. For example, it offers diverse input methods such as text-based inquiries like "Please tell me how to handle delays in sorting work" or "I want to know how to investigate the cause of inventory discrepancies in inventory management," voice-based inquiries like "Please tell me the recovery procedure if a transport robot stops" or "Please tell me what to do if a barcode cannot be read during receiving work," as well as the ability to attach photos and videos taken on-site, upload work record files, and send data from on-site sensors and automatically linked data from IoT devices. Field staff can make inquiries immediately using voice input, wearable devices, or AR glasses, even when their hands are occupied during work. For example, if a staff member wearing AR glasses detects an anomaly on-site, they can inquire with the AI ​​using eye-tracking input or voice commands and send on-site video footage directly.

[0069] Inquiries submitted from the inquiry reception department are forwarded to the server-side generation AI response unit. The business process information management department stores and manages a database of standard work procedures, troubleshooting measures, improvement examples, FAQs, interview items, on-site history, feedback information, work manuals, video manuals, checklists, work records, equipment specifications, IoT data, sensor history, past accident reports, on-site suggestion history, and training materials for each business process within the logistics center, including sorting, inventory management, receiving and shipping management, transportation, stocktaking, picking, packing, inspection, equipment inspection, troubleshooting, emergency response, regular maintenance, worker shift management, equipment operation monitoring, quality control, and accident / disaster response. For example, regarding sorting operations, the system maintains standard procedures such as "Scan the barcode and transport to the designated area. If the weight exceeds the limit, contact the manager," troubleshooting measures such as "Rescan if there is a scan error, and switch to a backup terminal if there is equipment failure," improvement examples such as "Examples of reducing mis-sorting through the introduction of AI image recognition," "Examples of improving work efficiency through the introduction of automated guided vehicles," "Examples of reducing delays through the optimization of worker movement paths," and "Examples of reducing manpower through the introduction of new conveyor belts," as well as FAQs such as "How to change sorting areas," "How to handle picking errors," "Charging timing for transport robots," and "Points to note when workers change shifts," and information gathered through interviews such as "Type of package," "Number of items to be sorted," "Number of workers," "Transportation distance," "Start time of work," and "Temperature and humidity at the site." Regarding inventory management, the standard procedure is "Read RFID tags upon receipt and register them in the inventory system. Periodic inventory counts are conducted once a month." Troubleshooting measures include "Verify history when inventory discrepancies occur and reissue tags if they are faulty." Improvement examples include "Examples of reducing inventory time through the introduction of automated inventory robots," "Examples of improving inventory forecast accuracy with AI," and "Examples of automating nighttime inventory work." FAQs cover topics such as "Inventory frequency," "Inventory data correction methods," "Storage conditions for inventory items," and "Safety measures during inventory counts." Information gathered through interviews includes details such as "Number of inventory items," "Inbound frequency," "Inventory staff," "Inventory turnover rate," and "Temperature and humidity of storage areas."Regarding transport operations, we maintain standard procedures and troubleshooting measures such as "procedures for optimizing transport routes," "methods for periodic inspection of transport robots," "responses when obstacles are detected," and "restart procedures in case of emergency stops," as well as improvement examples such as "examples of automatic transport route optimization using AI," "examples of extending the battery life of transport robots," and "examples of reducing the number of people required for transport operations," as well as FAQs such as "methods for detecting abnormal noises from transport robots" and "responses when transported items are damaged," and information gathered through interviews such as "weight of transported items," "transport distance," "number of robots," and "worker deployment."

[0070] The Generative AI Response Unit operates the Generative AI using the inquiry content received from the Inquiry Reception Unit and the information stored in the Business Process Information Management Unit. The Generative AI utilizes large-scale language models and business-specific AI models to analyze keywords in the inquiry content, on-site conditions, and images, videos, and IoT data transmitted from the site. For example, it extracts keywords such as "delay," "safety," "labor saving," "trouble," "efficiency," "anomaly," "recovery," "accident," "disaster," "equipment failure," "staff shortage," "increased workload," and "temperature and humidity anomaly," and automatically combines the most appropriate standard work procedures, troubleshooting measures, past improvement cases, FAQs, interview items, on-site history, and IoT data to generate an answer. For example, in response to an inquiry such as "Please tell me how to handle delays in sorting work," the AI ​​will present standard procedures and further present specific countermeasures as "emergency response procedures in case of delays," such as "temporarily increasing the number of workers," "prioritizing the processing of priority items," "temporarily changing the transport route," "redesigning the worker's movement path," "checking the temperature and humidity at the site," and "checking the operating status of transport robots." In addition, improvement examples such as "Examples of reducing mis-sorting through the introduction of AI image recognition," "Examples of improving work efficiency through the introduction of automated guided vehicles (AGVs)," and "Examples of reducing delays through optimizing worker movement" will also be presented as reference information for on-site use. As FAQs, frequently asked questions and answers from the field will be displayed, such as "How to change sorting areas," "How to handle picking errors," "When to charge AGVs," and "Points to note when workers change shifts." Additional information that should be confirmed will also be presented as items to be gathered, such as "Type of packages," "Number of items to be sorted," "Number of workers," "Transportation distance," "Start time of work," and "Temperature and humidity at the site."

[0071] The AI ​​also generates customized advice based on the content of the inquiry. For example, if the keyword "delay" is included, it will recommend "emergency response procedures in case of delays"; if "safety" is included, it will suggest "work instructions that prioritize safety"; if "labor saving" is included, it will suggest "labor saving plans using automated equipment"; and if "anomaly" is included, it will recommend "checking for anomaly values ​​in IoT sensors and ordering site inspections." In this way, it dynamically generates optimal advice according to the situation on site. Furthermore, the AI ​​learns from past on-site response history, improvement examples, feedback from the field, IoT data, worker shift information, equipment operating status, accident / disaster history, training history, on-site proposal history, etc., and can continuously improve the accuracy and suitability of its answers to on-site situations.

[0072] For example, if a user asks for instructions on how to recover if a transport robot stops during a transport operation, the AI ​​will provide standard procedures and troubleshooting steps such as "re-powering the robot," "checking for obstacles," "checking the error log," "switching to a backup robot," "checking the site temperature and humidity," "checking the battery level," and "referencing the robot's periodic maintenance history." It will also provide "case studies of recovery from similar problems in the past," "the latest maintenance information from the robot manufacturer," and "examples of abnormal sound detection by AI." As FAQs, it will display information such as "robot periodic maintenance frequency," "battery replacement method," "how to respond when obstacles are detected," and "how to update the robot's software," and will ask for information such as "robot model number," "time of malfunction," "site congestion," "weight of transported items," and "worker deployment status."

[0073] On-site personnel and managers can register new trouble cases, improvement examples, feedback information, work history, IoT data, accident reports, on-site suggestions, and training history with the Business Process Information Management Department as needed. For example, they can register "new transport robot failure cases," "AI image recognition false detection cases," "operational improvement cases for newly introduced equipment," "on-site improvement suggestions from workers," "on-site response records in the event of an accident," and "safety measures cases during nighttime work." This information is then used as training data for generative AI. This allows the AI ​​to continuously learn the latest on-site information and know-how, improving the accuracy and suitability of its responses to on-site situations.

[0074] The system controls the displayed content and operational scope according to the authority of field personnel and administrators. For example, field personnel are granted the authority to view and execute standard procedures, FAQs, and troubleshooting measures, while administrators are granted the authority to register improvement examples, analyze work history, register feedback to AI, create training materials, and approve field proposals. The security management department is responsible for ensuring information security at the logistics center by handling access control, communication encryption, audit log recording, IoT device authentication, remote locking of field terminals in case of loss, information leakage prevention measures, anonymization of field video data, and compliance with legal regulations.

[0075] Thus, the embodiments of the present invention are an extremely practical and scalable system that dramatically improves on-site responsiveness, operational efficiency, safety, quality, on-site capabilities, knowledge sharing, business standardization, troubleshooting capabilities, training efficiency, and on-site improvement capabilities by linking the inquiry reception department, the business process information management department, and the generative AI response department, with the generative AI at its core, to instantly and automatically generate and provide on-site optimal standard work procedures, troubleshooting measures, improvement examples, FAQs, interview items, custom advice, on-site history, IoT data, training history, on-site proposals, accident reports, etc., in response to all kinds of business challenges and troubles faced by on-site personnel and managers.

[0076] (System Configuration)

[0077] The system according to this embodiment comprises an inquiry reception unit, a business process information management unit, a generation-based AI response unit, a user interface unit, a field feedback management unit, a security management unit, a history analysis unit, and an education support unit. The inquiry reception unit has functions for field personnel and managers to input all kinds of business issues, troubles, and improvement requests that occur within the logistics center. It operates on various field terminals such as PCs, tablets, smartphones, wearable devices, AR glasses, voice input devices, and handheld terminals, and provides various input methods such as text input, voice input, photo / video attachment, file upload, transmission of IoT sensor linked data, and real-time transmission of field video. For example, a field person can input text such as "Please tell me how to handle delays in sorting work," or voice input such as "Please tell me the recovery procedure if a transport robot stops," or attach photos or videos of abnormal locations taken on-site, or link temperature and humidity abnormality data automatically transmitted from IoT sensors. The inquiry reception unit also performs functions such as automatic completion of input content, searching for similar cases from past inquiry history, dynamic presentation of input items according to the field situation, monitoring of the status of field terminals, and support for re-entry in case of input errors.

[0078] The Business Process Information Management Department stores and manages a database of standard work procedures, troubleshooting measures, improvement examples, FAQs, interview items, on-site history, feedback information, work manuals, video manuals, checklists, work records, equipment specifications, IoT data, sensor history, past accident reports, on-site suggestion history, and training materials for each business process within the logistics center, including sorting, inventory management, receiving and shipping management, transportation, stocktaking, picking, packing, inspection, equipment inspection, troubleshooting, emergency response, regular maintenance, worker shift management, equipment operation monitoring, quality control, and accident / disaster response. For example, regarding sorting operations, the system maintains standard procedures such as "Scan the barcode and transport to the designated area. If the weight exceeds the limit, contact the manager," troubleshooting measures such as "Rescan if there is a scan error, and switch to a backup terminal if there is equipment failure," improvement examples such as "Examples of reducing mis-sorting through the introduction of AI image recognition," "Examples of improving work efficiency through the introduction of automated guided vehicles," "Examples of reducing delays through the optimization of worker movement paths," and "Examples of reducing manpower through the introduction of new conveyor belts," as well as FAQs such as "How to change sorting areas," "How to handle picking errors," "Charging timing for transport robots," and "Points to note when workers change shifts," and information gathered through interviews such as "Type of package," "Number of items to be sorted," "Number of workers," "Transportation distance," "Start time of work," and "Temperature and humidity at the site." Regarding inventory management, the standard procedure is "Read RFID tags upon receipt and register them in the inventory system. Periodic inventory counts are conducted once a month." Troubleshooting measures include "Verify history when inventory discrepancies occur and reissue tags if they are faulty." Improvement examples include "Examples of reducing inventory time through the introduction of automated inventory robots," "Examples of improving inventory forecast accuracy with AI," and "Examples of automating nighttime inventory work." FAQs cover topics such as "Inventory frequency," "Inventory data correction methods," "Storage conditions for inventory items," and "Safety measures during inventory counts." Information gathered through interviews includes details such as "Number of inventory items," "Inbound frequency," "Inventory staff," "Inventory turnover rate," and "Temperature and humidity of storage areas."Regarding transport operations, we maintain standard procedures and troubleshooting measures such as "procedures for optimizing transport routes," "methods for periodic inspection of transport robots," "responses when obstacles are detected," and "restart procedures in case of emergency stops," as well as improvement examples such as "examples of automatic transport route optimization using AI," "examples of extending the battery life of transport robots," and "examples of reducing the number of people required for transport operations," as well as FAQs such as "methods for detecting abnormal noises from transport robots" and "responses when transported items are damaged," and information gathered through interviews such as "weight of transported items," "transport distance," "number of robots," and "worker deployment."

[0079] The generation-based AI response unit uses the inquiry content received from the inquiry reception unit and the information stored in the business process information management unit to activate the generation-based AI. It analyzes keywords in the inquiry content, on-site conditions, and images, videos, and IoT data sent from the site, and automatically combines the optimal standard work procedures, troubleshooting measures, past improvement examples, FAQs, interview items, on-site history, and IoT data to generate an answer. For example, in response to an inquiry such as "Please tell me how to handle delays in sorting work," the standard procedure is presented, along with specific countermeasures as "emergency response procedures in case of delays," such as "temporarily increasing the number of workers," "prioritizing the processing of priority items," "temporarily changing the transport route," "redesigning the worker's movement path," "checking the temperature and humidity at the site," and "checking the operating status of the transport robot." Improvement examples such as "cases of reducing mis-sorting through the introduction of AI image recognition," "cases of improving work efficiency through the introduction of automated transport robots," and "cases of reducing delays through the optimization of worker movement paths" are also presented. Frequently asked questions include "how to change the sorting area," "how to handle picking errors," "when to charge the transport robot," and "points to note when workers change shifts," and information such as "type of package," "number of items to be sorted," "number of workers," "transport distance," "start time of work," and "temperature and humidity at the site" are presented as items to be gathered. Specific examples of prompts to be fed into the generating AI include: "Based on the following on-site conditions, generate emergency response procedures in case of delays in sorting work, related improvement examples, FAQs, and additional questions to be asked. On-site temperature and humidity: 28 degrees, transport robot utilization rate: 80%, number of workers: 8, type of cargo: large home appliances, history of past delays." and "Generate recovery procedures, past similar trouble cases, FAQs, and questions to be asked if the transport robot stops. Robot model number: X100, time of failure: 10:00 AM, on-site congestion level: high, IoT sensor abnormal values ​​detected."

[0080] The user interface section provides screens and operating systems for field personnel and administrators to use the system on their terminals, and includes a variety of interfaces such as inquiry input screens, proposal display screens, FAQ viewing screens, interview item presentation screens, field history search screens, IoT data visualization screens, training video viewing screens, and field feedback input screens. For example, field personnel can use tablets to view and edit proposals on the spot, search FAQs in real time, input interview items while confirming them with the customer, and visualize field video and IoT data in graphs. The user interface section customizes the displayed content according to the permissions and usage history of field personnel and administrators, and immediately presents the most appropriate information according to the field situation and work content.

[0081] The Field Feedback Management Department has functions to allow field personnel and managers to register and manage new trouble cases, improvement cases, feedback information, work history, IoT data, accident reports, field suggestions, and training history as they occur on-site. For example, it can register "new transport robot failure cases," "AI image recognition false detection cases," "operational improvement cases for newly introduced equipment," "field improvement suggestions from workers," "records of on-site responses when accidents occur," and "safety measures cases during nighttime work." This information is used as training data for generative AI. The Field Feedback Management Department also has functions for approving registered content, evaluating and adopting field suggestions, and analyzing and reporting feedback content.

[0082] The Security Management Department has functions to ensure the information security of the entire system, including authentication and authorization of field personnel and administrators, encryption of communications, data access control, prevention of information leaks, recording of audit logs, authentication of IoT devices, remote locking of field terminals in case of loss, anonymization of field video data, and operation in compliance with laws and regulations. For example, it addresses all security risks, such as multi-factor authentication when field personnel access the system from terminals, management of access rights to business process information, masking of field information, detection of unauthorized access from external sources, and automatic masking of personal information in field video.

[0083] The History Analysis Department manages chronologically the inquiry history, proposal history, FAQ viewing history, interview information collection history, IoT data history, on-site response history, accident / disaster history, training history, and on-site proposal history for each on-site staff member and manager. It analyzes past success and failure cases, on-site trends, trends in work efficiency and safety, the effectiveness of on-site improvements, and the effectiveness of training. The History Analysis Department is also used for AI-driven sales negotiation analysis, on-site trend analysis, optimization of on-site activities, and raising the overall level of on-site capabilities.

[0084] The Education Support Department has functions to support the education and training of on-site personnel and new workers. It utilizes standard work procedures, troubleshooting measures, improvement case studies, FAQs, interview items, on-site history, IoT data, educational videos, checklists, training history, and on-site proposals to automatically generate and present optimal educational materials and programs tailored to on-site conditions and work content. For example, it provides diverse educational support such as basic training programs for new workers, case studies to promote on-site improvement proposals, emergency response training for accidents and disasters, and on-site improvement training utilizing IoT data.

[0085] As described above, the system according to this embodiment organically links the inquiry reception department, business process information management department, generative AI response department, user interface department, field feedback management department, security management department, history analysis department, and education support department. With generative AI at its core, it automatically generates and presents optimal standard work procedures, troubleshooting measures, improvement examples, FAQs, interview items, field history, IoT data, educational materials, field proposals, accident reports, etc., in response to all business challenges, troubles, improvement requests, and education / training needs faced by field personnel and managers at logistics centers. This makes it an extremely practical and scalable system that dramatically improves on-site responsiveness, operational efficiency, safety, quality, on-site capabilities, knowledge sharing, business standardization, troubleshooting capabilities, education efficiency, and on-site improvement capabilities.

[0086] (Implementation Steps)

[0087] Step 1: Enter and receive on-site inquiry information. On-site staff and managers can input operational issues, troubles, improvement requests, and on-site conditions that occur within the logistics center into the inquiry desk using various methods such as text input, voice input, photo / video attachment, file upload, IoT sensor data transmission, and real-time transmission of on-site video, via on-site terminals including PCs, tablets, smartphones, wearable devices, AR glasses, and handheld terminals. For example, they can request things like, "Please tell me how to handle delays in sorting work," "Please tell me the recovery procedure if a transport robot stops," "I want to know how to investigate the cause of inventory discrepancies in inventory management," or "The on-site temperature and humidity are showing abnormal values; please tell me what to do." A comprehensive range of input methods are provided to enable immediate responses to any situation that may occur on-site.

[0088] Step 2: Acquisition and management of business process information The Business Process Information Management Department stores and manages a database of standard work procedures, troubleshooting measures, improvement examples, FAQs, interview items, on-site history, feedback information, work manuals, video manuals, checklists, work records, equipment specifications, IoT data, sensor history, past accident reports, on-site proposal history, and training materials for each business process, including sorting, inventory management, receiving and shipping management, transportation, inventory counting, picking, packing, inspection, equipment inspection, troubleshooting, emergency response, regular maintenance, worker shift management, equipment operation monitoring, quality control, and accident / disaster response. For example, it comprehensively manages all information necessary on-site, such as standard procedures for sorting, troubleshooting measures for transportation, improvement examples for inventory management, FAQs for inventory counting, and interview items for inspection.

[0089] Step 3: Automatic response generation by generation AI The generation-based AI response unit uses the inquiry content received from the inquiry reception unit and the information stored in the business process information management unit to activate the generation-based AI. It analyzes keywords in the inquiry, the on-site situation, and images, videos, and IoT data sent from the site, and automatically combines the optimal standard work procedures, troubleshooting measures, past improvement examples, FAQs, interview items, on-site history, and IoT data to generate an answer. For example, in response to an inquiry such as "Please tell me how to handle delays in sorting work," it will present a combination of standard procedures, emergency response procedures in case of delays, redesign of worker movement paths, checking the operating status of transport robots, examples of reducing mis-sorting through the introduction of AI image recognition, FAQs, and interview items. Specific examples of prompts to be fed into the generating AI include: "Based on the following on-site conditions, generate emergency response procedures in case of delays in sorting work, related improvement examples, FAQs, and additional questions to be asked. On-site temperature and humidity: 28 degrees, transport robot utilization rate: 80%, number of workers: 8, type of cargo: large home appliances, history of past delays." and "Generate recovery procedures, past similar trouble cases, FAQs, and questions to be asked if the transport robot stops. Robot model number: X100, time of failure: 10:00 AM, on-site congestion level: high, IoT sensor abnormal values ​​detected."

[0090] Step 4: Presenting information to on-site personnel and handling on-site operations. Standard operating procedures, troubleshooting strategies, improvement examples, FAQs, interview questions, field history, IoT data, etc., automatically generated by the generative AI, are immediately displayed on the terminals of field personnel and administrators via the user interface. Field personnel can not only directly incorporate this information into their field operations, but can also edit parts of the content as needed, make additional inquiries, and receive additional advice from the AI ​​based on the field situation.

[0091] Step 5: Field Feedback, Knowledge Accumulation, and AI Learning On-site personnel and managers register new trouble cases, improvement examples, feedback information, work history, IoT data, accident reports, on-site suggestions, and training history with the On-Site Feedback Management Department as they occur. This information is reflected in the Business Process Information Management Department's database and used as training data for generative AI. As a result, the AI ​​continuously learns the latest on-site information and know-how, improving the accuracy and suitability of its responses to on-site situations.

[0092] Step 6: Historical analysis, educational support, and on-site skills improvement The History Analysis Department manages inquiry history, proposal history, FAQ viewing history, interview item collection history, IoT data history, on-site response history, accident / disaster history, training history, and on-site proposal history for each on-site staff member and manager in chronological order. It analyzes past success and failure cases, on-site trends, trends in work efficiency and safety, the effectiveness of on-site improvements, and the effectiveness of training. The Training Support Department utilizes standard work procedures, troubleshooting measures, improvement examples, FAQs, interview items, on-site history, IoT data, training videos, checklists, training history, and on-site proposals to automatically generate and present optimal training materials and programs tailored to on-site conditions and work content, thereby improving on-site capabilities, standardizing operations, and enhancing training efficiency.

[0093] (Specific use cases)

[0094] For example, consider a scenario in the sorting area of ​​a logistics center where a field worker inputs text into the inquiry reception section of a field terminal asking, "Please tell me how to handle delays in sorting work." In this case, the inquiry reception section sends the input to the server's generation AI response section, which then refers to the standard sorting procedures, troubleshooting measures, past improvement cases, FAQs, interview items, field history, IoT data, etc., stored in the business process information management section, and analyzes keywords such as "delay" and "sorting work" included in the inquiry, as well as the field situation. The generation AI is given the prompt message: "Based on the following field situation, generate emergency response procedures in case of delays in sorting work, related improvement cases, FAQs, and additional interview items to be confirmed. Field temperature and humidity: 28 degrees, transport robot utilization rate: 80%, number of workers: 8, type of cargo: large home appliances, history of past delays." The generating AI presents the standard procedure as "Scan the barcode and transport to the designated area. If the weight exceeds the limit, contact the manager." and suggests emergency response measures in case of delays, such as "Temporarily increase the number of workers," "Process priority packages first," "Temporarily change the transport route," "Redesign worker movement paths," "Check the temperature and humidity at the site," and "Check the operating status of transport robots." In addition, it also presents improvement examples such as "Examples of reducing mis-sorting through the introduction of AI image recognition," "Examples of improving work efficiency through the introduction of automated transport robots," and "Examples of reducing delays through the optimization of worker movement paths." It also displays FAQs such as "How to change the sorting area," "How to handle picking errors," "When to charge transport robots," and "Points to note when workers change shifts," and suggests items to be asked, such as "Type of package," "Number of items to be sorted," "Number of workers," "Transportation distance," "Start time of work," and "Temperature and humidity at the site."

[0095] For example, if a field worker in a transport operation voice-inputs "Please tell me the recovery procedure if the transport robot stops," the inquiry reception department converts the voice data into text and sends it to the generation AI response unit. The generation AI is given the prompt message: "Generate the recovery procedure if the transport robot stops, past similar trouble cases, FAQs, and interview questions. Robot model number: X100, time of failure: 10:00 AM, site congestion: high, IoT sensor abnormal values ​​detected." The generation AI then presents standard procedures and troubleshooting measures such as "re-powering the robot," "checking for obstacles," "checking the error log," "switching to a backup robot," "checking the site temperature and humidity," "checking the battery level," and "referencing the robot's periodic maintenance history." It also presents "recovery cases from similar troubles in the past," "latest maintenance information from the robot manufacturer," and "examples of abnormal sound detection by AI." The system displays FAQs such as "Robot inspection frequency," "Battery replacement method," "How to handle obstacle detection," and "Robot software update method," and presents information to be gathered, such as "Robot model number," "Time of malfunction," "Congestion level at the site," "Weight of transported items," and "Worker deployment status."

[0096] For example, if a field staff member inquired via tablet about inventory management, asking "How to investigate the cause of inventory discrepancies during inventory counting," the generating AI would be given the prompt "Generate the procedure for investigating the cause of inventory discrepancies during inventory counting, related improvement examples, FAQs, and interview questions. Number of inventory items: 1500, Inbound frequency: High, Inventory staff: 3, RFID tags used, History of past discrepancies exists." The generating AI would then present standard procedures and troubleshooting measures such as "Verification of RFID tag reading history at the time of inbound," "Verification of the inventory system database," "Reissuance of tags in case of failure," and "Verification of inventory staff's work records," as well as improvement examples such as "Examples of reducing inventory time by introducing automated inventory robots" and "Examples of improving inventory forecast accuracy with AI," FAQs such as "Inventory frequency," "Method of correcting inventory data," "Storage conditions for inventory items," and "Safety measures during inventory counting," and interview questions such as "Number of inventory items," "Inbound frequency," "Inventory staff," "Inventory turnover rate," and "Temperature and humidity of the storage area."

[0097] In this way, the system of the present invention provides the AI ​​with the most suitable prompt text according to the content of the inquiry and the situation on site for any business challenges or troubles that field personnel and managers face on-site. Based on the latest information from the Business Process Information Management Department, it automatically generates standard work procedures, troubleshooting measures, improvement examples, FAQs, interview items, on-site history, IoT data, etc., in real time, thereby supporting field personnel in responding quickly and accurately on-site.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] [Second Embodiment]

[0104] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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".

[0116] (Example 1)

[0117] Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0118] (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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] [Third Embodiment]

[0124] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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".

[0136] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0137] (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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] [Fourth Embodiment]

[0143] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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".

[0156] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0157] (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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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 robot 414.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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."

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] Furthermore, the following additional information is disclosed regarding the above explanation.

[0181] (Claim 1)

[0182] This system is designed to support on-site operations in a logistics center and comprises an inquiry reception unit, a business process information management unit, and a generative AI response unit. The inquiry reception unit receives inquiries from on-site staff and managers through various means such as text input, voice input, image attachment, and file upload. The business process information management unit stores and manages standard work procedures, troubleshooting measures, improvement examples, FAQs, interview items, on-site history, and feedback information in a database for each business process, such as sorting, inventory management, receiving and shipping management, transportation, and stocktaking. The generative AI response unit uses the inquiry content received from the inquiry reception unit and the information stored in the business process information management unit to activate a generative AI, automatically generating optimal standard work procedures, troubleshooting measures, past improvement examples, FAQs, interview items, and custom advice according to the inquiry content, and providing them immediately to on-site staff and managers. (Claim 2)

[0183] The system according to claim 1, wherein the generation-type AI response unit analyzes keywords and on-site conditions included in the inquiry, dynamically selects and combines the most relevant information from multiple standard procedures, troubleshooting measures, improvement examples, and FAQs stored in the business process information management unit, and further generates custom advice and additional interview items tailored to the on-site situation according to the inquiry, enabling on-site personnel to immediately implement the most appropriate response. (Claim 3)

[0184] The system described in paragraph 1 is characterized in that the business process information management department continuously receives new trouble cases, improvement cases, feedback information, work history, etc. from on-site personnel and managers and reflects them in the database, and the generation AI response unit learns and utilizes this latest information to continuously improve the accuracy and suitability of the responses to on-site situations, thereby dramatically improving on-site responsiveness, operational efficiency, safety, and quality. [Explanation of Symbols]

[0185] 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. This system enables corporate sales representatives to receive inquiries from customers by utilizing a dedicated generative AI agent for each product. Based on the content of the inquiry, the system automatically generates product overviews, pricing information, case studies, frequently asked questions, interview topics, and proposal strategies, and provides them to the corporate sales representatives immediately. The system comprises an inquiry reception unit, a product information management unit, and a generative AI response unit. The inquiry reception unit receives inquiries from corporate sales representatives. The product information management unit continuously receives and stores the latest information on each product, such as overviews, pricing, case studies, FAQs, and interview topics, from product representatives. The generative AI response unit uses the inquiry content received from the inquiry reception unit and the information stored in the product information management unit to activate the generative AI, automatically generating the optimal product overview, pricing information, case studies, FAQs, interview topics, and proposal strategies according to the inquiry content, and provides them to the corporate sales representatives immediately.

2. The system according to claim 1, wherein the generation-type AI response unit analyzes keywords and customer requests contained in the inquiry, selects and combines the most relevant information from multiple implementation cases and FAQs stored in the product information management unit, and dynamically generates a proposal strategy according to the inquiry, enabling corporate sales representatives to immediately provide customized proposals to customers.

3. The system according to claim 1, characterized in that the Product Information Management Department receives information update requests from product managers, and the Generating AI Response Department immediately reflects the updates, automatically responding to inquiries based on the latest product information at all times, enabling corporate sales representatives to present optimal proposals and quotations to customers in real time.

Images