system

Abstract

We provide the system. [Solution] Means of obtaining contract data, A method for analyzing acquired contract data using natural language processing and extracting conditions, A generation engine that matches extracted conditions with past transaction data to generate additional order conditions, A means of notifying the user of the generated additional order conditions and confirming them, A system that includes means for generating final order data and notifying relevant departments.

Description

【Technical Field】 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 The work of confirming contract conditions and additional orders in a corporate contract takes time and places a heavy burden on the sales department. There is also a risk of mistakes due to responses under incorrect conditions. Such an inefficient business process may reduce the productivity of the company and damage customer satisfaction. Therefore, there is a need for a system that can improve sales efficiency by quickly and accurately analyzing contract conditions and automatically providing optimal additional order conditions. 【Means for Solving the Problems】 【0005】 In this invention, contract information is collected from a company's database using means for acquiring contract data. Subsequently, the acquired contract data is analyzed using means for natural language processing, and specific conditions are extracted. The results of this analysis are compared with past transaction data, and based on this information, a generation engine generates additional order conditions. The generated conditions are notified to the user for confirmation. Finally, by generating order data and notifying the relevant departments, the invention provides a system that enables efficient and accurate business operations. 【0006】 "Contract data" refers to all information related to contracts concluded between corporations, and specifically includes data such as contract terms, customer information, and transaction conditions. 【0007】 "Natural language processing" is a technology that converts the language humans use in everyday life into a format that computers can understand, and extracts meaning and information from the text. 【0008】 A "generation engine" is a software component that automatically creates new conditions and results based on acquired data. 【0009】 "Order data" refers to data that compiles information about product and service orders from customers. 【0010】 "Matching" is the process of verifying and confirming the similarities and relationships between different pieces of information. [Brief explanation of the drawing] 【0011】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention] 【0012】 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. 【0013】 First, let's explain the terminology used in the following explanation. 【0014】 In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0015】 In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0016】 In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like. 【0017】 In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like. 【0018】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0019】 [First Embodiment] 【0020】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0021】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0022】 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). 【0023】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0024】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0025】 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. 【0026】 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. 【0027】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0028】 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. 【0029】 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. 【0030】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0031】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0032】 This invention is a system designed to improve the efficiency of business operations based on corporate contracts. The system mainly consists of a server, terminals, and users. 【0033】 The server has the capability to access a company's database to retrieve contract data and analyze it using natural language processing technology. The contract terms extracted through the analysis are compared with past transaction data, and based on this, the generation engine generates the optimal additional order terms. 【0034】 The terminal displays the generated additional order conditions to the user. Based on the displayed conditions, the user reviews the content, makes any necessary corrections, and then clicks the approval button to finalize the order. This order information is then sent back to the server and notified to the relevant departments, thereby being reflected in business operations. 【0035】 As a concrete example, consider a case where a company wants to deliver additional goods to a specific customer. First, the user specifies the customer's contract information on their terminal and requests data retrieval from the server. The server analyzes and verifies the retrieved data, and the generation engine generates appropriate delivery conditions based on that. The user can then review the proposed conditions displayed on their terminal and adjust them as needed, enabling them to process additional orders quickly and effectively. This reduces the burden on the sales department and improves the speed and accuracy of customer service. 【0036】 The following describes the processing flow. 【0037】 Step 1: 【0038】 The server connects to the company's database to search for and retrieve contract data and past transaction information for a specified customer. 【0039】 Step 2: 【0040】 The server analyzes the acquired contract data using a natural language processing engine to extract contract terms. Specifically, it tokenizes the contents of the contract and identifies conditional clauses and their meanings. 【0041】 Step 3: 【0042】 The server compares the extracted contract terms with historical transaction data using a matching algorithm to identify relevant business rules and patterns. This process determines which transaction terms are effective and common. 【0043】 Step 4: 【0044】 The server uses a generation engine to generate optimal additional order conditions based on the matching results. The generated conditions take into account past patterns and current contract terms, and are optimized to meet customer needs. 【0045】 Step 5: 【0046】 The terminal notifies the user of the generation conditions sent from the server. The user reviews the conditions presented on the screen and makes corrections or enters additional information as needed. 【0047】 Step 6: 【0048】 Once the user approves the conditions, the device sends that information back to the server, triggering the process of generating the final order data. 【0049】 Step 7: 【0050】 The server notifies the relevant departments of the final generated order data, and business processes are initiated in each department to execute the additional orders. 【0051】 (Example 1) 【0052】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0053】 Traditional contract management and condition generation systems have problems such as the time required to analyze vast amounts of contract data, making it difficult to propose and adjust transaction terms efficiently. Furthermore, data comparison and condition generation often rely on manual processes, making it difficult to achieve both speed and accuracy. 【0054】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0055】 In this invention, the server includes means for acquiring contract-related information, means for analyzing the acquired information using natural language processing technology and extracting conditions, and a generation device for comparing the extracted conditions with past data and generating additional conditions. This streamlines the contract management and condition generation processes, enabling rapid and accurate proposal and adjustment of conditions. 【0056】 "Means for obtaining contract-related information" refers to a device or method for retrieving necessary contract-related data, such as corporate contract information and customer data, from a database or similar source. 【0057】 "Methods for analyzing and extracting conditions using natural language processing technology" refers to automated technical processes for analyzing text data within a document and identifying and extracting important conditions and settings within it. 【0058】 A "generator for generating additional conditions by comparing extracted conditions with past data" refers to a program or system that compares past contract conditions and transaction records with current conditions to propose new, optimal conditions. 【0059】 "Means of displaying and allowing users to confirm the generated additional conditions" refers to methods of showing users the generated conditions via a computer screen or other interface, and allowing them to confirm and approve the content. 【0060】 "A means of generating final order information and notifying the relevant departments" refers to a mechanism for creating specific order information based on confirmed order conditions and communicating it to the departments that require it for business purposes. 【0061】 This invention is a system for streamlining operations based on corporate contracts. It mainly consists of servers, terminals, and users, and each component works in conjunction with the others to achieve its functions. 【0062】 The server plays a central role in data management. First, relational database management systems such as "MySQL®" and "PostgreSQL" are used for database access. This allows for the efficient acquisition of contract data and customer information. The server also utilizes natural language processing libraries such as "NLTK" and "spaCy" in "Python" to analyze the acquired data. This enables the automatic extraction of contract conditions and comparison with historical data. The generated additional conditions are optimized using a generative AI model. This process uses generative models such as "GPT-4®," and is given prompt statements such as "Generate appropriate additional order conditions based on these contract conditions" as input. 【0063】 The terminal provides an interface for users to review and modify generated information. Web technologies such as JavaScript and React are used for display and operation. The terminal receives conditional information from the server and presents it to the user in an intuitive format. The user reviews the conditions and makes modifications as needed through text fields. 【0064】 Users play a crucial role in confirming and modifying order information via their terminals. Once the final order is confirmed through user actions, the terminal sends that information back to the server. The server then uses this information to notify the relevant departments. This communication is conducted using the "HTTP" or "WebSocket" protocols, enabling real-time data processing. 【0065】 As a concrete example, consider a case where a company wants to deliver additional products to a specific customer. The user first uses a terminal to specify the target customer information and requests data retrieval from the server. The server retrieves and analyzes this data, and a generation engine generates appropriate delivery conditions. The user can then review the proposed conditions displayed on the terminal, make adjustments as needed, and process the additional order quickly and accurately. This system can improve operational efficiency and enhance customer service. 【0066】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0067】 Step 1: 【0068】 The server receives a request from the terminal. This request contains a specific customer ID or contract identifier. The server connects to the database and executes an SQL query to retrieve the necessary contract data. The input is the customer ID, and the output is the corresponding contract data. The specific actions involved in retrieving this contract data include extracting information from the database and communication between servers. 【0069】 Step 2: 【0070】 The server analyzes the acquired contract data using natural language processing technology. It utilizes Python's NLTK and spaCy to split the text data into tokens and tag them by part of speech. The input is the contract data acquired by the server, and the output is the conditions extracted through the analysis. In this step, keywords such as "payment terms" and "delivery date" are extracted from the contract text. 【0071】 Step 3: 【0072】 The server compares the extracted contract terms with historical transaction data. This involves using "Pandas" or "NumPy" to match past records as a data frame. The input consists of the extracted conditions and historical data, and the output is data that generates the optimal additional order conditions. Specifically, it analyzes which conditions have been effective in the past and generates new additional conditions. 【0073】 Step 4: 【0074】 The server uses a generation AI model to perform optimization based on the generated conditions. Using tools such as "GPT-4," the prompt message "Generate appropriate additional order conditions based on these contract conditions" is input. The input is the data from the previous step, and the output is the optimized additional order conditions. At this stage, natural language processing using AI is performed. 【0075】 Step 5: 【0076】 The terminal receives optimized additional order conditions and displays them to the user. JavaScript and React are used to visually present the conditions in the user interface. Input is the order conditions from the server, and output is the detailed information displayed to the user. Specifically, the information is formatted into tables and lists to make it easier for the user to understand. 【0077】 Step 6: 【0078】 The user reviews the displayed conditions and makes corrections as needed. Data can be edited directly using the terminal's input fields. The input is the displayed order conditions, and the output is the final, corrected order conditions. The specific actions involved modifying the information via the text fields and, once adjustments were complete, pressing the approve button. 【0079】 Step 7: 【0080】 The server receives the revised final order conditions and notifies the relevant departments. A process of rapid information transmission is carried out using "HTTP" or "WebSocket". The input is the order conditions modified by the user, and the output is the notification information sent to the relevant departments. Specifically, the system is designed to ensure that notifications are transmitted accurately in real time. 【0081】 (Application Example 1) 【0082】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0083】 In logistics operations, it is often necessary to quickly generate optimal additional requirements based on contract information. However, current systems make analyzing contract conditions and generating appropriate shipping conditions time-consuming, hindering efficiency. Therefore, there is a need for a system that can quickly analyze contract information and generate optimal conditions. 【0084】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0085】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing and extracting conditions, and a generation engine for comparing the extracted conditions with past business data and generating additional requirement conditions. This enables the automatic generation and modification of optimal shipping conditions based on contracts in logistics operations. 【0086】 "Contract information" refers to data concerning agreements and arrangements that corporations or companies enter into with other corporations or individuals. 【0087】 "Natural language processing" is a technology that allows computers to understand and analyze human language, with the aim of extracting grammar and meaning and processing the data. 【0088】 "Means for extracting conditions" refers to methods and processes for extracting important elements and provisions from contract information using natural language processing. 【0089】 "Business data" refers to records and information related to the activities that companies and corporations conduct on a daily basis, including past transactions and operational results. 【0090】 A "generation engine" refers to a system component that automatically creates optimal additional conditions and orders based on extracted conditions and information. 【0091】 "User" refers to a person who has the authority to use the system to review, modify, and approve contract terms and additional orders. 【0092】 "Additional requirements" refer to supplementary requirements that arise from existing contracts or transactions. 【0093】 "Final approval data" refers to data after the user has reviewed and formally approved the generated additional requirements. 【0094】 "Logistics operations" refers to the process of planning, executing, and managing the efficient movement of goods and raw materials. 【0095】 To implement this invention, the server first acquires contract information and analyzes its contents using natural language processing. This utilizes the Google® Cloud Natural Language API to extract conditions and provisions from the contract. The analyzed data is then compared with past business data, and the generation engine uses this information to automatically create optimal additional requirements. 【0096】 The terminal notifies the user of these generated additional requirements and provides an interface for review and modification. Users can use their smartphones to review the displayed conditions, manually correct them as needed, and then approve them. This streamlines shipping procedures based on contractual terms in logistics operations. 【0097】 The backend is implemented using Django and manages the entire process of acquiring contract information, analyzing data, and generating conditions using a generation engine. Final approved data is notified to the relevant departments in real time and reflected in business processes. 【0098】 For example, if a logistics center manager wants to ship goods immediately according to a specific contract, the system generates optimal shipping conditions, which can then be easily reviewed and modified. This allows for more efficient shipping procedures. 【0099】 An example of a prompt is, "Generate and confirm shipping terms based on a specific contract." Based on this prompt, the system automatically generates and notifies the conditions. 【0100】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0101】 Step 1: 【0102】 The server receives a request from a user to retrieve contract information, accesses the company's database, and retrieves the relevant contract data. In this process, the input is the contract ID specified by the user, and the output is the contract data itself. The server uses database queries to accurately retrieve the data related to the specified contract. 【0103】 Step 2: 【0104】 The server performs natural language analysis on the acquired contract data using the Google Cloud Natural Language API. The input is the contract data obtained in step 1, and the output is a list of conditions as a result of the analysis. The server sends the text of the contract to the API and extracts important conditions and elements along with analyzing the grammatical structure. 【0105】 Step 3: 【0106】 The server compares the list of conditions obtained through analysis with historical business data, and the generation engine generates the optimal additional requirements. The input is the list of conditions and historical business data, and the output is the additional requirements. The generation engine optimizes the conditions by considering business rules and transaction history. 【0107】 Step 4: 【0108】 The terminal notifies the user of the generated additional requirements and allows them to review and modify them on the interface. The input is the additional requirements from step 3, and the output is a confirmation screen before user approval. The terminal displays the requirements and provides the user with the ability to modify them as needed. 【0109】 Step 5: 【0110】 The user reviews the displayed additional requirements, makes any necessary modifications, and then presses the approve button. The input shows the user-modified requirements, and the output shows the final approved data. The user then verifies the compliance of the requirements and scrutinizes the modifications. 【0111】 Step 6: 【0112】 The server notifies the relevant departments of the approved final data and incorporates it into business processes. The input is the final approved data, and the output is the notification data for the relevant departments. The server generates a notification message and communicates it via email or integration into business systems. 【0113】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0114】 This invention is a system that analyzes contract data, generates optimal additional order conditions, and recognizes user emotions to provide more user-friendly suggestions. The system consists primarily of a server, terminals, and users. 【0115】 The server accesses the company's database and collects relevant contract data and historical transaction information. This data is analyzed using natural language processing technology to extract contract terms. The extracted terms are then compared with historical transaction data, and a generation engine generates the optimal additional order terms. 【0116】 Furthermore, the server is equipped with an emotion engine. The emotion engine analyzes user input and responses to identify the user's emotions. Based on this emotion information, the suggested order conditions are adjusted accordingly. As a result, the suggestions become more appropriate to the user's emotional state, improving user satisfaction. 【0117】 The terminal's role is to present the generated and adjusted order conditions sent from the server to the user. The user can review the conditions presented via the terminal and make modifications as needed. Once the user approves the conditions, the terminal sends that information to the server, and the final order data is generated. 【0118】 For example, when a user places an additional order, the emotion engine may recognize that the user is dissatisfied with the order conditions displayed on the terminal. In this case, the server can revise the suggested conditions and quickly confirm a more attractive offer. This increases customer satisfaction and further improves the efficiency of the sales process. 【0119】 The following describes the processing flow. 【0120】 Step 1: 【0121】 The server retrieves contract data and past transaction information related to a specific customer from the company's database. The retrieval process uses customer IDs and contract numbers as keys for searching. 【0122】 Step 2: 【0123】 The server analyzes the acquired contract data using natural language processing technology to extract contract terms. This process tokenizes the contents of the contract and identifies specific conditions and clauses. 【0124】 Step 3: 【0125】 The server compares the extracted contract terms with historical transaction data and applies relevant business rules to analyze patterns. Based on this analysis, the generation engine creates appropriate additional order conditions. 【0126】 Step 4: 【0127】 The server uses an emotion engine to estimate the user's emotional state based on their input and past responses. It then uses text analysis and speech recognition technologies to evaluate the user's emotions using multiple metrics. 【0128】 Step 5: 【0129】 Based on feedback from the emotion engine, the server fine-tunes the generated order conditions to match the user's psychological state. This adjustment ensures that the user receives more satisfying suggestions. 【0130】 Step 6: 【0131】 The terminal displays the adjusted order conditions to the user. The user can review the conditions on the terminal screen and modify them if necessary. Once approved, the process proceeds to the final step. 【0132】 Step 7: 【0133】 Once the user approves the order conditions, the terminal sends that information to the server, which generates the final order data. The server then notifies the relevant departments of the generated order data, and order processing begins. 【0134】 (Example 2) 【0135】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0136】 Conventional contract data analysis systems treat the acquisition and analysis of contract information, the extraction of conditions, the further optimization of those conditions, and the notification of adjusted proposals to users as separate processes, resulting in low overall efficiency. Furthermore, they do not take into account the user's emotional state when adjusting proposals, which can lead to decreased user satisfaction. 【0137】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0138】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing technology and extracting conditions, and a generation module for comparing the extracted conditions with past transaction history and generating additional order conditions. This integrates the process from acquiring and analyzing contract information to generating and adjusting conditions, enabling efficient and user-responsive suggestions. 【0139】 "Contract information" refers to data that includes the terms and conditions concluded in commercial transactions. 【0140】 "Natural language processing technology" is the technology that enables computers to understand and manipulate human language. 【0141】 A "means of extracting conditions" refers to a mechanism for extracting specific requirements or clauses from contract information. 【0142】 A "transaction history" is a record of commercial activities that have taken place in the past. 【0143】 A "generating module" is a component used to create new proposals and conditions based on acquired information. 【0144】 An "emotion engine" is a device or program that analyzes user input and responses to identify their emotional state. 【0145】 A "means of adjustment" refers to a mechanism for further modifying or optimizing the information and conditions obtained. 【0146】 "Means of presentation" refers to display devices or methods used to show generated information or conditions to the user and facilitate their understanding. 【0147】 "Final order information" refers to the final record of a transaction created based on the conditions approved by the user. 【0148】 "Relevant department" refers to the part of the organization responsible for executing or managing the generated final order information. 【0149】 This invention relates to a system that analyzes contract information and generates optimized additional order conditions. This system primarily consists of a server, terminals, and users. 【0150】 The server accesses the company's database to retrieve contract information and past transaction history. This process utilizes SQL database systems and other appropriate data management technologies. The obtained data is then analyzed using natural language processing techniques. Specifically, libraries such as NLTK and spaCy are used to extract necessary conditions from the contract documents. 【0151】 The extracted conditions are compared with past transaction history. In this process, a generation AI model is utilized to generate the optimal additional order conditions. The generation engine is given instructions such as "Generate proposed conditions for product Y based on current market conditions and past transaction data" as a prompt. 【0152】 The server is equipped with an emotion engine that analyzes user input and responses to identify emotional states. For example, it uses OpenAI's emotion recognition model to analyze user text and voice input. Based on the identified emotions, the generated order conditions are optimized. 【0153】 The terminal presents the user with order conditions adjusted by the server. This process is carried out through a web application or mobile application. The user can review the conditions and make modifications as needed. 【0154】 Once the user approves the terms, the terminal sends that information to the server, which generates the final order information. This information is then notified to the appropriate department. 【0155】 As a concrete example, when a user places an additional order for a product on an online platform, the server considers the user's emotions and generates suggested conditions, which are then displayed on the terminal to enhance user satisfaction. An example of a prompt message for the generating AI model is, "Based on the provided data, create the optimal contract terms for product X." 【0156】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0157】 Step 1: 【0158】 The server accesses the company's database to retrieve contract information and historical transaction history. It takes database queries as input to collect relevant contract information and transaction history. The output is these datasets. Specifically, it uses SQL queries to extract the necessary information and stores it on the server in JSON format. 【0159】 Step 2: 【0160】 The server analyzes the acquired contract information using natural language processing technology and extracts conditions. The input is the contract information obtained in step 1. The output is the extracted contract conditions. Specifically, it tokenizes the text data using the Python NLTK library, tags parts of speech, and identifies conditional statements. 【0161】 Step 3: 【0162】 The server uses the extracted conditions to compare them with past transaction history and generates optimal additional order conditions using a generative AI model. The inputs used are the extracted conditions and past transaction history. The output is the optimized additional order conditions. Specifically, the generative AI model is given a prompt such as "Consider the market trends for product A and generate the optimal proposed conditions" to generate the conditions. 【0163】 Step 4: 【0164】 The server analyzes user input and responses using an emotion engine to identify emotional states. Input consists of user text messages and voice messages. Output is emotional state data. Specifically, it uses an emotion recognition API to identify the user's emotions from the tone and content of the text. 【0165】 Step 5: 【0166】 The server adjusts the order conditions generated based on sentiment information. The inputs are the additional order conditions generated in step 3 and the sentiment information obtained in step 4. The output is the adjusted order proposal. Specifically, this involves fine-tuning the amount and contract terms within the conditions to avoid causing discomfort to the user. 【0167】 Step 6: 【0168】 The terminal presents the user with adjusted order conditions. The input is the adjusted order proposal. The output is the user's response. Specifically, a pop-up notification is displayed in the web browser or application to prompt the user to confirm the content. 【0169】 Step 7: 【0170】 The user reviews the presented conditions and modifies them as needed. The input is the order conditions displayed on the terminal. The output is the modified order conditions or the approved conditions. For example, the user fine-tunes the conditions on the screen using sliders and text boxes and completes the modification by pressing the final confirmation button. 【0171】 Step 8: 【0172】 The terminal sends the conditions approved by the user to the server. The input is the modified or approved conditions. The output is the final order information. Specifically, the conditions data is sent to the server using a secure protocol, and a confirmation email is delivered to the user. 【0173】 Step 9: 【0174】 The server generates final order information and notifies the relevant departments. The input is the final order information sent from the terminal. The output is the necessary notifications to the relevant departments and actionable order information. Specifically, it registers the data in the ERP system and generates alerts for the responsible personnel. 【0175】 (Application Example 2) 【0176】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0177】 In modern online business transactions, proposals that consider the user's emotions or past transaction history are rare, and often only standardized terms are presented. This makes it difficult to offer optimal order suggestions that take the user's feelings into account, potentially leading to decreased customer satisfaction. This, in turn, can negatively impact a company's sales. 【0178】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0179】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing and extracting conditions, and an emotion analysis device for analyzing user input data to identify emotions and adjust proposed conditions. This makes it possible to propose individually optimized additional transaction conditions that take the user's emotions into consideration. 【0180】 "Contract information" refers to a collection of data that shows the details of agreements regarding commercial transactions and service provision. 【0181】 "Natural language processing" is a computer technology used to analyze and understand human language. 【0182】 "Conditions" refer to the provisions or agreements necessary for a contract or proposal to be valid. 【0183】 "Transaction history" refers to information that shows records of commercial transactions that have taken place in the past. 【0184】 A "generation device" is a device or system that generates specific conditions or suggestions based on given data. 【0185】 An "emotion analysis device" is a device or function that analyzes a user's input data to identify their emotions. 【0186】 A "communication terminal" is an electronic device used by a user to receive or transmit information. 【0187】 "Final transaction data" refers to data that shows the final agreed-upon terms and conditions at the time the transaction was completed. 【0188】 A "business department" is a department within a company or organization that is responsible for specific tasks. 【0189】 This system enables automated analysis of contract information and optimized recommendations using user sentiment recognition. First, the server retrieves contract information from the company's database via the network. The retrieved contract information is then analyzed using natural language processing with the Google Cloud Natural Language API to extract important conditions. 【0190】 The server compares the transaction history stored in Amazon RDS with the extracted conditions, and a generator uses a Python script to generate the optimal transaction conditions. During this process, the Emotion API of Microsoft Azure® is used to analyze the user's emotions from the input data. The results of the emotion analysis are used to adapt the generated conditions to the user's emotions. 【0191】 The adjusted proposed terms will be communicated to the user via a communication terminal application developed with React Native. The user can review the transaction terms and make modifications as needed. The reviewed or modified terms will be resent to the server, the final transaction data will be generated, and the operational department will be notified. 【0192】 For example, when a user attempts to place a new order for a product they have previously purchased, if their past reviews for that product are negative, the system can encourage repeat purchases by offering discounts or additional benefits. 【0193】 An example of a prompt message is: "Based on past purchase history and customer feedback, create product suggestions tailored to this user. Include incentives that evoke positive emotions." 【0194】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0195】 Step 1: 【0196】 The server retrieves contract information from the company's database. It then begins processing this retrieved contract information as input. 【0197】 Step 2: 【0198】 The server uses the Google Cloud Natural Language API to analyze the retrieved contract information using natural language processing. Here, the information is broken down into its elements, and the contract terms are extracted. The input is the contract information, and the output is the extracted terms. 【0199】 Step 3: 【0200】 The server retrieves historical transaction history stored in Amazon RDS and matches it against the criteria extracted in step 2. This matching identifies relevant transaction data. The inputs are the extracted criteria and transaction history, and the output is the matching result. 【0201】 Step 4: 【0202】 The server uses a Python script to perform data calculations so that the generator can produce optimal trading conditions. The input is the matching result from step 3, and the output is the generated optimized trading conditions. 【0203】 Step 5: 【0204】 The server uses the Microsoft Azure Emotion API to analyze the user's emotions from their input data. Using this analysis, it adjusts the proposed conditions to match the user's emotions. The input is the user's input data, and the output is the analyzed emotions and the adjusted conditions. 【0205】 Step 6: 【0206】 The device notifies the user of the adjusted suggested conditions through a user interface developed with React Native. The user can review the displayed conditions and modify them as needed. The input is the adjusted conditions, and the output is the user's response or modified conditions. 【0207】 Step 7: 【0208】 The terminal resends the user's confirmed or modified conditions to the server. The server generates the final transaction data and notifies the business department. The input is the user's final confirmed conditions, and the output is the final transaction data. 【0209】 The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data. 【0210】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0211】 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. 【0212】 [Second Embodiment] 【0213】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0214】 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. 【0215】 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). 【0216】 The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52. 【0217】 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. 【0218】 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). 【0219】 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. 【0220】 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. 【0221】 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. 【0222】 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. 【0223】 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. 【0224】 Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0225】 This invention is a system designed to improve the efficiency of business operations based on corporate contracts. The system mainly consists of a server, terminals, and users. 【0226】 The server has the capability to access a company's database to retrieve contract data and analyze it using natural language processing technology. The contract terms extracted through the analysis are compared with past transaction data, and based on this, the generation engine generates the optimal additional order terms. 【0227】 The terminal displays the generated additional order conditions to the user. Based on the displayed conditions, the user reviews the content, makes any necessary corrections, and then clicks the approval button to finalize the order. This order information is then sent back to the server and notified to the relevant departments, thereby being reflected in business operations. 【0228】 As a concrete example, consider a case where a company wants to deliver additional goods to a specific customer. First, the user specifies the customer's contract information on their terminal and requests data retrieval from the server. The server analyzes and verifies the retrieved data, and the generation engine generates appropriate delivery conditions based on that. The user can then review the proposed conditions displayed on their terminal and adjust them as needed, enabling them to process additional orders quickly and effectively. This reduces the burden on the sales department and improves the speed and accuracy of customer service. 【0229】 The following describes the processing flow. 【0230】 Step 1: 【0231】 The server connects to the company's database to search for and retrieve contract data and past transaction information for a specified customer. 【0232】 Step 2: 【0233】 The server analyzes the acquired contract data using a natural language processing engine to extract contract terms. Specifically, it tokenizes the contents of the contract and identifies conditional clauses and their meanings. 【0234】 Step 3: 【0235】 The server compares the extracted contract terms with historical transaction data using a matching algorithm to identify relevant business rules and patterns. This process determines which transaction terms are effective and common. 【0236】 Step 4: 【0237】 The server uses a generation engine to generate optimal additional order conditions based on the matching results. The generated conditions take into account past patterns and current contract terms, and are optimized to meet customer needs. 【0238】 Step 5: 【0239】 The terminal notifies the user of the generation conditions sent from the server. The user reviews the conditions presented on the screen and makes corrections or enters additional information as needed. 【0240】 Step 6: 【0241】 Once the user approves the conditions, the device sends that information back to the server, triggering the process of generating the final order data. 【0242】 Step 7: 【0243】 The server notifies the relevant departments of the final generated order data, and business processes are initiated in each department to execute the additional orders. 【0244】 (Example 1) 【0245】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0246】 Traditional contract management and condition generation systems have problems such as the time required to analyze vast amounts of contract data, making it difficult to propose and adjust transaction terms efficiently. Furthermore, data comparison and condition generation often rely on manual processes, making it difficult to achieve both speed and accuracy. 【0247】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0248】 In this invention, the server includes means for acquiring contract-related information, means for analyzing the acquired information using natural language processing technology and extracting conditions, and a generation device for comparing the extracted conditions with past data and generating additional conditions. This streamlines the contract management and condition generation processes, enabling rapid and accurate proposal and adjustment of conditions. 【0249】 "Means for obtaining contract-related information" refers to a device or method for retrieving necessary contract-related data, such as corporate contract information and customer data, from a database or similar source. 【0250】 "Methods for analyzing and extracting conditions using natural language processing technology" refers to automated technical processes for analyzing text data within a document and identifying and extracting important conditions and settings within it. 【0251】 A "generator for generating additional conditions by comparing extracted conditions with past data" refers to a program or system that compares past contract conditions and transaction records with current conditions to propose new, optimal conditions. 【0252】 "Means of displaying and allowing users to confirm the generated additional conditions" refers to methods of showing users the generated conditions via a computer screen or other interface, and allowing them to confirm and approve the content. 【0253】 "A means of generating final order information and notifying the relevant departments" refers to a mechanism for creating specific order information based on confirmed order conditions and communicating it to the departments that require it for business purposes. 【0254】 This invention is a system for streamlining operations based on corporate contracts. It mainly consists of servers, terminals, and users, and each component works in conjunction with the others to achieve its functions. 【0255】 The server plays a central role in data management. First, relational database management systems such as MySQL and PostgreSQL are used for database access. This allows for the efficient acquisition of contract data and customer information. The server also utilizes natural language processing libraries such as Python's NLTK and spaCy to analyze the acquired data. This enables the automatic extraction of contract terms and allows for comparison with historical data. The generated additional conditions are optimized using a generative AI model. Generative models such as GPT-4 are used in this process, and prompt statements such as "Generate appropriate additional order conditions based on these contract terms" are passed as input. 【0256】 The terminal provides an interface for users to review and modify generated information. Web technologies such as JavaScript and React are used for display and operation. The terminal receives conditional information from the server and presents it to the user in an intuitive format. The user reviews the conditions and makes modifications as needed through text fields. 【0257】 Users play a crucial role in confirming and modifying order information via their terminals. Once the final order is confirmed through user actions, the terminal sends that information back to the server. The server then uses this information to notify the relevant departments. This communication is conducted using the "HTTP" or "WebSocket" protocols, enabling real-time data processing. 【0258】 As a concrete example, consider a case where a company wants to deliver additional products to a specific customer. The user first uses a terminal to specify the target customer information and requests data retrieval from the server. The server retrieves and analyzes this data, and a generation engine generates appropriate delivery conditions. The user can then review the proposed conditions displayed on the terminal, make adjustments as needed, and process the additional order quickly and accurately. This system can improve operational efficiency and enhance customer service. 【0259】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0260】 Step 1: 【0261】 The server receives a request from the terminal. This request contains a specific customer ID or contract identifier. The server connects to the database and executes an SQL query to retrieve the necessary contract data. The input is the customer ID, and the output is the corresponding contract data. The specific actions involved in retrieving this contract data include extracting information from the database and communication between servers. 【0262】 Step 2: 【0263】 The server analyzes the acquired contract data using natural language processing technology. It utilizes Python's NLTK and spaCy to split the text data into tokens and tag them by part of speech. The input is the contract data acquired by the server, and the output is the conditions extracted through the analysis. In this step, keywords such as "payment terms" and "delivery date" are extracted from the contract text. 【0264】 Step 3: 【0265】 The server compares the extracted contract terms with historical transaction data. This involves using "Pandas" or "NumPy" to match past records as a data frame. The input consists of the extracted conditions and historical data, and the output is data that generates the optimal additional order conditions. Specifically, it analyzes which conditions have been effective in the past and generates new additional conditions. 【0266】 Step 4: 【0267】 The server uses a generation AI model to perform optimization based on the generated conditions. Using tools such as "GPT-4," the prompt message "Generate appropriate additional order conditions based on these contract conditions" is input. The input is the data from the previous step, and the output is the optimized additional order conditions. At this stage, natural language processing using AI is performed. 【0268】 Step 5: 【0269】 The terminal receives optimized additional order conditions and displays them to the user. JavaScript and React are used to visually present the conditions in the user interface. Input is the order conditions from the server, and output is the detailed information displayed to the user. Specifically, the information is formatted into tables and lists to make it easier for the user to understand. 【0270】 Step 6: 【0271】 The user reviews the displayed conditions and makes corrections as needed. Data can be edited directly using the terminal's input fields. The input is the displayed order conditions, and the output is the final, corrected order conditions. The specific actions involved modifying the information via the text fields and, once adjustments were complete, pressing the approve button. 【0272】 Step 7: 【0273】 The server receives the revised final order conditions and notifies the relevant departments. A process of rapid information transmission is carried out using "HTTP" or "WebSocket". The input is the order conditions modified by the user, and the output is the notification information sent to the relevant departments. Specifically, the system is designed to ensure that notifications are transmitted accurately in real time. 【0274】 (Application Example 1) 【0275】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0276】 In logistics operations, it is often necessary to quickly generate optimal additional requirements based on contract information. However, current systems make analyzing contract conditions and generating appropriate shipping conditions time-consuming, hindering efficiency. Therefore, there is a need for a system that can quickly analyze contract information and generate optimal conditions. 【0277】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0278】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing and extracting conditions, and a generation engine for comparing the extracted conditions with past business data and generating additional requirement conditions. This enables the automatic generation and modification of optimal shipping conditions based on contracts in logistics operations. 【0279】 "Contract information" refers to data concerning agreements and arrangements that corporations or companies enter into with other corporations or individuals. 【0280】 "Natural language processing" is a technology that allows computers to understand and analyze human language, with the aim of extracting grammar and meaning and processing the data. 【0281】 "Means for extracting conditions" refers to methods and processes for extracting important elements and provisions from contract information using natural language processing. 【0282】 "Business data" refers to records and information related to the activities that companies and corporations conduct on a daily basis, including past transactions and operational results. 【0283】 A "generation engine" refers to a system component that automatically creates optimal additional conditions and orders based on extracted conditions and information. 【0284】 "User" refers to a person who has the authority to check, modify, and approve contract terms and additional orders using the system. 【0285】 "Additional requirements" refers to supplementary requirements newly generated based on existing contracts or transactions. 【0286】 "Final approval data" refers to the data after the user has checked and formally approved the generated additional requirements. 【0287】 "Logistics operations" refers to the process of planning, executing, and managing the efficient movement of goods and raw materials. 【0288】 To implement this invention, first the server acquires contract information and analyzes its content using natural language analysis. For this, the Google Cloud Natural Language API is utilized to extract conditions and regulations from the contract document. The analyzed data is compared with past business data, and the generation engine uses this information to automatically create optimal additional requirements. 【0289】 The terminal notifies the user of the generated additional requirements and provides an interface for confirmation and modification. The user can use a smartphone to check the displayed conditions, manually correct them if necessary, and then give approval. This streamlines the shipping procedures based on the contract terms in logistics operations. 【0290】 The backend is implemented using Django and manages the acquisition of contract information, data analysis, and condition generation by the generation engine as a series of processes. The finally approved data is notified to the relevant departments in real time and reflected in the business process. 【0291】 For example, if a logistics center manager wants to ship goods immediately according to a specific contract, the system generates optimal shipping conditions, which can then be easily reviewed and modified. This allows for more efficient shipping procedures. 【0292】 An example of a prompt is, "Generate and confirm shipping terms based on a specific contract." Based on this prompt, the system automatically generates and notifies the conditions. 【0293】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0294】 Step 1: 【0295】 The server receives a request from a user to retrieve contract information, accesses the company's database, and retrieves the relevant contract data. In this process, the input is the contract ID specified by the user, and the output is the contract data itself. The server uses database queries to accurately retrieve the data related to the specified contract. 【0296】 Step 2: 【0297】 The server performs natural language analysis on the acquired contract data using the Google Cloud Natural Language API. The input is the contract data obtained in step 1, and the output is a list of conditions as a result of the analysis. The server sends the text of the contract to the API and extracts important conditions and elements along with analyzing the grammatical structure. 【0298】 Step 3: 【0299】 The server compares the list of conditions obtained through analysis with historical business data, and the generation engine generates the optimal additional requirements. The input is the list of conditions and historical business data, and the output is the additional requirements. The generation engine optimizes the conditions by considering business rules and transaction history. 【0300】 Step 4: 【0301】 The terminal notifies the user of the generated additional requirement conditions and enables confirmation and modification on the interface. The input is the additional requirement conditions from Step 3, and the output is the confirmation screen before user approval. The terminal displays the conditions and provides a function for the user to modify them as needed. 【0302】 Step 5: 【0303】 After the user checks the displayed additional requirement conditions and makes modifications as needed, the user presses the approval button. The input is the conditions after user modification, and the output is the final approval data. The user checks the compliance of the conditions and scrutinizes the modified content. 【0304】 Step 6: 【0305】 The server notifies the related departments of the approved final data and reflects it in the business process. The input is the final approved data, and the output is the notification data to the related departments. The server generates a notification message and communicates through integration with email or the business system. 【0306】 Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion. 【0307】 This invention is a system that analyzes contract data, generates optimal additional order conditions, and realizes a more user-friendly proposal by recognizing the user's emotion. The system is mainly composed of a server, a terminal, and a user. 【0308】 The server accesses the enterprise's database and plays a role in collecting the corresponding contract data and past transaction information. This data is analyzed by natural language processing technology, and contract conditions are extracted. The extracted conditions are compared with past transaction data, and the generation engine generates optimal additional order conditions. 【0309】 Furthermore, the server is equipped with an emotion engine. The emotion engine analyzes user input and responses to identify the user's emotions. Based on this emotion information, the suggested order conditions are adjusted accordingly. As a result, the suggestions become more appropriate to the user's emotional state, improving user satisfaction. 【0310】 The terminal's role is to present the generated and adjusted order conditions sent from the server to the user. The user can review the conditions presented via the terminal and make modifications as needed. Once the user approves the conditions, the terminal sends that information to the server, and the final order data is generated. 【0311】 For example, when a user places an additional order, the emotion engine may recognize that the user is dissatisfied with the order conditions displayed on the terminal. In this case, the server can revise the suggested conditions and quickly confirm a more attractive offer. This increases customer satisfaction and further improves the efficiency of the sales process. 【0312】 The following describes the processing flow. 【0313】 Step 1: 【0314】 The server retrieves contract data and past transaction information related to a specific customer from the company's database. The retrieval process uses customer IDs and contract numbers as keys for searching. 【0315】 Step 2: 【0316】 The server analyzes the acquired contract data using natural language processing technology to extract contract terms. This process tokenizes the contents of the contract and identifies specific conditions and clauses. 【0317】 Step 3: 【0318】 The server compares the extracted contract terms with historical transaction data and applies relevant business rules to analyze patterns. Based on this analysis, the generation engine creates appropriate additional order conditions. 【0319】 Step 4: 【0320】 The server uses an emotion engine to estimate the user's emotional state based on their input and past responses. It then uses text analysis and speech recognition technologies to evaluate the user's emotions using multiple metrics. 【0321】 Step 5: 【0322】 Based on feedback from the emotion engine, the server fine-tunes the generated order conditions to match the user's psychological state. This adjustment ensures that the user receives more satisfying suggestions. 【0323】 Step 6: 【0324】 The terminal displays the adjusted order conditions to the user. The user can review the conditions on the terminal screen and modify them if necessary. Once approved, the process proceeds to the final step. 【0325】 Step 7: 【0326】 Once the user approves the order conditions, the terminal sends that information to the server, which generates the final order data. The server then notifies the relevant departments of the generated order data, and order processing begins. 【0327】 (Example 2) 【0328】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0329】 Conventional contract data analysis systems treat the acquisition and analysis of contract information, the extraction of conditions, the further optimization of those conditions, and the notification of adjusted proposals to users as separate processes, resulting in low overall efficiency. Furthermore, they do not take into account the user's emotional state when adjusting proposals, which can lead to decreased user satisfaction. 【0330】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0331】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing technology and extracting conditions, and a generation module for comparing the extracted conditions with past transaction history and generating additional order conditions. This integrates the process from acquiring and analyzing contract information to generating and adjusting conditions, enabling efficient and user-responsive suggestions. 【0332】 "Contract information" refers to data that includes the terms and conditions concluded in commercial transactions. 【0333】 "Natural language processing technology" is the technology that enables computers to understand and manipulate human language. 【0334】 A "means of extracting conditions" refers to a mechanism for extracting specific requirements or clauses from contract information. 【0335】 A "transaction history" is a record of commercial activities that have taken place in the past. 【0336】 A "generating module" is a component used to create new proposals and conditions based on acquired information. 【0337】 An "emotion engine" is a device or program that analyzes user input and responses to identify their emotional state. 【0338】 A "means of adjustment" refers to a mechanism for further modifying or optimizing the information and conditions obtained. 【0339】 "Means of presentation" refers to display devices or methods used to show generated information or conditions to the user and facilitate their understanding. 【0340】 "Final order information" refers to the final record of a transaction created based on the conditions approved by the user. 【0341】 "Relevant department" refers to the part of the organization responsible for executing or managing the generated final order information. 【0342】 This invention relates to a system that analyzes contract information and generates optimized additional order conditions. This system primarily consists of a server, terminals, and users. 【0343】 The server accesses the company's database to retrieve contract information and past transaction history. This process utilizes SQL database systems and other appropriate data management technologies. The obtained data is then analyzed using natural language processing techniques. Specifically, libraries such as NLTK and spaCy are used to extract necessary conditions from the contract documents. 【0344】 The extracted conditions are compared with past transaction history. In this process, a generation AI model is utilized to generate the optimal additional order conditions. The generation engine is given instructions such as "Generate proposed conditions for product Y based on current market conditions and past transaction data" as a prompt. 【0345】 The server is equipped with an emotion engine that analyzes user input and responses to identify emotional states. For example, it uses OpenAI's emotion recognition model to analyze user text and voice input. Based on the identified emotions, the generated order conditions are optimized. 【0346】 The terminal presents the user with order conditions adjusted by the server. This process is carried out through a web application or mobile application. The user can review the conditions and make modifications as needed. 【0347】 Once the user approves the terms, the terminal sends that information to the server, which generates the final order information. This information is then notified to the appropriate department. 【0348】 As a concrete example, when a user places an additional order for a product on an online platform, the server considers the user's emotions and generates suggested conditions, which are then displayed on the terminal to enhance user satisfaction. An example of a prompt message for the generating AI model is, "Based on the provided data, create the optimal contract terms for product X." 【0349】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0350】 Step 1: 【0351】 The server accesses the company's database to retrieve contract information and historical transaction history. It takes database queries as input to collect relevant contract information and transaction history. The output is these datasets. Specifically, it uses SQL queries to extract the necessary information and stores it on the server in JSON format. 【0352】 Step 2: 【0353】 The server analyzes the acquired contract information using natural language processing technology and extracts conditions. The input is the contract information obtained in step 1. The output is the extracted contract conditions. Specifically, it tokenizes the text data using the Python NLTK library, tags parts of speech, and identifies conditional statements. 【0354】 Step 3: 【0355】 The server uses the extracted conditions to compare them with past transaction history and generates optimal additional order conditions using a generative AI model. The inputs used are the extracted conditions and past transaction history. The output is the optimized additional order conditions. Specifically, the generative AI model is given a prompt such as "Consider the market trends for product A and generate the optimal proposed conditions" to generate the conditions. 【0356】 Step 4: 【0357】 The server analyzes user input and responses using an emotion engine to identify emotional states. Input consists of user text messages and voice messages. Output is emotional state data. Specifically, it uses an emotion recognition API to identify the user's emotions from the tone and content of the text. 【0358】 Step 5: 【0359】 The server adjusts the order conditions generated based on sentiment information. The inputs are the additional order conditions generated in step 3 and the sentiment information obtained in step 4. The output is the adjusted order proposal. Specifically, this involves fine-tuning the amount and contract terms within the conditions to avoid causing discomfort to the user. 【0360】 Step 6: 【0361】 The terminal presents the user with adjusted order conditions. The input is the adjusted order proposal. The output is the user's response. Specifically, a pop-up notification is displayed in the web browser or application to prompt the user to confirm the content. 【0362】 Step 7: 【0363】 The user reviews the presented conditions and modifies them as needed. The input is the order conditions displayed on the terminal. The output is the modified order conditions or the approved conditions. For example, the user fine-tunes the conditions on the screen using sliders and text boxes and completes the modification by pressing the final confirmation button. 【0364】 Step 8: 【0365】 The terminal sends the conditions approved by the user to the server. The input is the modified or approved conditions. The output is the final order information. Specifically, the conditions data is sent to the server using a secure protocol, and a confirmation email is delivered to the user. 【0366】 Step 9: 【0367】 The server generates final order information and notifies the relevant departments. The input is the final order information sent from the terminal. The output is the necessary notifications to the relevant departments and actionable order information. Specifically, it registers the data in the ERP system and generates alerts for the responsible personnel. 【0368】 (Application Example 2) 【0369】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0370】 In modern online business transactions, proposals that consider the user's emotions or past transaction history are rare, and often only standardized terms are presented. This makes it difficult to offer optimal order suggestions that take the user's feelings into account, potentially leading to decreased customer satisfaction. This, in turn, can negatively impact a company's sales. 【0371】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0372】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing and extracting conditions, and an emotion analysis device for analyzing user input data to identify emotions and adjust proposed conditions. This makes it possible to propose individually optimized additional transaction conditions that take the user's emotions into consideration. 【0373】 "Contract information" refers to a collection of data that shows the details of agreements regarding commercial transactions and service provision. 【0374】 "Natural language processing" is a computer technology used to analyze and understand human language. 【0375】 "Conditions" refer to the provisions or agreements necessary for a contract or proposal to be valid. 【0376】 "Transaction history" refers to information that shows records of commercial transactions that have taken place in the past. 【0377】 A "generation device" is a device or system that generates specific conditions or suggestions based on given data. 【0378】 An "emotion analysis device" is a device or function that analyzes a user's input data to identify their emotions. 【0379】 A "communication terminal" is an electronic device used by a user to receive or transmit information. 【0380】 "Final transaction data" refers to data that shows the final agreed-upon terms and conditions at the time the transaction was completed. 【0381】 A "business department" is a department within a company or organization that is responsible for specific tasks. 【0382】 This system enables automated analysis of contract information and optimized recommendations using user sentiment recognition. First, the server retrieves contract information from the company's database via the network. The retrieved contract information is then analyzed using natural language processing with the Google Cloud Natural Language API to extract important conditions. 【0383】 The server matches the transaction history stored in Amazon RDS with the extracted conditions, and a generator using a Python script generates the optimal transaction conditions. During this process, the Microsoft Azure Emotion API is used to analyze the user's emotions from the input data. The results of the emotion analysis are used to adapt the generated conditions to the user's emotions. 【0384】 The adjusted proposed terms will be communicated to the user via a communication terminal application developed with React Native. The user can review the transaction terms and make modifications as needed. The reviewed or modified terms will be resent to the server, the final transaction data will be generated, and the operational department will be notified. 【0385】 For example, when a user attempts to place a new order for a product they have previously purchased, if their past reviews for that product are negative, the system can encourage repeat purchases by offering discounts or additional benefits. 【0386】 An example of a prompt message is: "Based on past purchase history and customer feedback, create product suggestions tailored to this user. Include incentives that evoke positive emotions." 【0387】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0388】 Step 1: 【0389】 The server retrieves contract information from the company's database. It then begins processing this retrieved contract information as input. 【0390】 Step 2: 【0391】 The server uses the Google Cloud Natural Language API to analyze the retrieved contract information using natural language processing. Here, the information is broken down into its elements, and the contract terms are extracted. The input is the contract information, and the output is the extracted terms. 【0392】 Step 3: 【0393】 The server retrieves historical transaction history stored in Amazon RDS and matches it against the criteria extracted in step 2. This matching identifies relevant transaction data. The inputs are the extracted criteria and transaction history, and the output is the matching result. 【0394】 Step 4: 【0395】 The server uses a Python script to perform data calculations so that the generator can produce optimal trading conditions. The input is the matching result from step 3, and the output is the generated optimized trading conditions. 【0396】 Step 5: 【0397】 The server uses the Microsoft Azure Emotion API to analyze the user's emotions from their input data. Using this analysis, it adjusts the proposed conditions to match the user's emotions. The input is the user's input data, and the output is the analyzed emotions and the adjusted conditions. 【0398】 Step 6: 【0399】 The device notifies the user of the adjusted suggested conditions through a user interface developed with React Native. The user can review the displayed conditions and modify them as needed. The input is the adjusted conditions, and the output is the user's response or modified conditions. 【0400】 Step 7: 【0401】 The terminal resends the user's confirmed or modified conditions to the server. The server generates the final transaction data and notifies the business department. The input is the user's final confirmed conditions, and the output is the final transaction data. 【0402】 The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0403】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0404】 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. 【0405】 [Third Embodiment] 【0406】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0407】 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. 【0408】 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). 【0409】 The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52. 【0410】 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. 【0411】 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). 【0412】 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. 【0413】 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. 【0414】 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. 【0415】 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. 【0416】 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. 【0417】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal". 【0418】 This invention is a system designed to improve the efficiency of business operations based on corporate contracts. The system mainly consists of a server, terminals, and users. 【0419】 The server has the capability to access a company's database to retrieve contract data and analyze it using natural language processing technology. The contract terms extracted through the analysis are compared with past transaction data, and based on this, the generation engine generates the optimal additional order terms. 【0420】 The terminal displays the generated additional order conditions to the user. Based on the displayed conditions, the user reviews the content, makes any necessary corrections, and then clicks the approval button to finalize the order. This order information is then sent back to the server and notified to the relevant departments, thereby being reflected in business operations. 【0421】 As a concrete example, consider a case where a company wants to deliver additional goods to a specific customer. First, the user specifies the customer's contract information on their terminal and requests data retrieval from the server. The server analyzes and verifies the retrieved data, and the generation engine generates appropriate delivery conditions based on that. The user can then review the proposed conditions displayed on their terminal and adjust them as needed, enabling them to process additional orders quickly and effectively. This reduces the burden on the sales department and improves the speed and accuracy of customer service. 【0422】 The following describes the processing flow. 【0423】 Step 1: 【0424】 The server connects to the company's database to search for and retrieve contract data and past transaction information for a specified customer. 【0425】 Step 2: 【0426】 The server analyzes the acquired contract data using a natural language processing engine to extract contract terms. Specifically, it tokenizes the contents of the contract and identifies conditional clauses and their meanings. 【0427】 Step 3: 【0428】 The server compares the extracted contract terms with historical transaction data using a matching algorithm to identify relevant business rules and patterns. This process determines which transaction terms are effective and common. 【0429】 Step 4: 【0430】 The server uses a generation engine to generate optimal additional order conditions based on the matching results. The generated conditions take into account past patterns and current contract terms, and are optimized to meet customer needs. 【0431】 Step 5: 【0432】 The terminal notifies the user of the generation conditions sent from the server. The user reviews the conditions presented on the screen and makes corrections or enters additional information as needed. 【0433】 Step 6: 【0434】 Once the user approves the conditions, the device sends that information back to the server, triggering the process of generating the final order data. 【0435】 Step 7: 【0436】 The server notifies the relevant departments of the final generated order data, and business processes are initiated in each department to execute the additional orders. 【0437】 (Example 1) 【0438】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0439】 Traditional contract management and condition generation systems have problems such as the time required to analyze vast amounts of contract data, making it difficult to propose and adjust transaction terms efficiently. Furthermore, data comparison and condition generation often rely on manual processes, making it difficult to achieve both speed and accuracy. 【0440】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0441】 In this invention, the server includes means for acquiring contract-related information, means for analyzing the acquired information using natural language processing technology and extracting conditions, and a generation device for comparing the extracted conditions with past data and generating additional conditions. This streamlines the contract management and condition generation processes, enabling rapid and accurate proposal and adjustment of conditions. 【0442】 "Means for obtaining contract-related information" refers to a device or method for retrieving necessary contract-related data, such as corporate contract information and customer data, from a database or similar source. 【0443】 "Methods for analyzing and extracting conditions using natural language processing technology" refers to automated technical processes for analyzing text data within a document and identifying and extracting important conditions and settings within it. 【0444】 A "generator for generating additional conditions by comparing extracted conditions with past data" refers to a program or system that compares past contract conditions and transaction records with current conditions to propose new, optimal conditions. 【0445】 "Means of displaying and allowing users to confirm the generated additional conditions" refers to methods of showing users the generated conditions via a computer screen or other interface, and allowing them to confirm and approve the content. 【0446】 "A means of generating final order information and notifying the relevant departments" refers to a mechanism for creating specific order information based on confirmed order conditions and communicating it to the departments that require it for business purposes. 【0447】 This invention is a system for streamlining operations based on corporate contracts. It mainly consists of servers, terminals, and users, and each component works in conjunction with the others to achieve its functions. 【0448】 The server plays a central role in data management. First, relational database management systems such as MySQL and PostgreSQL are used for database access. This allows for the efficient acquisition of contract data and customer information. The server also utilizes natural language processing libraries such as Python's NLTK and spaCy to analyze the acquired data. This enables the automatic extraction of contract terms and allows for comparison with historical data. The generated additional conditions are optimized using a generative AI model. Generative models such as GPT-4 are used in this process, and prompt statements such as "Generate appropriate additional order conditions based on these contract terms" are passed as input. 【0449】 The terminal provides an interface for users to review and modify generated information. Web technologies such as JavaScript and React are used for display and operation. The terminal receives conditional information from the server and presents it to the user in an intuitive format. The user reviews the conditions and makes modifications as needed through text fields. 【0450】 Users play a crucial role in confirming and modifying order information via their terminals. Once the final order is confirmed through user actions, the terminal sends that information back to the server. The server then uses this information to notify the relevant departments. This communication is conducted using the "HTTP" or "WebSocket" protocols, enabling real-time data processing. 【0451】 As a concrete example, consider a case where a company wants to deliver additional products to a specific customer. The user first uses a terminal to specify the target customer information and requests data retrieval from the server. The server retrieves and analyzes this data, and a generation engine generates appropriate delivery conditions. The user can then review the proposed conditions displayed on the terminal, make adjustments as needed, and process the additional order quickly and accurately. This system can improve operational efficiency and enhance customer service. 【0452】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0453】 Step 1: 【0454】 The server receives a request from the terminal. This request contains a specific customer ID or contract identifier. The server connects to the database and executes an SQL query to retrieve the necessary contract data. The input is the customer ID, and the output is the corresponding contract data. The specific actions involved in retrieving this contract data include extracting information from the database and communication between servers. 【0455】 Step 2: 【0456】 The server analyzes the acquired contract data using natural language processing technology. It utilizes Python's NLTK and spaCy to split the text data into tokens and tag them by part of speech. The input is the contract data acquired by the server, and the output is the conditions extracted through the analysis. In this step, keywords such as "payment terms" and "delivery date" are extracted from the contract text. 【0457】 Step 3: 【0458】 The server compares the extracted contract terms with historical transaction data. This involves using "Pandas" or "NumPy" to match past records as a data frame. The input consists of the extracted conditions and historical data, and the output is data that generates the optimal additional order conditions. Specifically, it analyzes which conditions have been effective in the past and generates new additional conditions. 【0459】 Step 4: 【0460】 The server uses a generation AI model to perform optimization based on the generated conditions. Using tools such as "GPT-4," the prompt message "Generate appropriate additional order conditions based on these contract conditions" is input. The input is the data from the previous step, and the output is the optimized additional order conditions. At this stage, natural language processing using AI is performed. 【0461】 Step 5: 【0462】 The terminal receives optimized additional order conditions and displays them to the user. JavaScript and React are used to visually present the conditions in the user interface. Input is the order conditions from the server, and output is the detailed information displayed to the user. Specifically, the information is formatted into tables and lists to make it easier for the user to understand. 【0463】 Step 6: 【0464】 The user reviews the displayed conditions and makes corrections as needed. Data can be edited directly using the terminal's input fields. The input is the displayed order conditions, and the output is the final, corrected order conditions. The specific actions involved modifying the information via the text fields and, once adjustments were complete, pressing the approve button. 【0465】 Step 7: 【0466】 The server receives the revised final order conditions and notifies the relevant departments. A process of rapid information transmission is carried out using "HTTP" or "WebSocket". The input is the order conditions modified by the user, and the output is the notification information sent to the relevant departments. Specifically, the system is designed to ensure that notifications are transmitted accurately in real time. 【0467】 (Application Example 1) 【0468】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0469】 In logistics operations, it is often necessary to quickly generate optimal additional requirements based on contract information. However, current systems make analyzing contract conditions and generating appropriate shipping conditions time-consuming, hindering efficiency. Therefore, there is a need for a system that can quickly analyze contract information and generate optimal conditions. 【0470】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0471】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing and extracting conditions, and a generation engine for comparing the extracted conditions with past business data and generating additional requirement conditions. This enables the automatic generation and modification of optimal shipping conditions based on contracts in logistics operations. 【0472】 "Contract information" refers to data concerning agreements and arrangements that corporations or companies enter into with other corporations or individuals. 【0473】 "Natural language processing" is a technology that allows computers to understand and analyze human language, with the aim of extracting grammar and meaning and processing the data. 【0474】 "Means for extracting conditions" refers to methods and processes for extracting important elements and provisions from contract information using natural language processing. 【0475】 "Business data" refers to records and information related to the activities that companies and corporations conduct on a daily basis, including past transactions and operational results. 【0476】 A "generation engine" refers to a system component that automatically creates optimal additional conditions and orders based on extracted conditions and information. 【0477】 "User" refers to a person who has the authority to use the system to review, modify, and approve contract terms and additional orders. 【0478】 "Additional requirements" refer to supplementary requirements that arise from existing contracts or transactions. 【0479】 "Final approval data" refers to data after the user has reviewed and formally approved the generated additional requirements. 【0480】 "Logistics operations" refers to the process of planning, executing, and managing the efficient movement of goods and raw materials. 【0481】 To implement this invention, the server first acquires contract information and analyzes its contents using natural language processing. This utilizes the Google Cloud Natural Language API to extract conditions and provisions from the contract. The analyzed data is then compared with past business data, and the generation engine uses this information to automatically create optimal additional requirements. 【0482】 The terminal notifies the user of these generated additional requirements and provides an interface for review and modification. Users can use their smartphones to review the displayed conditions, manually correct them as needed, and then approve them. This streamlines shipping procedures based on contractual terms in logistics operations. 【0483】 The backend is implemented using Django and manages the entire process of acquiring contract information, analyzing data, and generating conditions using a generation engine. Final approved data is notified to the relevant departments in real time and reflected in business processes. 【0484】 For example, if a logistics center manager wants to ship goods immediately according to a specific contract, the system generates optimal shipping conditions, which can then be easily reviewed and modified. This allows for more efficient shipping procedures. 【0485】 An example of a prompt is, "Generate and confirm shipping terms based on a specific contract." Based on this prompt, the system automatically generates and notifies the conditions. 【0486】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0487】 Step 1: 【0488】 The server receives a request from a user to retrieve contract information, accesses the company's database, and retrieves the relevant contract data. In this process, the input is the contract ID specified by the user, and the output is the contract data itself. The server uses database queries to accurately retrieve the data related to the specified contract. 【0489】 Step 2: 【0490】 The server performs natural language analysis on the acquired contract data using the Google Cloud Natural Language API. The input is the contract data obtained in step 1, and the output is a list of conditions as a result of the analysis. The server sends the text of the contract to the API and extracts important conditions and elements along with analyzing the grammatical structure. 【0491】 Step 3: 【0492】 The server compares the list of conditions obtained through analysis with historical business data, and the generation engine generates the optimal additional requirements. The input is the list of conditions and historical business data, and the output is the additional requirements. The generation engine optimizes the conditions by considering business rules and transaction history. 【0493】 Step 4: 【0494】 The terminal notifies the user of the generated additional requirements and allows them to review and modify them on the interface. The input is the additional requirements from step 3, and the output is a confirmation screen before user approval. The terminal displays the requirements and provides the user with the ability to modify them as needed. 【0495】 Step 5: 【0496】 The user reviews the displayed additional requirements, makes any necessary modifications, and then presses the approve button. The input shows the user-modified requirements, and the output shows the final approved data. The user then verifies the compliance of the requirements and scrutinizes the modifications. 【0497】 Step 6: 【0498】 The server notifies the relevant departments of the approved final data and incorporates it into business processes. The input is the final approved data, and the output is the notification data for the relevant departments. The server generates a notification message and communicates it via email or integration into business systems. 【0499】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0500】 This invention is a system that analyzes contract data, generates optimal additional order conditions, and recognizes user emotions to provide more user-friendly suggestions. The system consists primarily of a server, terminals, and users. 【0501】 The server accesses the company's database and collects relevant contract data and historical transaction information. This data is analyzed using natural language processing technology to extract contract terms. The extracted terms are then compared with historical transaction data, and a generation engine generates the optimal additional order terms. 【0502】 Furthermore, the server is equipped with an emotion engine. The emotion engine analyzes user input and responses to identify the user's emotions. Based on this emotion information, the suggested order conditions are adjusted accordingly. As a result, the suggestions become more appropriate to the user's emotional state, improving user satisfaction. 【0503】 The terminal's role is to present the generated and adjusted order conditions sent from the server to the user. The user can review the conditions presented via the terminal and make modifications as needed. Once the user approves the conditions, the terminal sends that information to the server, and the final order data is generated. 【0504】 For example, when a user places an additional order, the emotion engine may recognize that the user is dissatisfied with the order conditions displayed on the terminal. In this case, the server can revise the suggested conditions and quickly confirm a more attractive offer. This increases customer satisfaction and further improves the efficiency of the sales process. 【0505】 The following describes the processing flow. 【0506】 Step 1: 【0507】 The server retrieves contract data and past transaction information related to a specific customer from the company's database. The retrieval process uses customer IDs and contract numbers as keys for searching. 【0508】 Step 2: 【0509】 The server analyzes the acquired contract data using natural language processing technology to extract contract terms. This process tokenizes the contents of the contract and identifies specific conditions and clauses. 【0510】 Step 3: 【0511】 The server compares the extracted contract terms with historical transaction data and applies relevant business rules to analyze patterns. Based on this analysis, the generation engine creates appropriate additional order conditions. 【0512】 Step 4: 【0513】 The server uses an emotion engine to estimate the user's emotional state based on their input and past responses. It then uses text analysis and speech recognition technologies to evaluate the user's emotions using multiple metrics. 【0514】 Step 5: 【0515】 Based on feedback from the emotion engine, the server fine-tunes the generated order conditions to match the user's psychological state. This adjustment ensures that the user receives more satisfying suggestions. 【0516】 Step 6: 【0517】 The terminal displays the adjusted order conditions to the user. The user can review the conditions on the terminal screen and modify them if necessary. Once approved, the process proceeds to the final step. 【0518】 Step 7: 【0519】 Once the user approves the order conditions, the terminal sends that information to the server, which generates the final order data. The server then notifies the relevant departments of the generated order data, and order processing begins. 【0520】 (Example 2) 【0521】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0522】 Conventional contract data analysis systems treat the acquisition and analysis of contract information, the extraction of conditions, the further optimization of those conditions, and the notification of adjusted proposals to users as separate processes, resulting in low overall efficiency. Furthermore, they do not take into account the user's emotional state when adjusting proposals, which can lead to decreased user satisfaction. 【0523】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0524】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing technology and extracting conditions, and a generation module for comparing the extracted conditions with past transaction history and generating additional order conditions. This integrates the process from acquiring and analyzing contract information to generating and adjusting conditions, enabling efficient and user-responsive suggestions. 【0525】 "Contract information" refers to data that includes the terms and conditions concluded in commercial transactions. 【0526】 "Natural language processing technology" is the technology that enables computers to understand and manipulate human language. 【0527】 A "means of extracting conditions" refers to a mechanism for extracting specific requirements or clauses from contract information. 【0528】 A "transaction history" is a record of commercial activities that have taken place in the past. 【0529】 A "generating module" is a component used to create new proposals and conditions based on acquired information. 【0530】 An "emotion engine" is a device or program that analyzes user input and responses to identify their emotional state. 【0531】 A "means of adjustment" refers to a mechanism for further modifying or optimizing the information and conditions obtained. 【0532】 "Means of presentation" refers to display devices or methods used to show generated information or conditions to the user and facilitate their understanding. 【0533】 "Final order information" refers to the final record of a transaction created based on the conditions approved by the user. 【0534】 "Relevant department" refers to the part of the organization responsible for executing or managing the generated final order information. 【0535】 This invention relates to a system that analyzes contract information and generates optimized additional order conditions. This system primarily consists of a server, terminals, and users. 【0536】 The server accesses the company's database to retrieve contract information and past transaction history. This process utilizes SQL database systems and other appropriate data management technologies. The obtained data is then analyzed using natural language processing techniques. Specifically, libraries such as NLTK and spaCy are used to extract necessary conditions from the contract documents. 【0537】 The extracted conditions are compared with past transaction history. In this process, a generation AI model is utilized to generate the optimal additional order conditions. The generation engine is given instructions such as "Generate proposed conditions for product Y based on current market conditions and past transaction data" as a prompt. 【0538】 The server is equipped with an emotion engine that analyzes user input and responses to identify emotional states. For example, it uses OpenAI's emotion recognition model to analyze user text and voice input. Based on the identified emotions, the generated order conditions are optimized. 【0539】 The terminal presents the user with order conditions adjusted by the server. This process is carried out through a web application or mobile application. The user can review the conditions and make modifications as needed. 【0540】 Once the user approves the terms, the terminal sends that information to the server, which generates the final order information. This information is then notified to the appropriate department. 【0541】 As a concrete example, when a user places an additional order for a product on an online platform, the server considers the user's emotions and generates suggested conditions, which are then displayed on the terminal to enhance user satisfaction. An example of a prompt message for the generating AI model is, "Based on the provided data, create the optimal contract terms for product X." 【0542】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0543】 Step 1: 【0544】 The server accesses the company's database to retrieve contract information and historical transaction history. It takes database queries as input to collect relevant contract information and transaction history. The output is these datasets. Specifically, it uses SQL queries to extract the necessary information and stores it on the server in JSON format. 【0545】 Step 2: 【0546】 The server analyzes the acquired contract information using natural language processing technology and extracts conditions. The input is the contract information obtained in step 1. The output is the extracted contract conditions. Specifically, it tokenizes the text data using the Python NLTK library, tags parts of speech, and identifies conditional statements. 【0547】 Step 3: 【0548】 The server uses the extracted conditions to compare them with past transaction history and generates optimal additional order conditions using a generative AI model. The inputs used are the extracted conditions and past transaction history. The output is the optimized additional order conditions. Specifically, the generative AI model is given a prompt such as "Consider the market trends for product A and generate the optimal proposed conditions" to generate the conditions. 【0549】 Step 4: 【0550】 The server analyzes user input and responses using an emotion engine to identify emotional states. Input consists of user text messages and voice messages. Output is emotional state data. Specifically, it uses an emotion recognition API to identify the user's emotions from the tone and content of the text. 【0551】 Step 5: 【0552】 The server adjusts the order conditions generated based on sentiment information. The inputs are the additional order conditions generated in step 3 and the sentiment information obtained in step 4. The output is the adjusted order proposal. Specifically, this involves fine-tuning the amount and contract terms within the conditions to avoid causing discomfort to the user. 【0553】 Step 6: 【0554】 The terminal presents the user with adjusted order conditions. The input is the adjusted order proposal. The output is the user's response. Specifically, a pop-up notification is displayed in the web browser or application to prompt the user to confirm the content. 【0555】 Step 7: 【0556】 The user reviews the presented conditions and modifies them as needed. The input is the order conditions displayed on the terminal. The output is the modified order conditions or the approved conditions. For example, the user fine-tunes the conditions on the screen using sliders and text boxes and completes the modification by pressing the final confirmation button. 【0557】 Step 8: 【0558】 The terminal sends the conditions approved by the user to the server. The input is the modified or approved conditions. The output is the final order information. Specifically, the conditions data is sent to the server using a secure protocol, and a confirmation email is delivered to the user. 【0559】 Step 9: 【0560】 The server generates final order information and notifies the relevant departments. The input is the final order information sent from the terminal. The output is the necessary notifications to the relevant departments and actionable order information. Specifically, it registers the data in the ERP system and generates alerts for the responsible personnel. 【0561】 (Application Example 2) 【0562】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0563】 In modern online business transactions, proposals that consider the user's emotions or past transaction history are rare, and often only standardized terms are presented. This makes it difficult to offer optimal order suggestions that take the user's feelings into account, potentially leading to decreased customer satisfaction. This, in turn, can negatively impact a company's sales. 【0564】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0565】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing and extracting conditions, and an emotion analysis device for analyzing user input data to identify emotions and adjust proposed conditions. This makes it possible to propose individually optimized additional transaction conditions that take the user's emotions into consideration. 【0566】 "Contract information" refers to a collection of data that shows the details of agreements regarding commercial transactions and service provision. 【0567】 "Natural language processing" is a computer technology used to analyze and understand human language. 【0568】 "Conditions" refer to the provisions or agreements necessary for a contract or proposal to be valid. 【0569】 "Transaction history" refers to information that shows records of commercial transactions that have taken place in the past. 【0570】 A "generation device" is a device or system that generates specific conditions or suggestions based on given data. 【0571】 An "emotion analysis device" is a device or function that analyzes a user's input data to identify their emotions. 【0572】 A "communication terminal" is an electronic device used by a user to receive or transmit information. 【0573】 "Final transaction data" refers to data that shows the final agreed-upon terms and conditions at the time the transaction was completed. 【0574】 A "business department" is a department within a company or organization that is responsible for specific tasks. 【0575】 This system enables automated analysis of contract information and optimized recommendations using user sentiment recognition. First, the server retrieves contract information from the company's database via the network. The retrieved contract information is then analyzed using natural language processing with the Google Cloud Natural Language API to extract important conditions. 【0576】 The server matches the transaction history stored in Amazon RDS with the extracted conditions, and a generator using a Python script generates the optimal transaction conditions. During this process, the Microsoft Azure Emotion API is used to analyze the user's emotions from the input data. The results of the emotion analysis are used to adapt the generated conditions to the user's emotions. 【0577】 The adjusted proposed terms will be communicated to the user via a communication terminal application developed with React Native. The user can review the transaction terms and make modifications as needed. The reviewed or modified terms will be resent to the server, the final transaction data will be generated, and the operational department will be notified. 【0578】 For example, when a user attempts to place a new order for a product they have previously purchased, if their past reviews for that product are negative, the system can encourage repeat purchases by offering discounts or additional benefits. 【0579】 An example of a prompt message is: "Based on past purchase history and customer feedback, create product suggestions tailored to this user. Include incentives that evoke positive emotions." 【0580】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0581】 Step 1: 【0582】 The server retrieves contract information from the company's database. It then begins processing this retrieved contract information as input. 【0583】 Step 2: 【0584】 The server uses the Google Cloud Natural Language API to analyze the retrieved contract information using natural language processing. Here, the information is broken down into its elements, and the contract terms are extracted. The input is the contract information, and the output is the extracted terms. 【0585】 Step 3: 【0586】 The server retrieves historical transaction history stored in Amazon RDS and matches it against the criteria extracted in step 2. This matching identifies relevant transaction data. The inputs are the extracted criteria and transaction history, and the output is the matching result. 【0587】 Step 4: 【0588】 The server uses a Python script to perform data calculations so that the generator can produce optimal trading conditions. The input is the matching result from step 3, and the output is the generated optimized trading conditions. 【0589】 Step 5: 【0590】 The server uses the Microsoft Azure Emotion API to analyze the user's emotions from their input data. Using this analysis, it adjusts the proposed conditions to match the user's emotions. The input is the user's input data, and the output is the analyzed emotions and the adjusted conditions. 【0591】 Step 6: 【0592】 The device notifies the user of the adjusted suggested conditions through a user interface developed with React Native. The user can review the displayed conditions and modify them as needed. The input is the adjusted conditions, and the output is the user's response or modified conditions. 【0593】 Step 7: 【0594】 The terminal resends the user's confirmed or modified conditions to the server. The server generates the final transaction data and notifies the business department. The input is the user's final confirmed conditions, and the output is the final transaction data. 【0595】 The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0596】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0597】 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. 【0598】 [Fourth Embodiment] 【0599】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0600】 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. 【0601】 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). 【0602】 The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52. 【0603】 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. 【0604】 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). 【0605】 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. 【0606】 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. 【0607】 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. 【0608】 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. 【0609】 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. 【0610】 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. 【0611】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0612】 This invention is a system designed to improve the efficiency of business operations based on corporate contracts. The system mainly consists of a server, terminals, and users. 【0613】 The server has the capability to access a company's database to retrieve contract data and analyze it using natural language processing technology. The contract terms extracted through the analysis are compared with past transaction data, and based on this, the generation engine generates the optimal additional order terms. 【0614】 The terminal displays the generated additional order conditions to the user. Based on the displayed conditions, the user reviews the content, makes any necessary corrections, and then clicks the approval button to finalize the order. This order information is then sent back to the server and notified to the relevant departments, thereby being reflected in business operations. 【0615】 As a concrete example, consider a case where a company wants to deliver additional goods to a specific customer. First, the user specifies the customer's contract information on their terminal and requests data retrieval from the server. The server analyzes and verifies the retrieved data, and the generation engine generates appropriate delivery conditions based on that. The user can then review the proposed conditions displayed on their terminal and adjust them as needed, enabling them to process additional orders quickly and effectively. This reduces the burden on the sales department and improves the speed and accuracy of customer service. 【0616】 The following describes the processing flow. 【0617】 Step 1: 【0618】 The server connects to the company's database to search for and retrieve contract data and past transaction information for a specified customer. 【0619】 Step 2: 【0620】 The server analyzes the acquired contract data using a natural language processing engine to extract contract terms. Specifically, it tokenizes the contents of the contract and identifies conditional clauses and their meanings. 【0621】 Step 3: 【0622】 The server compares the extracted contract terms with historical transaction data using a matching algorithm to identify relevant business rules and patterns. This process determines which transaction terms are effective and common. 【0623】 Step 4: 【0624】 The server uses a generation engine to generate optimal additional order conditions based on the matching results. The generated conditions take into account past patterns and current contract terms, and are optimized to meet customer needs. 【0625】 Step 5: 【0626】 The terminal notifies the user of the generation conditions sent from the server. The user reviews the conditions presented on the screen and makes corrections or enters additional information as needed. 【0627】 Step 6: 【0628】 Once the user approves the conditions, the device sends that information back to the server, triggering the process of generating the final order data. 【0629】 Step 7: 【0630】 The server notifies the relevant departments of the final generated order data, and business processes are initiated in each department to execute the additional orders. 【0631】 (Example 1) 【0632】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0633】 Traditional contract management and condition generation systems have problems such as the time required to analyze vast amounts of contract data, making it difficult to propose and adjust transaction terms efficiently. Furthermore, data comparison and condition generation often rely on manual processes, making it difficult to achieve both speed and accuracy. 【0634】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0635】 In this invention, the server includes means for acquiring contract-related information, means for analyzing the acquired information using natural language processing technology and extracting conditions, and a generation device for comparing the extracted conditions with past data and generating additional conditions. This streamlines the contract management and condition generation processes, enabling rapid and accurate proposal and adjustment of conditions. 【0636】 "Means for obtaining contract-related information" refers to a device or method for retrieving necessary contract-related data, such as corporate contract information and customer data, from a database or similar source. 【0637】 "Methods for analyzing and extracting conditions using natural language processing technology" refers to automated technical processes for analyzing text data within a document and identifying and extracting important conditions and settings within it. 【0638】 A "generator for generating additional conditions by comparing extracted conditions with past data" refers to a program or system that compares past contract conditions and transaction records with current conditions to propose new, optimal conditions. 【0639】 "Means of displaying and allowing users to confirm the generated additional conditions" refers to methods of showing users the generated conditions via a computer screen or other interface, and allowing them to confirm and approve the content. 【0640】 "A means of generating final order information and notifying the relevant departments" refers to a mechanism for creating specific order information based on confirmed order conditions and communicating it to the departments that require it for business purposes. 【0641】 This invention is a system for streamlining operations based on corporate contracts. It mainly consists of servers, terminals, and users, and each component works in conjunction with the others to achieve its functions. 【0642】 The server plays a central role in data management. First, relational database management systems such as MySQL and PostgreSQL are used for database access. This allows for the efficient acquisition of contract data and customer information. The server also utilizes natural language processing libraries such as Python's NLTK and spaCy to analyze the acquired data. This enables the automatic extraction of contract terms and allows for comparison with historical data. The generated additional conditions are optimized using a generative AI model. Generative models such as GPT-4 are used in this process, and prompt statements such as "Generate appropriate additional order conditions based on these contract terms" are passed as input. 【0643】 The terminal provides an interface for users to review and modify generated information. Web technologies such as JavaScript and React are used for display and operation. The terminal receives conditional information from the server and presents it to the user in an intuitive format. The user reviews the conditions and makes modifications as needed through text fields. 【0644】 Users play a crucial role in confirming and modifying order information via their terminals. Once the final order is confirmed through user actions, the terminal sends that information back to the server. The server then uses this information to notify the relevant departments. This communication is conducted using the "HTTP" or "WebSocket" protocols, enabling real-time data processing. 【0645】 As a concrete example, consider a case where a company wants to deliver additional products to a specific customer. The user first uses a terminal to specify the target customer information and requests data retrieval from the server. The server retrieves and analyzes this data, and a generation engine generates appropriate delivery conditions. The user can then review the proposed conditions displayed on the terminal, make adjustments as needed, and process the additional order quickly and accurately. This system can improve operational efficiency and enhance customer service. 【0646】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0647】 Step 1: 【0648】 The server receives a request from the terminal. This request contains a specific customer ID or contract identifier. The server connects to the database and executes an SQL query to retrieve the necessary contract data. The input is the customer ID, and the output is the corresponding contract data. The specific actions involved in retrieving this contract data include extracting information from the database and communication between servers. 【0649】 Step 2: 【0650】 The server analyzes the acquired contract data using natural language processing technology. It utilizes Python's NLTK and spaCy to split the text data into tokens and tag them by part of speech. The input is the contract data acquired by the server, and the output is the conditions extracted through the analysis. In this step, keywords such as "payment terms" and "delivery date" are extracted from the contract text. 【0651】 Step 3: 【0652】 The server compares the extracted contract terms with historical transaction data. This involves using "Pandas" or "NumPy" to match past records as a data frame. The input consists of the extracted conditions and historical data, and the output is data that generates the optimal additional order conditions. Specifically, it analyzes which conditions have been effective in the past and generates new additional conditions. 【0653】 Step 4: 【0654】 The server uses a generation AI model to perform optimization based on the generated conditions. Using tools such as "GPT-4," the prompt message "Generate appropriate additional order conditions based on these contract conditions" is input. The input is the data from the previous step, and the output is the optimized additional order conditions. At this stage, natural language processing using AI is performed. 【0655】 Step 5: 【0656】 The terminal receives optimized additional order conditions and displays them to the user. JavaScript and React are used to visually present the conditions in the user interface. Input is the order conditions from the server, and output is the detailed information displayed to the user. Specifically, the information is formatted into tables and lists to make it easier for the user to understand. 【0657】 Step 6: 【0658】 The user reviews the displayed conditions and makes corrections as needed. Data can be edited directly using the terminal's input fields. The input is the displayed order conditions, and the output is the final, corrected order conditions. The specific actions involved modifying the information via the text fields and, once adjustments were complete, pressing the approve button. 【0659】 Step 7: 【0660】 The server receives the revised final order conditions and notifies the relevant departments. A process of rapid information transmission is carried out using "HTTP" or "WebSocket". The input is the order conditions modified by the user, and the output is the notification information sent to the relevant departments. Specifically, the system is designed to ensure that notifications are transmitted accurately in real time. 【0661】 (Application Example 1) 【0662】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0663】 In logistics operations, it is often necessary to quickly generate optimal additional requirements based on contract information. However, current systems make analyzing contract conditions and generating appropriate shipping conditions time-consuming, hindering efficiency. Therefore, there is a need for a system that can quickly analyze contract information and generate optimal conditions. 【0664】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0665】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing and extracting conditions, and a generation engine for comparing the extracted conditions with past business data and generating additional requirement conditions. This enables the automatic generation and modification of optimal shipping conditions based on contracts in logistics operations. 【0666】 "Contract information" refers to data concerning agreements and arrangements that corporations or companies enter into with other corporations or individuals. 【0667】 "Natural language processing" is a technology that allows computers to understand and analyze human language, with the aim of extracting grammar and meaning and processing the data. 【0668】 "Means for extracting conditions" refers to methods and processes for extracting important elements and provisions from contract information using natural language processing. 【0669】 "Business data" refers to records and information related to the activities that companies and corporations conduct on a daily basis, including past transactions and operational results. 【0670】 A "generation engine" refers to a system component that automatically creates optimal additional conditions and orders based on extracted conditions and information. 【0671】 "User" refers to a person who has the authority to use the system to review, modify, and approve contract terms and additional orders. 【0672】 "Additional requirements" refer to supplementary requirements that arise from existing contracts or transactions. 【0673】 "Final approval data" refers to data after the user has reviewed and formally approved the generated additional requirements. 【0674】 "Logistics operations" refers to the process of planning, executing, and managing the efficient movement of goods and raw materials. 【0675】 To implement this invention, the server first acquires contract information and analyzes its contents using natural language processing. This utilizes the Google Cloud Natural Language API to extract conditions and provisions from the contract. The analyzed data is then compared with past business data, and the generation engine uses this information to automatically create optimal additional requirements. 【0676】 The terminal notifies the user of these generated additional requirements and provides an interface for review and modification. Users can use their smartphones to review the displayed conditions, manually correct them as needed, and then approve them. This streamlines shipping procedures based on contractual terms in logistics operations. 【0677】 The backend is implemented using Django and manages the entire process of acquiring contract information, analyzing data, and generating conditions using a generation engine. Final approved data is notified to the relevant departments in real time and reflected in business processes. 【0678】 For example, if a logistics center manager wants to ship goods immediately according to a specific contract, the system generates optimal shipping conditions, which can then be easily reviewed and modified. This allows for more efficient shipping procedures. 【0679】 An example of a prompt is, "Generate and confirm shipping terms based on a specific contract." Based on this prompt, the system automatically generates and notifies the conditions. 【0680】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0681】 Step 1: 【0682】 The server receives a request from a user to retrieve contract information, accesses the company's database, and retrieves the relevant contract data. In this process, the input is the contract ID specified by the user, and the output is the contract data itself. The server uses database queries to accurately retrieve the data related to the specified contract. 【0683】 Step 2: 【0684】 The server performs natural language analysis on the acquired contract data using the Google Cloud Natural Language API. The input is the contract data obtained in step 1, and the output is a list of conditions as a result of the analysis. The server sends the text of the contract to the API and extracts important conditions and elements along with analyzing the grammatical structure. 【0685】 Step 3: 【0686】 The server compares the list of conditions obtained through analysis with historical business data, and the generation engine generates the optimal additional requirements. The input is the list of conditions and historical business data, and the output is the additional requirements. The generation engine optimizes the conditions by considering business rules and transaction history. 【0687】 Step 4: 【0688】 The terminal notifies the user of the generated additional requirements and allows them to review and modify them on the interface. The input is the additional requirements from step 3, and the output is a confirmation screen before user approval. The terminal displays the requirements and provides the user with the ability to modify them as needed. 【0689】 Step 5: 【0690】 The user reviews the displayed additional requirements, makes any necessary modifications, and then presses the approve button. The input shows the user-modified requirements, and the output shows the final approved data. The user then verifies the compliance of the requirements and scrutinizes the modifications. 【0691】 Step 6: 【0692】 The server notifies the relevant departments of the approved final data and incorporates it into business processes. The input is the final approved data, and the output is the notification data for the relevant departments. The server generates a notification message and communicates it via email or integration into business systems. 【0693】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0694】 This invention is a system that analyzes contract data, generates optimal additional order conditions, and recognizes user emotions to provide more user-friendly suggestions. The system consists primarily of a server, terminals, and users. 【0695】 The server accesses the company's database and collects relevant contract data and historical transaction information. This data is analyzed using natural language processing technology to extract contract terms. The extracted terms are then compared with historical transaction data, and a generation engine generates the optimal additional order terms. 【0696】 Furthermore, the server is equipped with an emotion engine. The emotion engine analyzes user input and responses to identify the user's emotions. Based on this emotion information, the suggested order conditions are adjusted accordingly. As a result, the suggestions become more appropriate to the user's emotional state, improving user satisfaction. 【0697】 The terminal's role is to present the generated and adjusted order conditions sent from the server to the user. The user can review the conditions presented via the terminal and make modifications as needed. Once the user approves the conditions, the terminal sends that information to the server, and the final order data is generated. 【0698】 For example, when a user places an additional order, the emotion engine may recognize that the user is dissatisfied with the order conditions displayed on the terminal. In this case, the server can revise the suggested conditions and quickly confirm a more attractive offer. This increases customer satisfaction and further improves the efficiency of the sales process. 【0699】 The following describes the processing flow. 【0700】 Step 1: 【0701】 The server retrieves contract data and past transaction information related to a specific customer from the company's database. The retrieval process uses customer IDs and contract numbers as keys for searching. 【0702】 Step 2: 【0703】 The server analyzes the acquired contract data using natural language processing technology to extract contract terms. This process tokenizes the contents of the contract and identifies specific conditions and clauses. 【0704】 Step 3: 【0705】 The server compares the extracted contract terms with historical transaction data and applies relevant business rules to analyze patterns. Based on this analysis, the generation engine creates appropriate additional order conditions. 【0706】 Step 4: 【0707】 The server uses an emotion engine to estimate the user's emotional state based on their input and past responses. It then uses text analysis and speech recognition technologies to evaluate the user's emotions using multiple metrics. 【0708】 Step 5: 【0709】 Based on feedback from the emotion engine, the server fine-tunes the generated order conditions to match the user's psychological state. This adjustment ensures that the user receives more satisfying suggestions. 【0710】 Step 6: 【0711】 The terminal displays the adjusted order conditions to the user. The user can review the conditions on the terminal screen and modify them if necessary. Once approved, the process proceeds to the final step. 【0712】 Step 7: 【0713】 Once the user approves the order conditions, the terminal sends that information to the server, which generates the final order data. The server then notifies the relevant departments of the generated order data, and order processing begins. 【0714】 (Example 2) 【0715】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0716】 Conventional contract data analysis systems treat the acquisition and analysis of contract information, the extraction of conditions, the further optimization of those conditions, and the notification of adjusted proposals to users as separate processes, resulting in low overall efficiency. Furthermore, they do not take into account the user's emotional state when adjusting proposals, which can lead to decreased user satisfaction. 【0717】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0718】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing technology and extracting conditions, and a generation module for comparing the extracted conditions with past transaction history and generating additional order conditions. This integrates the process from acquiring and analyzing contract information to generating and adjusting conditions, enabling efficient and user-responsive suggestions. 【0719】 "Contract information" refers to data that includes the terms and conditions concluded in commercial transactions. 【0720】 "Natural language processing technology" is the technology that enables computers to understand and manipulate human language. 【0721】 A "means of extracting conditions" refers to a mechanism for extracting specific requirements or clauses from contract information. 【0722】 A "transaction history" is a record of commercial activities that have taken place in the past. 【0723】 A "generating module" is a component used to create new proposals and conditions based on acquired information. 【0724】 An "emotion engine" is a device or program that analyzes user input and responses to identify their emotional state. 【0725】 A "means of adjustment" refers to a mechanism for further modifying or optimizing the information and conditions obtained. 【0726】 "Means of presentation" refers to display devices or methods used to show generated information or conditions to the user and facilitate their understanding. 【0727】 "Final order information" refers to the final record of a transaction created based on the conditions approved by the user. 【0728】 "Relevant department" refers to the part of the organization responsible for executing or managing the generated final order information. 【0729】 This invention relates to a system that analyzes contract information and generates optimized additional order conditions. This system primarily consists of a server, terminals, and users. 【0730】 The server accesses the company's database to retrieve contract information and past transaction history. This process utilizes SQL database systems and other appropriate data management technologies. The obtained data is then analyzed using natural language processing techniques. Specifically, libraries such as NLTK and spaCy are used to extract necessary conditions from the contract documents. 【0731】 The extracted conditions are compared with past transaction history. In this process, a generation AI model is utilized to generate the optimal additional order conditions. The generation engine is given instructions such as "Generate proposed conditions for product Y based on current market conditions and past transaction data" as a prompt. 【0732】 The server is equipped with an emotion engine that analyzes user input and responses to identify emotional states. For example, it uses OpenAI's emotion recognition model to analyze user text and voice input. Based on the identified emotions, the generated order conditions are optimized. 【0733】 The terminal presents the user with order conditions adjusted by the server. This process is carried out through a web application or mobile application. The user can review the conditions and make modifications as needed. 【0734】 Once the user approves the terms, the terminal sends that information to the server, which generates the final order information. This information is then notified to the appropriate department. 【0735】 As a concrete example, when a user places an additional order for a product on an online platform, the server considers the user's emotions and generates suggested conditions, which are then displayed on the terminal to enhance user satisfaction. An example of a prompt message for the generating AI model is, "Based on the provided data, create the optimal contract terms for product X." 【0736】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0737】 Step 1: 【0738】 The server accesses the company's database to retrieve contract information and historical transaction history. It takes database queries as input to collect relevant contract information and transaction history. The output is these datasets. Specifically, it uses SQL queries to extract the necessary information and stores it on the server in JSON format. 【0739】 Step 2: 【0740】 The server analyzes the acquired contract information using natural language processing technology and extracts conditions. The input is the contract information obtained in step 1. The output is the extracted contract conditions. Specifically, it tokenizes the text data using the Python NLTK library, tags parts of speech, and identifies conditional statements. 【0741】 Step 3: 【0742】 The server uses the extracted conditions to compare them with past transaction history and generates optimal additional order conditions using a generative AI model. The inputs used are the extracted conditions and past transaction history. The output is the optimized additional order conditions. Specifically, the generative AI model is given a prompt such as "Consider the market trends for product A and generate the optimal proposed conditions" to generate the conditions. 【0743】 Step 4: 【0744】 The server analyzes user input and responses using an emotion engine to identify emotional states. Input consists of user text messages and voice messages. Output is emotional state data. Specifically, it uses an emotion recognition API to identify the user's emotions from the tone and content of the text. 【0745】 Step 5: 【0746】 The server adjusts the order conditions generated based on sentiment information. The inputs are the additional order conditions generated in step 3 and the sentiment information obtained in step 4. The output is the adjusted order proposal. Specifically, this involves fine-tuning the amount and contract terms within the conditions to avoid causing discomfort to the user. 【0747】 Step 6: 【0748】 The terminal presents the user with adjusted order conditions. The input is the adjusted order proposal. The output is the user's response. Specifically, a pop-up notification is displayed in the web browser or application to prompt the user to confirm the content. 【0749】 Step 7: 【0750】 The user reviews the presented conditions and modifies them as needed. The input is the order conditions displayed on the terminal. The output is the modified order conditions or the approved conditions. For example, the user fine-tunes the conditions on the screen using sliders and text boxes and completes the modification by pressing the final confirmation button. 【0751】 Step 8: 【0752】 The terminal sends the conditions approved by the user to the server. The input is the modified or approved conditions. The output is the final order information. Specifically, the conditions data is sent to the server using a secure protocol, and a confirmation email is delivered to the user. 【0753】 Step 9: 【0754】 The server generates final order information and notifies the relevant departments. The input is the final order information sent from the terminal. The output is the necessary notifications to the relevant departments and actionable order information. Specifically, it registers the data in the ERP system and generates alerts for the responsible personnel. 【0755】 (Application Example 2) 【0756】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0757】 In modern online business transactions, proposals that consider the user's emotions or past transaction history are rare, and often only standardized terms are presented. This makes it difficult to offer optimal order suggestions that take the user's feelings into account, potentially leading to decreased customer satisfaction. This, in turn, can negatively impact a company's sales. 【0758】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0759】 In this invention, the server includes means for acquiring contract information, means for analyzing the acquired contract information using natural language processing and extracting conditions, and an emotion analysis device for analyzing user input data to identify emotions and adjust proposed conditions. This makes it possible to propose individually optimized additional transaction conditions that take the user's emotions into consideration. 【0760】 "Contract information" refers to a collection of data that shows the details of agreements regarding commercial transactions and service provision. 【0761】 "Natural language processing" is a computer technology used to analyze and understand human language. 【0762】 "Conditions" refer to the provisions or agreements necessary for a contract or proposal to be valid. 【0763】 "Transaction history" refers to information that shows records of commercial transactions that have taken place in the past. 【0764】 A "generation device" is a device or system that generates specific conditions or suggestions based on given data. 【0765】 An "emotion analysis device" is a device or function that analyzes a user's input data to identify their emotions. 【0766】 A "communication terminal" is an electronic device used by a user to receive or transmit information. 【0767】 "Final transaction data" refers to data that shows the final agreed-upon terms and conditions at the time the transaction was completed. 【0768】 A "business department" is a department within a company or organization that is responsible for specific tasks. 【0769】 This system enables automated analysis of contract information and optimized recommendations using user sentiment recognition. First, the server retrieves contract information from the company's database via the network. The retrieved contract information is then analyzed using natural language processing with the Google Cloud Natural Language API to extract important conditions. 【0770】 The server matches the transaction history stored in Amazon RDS with the extracted conditions, and a generator using a Python script generates the optimal transaction conditions. During this process, the Microsoft Azure Emotion API is used to analyze the user's emotions from the input data. The results of the emotion analysis are used to adapt the generated conditions to the user's emotions. 【0771】 The adjusted proposed terms will be communicated to the user via a communication terminal application developed with React Native. The user can review the transaction terms and make modifications as needed. The reviewed or modified terms will be resent to the server, the final transaction data will be generated, and the operational department will be notified. 【0772】 For example, when a user attempts to place a new order for a product they have previously purchased, if their past reviews for that product are negative, the system can encourage repeat purchases by offering discounts or additional benefits. 【0773】 An example of a prompt message is: "Based on past purchase history and customer feedback, create product suggestions tailored to this user. Include incentives that evoke positive emotions." 【0774】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0775】 Step 1: 【0776】 The server retrieves contract information from the company's database. It then begins processing this retrieved contract information as input. 【0777】 Step 2: 【0778】 The server uses the Google Cloud Natural Language API to analyze the retrieved contract information using natural language processing. Here, the information is broken down into its elements, and the contract terms are extracted. The input is the contract information, and the output is the extracted terms. 【0779】 Step 3: 【0780】 The server retrieves historical transaction history stored in Amazon RDS and matches it against the criteria extracted in step 2. This matching identifies relevant transaction data. The inputs are the extracted criteria and transaction history, and the output is the matching result. 【0781】 Step 4: 【0782】 The server uses a Python script to perform data calculations so that the generator can produce optimal trading conditions. The input is the matching result from step 3, and the output is the generated optimized trading conditions. 【0783】 Step 5: 【0784】 The server uses the Microsoft Azure Emotion API to analyze the user's emotions from their input data. Using this analysis, it adjusts the proposed conditions to match the user's emotions. The input is the user's input data, and the output is the analyzed emotions and the adjusted conditions. 【0785】 Step 6: 【0786】 The device notifies the user of the adjusted suggested conditions through a user interface developed with React Native. The user can review the displayed conditions and modify them as needed. The input is the adjusted conditions, and the output is the user's response or modified conditions. 【0787】 Step 7: 【0788】 The terminal resends the user's confirmed or modified conditions to the server. The server generates the final transaction data and notifies the business department. The input is the user's final confirmed conditions, and the output is the final transaction data. 【0789】 The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0790】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0791】 In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0792】 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. 【0793】 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. 【0794】 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. 【0795】 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. 【0796】 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. 【0797】 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." 【0798】 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. 【0799】 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. 【0800】 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. 【0801】 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. 【0802】 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. 【0803】 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. 【0804】 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. 【0805】 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. 【0806】 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. 【0807】 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. 【0808】 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. 【0809】 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. 【0810】 The following is further disclosed regarding the embodiments described above. 【0811】 (Claim 1) 【0812】 Means of obtaining contract data, 【0813】 A method for analyzing acquired contract data using natural language processing and extracting conditions, 【0814】 A generation engine that matches extracted conditions with past transaction data to generate additional order conditions, 【0815】 A means of notifying the user of the generated additional order conditions and confirming them, 【0816】 A system that includes means for generating final order data and notifying relevant departments. 【0817】 (Claim 2) 【0818】 The system according to claim 1, which uses natural language processing to divide the clauses of a contract into tokens, recognizes the parts of speech, and extracts conditions. 【0819】 (Claim 3) 【0820】 The system according to claim 1, wherein the generation engine generates an optimized set of additional order conditions, taking into account past conditions and the business environment. 【0821】 "Example 1" 【0822】 (Claim 1) 【0823】 Means of obtaining information related to the contract, 【0824】 A means of analyzing acquired information using natural language processing technology and extracting conditions, 【0825】 A generator for generating additional conditions by comparing extracted conditions with past data, 【0826】 A means of displaying and allowing the user to confirm the generated additional conditions, 【0827】 A system that includes means for generating final order information and notifying the relevant departments. 【0828】 (Claim 2) 【0829】 The system according to claim 1, which uses natural language processing technology to divide information in a contract into smaller units, recognizes the linguistic roles, and extracts conditions. 【0830】 (Claim 3) 【0831】 The system according to claim 1, wherein the generating device creates optimal additional conditions considering past conditions and the work environment. 【0832】 "Application Example 1" 【0833】 (Claim 1) 【0834】 Means of obtaining contract information, 【0835】 A means of analyzing acquired contract information using natural language processing and extracting conditions, 【0836】 A generation engine that compares extracted conditions with past business data to generate additional requirements, 【0837】 A means to notify the user of the generated additional requirements and to enable them to confirm and modify them, 【0838】 A system that includes means for generating final approval data and notifying the relevant departments. 【0839】 (Claim 2) 【0840】 The system according to claim 1, which uses natural language processing to divide the contents of a contract into elements, recognizes the grammatical structure, and extracts conditions. 【0841】 (Claim 3) 【0842】 The system according to claim 1, wherein the generation engine generates an optimized set of additional requirements, taking into account past conditions and the business environment. 【0843】 "Example 2 of combining an emotion engine" 【0844】 (Claim 1) 【0845】 Means of obtaining contract information, 【0846】 A means of analyzing acquired contract information using natural language processing technology and extracting conditions, 【0847】 A generation module for matching extracted conditions with past transaction history and generating additional order conditions, 【0848】 An emotion engine that analyzes user input and responses to identify emotional states, 【0849】 A means for adjusting additional order conditions generated based on emotional information, 【0850】 A means of presenting and confirming the adjusted additional order conditions to the user, 【0851】 A system that includes means for generating final order information based on user-approved conditions and notifying relevant departments. 【0852】 (Claim 2) 【0853】 The system according to claim 1, which tokenizes clauses in a contract, recognizes parts of speech, and extracts conditions. 【0854】 (Claim 3) 【0855】 The system according to claim 1, wherein the generation module generates optimized additional order conditions taking into account past conditions and environmental conditions. 【0856】 "Application example 2 when combining with an emotional engine" 【0857】 (Claim 1) 【0858】 Means of obtaining contract information, 【0859】 A means of analyzing acquired contract information using natural language processing and extracting conditions, 【0860】 A generator for matching extracted conditions with past transaction history and generating additional transaction conditions, 【0861】 An emotion analysis device that analyzes user input data to identify emotions and adjust suggested conditions, 【0862】 A means of notifying the user of the generated proposed conditions via a communication terminal and confirming them, 【0863】 A system that includes means for generating final transaction data and notifying business departments. 【0864】 (Claim 2) 【0865】 The system according to claim 1, which uses natural language processing to decompose the clauses of a contract document into elements, determine the parts of speech, and extract conditions. 【0866】 (Claim 3) 【0867】 The system according to claim 1, wherein the generating device generates optimized additional trading conditions taking into account past conditions and market conditions. [Explanation of Symbols] 【0868】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] Means of obtaining contract data, A method for analyzing acquired contract data using natural language processing and extracting conditions, A generation engine that matches extracted conditions with past transaction data to generate additional order conditions, A means of notifying the user of the generated additional order conditions and confirming them, A system that includes means for generating final order data and notifying relevant departments. [Claim 2] The system according to claim 1, which uses natural language processing to divide the clauses of a contract into tokens, recognizes the parts of speech, and extracts conditions. [Claim 3] The system according to claim 1, wherein the generation engine generates an optimized set of additional order conditions, taking into account past conditions and the business environment.

Images