system

Abstract

We provide the system. [Solution] A means of obtaining purchase requests from a database, A method for evaluating acquired purchase requests using an artificial intelligence tool, A means of saving the assessment results to a database, A means of determining whether the assessment results are appropriate, A means of skipping pre-purchase consultations and approving payment requests if deemed appropriate, A system that includes means for notifying the need for pre-purchase consultation if it is deemed inappropriate.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional payment request process, the pre-purchase consultation requires time and labor, so the request process tends to be delayed. In addition, there are many manual operations for confirming the validity of the purchase, resulting in a problem of reduced work efficiency. The object of the present invention is to solve these problems and provide a system capable of performing the payment request process quickly and efficiently.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for obtaining purchase requests from a database, means for evaluating the obtained purchase requests using an artificial intelligence tool, means for storing the evaluation results in a database, means for determining whether the evaluation results are appropriate, means for skipping pre-purchase consultation and approving the payment request if it is determined to be appropriate, and means for notifying the user of the need for pre-purchase consultation if it is deemed inappropriate. Specifically, the system provides an artificial intelligence tool that evaluates purchase requests based on price, specifications, and past purchase history, and that can accept purchase requests from a terminal. This allows the system to determine the need for pre-purchase consultation and conduct manual consultation only when necessary, thereby speeding up the payment request processing and reducing man-hours.

[0006] A "purchase request" is a request that a user sends to a system within a company or organization in order to purchase a specific item or service.

[0007] A "database" is a digital system designed to systematically store and manage information, and is used to efficiently store, retrieve, and update data such as purchase requests and appraisal results.

[0008] "Artificial intelligence tools" refer to software or algorithms that automatically analyze purchase requests and evaluate their validity based on factors such as price, specifications, and past purchase history.

[0009] "Assessment" refers to the process in which artificial intelligence tools analyze the content of a purchase request and determine the appropriateness of the price and the necessity of the purchase.

[0010] "Storage" refers to the act of storing generated information or data in a storage medium such as a database, making it accessible later.

[0011] "Judgment" refers to the decision-making process that determines whether or not the information is valid based on the assessment results.

[0012] "Appropriate" refers to a state where the assessment results from the artificial intelligence tool are judged to meet the standards and requirements of the company or organization.

[0013] "Prior purchase consultation" refers to a consultation process conducted in advance by relevant departments and personnel to ensure that a purchase request complies with organizational regulations.

[0014] "Payment approval process" refers to the process by which a company or organization formally approves payments for the purchase of goods or services.

[0015] "Notification" refers to the act of transmitting information to inform other systems or people of specific facts or conditions. [Brief explanation of the drawing]

[0016] [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]Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention relates to a system for streamlining the payment approval process within companies and organizations. This system automates the assessment of purchase requests using artificial intelligence and, when necessary, skips pre-purchase consultations, thereby accelerating the approval process.

[0038] System Overview

[0039] This system consists of the following main components:

[0040] 1. User terminal (terminal): An interface for users to enter purchase requests.

[0041] 2. Server: This server has the central functions of acquiring purchase requests, performing AI-based assessments, saving assessment results, determining appropriateness, and notifying users of the need for payment approval or pre-purchase consultation.

[0042] 3. Artificial intelligence tools: Software for automatically assessing purchase requests and evaluating their validity.

[0043] Program processing

[0044] Retrieving purchase requests

[0045] The user enters a purchase request for a computer or other item from their terminal. The server retrieves this request from the database. For example, it searches the database using the purchase request ID (purchase_request_id) and retrieves the corresponding request.

[0046] Purchase request assessment

[0047] The server passes the acquired purchase request details to an artificial intelligence tool for assessment. The AI ​​tool evaluates the validity of the request based on price, specifications, past purchase history, and other factors. This makes it possible to quickly and objectively determine the appropriateness of the purchase request.

[0048] Saving of assessment results

[0049] The server stores the assessment results from the artificial intelligence tool in a database. These assessment results are stored appropriately as they may be used for reference later.

[0050] Assessment results and next steps

[0051] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result. If it is deemed valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the server that a pre-purchase consultation is required.

[0052] Return of the payment approval result

[0053] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[0054] Specific example

[0055] For example, suppose a user wants to buy a new computer. In that case, the following flow would be executed:

[0056] 1. The user enters a request to purchase a new computer from their device.

[0057] 2. The server retrieves the purchase request from the database.

[0058] 3. The server passes the acquired requests to an artificial intelligence tool for assessment.

[0059] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[0060] 5. The server saves the assessment results from the artificial intelligence tool to the database.

[0061] 6. The server evaluates the assessment results and, if deemed appropriate, skips the pre-purchase consultation and approves the payment request, returning "Approved" as the final result. If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[0062] In this way, the system of the present invention can streamline the pre-purchase consultation process and expedite the processing of payment approval requests.

[0063] The following describes the processing flow.

[0064] Step 1:

[0065] The user enters a request to purchase a new computer from their device.

[0066] Step 2:

[0067] The server retrieves purchase requests submitted by users from the database. Specifically, it searches the database using the purchase request ID (e.g., purchase_request_id) and retrieves the corresponding requests.

[0068] Step 3:

[0069] The server passes the acquired purchase request details to the artificial intelligence tool. At this time, it provides the AI ​​tool with detailed information about the purchase request (price, specifications, quantity, etc.).

[0070] Step 4:

[0071] The artificial intelligence tool performs an assessment based on the provided purchase request information. Specifically, it evaluates the following items:

[0072] Comparison with market price

[0073] Compatibility of specifications and specs

[0074] Comparison with past similar purchase history

[0075] Step 5:

[0076] The server receives the assessment results from the artificial intelligence tool. It is expected that the assessment results will be returned in JSON format or other data formats, as is typical.

[0077] Step 6:

[0078] The server saves the received assessment results to a database. This data is stored in an appropriate format so that it can be referenced later.

[0079] Step 7:

[0080] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result.

[0081] Step 8:

[0082] If the "is_approved" flag is true, the server skips the pre-purchase consultation and proceeds directly to approving the payment request. Specifically, it triggers the purchase approval flow in its internal system, which returns "Approved" as a result.

[0083] Step 9:

[0084] If the "is_approved" flag is false, the server will notify that pre-purchase consultation is necessary. In this case, it will send a message to the purchasing officer or relevant department stating "Needs Pre-purchase Approval".

[0085] The above steps ensure efficient assessment and approval of purchase requests. If pre-purchase consultations can be skipped, the overall process speed increases significantly, improving operational efficiency.

[0086] (Example 1)

[0087] 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."

[0088] The purchasing approval process within companies and organizations often requires manual evaluation and consultation, which is time-consuming and labor-intensive. Furthermore, unclear evaluation criteria create a risk of erroneous approvals or rejections based on subjective judgments. There is a need to resolve these issues and achieve a swift and fair purchasing approval process.

[0089] 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.

[0090] In this invention, the server includes means for recording the details of a purchase request, means for retrieving the recorded purchase request from a database, means for evaluating the retrieved purchase request using an artificial intelligence tool, means for storing the evaluation results in a database, means for determining whether the evaluation results are valid, means for skipping the pre-purchase review and completing the approval process if the results are deemed valid, and means for notifying the server of the need for a pre-purchase review if the results are not valid. This automates the evaluation and approval process of purchase requests, enabling them to be processed quickly and fairly.

[0091] A "purchase request" is a request document that includes details of a desire to purchase goods or services.

[0092] A "database" is a digital information repository used to systematically store purchase requests and related information.

[0093] An "artificial intelligence tool" is a program or algorithm that uses machine learning and data analysis techniques to automatically evaluate the content of a purchase request.

[0094] "Evaluation results" refer to information indicating the validity and appropriateness of a purchase request, calculated by an artificial intelligence tool.

[0095] A "Request ID" is an identification number used to uniquely identify a purchase request within the database.

[0096] "Recording means" refers to a mechanism or program for saving the details of a purchase request in a database.

[0097] "Acquisition method" refers to the process or program used to retrieve a specific purchase request from a database.

[0098] "Evaluation method" refers to the process of analyzing the content of purchase requests using artificial intelligence tools and evaluating their validity.

[0099] A "determination method" refers to a process or program used to determine whether or not to approve a purchase request based on the evaluation results.

[0100] A "notification mechanism" is a mechanism or program that informs the user if a purchase request is invalid.

[0101] This invention relates to a system for effectively managing purchase requests and automating the approval process. The system includes a user terminal, a server for processing and storing data, and an artificial intelligence tool for evaluating purchase requests. Specific embodiments of the invention are described below.

[0102] System Configuration

[0103] The user terminal has an interface for entering purchase requests. The user uses a dedicated application or web browser to enter details of the required products (e.g., name, quantity, budget) into a form and presses the submit button. This information is sent to the server in real time.

[0104] The server has the function of saving received purchase requests to a database. Each request is assigned a unique request ID, which is recorded in the database. The server uses a SQL database or similar to efficiently store and retrieve data.

[0105] The server then retrieves new purchase requests from the database and passes the data to an artificial intelligence tool. The AI ​​tool evaluates the validity of the purchase request based on its price, specifications, and past purchase history. This evaluation uses machine learning algorithms such as random forests and neural networks.

[0106] The evaluation results returned by the artificial intelligence tool are again stored in the database by the server. These results include flags indicating whether the purchase request is valid and detailed evaluation information.

[0107] Next, the server determines the validity of the request based on the evaluation results. If the evaluation results are deemed valid, the server skips the pre-purchase review and approves the direct payment request. In this case, the user receives a notification that it has been approved. On the other hand, if the evaluation results are deemed invalid, the server notifies the user of the need for pre-purchase review, displaying the message "Needs Pre-purchase Approval".

[0108] Specific example

[0109] For example, let's specifically describe the flow when a user requests the purchase of a new computer (e.g., a laptop):

[0110] 1. The user enters a purchase request for a "laptop (specs: 16GB RAM, 512GB SSD, 13-inch)" from their terminal and presses the submit button. This sends the request to the server.

[0111] 2. The server saves this request in the database and generates a request ID (e.g., ID 101).

[0112] 3. The server retrieves the details of request ID 101 from the database and passes the data to the artificial intelligence tool. The artificial intelligence tool evaluates the validity of this request by comparing it with past purchase history and returns a "yes" or "no" flag.

[0113] 4. The server saves the evaluation results to the database and updates the status of the corresponding request.

[0114] 5. If the evaluation result is "yes," the server approves the payment request and notifies the user with "Approved." If the evaluation result is "no," the server notifies the user with "Needs Pre-purchase Approval."

[0115] In this way, the system streamlines purchasing operations within companies and organizations by conducting the assessment and approval process of purchase requests efficiently and fairly.

[0116] Specific examples of input prompts for generative AI models

[0117] When requesting a system description from a generative AI model, you can use prompt statements like the following:

[0118] "Please describe in detail a system that automates the processing of purchase requests within a company. Explain the specific steps involved in how this system uses artificial intelligence to evaluate the validity of requests and expedite the approval process."

[0119] This prompt allows you to obtain a detailed and specific system description from the generated AI model.

[0120] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0121] Step 1:

[0122] The user enters a purchase request using a terminal. The user enters detailed information such as the name of the item to be purchased, quantity, desired delivery date, and budget into a form in a dedicated application or web browser, and then presses the submit button. The input data includes specific request details, and the terminal sends this information to the server.

[0123] Input: Detailed information of the purchase request entered by the user (name, quantity, desired delivery date, budget).

[0124] Output: Sending purchase request data from the terminal to the server.

[0125] Step 2:

[0126] The server saves purchase requests received from terminals to a database. When saving, it generates a unique request ID for each purchase request and saves it along with the request information. Specifically, it adds data to the SQL database using an INSERT statement.

[0127] Input: Purchase request data sent from the terminal.

[0128] Output: Save purchase request information to the database and generate a request ID.

[0129] Step 3:

[0130] The server retrieves new purchase requests from the database. Specifically, it searches for requests with a status of "pending" using an SQL query and retrieves their detailed information. For example, it executes a query like SELECT FROM purchase_requests WHERE status = 'pending'.

[0131] Input: Purchase request information stored in the database.

[0132] Output: Retrieved purchase request information.

[0133] Step 4:

[0134] The server passes the acquired purchase request information to an artificial intelligence tool for evaluation. This evaluation uses data such as past purchase history, price, and specifications. The artificial intelligence tool calculates the validity of the purchase request using machine learning algorithms such as random forests and neural networks.

[0135] Input: Purchase request information provided by the server, as well as past purchase history, price, and specification data.

[0136] Output: Validity results of purchase requests evaluated by an artificial intelligence tool.

[0137] Step 5:

[0138] The server stores the evaluation results returned by the artificial intelligence tool in a database. The evaluation results include flags indicating the validity of the purchase request and evaluation details. Saving is performed using an SQL statement such as UPDATE purchase_requests SET ai_result = 'result', is_approved = 'yes / no' WHERE purchase_request_id = 'id'.

[0139] Input: Evaluation results provided by an artificial intelligence tool.

[0140] Output: Saving evaluation results to the database.

[0141] Step 6:

[0142] The server determines the validity of the purchase request based on the stored evaluation results. Specifically, it checks the `is_approved` flag in the evaluation results. If the flag is "yes", it skips the pre-purchase review and approves the direct payment request. If the flag is "no", it notifies the server that a pre-purchase review is necessary.

[0143] Input: Evaluation results stored in the database.

[0144] Output: Approval of purchase request or notification of the need for pre-purchase review.

[0145] Step 7:

[0146] The server sends a notification to the user based on the decision. The notification will include messages such as "Approved" if the purchase request is approved, or "Needs Pre-purchase Approval" if pre-purchase review is required. The notification will be sent via email or the company's internal messaging system.

[0147] Input: Approval or pre-purchase review decision result.

[0148] Output: Sending a notification to the user.

[0149] In this way, this system can efficiently evaluate and approve purchase requests, enabling faster progress in purchasing operations within a company.

[0150] (Application Example 1)

[0151] 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."

[0152] Many factories face problems with time-consuming purchasing request processing and inefficient pre-purchase consultation and payment approval processes. Furthermore, manual verification processes are cumbersome and can lack consistency and objectivity in decision-making. This results in wasted costs and time, leading to decreased operational efficiency.

[0153] 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.

[0154] In this invention, the server includes means for obtaining purchase requests from a database, means for assessing the obtained purchase requests using an artificial intelligence tool, means for storing the assessment results in the database, means for determining whether the assessment results are appropriate, means for skipping pre-purchase consultation and approving the payment request if it is determined to be appropriate, means for notifying the need for pre-purchase consultation if it is not appropriate, means for receiving input of purchase requests from factory robots within the factory, and means for rapidly processing the assessment results by the factory robots. As a result, the processing of purchase requests is accelerated, enabling improved operational efficiency and cost reduction.

[0155] A "purchase request" refers to a request to buy goods or services needed within a factory.

[0156] A "database" is an organized collection used to store, search, and manage information such as purchase requests and appraisal results.

[0157] An "artificial intelligence tool" is software or hardware that evaluates the validity of a purchase request based on factors such as price, specifications, and past purchase history.

[0158] "Assessment result" refers to the judgment made after the validity of a purchase request has been evaluated by an artificial intelligence tool.

[0159] A "factory robot" refers to a machine or device that automatically processes requests for the purchase of goods or services within a factory.

[0160] "Prior purchase consultation" refers to the necessary approval process that takes place in advance of a purchase request.

[0161] "Payment approval process" refers to the payment procedure carried out after a purchase request has been approved.

[0162] "Terminal" refers to input devices such as computers and tablets used by operators within a factory.

[0163] This invention relates to a system for efficiently processing purchase requests within a factory. The system aims to expedite the approval process by automating the assessment of purchase requests using artificial intelligence and skipping pre-purchase consultations as needed.

[0164] System Overview

[0165] This system consists of the following main components:

[0166] 1. Terminal

[0167] These are input devices such as computers and tablets used by operators within a factory, and they provide an input interface for purchase requests.

[0168] 2. Server

[0169] It plays a central role in acquiring purchase requests, conducting AI-powered assessments, saving assessment results, determining their validity, and notifying users of the need for payment approval or pre-purchase consultation.

[0170] 3. Artificial Intelligence Tools

[0171] This software automatically assesses purchase requests and evaluates their validity. It makes its determination based on factors such as price, specifications, and past purchase history.

[0172] Program processing and detailed description

[0173] Retrieving purchase requests

[0174] The user, acting as an operator within the factory, enters a purchase request from a terminal. Specifically, they enter details such as the name, price, specifications, and quantity of the goods or services they wish to purchase. The server retrieves this request from the database. For example, it searches the database using the purchase request ID and retrieves the corresponding request.

[0175] Purchase request assessment

[0176] The server passes the acquired purchase request details to an artificial intelligence tool for assessment. The AI ​​tool evaluates the validity of the request based on data such as price, specifications, and past purchase history. This makes it possible to quickly and objectively determine the appropriateness of the purchase request.

[0177] Saving of assessment results

[0178] The server stores the assessment results from the artificial intelligence tool in a database. These assessment results are stored appropriately as they may be used for reference later.

[0179] Assessment results and next steps

[0180] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result. If it is deemed valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the server that a pre-purchase consultation is required.

[0181] Return of the payment approval result

[0182] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[0183] Hardware and software to be used

[0184] Hardware:

[0185] Tablets and dedicated terminals installed on factory robots.

[0186] software:

[0187] An artificial intelligence tool using Python, pandas, and the scikit-learn library.

[0188] Specific example

[0189] For example, if an operator wants to purchase a new machine tool, they would enter the following into a terminal in the factory:

[0190] "I would like to purchase a new machine tool. The price is 500,000 yen, the specifications are CNC 5-axis, and the quantity is 1 unit."

[0191] This system receives the request, performs an assessment based on past data, and returns either an "Approved" or "Needs Pre-purchase Approval" result. Through this specific example, applying the system of the present invention to factory robots not only streamlines the purchasing process within the factory but also enables quick and objective decision-making.

[0192] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0193] Step 1:

[0194] Users enter purchase requests using terminals within the factory. The information entered includes the name of the item or service, price, specifications, and quantity. This input data is sent to a server, which stores the received data in a database.

[0195] Step 2:

[0196] The server retrieves newly saved purchase requests from the database. Based on identification information such as the ID used for retrieval, it extracts detailed information about the associated purchase requests. The retrieved data is used in the next processing step.

[0197] Step 3:

[0198] The server passes the acquired purchase request data to an artificial intelligence tool for assessment. Specifically, the AI ​​model evaluates the validity of the purchase based on data such as price, specifications, and past purchase history. Price, specifications, and past data are provided as input data, and the AI ​​model outputs the evaluation result of the validity.

[0199] Step 4:

[0200] The server saves the assessment results generated by the artificial intelligence tool back into the database. This makes it possible to reuse the assessment results in the future. When saving the data, appropriate identification information (such as a purchase request ID) is used.

[0201] Step 5:

[0202] The server determines whether the saved assessment results are valid. Specifically, it checks the status of the "is_approved" flag included in the assessment results. Depending on whether the flag indicates "valid" or "not valid," the next action is determined accordingly.

[0203] Step 6:

[0204] If the server determines that the assessment results are reasonable, it skips the pre-purchase consultation and proceeds with approving the payment request. It returns an "Approved" result as the final outcome, completing the process. This expedites the purchasing process.

[0205] Step 7:

[0206] If the server determines that the assessment result is unsatisfactory, it will notify the user that pre-purchase consultation is required. This notification will include a result of "Needs Pre-purchase Approval" and will proceed to another pre-purchase consultation step. The notification will be displayed on the device.

[0207] In this way, the roles of the server, terminal, and user are clearly defined in each processing step, ensuring that purchase requests are processed quickly and efficiently.

[0208] 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.

[0209] This invention relates to a system for streamlining the payment approval process within companies and organizations. In particular, it automates the assessment of purchase requests using artificial intelligence, combines this with an emotion engine that recognizes user emotions, and skips pre-purchase consultations as needed, thereby enabling rapid approval processing.

[0210] System Overview

[0211] This system consists of the following main components:

[0212] 1. User terminal (terminal): An interface for users to input purchase requests and their emotional information at that time.

[0213] 2. Server: Has the central functions of acquiring purchase requests, conducting assessments using artificial intelligence and emotion engines, saving assessment results, determining appropriateness, and notifying of the need for payment approval or pre-purchase consultation.

[0214] 3. Artificial intelligence tools: Software for automatically assessing purchase requests and evaluating their validity.

[0215] 4. Emotion Engine: Software that recognizes emotions from user input and reflects the analysis results in the assessment of purchase requests.

[0216] Program processing

[0217] Retrieving purchase requests

[0218] The user enters a purchase request for a new computer or other device from their terminal, and also provides emotional information (e.g., text message, voice input) along with the request. The server retrieves this request and emotional information from its database.

[0219] Purchase request assessment

[0220] The server passes the acquired purchase request content and emotional information to the artificial intelligence tool and emotion engine for assessment. The artificial intelligence tool evaluates the appropriateness based on price, specifications, past purchase history, etc. Meanwhile, the emotion engine analyzes the emotional information and identifies the user's emotional state (e.g., urgency, reassurance, anxiety, etc.).

[0221] Saving of assessment results

[0222] The server stores assessment results from artificial intelligence tools and emotion engines in a database. These assessment results are stored appropriately as they will be used later for reference.

[0223] Assessment results and next steps

[0224] The server determines whether the assessment results received from the artificial intelligence tools and the sentiment engine are valid. Specifically, it comprehensively evaluates the "is_approved" flag in the assessment results and the sentiment analysis results. If it is determined to be valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the user that a pre-purchase consultation is required.

[0225] Return of the payment approval result

[0226] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[0227] Specific example

[0228] For example, suppose a user wants to buy a new computer. In that case, the following flow would be executed:

[0229] 1. The user enters a request to purchase a new computer from their device, and at the same time, includes the emotional information "I need this urgently" as a text message.

[0230] 2. The server retrieves the purchase request and sentiment information from the database.

[0231] 3. The server passes the acquired requests to artificial intelligence tools and an emotion engine for assessment.

[0232] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[0233] 5. The emotion engine analyzes the emotional information provided by the user and evaluates the user's emotional state (in this case, "urgency").

[0234] 6. The server stores the assessment results from the artificial intelligence tools and emotion engine in a database.

[0235] 7. The server evaluates the assessment results, and if deemed appropriate, it skips the pre-purchase consultation and approves the payment request, returning "Approved" as the final result. If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[0236] In this way, the system of the present invention can streamline the pre-purchase consultation process and enable rapid payment approval processing that takes user sentiment into consideration.

[0237] The following describes the processing flow.

[0238] Step 1:

[0239] A user enters a request to purchase a new computer via a terminal. At the same time, the user sends emotional information (for example, a message such as "I need this urgently").

[0240] Step 2:

[0241] The server retrieves purchase requests and sentiment information sent by users from the database. Specifically, it searches the database using the purchase request ID (e.g., purchase_request_id) and retrieves the corresponding request and sentiment information.

[0242] Step 3:

[0243] The server separates the acquired purchase request from the sentiment information, passes the purchase request content to an artificial intelligence tool, and passes the sentiment information to the sentiment engine.

[0244] Step 4:

[0245] The artificial intelligence tool assesses the content of the provided purchase request. Specifically, it evaluates the following items:

[0246] Comparison with market price

[0247] Compatibility of specifications and specs

[0248] Comparison with past similar purchase history

[0249] Step 5:

[0250] The emotion engine analyzes the provided emotional information and evaluates the user's emotional state (e.g., "urgency" or "sense of security"). An emotion recognition algorithm is used to ensure accurate analysis results.

[0251] Step 6:

[0252] The server retrieves evaluation results obtained from artificial intelligence tools and emotion engines.

[0253] Step 7:

[0254] The server stores the assessment results of the artificial intelligence tool and the evaluation results of the emotion engine in a database. This ensures that each evaluation result is accurately recorded so that it can be referenced in the future.

[0255] Step 8:

[0256] The server determines whether the assessment results are valid. This determination includes the "is_approved" flag from the artificial intelligence tool and the evaluation results from the sentiment engine.

[0257] Step 9:

[0258] If the "is_approved" flag is true and the sentiment engine's analysis results support the need for purchase, the server skips the pre-purchase consultation and proceeds directly to approving the payment request. In this case, it returns the result "Approved".

[0259] Step 10:

[0260] If the "is_approved" flag is false, or if the sentiment engine's analysis does not support the need for purchase, the server will notify the server of the need for pre-purchase consultation. In this case, it will return the result "Needs Pre-purchase Approval".

[0261] The above steps enable efficient assessment and approval of purchase requests. By considering user sentiment information, it becomes possible to more accurately evaluate the appropriateness and urgency of purchases, thereby improving the speed and reliability of the entire process.

[0262] (Example 2)

[0263] 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".

[0264] The approval process for purchase requests within companies and organizations is often manual, which can lead to delays in decision-making and errors. Furthermore, because it proceeds formally without considering user emotions or urgency, it fails to respond quickly to urgent requests. Traditional systems lacked effective solutions to these problems.

[0265] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring purchase requests and sentiment information from a database, means for assessing the acquired purchase requests and sentiment information using an artificial intelligence tool and a sentiment engine, and means for storing the assessment results in the database. This makes it possible to comprehensively judge the validity of purchase requests and the emotional state of the user, and to quickly approve payment requests when prior consultation on purchases is not required.

[0266] A "purchase request" is an application submitted by a user to purchase a specific product or service.

[0267] "Emotional information" refers to data that indicates a user's emotional state, and is expressed through text messages, voice input, and other means.

[0268] A "database" is a system that centrally stores and manages data such as purchase requests, sentiment information, and appraisal results.

[0269] An "artificial intelligence tool" is software that uses machine learning algorithms and data analysis techniques to evaluate the validity of purchase requests.

[0270] An "emotion engine" is software that analyzes emotional information provided by the user and recognizes and evaluates that emotional state.

[0271] "Assessment results" refer to information regarding the validity and emotional state of a purchase request, as evaluated by artificial intelligence tools and an emotion engine.

[0272] "Pre-purchase consultation" refers to the detailed review and discussion process that takes place before a purchase request is approved.

[0273] A "payment approval request" is an approval process related to the payment procedures for expenses that are carried out after a purchase request has been finally approved.

[0274] A "server" is a central computer system that retrieves, analyzes, stores, and evaluates purchase requests.

[0275] A "terminal" is a device used by a user to input purchase requests or emotional information, and includes computers, smartphones, and other similar devices.

[0276] This invention relates to a system for streamlining the payment approval process within companies and organizations.

[0277] System Configuration

[0278] This system consists of the following main components:

[0279] 1. User terminal (terminal)

[0280] An interface for users to input purchase requests and sentiment information. Specifically, this includes devices such as computers and smartphones.

[0281] 2. Server

[0282] It has central functions for acquiring purchase requests, assessing them using artificial intelligence tools and an emotion engine, saving assessment results, determining their validity, and notifying users of the need for payment approval or pre-purchase consultation.

[0283] 3. Artificial Intelligence Tools

[0284] Software for automatically assessing purchase requests and evaluating their validity. Specifically, it operates using machine learning algorithms and data analysis techniques.

[0285] 4. Emotion Engine

[0286] Software for recognizing emotions from user inputs and reflecting the analysis results in the assessment of purchase requests. It includes text analysis and voice analysis algorithms.

[0287] Specific Explanation of Program Processing

[0288] Obtaining Purchase Requests

[0289] The user inputs a purchase request for a new computer or the like from a terminal, and also provides the emotional information (e.g., text message, voice input, etc.) at that time. The server obtains this request and emotional information from the database. At this time, the data is transmitted and stored in JSON format or other appropriate data formats.

[0290] Assessing Purchase Requests

[0291] The server passes the content of the obtained purchase request and emotional information to the artificial intelligence tool and the emotion engine for assessment. The artificial intelligence tool evaluates its validity based on factors such as price, specifications, and past purchase history. On the other hand, the emotion engine analyzes the emotional information and identifies the user's emotional state (e.g., urgency, sense of security, sense of uneasiness, etc.). At this time, machine learning models and natural language processing (NLP) algorithms are used.

[0292] Saving Assessment Results

[0293] The server saves the assessment results from the artificial intelligence tool and the emotion engine in the database. The obtained results are written into the database in JSON format or other appropriate data formats and are later used as a reference.

[0294] Evaluation and determination of assessment results

[0295] The server determines whether the assessment results received from the artificial intelligence tools and the sentiment engine are valid. Specifically, it decides whether the request can be approved based on the "is_approved" flag and the sentiment analysis results.

[0296] Notification of the result of the payment approval request

[0297] The server will either approve the payment request based on the final evaluation, or notify the user that pre-purchase consultation is required. If approved, it will send an "Approved" result to the user's terminal, and the process will be complete. If not approved, it will send a "Needs Pre-purchase Approval" result, and request pre-purchase consultation.

[0298] Specific example

[0299] For example, if a user wants to buy a new computer, the following steps are taken:

[0300] 1. The user enters a request to purchase a new computer from their device, and at the same time, includes the emotional information "I need this urgently" as a text message.

[0301] 2. The server retrieves the purchase request and sentiment information from the database.

[0302] 3. The server passes the acquired requests to artificial intelligence tools and an emotion engine for assessment.

[0303] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[0304] 5. The emotion engine analyzes the emotional information provided by the user and evaluates the user's emotional state (in this case, "urgency").

[0305] 6. The server saves the evaluation results from the artificial intelligence tool and the sentiment engine in the database.

[0306] 7. The server determines the evaluation results. If it is judged to be appropriate, it approves the payment request and returns "Approved". If it is not appropriate, it returns "Needs Pre-purchase Approval".

[0307] Example of a prompt sentence:

[0308] "A purchase request for a new computer has been entered. It is needed urgently. Please evaluate the validity with an AI tool considering the past purchase history, current price, and specifications. Also, analyze my sentiment information with the sentiment engine and make a final judgment on the payment request."

[0309] In this way, the system of the present invention can streamline the process of pre-purchase agreement and achieve rapid processing of payment requests considering the user's sentiment.

[0310] The flow of specific processing in Example 2 will be described using FIG. 13.

[0311] Step 1: The user inputs a purchase request and sentiment information into the terminal.

[0312] The user uses the terminal to input a purchase request (e.g., the desire to purchase a new computer) and sentiment information (e.g., the text message "It is needed urgently"). The input data is sent to the server by pressing the send button.

[0313] Input: Purchase request, sentiment information

[0314] Output: Transmission of request data

[0315] Step 2: The server receives the purchase request and sentiment information and saves them in the database.

[0316] The server receives purchase requests and sentiment information sent by users. The received data is converted to JSON format or an appropriate data format and stored in the database.

[0317] Input: User request data

[0318] Output: Saving data to the database

[0319] Step 3: The server retrieves and processes the request data from the database.

[0320] The server retrieves purchase requests and sentiment information from the database and processes it into a data format for passing to artificial intelligence tools and sentiment engines. Specifically, it converts the data into the appropriate JSON format.

[0321] Input: Request data from the database

[0322] Output: Processed data

[0323] Step 4: The server passes the request data to the AI ​​tool and emotion engine and requests an assessment.

[0324] The server passes the processed data to an artificial intelligence tool and an emotion engine. The AI ​​tool evaluates the validity of the purchase request based on price, specifications, and past purchase history, while the emotion engine analyzes emotional information to determine the user's urgency and stress level.

[0325] Input: Processed data

[0326] Output: Assessment results from AI tools and emotion engine

[0327] Step 5: The server saves the assessment results to the database.

[0328] The server stores assessment results received from artificial intelligence tools and emotion engines in a database. This stored data is then used for future processing and reference.

[0329] Input: Assessment result

[0330] Output: Save to database

[0331] Step 6: The server evaluates the assessment results and determines their validity.

[0332] The server refers to the assessment results stored in the database and comprehensively evaluates their validity. In particular, it decides whether to approve or reject the purchase request based on the "is_approved" flag and the sentiment analysis results.

[0333] Input: Assessment results from the database

[0334] Output: Evaluation result (Approval / Rejection)

[0335] Step 7: The server notifies the user of the approval result.

[0336] Based on the final evaluation, the server will either approve the payment request or notify the user that pre-purchase consultation is required. If approved, it will return "Approved"; if not approved, it will return "Needs Pre-purchase Approval" and notify the user's terminal.

[0337] Input: Evaluation result

[0338] Output: Notification to user terminal

[0339] (Application Example 2)

[0340] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0341] Traditional purchasing approval systems failed to adequately consider user emotions and urgency when evaluating the validity of purchase requests. As a result, even highly urgent purchase requests could experience delays, potentially disrupting business operations. Furthermore, the inability to provide personalized content recommendations that reflected user emotions made improving user satisfaction difficult.

[0342] 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. In this invention, the server includes means for acquiring purchase requests from a database, means for evaluating the acquired purchase requests using an artificial intelligence tool, means for storing the evaluation results in a database, means including an emotion engine that acquires and analyzes user emotion information, and means for determining the urgency and priority of purchase requests based on emotion information and reflecting this in the evaluation. This enables rapid approval processing that takes into account the urgency of purchase requests and user emotions. Furthermore, it is possible to recommend the most suitable content based on user viewing requests and emotion information, thereby improving user satisfaction.

[0343] A "purchase request" refers to a request or application submitted by a user when they wish to purchase a new product or service.

[0344] A "database" is a repository of information that stores information in an efficient and organized manner, making it easy to search and retrieve.

[0345] An "artificial intelligence tool" is a computer program that uses technologies such as machine learning and neural networks to analyze data and make predictions and judgments.

[0346] "Assessment" is the process of evaluating and judging the validity and appropriateness of a purchase request.

[0347] "Emotional information" refers to data that represents a user's psychological state and emotions, and is obtained from sources such as text, voice, and facial expressions.

[0348] An "emotion engine" is software that analyzes a user's emotional information and identifies their emotional state.

[0349] "Urgency" refers to the degree to which a particular purchase request or task is urgent.

[0350] "Priority" is an indicator that shows which of several tasks or requests is more important than others.

[0351] A "pre-purchase consultation" is a meeting or discussion held to confirm necessary information and conditions before formally approving a purchase request.

[0352] "Rin-gi" refers to the process of seeking approval or decision-making within a company, and often specifically refers to the approval process for payments.

[0353] "Assessment results" refer to the results after evaluating the validity and urgency of a purchase request using artificial intelligence tools and emotion engines.

[0354] "Relevance" is an evaluation criterion that indicates whether a purchase request is feasible and conforms to the company's policies and standards.

[0355] "Recommendation" refers to suggesting the most suitable products or services based on the user's past behavior, preferences, and emotional information.

[0356] "Viewing trend data" refers to data that shows information about user and market viewing trends and popular content.

[0357] To implement this invention, the following system configuration and processing flow are used. The system consists of a user terminal, a server, an artificial intelligence tool, an emotion engine, and a database. The specific hardware used is a smartphone, smart glasses, and a server, and the software includes a user interface, an artificial intelligence tool (e.g., TENSORFLOW®, PyTorch), and an emotion engine (e.g., Emotion API, Facial Recognition API).

[0358] System components

[0359] User terminal

[0360] The user terminal consists of a smartphone or smart glasses and provides an interface for users to input emotional information and content viewing requests. This ensures smooth user operation.

[0361] server

[0362] The server plays a central role in the system, retrieving purchase requests and sentiment information from the database and analyzing them using artificial intelligence tools and a sentiment engine. The analysis results are then evaluated again by the server and stored in the database. Furthermore, based on the results, it either notifies the customer of the need for pre-purchase consultation or approves the payment request.

[0363] Artificial intelligence tools

[0364] Artificial intelligence tools are software that evaluates the validity of purchase requests. They analyze and evaluate requests based on price, specifications, past purchase history, and viewing trend data. Specifically, they use TensorFlow and PyTorch to build machine learning models and make purchase requests and content recommendations.

[0365] Emotional Engine

[0366] An emotion engine is software that analyzes a user's emotional information. It analyzes text messages and voice data acquired from the device to identify the user's emotional state. For example, the Emotion API and Facial Recognition API are used for emotion analysis.

[0367] database

[0368] The database is an information management system for storing purchase requests, sentiment information, analysis results, past purchase and viewing history, and viewing trend data. This makes the data available for later analysis and reference.

[0369] Add specific examples to the description.

[0370] Examples of content recommendations

[0371] For example, a user might type "I want to watch a relaxing movie" on their smartphone and also voice-input "I'm a little tired." The server passes this information to an artificial intelligence tool and an emotion engine for analysis. The AI ​​tool analyzes past viewing history and trends in relaxing movies, while the emotion engine determines the user's emotions from the voice input "I'm a little tired." Finally, the server recommends and notifies the user of the most suitable content.

[0372] Examples of prompts for generative AI models

[0373] The following are examples of prompts for a generative AI model:

[0374] Point down

[0375] A user types "I want to watch a relaxing movie" on their smartphone and also voice-inputs "I'm a little tired." An emotion engine analyzes the user's voice information, and an artificial intelligence tool recommends the most suitable content based on past viewing history and trends in relaxing movies. What models or APIs should I use to achieve this?

[0376] By implementing this invention, personalized content recommendations that take into account the user's emotions and past viewing history become possible, which is expected to improve user satisfaction. Furthermore, rapid processing of purchase requests can also be achieved simultaneously.

[0377] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0378] Step 1:

[0379] Users use their smartphones or smart glasses to input viewing requests and emotional information. Specifically, they launch the application and input text such as "I want to watch a relaxing movie" and voice information such as "I'm a little tired." The input data is stored on the device and sent to the server.

[0380] Step 2:

[0381] The server retrieves the received viewing requests and sentiment information from the database. Specifically, data sent to the server in the form of "purchase requests" and "sentiment information" retrieves information from the database and passes it on to the next processing step.

[0382] Step 3:

[0383] The server passes the content of the acquired viewing request to an artificial intelligence tool, and then passes the emotional information to an emotion engine. The artificial intelligence tool uses past viewing history and viewing trend data to analyze the data and evaluate the validity of the request and recommend content. The emotion engine analyzes the emotional state from the audio data and derives the result "slightly tired."

[0384] Step 4:

[0385] The server integrates analysis results from artificial intelligence tools and an emotion engine. Specifically, it combines a list of relaxing movies recommended by the AI ​​tool with the user's emotional state analyzed by the emotion engine to select the most suitable content. For example, it selects the content with the highest "relaxation level" and "viewing recommendation level" from the list of relaxing movies.

[0386] Step 5:

[0387] The server notifies the user of the most suitable content it has selected. Specifically, it sends a message to the user's device saying, "Here is the best movie for you: XXXXX," along with a link to view the content.

[0388] Step 6:

[0389] Users can start watching by checking the notification they receive and clicking the provided link. This makes it easy for users to watch the relaxing movie they want.

[0390] The specific flow and processing steps enable personalized content recommendations based on user viewing requests and sentiment information.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] [Second Embodiment]

[0395] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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".

[0407] This invention relates to a system for streamlining the payment approval process within companies and organizations. This system automates the assessment of purchase requests using artificial intelligence and, when necessary, skips pre-purchase consultations, thereby accelerating the approval process.

[0408] System Overview

[0409] This system consists of the following main components:

[0410] 1. User terminal (terminal): An interface for users to enter purchase requests.

[0411] 2. Server: This server has the central functions of acquiring purchase requests, performing AI-based assessments, saving assessment results, determining appropriateness, and notifying users of the need for payment approval or pre-purchase consultation.

[0412] 3. Artificial intelligence tools: Software for automatically assessing purchase requests and evaluating their validity.

[0413] Program processing

[0414] Retrieving purchase requests

[0415] The user enters a purchase request for a computer or other item from their terminal. The server retrieves this request from the database. For example, it searches the database using the purchase request ID (purchase_request_id) and retrieves the corresponding request.

[0416] Purchase request assessment

[0417] The server passes the acquired purchase request details to an artificial intelligence tool for assessment. The AI ​​tool evaluates the validity of the request based on price, specifications, past purchase history, and other factors. This makes it possible to quickly and objectively determine the appropriateness of the purchase request.

[0418] Saving of assessment results

[0419] The server stores the assessment results from the artificial intelligence tool in a database. These assessment results are stored appropriately as they may be used for reference later.

[0420] Assessment results and next steps

[0421] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result. If it is deemed valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the server that a pre-purchase consultation is required.

[0422] Return of the payment approval result

[0423] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[0424] Specific example

[0425] For example, suppose a user wants to buy a new computer. In that case, the following flow would be executed:

[0426] 1. The user enters a request to purchase a new computer from their device.

[0427] 2. The server retrieves the purchase request from the database.

[0428] 3. The server passes the acquired requests to an artificial intelligence tool for assessment.

[0429] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[0430] 5. The server saves the assessment results from the artificial intelligence tool to the database.

[0431] 6. The server evaluates the assessment results and, if deemed appropriate, skips the pre-purchase consultation and approves the payment request, returning "Approved" as the final result. If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[0432] In this way, the system of the present invention can streamline the pre-purchase consultation process and expedite the processing of payment approval requests.

[0433] The following describes the processing flow.

[0434] Step 1:

[0435] The user enters a request to purchase a new computer from their device.

[0436] Step 2:

[0437] The server retrieves purchase requests submitted by users from the database. Specifically, it searches the database using the purchase request ID (e.g., purchase_request_id) and retrieves the corresponding requests.

[0438] Step 3:

[0439] The server passes the acquired purchase request details to the artificial intelligence tool. At this time, it provides the AI ​​tool with detailed information about the purchase request (price, specifications, quantity, etc.).

[0440] Step 4:

[0441] The artificial intelligence tool performs an assessment based on the provided purchase request information. Specifically, it evaluates the following items:

[0442] Comparison with market price

[0443] Compatibility of specifications and specs

[0444] Comparison with past similar purchase history

[0445] Step 5:

[0446] The server receives the assessment results from the artificial intelligence tool. It is expected that the assessment results will be returned in JSON format or other data formats, as is typical.

[0447] Step 6:

[0448] The server saves the received assessment results to a database. This data is stored in an appropriate format so that it can be referenced later.

[0449] Step 7:

[0450] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result.

[0451] Step 8:

[0452] If the "is_approved" flag is true, the server skips the pre-purchase consultation and proceeds directly to approving the payment request. Specifically, it triggers the purchase approval flow in its internal system, which returns "Approved" as a result.

[0453] Step 9:

[0454] If the "is_approved" flag is false, the server will notify that pre-purchase consultation is necessary. In this case, it will send a message to the purchasing officer or relevant department stating "Needs Pre-purchase Approval".

[0455] The above steps ensure efficient assessment and approval of purchase requests. If pre-purchase consultations can be skipped, the overall process speed increases significantly, improving operational efficiency.

[0456] (Example 1)

[0457] 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."

[0458] The purchasing approval process within companies and organizations often requires manual evaluation and consultation, which is time-consuming and labor-intensive. Furthermore, unclear evaluation criteria create a risk of erroneous approvals or rejections based on subjective judgments. There is a need to resolve these issues and achieve a swift and fair purchasing approval process.

[0459] 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.

[0460] In this invention, the server includes means for recording the details of a purchase request, means for retrieving the recorded purchase request from a database, means for evaluating the retrieved purchase request using an artificial intelligence tool, means for storing the evaluation results in a database, means for determining whether the evaluation results are valid, means for skipping the pre-purchase review and completing the approval process if the results are deemed valid, and means for notifying the server of the need for a pre-purchase review if the results are not valid. This automates the evaluation and approval process of purchase requests, enabling them to be processed quickly and fairly.

[0461] A "purchase request" is a request document that includes details of a desire to purchase goods or services.

[0462] A "database" is a digital information repository used to systematically store purchase requests and related information.

[0463] An "artificial intelligence tool" is a program or algorithm that uses machine learning and data analysis techniques to automatically evaluate the content of a purchase request.

[0464] "Evaluation results" refer to information indicating the validity and appropriateness of a purchase request, calculated by an artificial intelligence tool.

[0465] A "Request ID" is an identification number used to uniquely identify a purchase request within the database.

[0466] "Recording means" refers to a mechanism or program for saving the details of a purchase request in a database.

[0467] "Acquisition method" refers to the process or program used to retrieve a specific purchase request from a database.

[0468] "Evaluation method" refers to the process of analyzing the content of purchase requests using artificial intelligence tools and evaluating their validity.

[0469] A "determination method" refers to a process or program used to determine whether or not to approve a purchase request based on the evaluation results.

[0470] A "notification mechanism" is a mechanism or program that informs the user if a purchase request is invalid.

[0471] This invention relates to a system for effectively managing purchase requests and automating the approval process. The system includes a user terminal, a server for processing and storing data, and an artificial intelligence tool for evaluating purchase requests. Specific embodiments of the invention are described below.

[0472] System Configuration

[0473] The user terminal has an interface for entering purchase requests. The user uses a dedicated application or web browser to enter details of the required products (e.g., name, quantity, budget) into a form and presses the submit button. This information is sent to the server in real time.

[0474] The server has the function of saving received purchase requests to a database. Each request is assigned a unique request ID, which is recorded in the database. The server uses a SQL database or similar to efficiently store and retrieve data.

[0475] The server then retrieves new purchase requests from the database and passes the data to an artificial intelligence tool. The AI ​​tool evaluates the validity of the purchase request based on its price, specifications, and past purchase history. This evaluation uses machine learning algorithms such as random forests and neural networks.

[0476] The evaluation results returned by the artificial intelligence tool are again stored in the database by the server. These results include flags indicating whether the purchase request is valid and detailed evaluation information.

[0477] Next, the server determines the validity of the request based on the evaluation results. If the evaluation results are deemed valid, the server skips the pre-purchase review and approves the direct payment request. In this case, the user receives a notification that it has been approved. On the other hand, if the evaluation results are deemed invalid, the server notifies the user of the need for pre-purchase review, displaying the message "Needs Pre-purchase Approval".

[0478] Specific example

[0479] For example, let's specifically describe the flow when a user requests the purchase of a new computer (e.g., a laptop):

[0480] 1. The user enters a purchase request for a "laptop (specs: 16GB RAM, 512GB SSD, 13-inch)" from their terminal and presses the submit button. This sends the request to the server.

[0481] 2. The server saves this request in the database and generates a request ID (e.g., ID 101).

[0482] 3. The server retrieves the details of request ID 101 from the database and passes the data to the artificial intelligence tool. The artificial intelligence tool evaluates the validity of this request by comparing it with past purchase history and returns a "yes" or "no" flag.

[0483] 4. The server saves the evaluation results to the database and updates the status of the corresponding request.

[0484] 5. If the evaluation result is "yes," the server approves the payment request and notifies the user with "Approved." If the evaluation result is "no," the server notifies the user with "Needs Pre-purchase Approval."

[0485] In this way, the system streamlines purchasing operations within companies and organizations by conducting the assessment and approval process of purchase requests efficiently and fairly.

[0486] Specific examples of input prompts for generative AI models

[0487] When requesting a system description from a generative AI model, you can use prompt statements like the following:

[0488] "Please describe in detail a system that automates the processing of purchase requests within a company. Explain the specific steps involved in how this system uses artificial intelligence to evaluate the validity of requests and expedite the approval process."

[0489] This prompt allows you to obtain a detailed and specific system description from the generated AI model.

[0490] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0491] Step 1:

[0492] The user enters a purchase request using a terminal. The user enters detailed information such as the name of the item to be purchased, quantity, desired delivery date, and budget into a form in a dedicated application or web browser, and then presses the submit button. The input data includes specific request details, and the terminal sends this information to the server.

[0493] Input: Detailed information of the purchase request entered by the user (name, quantity, desired delivery date, budget).

[0494] Output: Sending purchase request data from the terminal to the server.

[0495] Step 2:

[0496] The server saves purchase requests received from terminals to a database. When saving, it generates a unique request ID for each purchase request and saves it along with the request information. Specifically, it adds data to the SQL database using an INSERT statement.

[0497] Input: Purchase request data sent from the terminal.

[0498] Output: Save purchase request information to the database and generate a request ID.

[0499] Step 3:

[0500] The server retrieves new purchase requests from the database. Specifically, it searches for requests with a status of "pending" using an SQL query and retrieves their detailed information. For example, it executes a query like SELECT FROM purchase_requests WHERE status = 'pending'.

[0501] Input: Purchase request information stored in the database.

[0502] Output: Retrieved purchase request information.

[0503] Step 4:

[0504] The server passes the acquired purchase request information to an artificial intelligence tool for evaluation. This evaluation uses data such as past purchase history, price, and specifications. The artificial intelligence tool calculates the validity of the purchase request using machine learning algorithms such as random forests and neural networks.

[0505] Input: Purchase request information provided by the server, as well as past purchase history, price, and specification data.

[0506] Output: Validity results of purchase requests evaluated by an artificial intelligence tool.

[0507] Step 5:

[0508] The server stores the evaluation results returned by the artificial intelligence tool in a database. The evaluation results include flags indicating the validity of the purchase request and evaluation details. Saving is performed using an SQL statement such as UPDATE purchase_requests SET ai_result = 'result', is_approved = 'yes / no' WHERE purchase_request_id = 'id'.

[0509] Input: Evaluation results provided by an artificial intelligence tool.

[0510] Output: Saving evaluation results to the database.

[0511] Step 6:

[0512] The server determines the validity of the purchase request based on the stored evaluation results. Specifically, it checks the `is_approved` flag in the evaluation results. If the flag is "yes", it skips the pre-purchase review and approves the direct payment request. If the flag is "no", it notifies the server that a pre-purchase review is necessary.

[0513] Input: Evaluation results stored in the database.

[0514] Output: Approval of purchase request or notification of the need for pre-purchase review.

[0515] Step 7:

[0516] The server sends a notification to the user based on the decision. The notification will include messages such as "Approved" if the purchase request is approved, or "Needs Pre-purchase Approval" if pre-purchase review is required. The notification will be sent via email or the company's internal messaging system.

[0517] Input: Approval or pre-purchase review decision result.

[0518] Output: Sending a notification to the user.

[0519] In this way, this system can efficiently evaluate and approve purchase requests, enabling faster progress in purchasing operations within a company.

[0520] (Application Example 1)

[0521] 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."

[0522] Many factories face problems with time-consuming purchasing request processing and inefficient pre-purchase consultation and payment approval processes. Furthermore, manual verification processes are cumbersome and can lack consistency and objectivity in decision-making. This results in wasted costs and time, leading to decreased operational efficiency.

[0523] 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.

[0524] In this invention, the server includes means for obtaining purchase requests from a database, means for assessing the obtained purchase requests using an artificial intelligence tool, means for storing the assessment results in the database, means for determining whether the assessment results are appropriate, means for skipping pre-purchase consultation and approving the payment request if it is determined to be appropriate, means for notifying the need for pre-purchase consultation if it is not appropriate, means for receiving input of purchase requests from factory robots within the factory, and means for rapidly processing the assessment results by the factory robots. As a result, the processing of purchase requests is accelerated, enabling improved operational efficiency and cost reduction.

[0525] A "purchase request" refers to a request to buy goods or services needed within a factory.

[0526] A "database" is an organized collection used to store, search, and manage information such as purchase requests and appraisal results.

[0527] An "artificial intelligence tool" is software or hardware that evaluates the validity of a purchase request based on factors such as price, specifications, and past purchase history.

[0528] "Assessment result" refers to the judgment made after the validity of a purchase request has been evaluated by an artificial intelligence tool.

[0529] A "factory robot" refers to a machine or device that automatically processes requests for the purchase of goods or services within a factory.

[0530] "Prior purchase consultation" refers to the necessary approval process that takes place in advance of a purchase request.

[0531] "Payment approval process" refers to the payment procedure carried out after a purchase request has been approved.

[0532] "Terminal" refers to input devices such as computers and tablets used by operators within a factory.

[0533] This invention relates to a system for efficiently processing purchase requests within a factory. The system aims to expedite the approval process by automating the assessment of purchase requests using artificial intelligence and skipping pre-purchase consultations as needed.

[0534] System Overview

[0535] This system consists of the following main components:

[0536] 1. Terminal

[0537] These are input devices such as computers and tablets used by operators within a factory, and they provide an input interface for purchase requests.

[0538] 2. Server

[0539] It plays a central role in acquiring purchase requests, conducting AI-powered assessments, saving assessment results, determining their validity, and notifying users of the need for payment approval or pre-purchase consultation.

[0540] 3. Artificial Intelligence Tools

[0541] This software automatically assesses purchase requests and evaluates their validity. It makes its determination based on factors such as price, specifications, and past purchase history.

[0542] Program processing and detailed description

[0543] Retrieving purchase requests

[0544] The user, acting as an operator within the factory, enters a purchase request from a terminal. Specifically, they enter details such as the name, price, specifications, and quantity of the goods or services they wish to purchase. The server retrieves this request from the database. For example, it searches the database using the purchase request ID and retrieves the corresponding request.

[0545] Purchase request assessment

[0546] The server passes the acquired purchase request details to an artificial intelligence tool for assessment. The AI ​​tool evaluates the validity of the request based on data such as price, specifications, and past purchase history. This makes it possible to quickly and objectively determine the appropriateness of the purchase request.

[0547] Saving of assessment results

[0548] The server stores the assessment results from the artificial intelligence tool in a database. These assessment results are stored appropriately as they may be used for reference later.

[0549] Assessment results and next steps

[0550] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result. If it is deemed valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the server that a pre-purchase consultation is required.

[0551] Return of the payment approval result

[0552] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[0553] Hardware and software to be used

[0554] Hardware:

[0555] Tablets and dedicated terminals installed on factory robots.

[0556] software:

[0557] An artificial intelligence tool using Python, pandas, and the scikit-learn library.

[0558] Specific example

[0559] For example, if an operator wants to purchase a new machine tool, they would enter the following into a terminal in the factory:

[0560] "I would like to purchase a new machine tool. The price is 500,000 yen, the specifications are CNC 5-axis, and the quantity is 1 unit."

[0561] This system receives the request, performs an assessment based on past data, and returns either an "Approved" or "Needs Pre-purchase Approval" result. Through this specific example, applying the system of the present invention to factory robots not only streamlines the purchasing process within the factory but also enables quick and objective decision-making.

[0562] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0563] Step 1:

[0564] Users enter purchase requests using terminals within the factory. The information entered includes the name of the item or service, price, specifications, and quantity. This input data is sent to a server, which stores the received data in a database.

[0565] Step 2:

[0566] The server retrieves newly saved purchase requests from the database. Based on identification information such as the ID used for retrieval, it extracts detailed information about the associated purchase requests. The retrieved data is used in the next processing step.

[0567] Step 3:

[0568] The server passes the acquired purchase request data to an artificial intelligence tool for assessment. Specifically, the AI ​​model evaluates the validity of the purchase based on data such as price, specifications, and past purchase history. Price, specifications, and past data are provided as input data, and the AI ​​model outputs the evaluation result of the validity.

[0569] Step 4:

[0570] The server saves the assessment results generated by the artificial intelligence tool back into the database. This makes it possible to reuse the assessment results in the future. When saving the data, appropriate identification information (such as a purchase request ID) is used.

[0571] Step 5:

[0572] The server determines whether the saved assessment results are valid. Specifically, it checks the status of the "is_approved" flag included in the assessment results. Depending on whether the flag indicates "valid" or "not valid," the next action is determined accordingly.

[0573] Step 6:

[0574] If the server determines that the assessment results are reasonable, it skips the pre-purchase consultation and proceeds with approving the payment request. It returns an "Approved" result as the final outcome, completing the process. This expedites the purchasing process.

[0575] Step 7:

[0576] If the server determines that the assessment result is unsatisfactory, it will notify the user that pre-purchase consultation is required. This notification will include a result of "Needs Pre-purchase Approval" and will proceed to another pre-purchase consultation step. The notification will be displayed on the device.

[0577] In this way, the roles of the server, terminal, and user are clearly defined in each processing step, ensuring that purchase requests are processed quickly and efficiently.

[0578] 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.

[0579] This invention relates to a system for streamlining the payment approval process within companies and organizations. In particular, it automates the assessment of purchase requests using artificial intelligence, combines this with an emotion engine that recognizes user emotions, and skips pre-purchase consultations as needed, thereby enabling rapid approval processing.

[0580] System Overview

[0581] This system consists of the following main components:

[0582] 1. User terminal (terminal): An interface for users to input purchase requests and their emotional information at that time.

[0583] 2. Server: Has the central functions of acquiring purchase requests, conducting assessments using artificial intelligence and emotion engines, saving assessment results, determining appropriateness, and notifying of the need for payment approval or pre-purchase consultation.

[0584] 3. Artificial intelligence tools: Software for automatically assessing purchase requests and evaluating their validity.

[0585] 4. Emotion Engine: Software that recognizes emotions from user input and reflects the analysis results in the assessment of purchase requests.

[0586] Program processing

[0587] Retrieving purchase requests

[0588] The user enters a purchase request for a new computer or other device from their terminal, and also provides emotional information (e.g., text message, voice input) along with the request. The server retrieves this request and emotional information from its database.

[0589] Purchase request assessment

[0590] The server passes the acquired purchase request content and emotional information to the artificial intelligence tool and emotion engine for assessment. The artificial intelligence tool evaluates the appropriateness based on price, specifications, past purchase history, etc. Meanwhile, the emotion engine analyzes the emotional information and identifies the user's emotional state (e.g., urgency, reassurance, anxiety, etc.).

[0591] Saving of assessment results

[0592] The server stores assessment results from artificial intelligence tools and emotion engines in a database. These assessment results are stored appropriately as they will be used later for reference.

[0593] Assessment results and next steps

[0594] The server determines whether the assessment results received from the artificial intelligence tools and the sentiment engine are valid. Specifically, it comprehensively evaluates the "is_approved" flag in the assessment results and the sentiment analysis results. If it is determined to be valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the user that a pre-purchase consultation is required.

[0595] Return of the payment approval result

[0596] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[0597] Specific example

[0598] For example, suppose a user wants to buy a new computer. In that case, the following flow would be executed:

[0599] 1. The user enters a request to purchase a new computer from their device, and at the same time, includes the emotional information "I need this urgently" as a text message.

[0600] 2. The server retrieves the purchase request and sentiment information from the database.

[0601] 3. The server passes the acquired requests to artificial intelligence tools and an emotion engine for assessment.

[0602] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[0603] 5. The emotion engine analyzes the emotional information provided by the user and evaluates the user's emotional state (in this case, "urgency").

[0604] 6. The server stores the assessment results from the artificial intelligence tools and emotion engine in a database.

[0605] 7. The server evaluates the assessment results, and if deemed appropriate, it skips the pre-purchase consultation and approves the payment request, returning "Approved" as the final result. If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[0606] In this way, the system of the present invention can streamline the pre-purchase consultation process and enable rapid payment approval processing that takes user sentiment into consideration.

[0607] The following describes the processing flow.

[0608] Step 1:

[0609] A user enters a request to purchase a new computer via a terminal. At the same time, the user sends emotional information (for example, a message such as "I need this urgently").

[0610] Step 2:

[0611] The server retrieves purchase requests and sentiment information sent by users from the database. Specifically, it searches the database using the purchase request ID (e.g., purchase_request_id) and retrieves the corresponding request and sentiment information.

[0612] Step 3:

[0613] The server separates the acquired purchase request from the sentiment information, passes the purchase request content to an artificial intelligence tool, and passes the sentiment information to the sentiment engine.

[0614] Step 4:

[0615] The artificial intelligence tool assesses the content of the provided purchase request. Specifically, it evaluates the following items:

[0616] Comparison with market price

[0617] Compatibility of specifications and specs

[0618] Comparison with past similar purchase history

[0619] Step 5:

[0620] The emotion engine analyzes the provided emotional information and evaluates the user's emotional state (e.g., "urgency" or "sense of security"). An emotion recognition algorithm is used to ensure accurate analysis results.

[0621] Step 6:

[0622] The server retrieves evaluation results obtained from artificial intelligence tools and emotion engines.

[0623] Step 7:

[0624] The server stores the assessment results of the artificial intelligence tool and the evaluation results of the emotion engine in a database. This ensures that each evaluation result is accurately recorded so that it can be referenced in the future.

[0625] Step 8:

[0626] The server determines whether the assessment results are valid. This determination includes the "is_approved" flag from the artificial intelligence tool and the evaluation results from the sentiment engine.

[0627] Step 9:

[0628] If the "is_approved" flag is true and the sentiment engine's analysis results support the need for purchase, the server skips the pre-purchase consultation and proceeds directly to approving the payment request. In this case, it returns the result "Approved".

[0629] Step 10:

[0630] If the "is_approved" flag is false, or if the sentiment engine's analysis does not support the need for purchase, the server will notify the server of the need for pre-purchase consultation. In this case, it will return the result "Needs Pre-purchase Approval".

[0631] The above steps enable efficient assessment and approval of purchase requests. By considering user sentiment information, it becomes possible to more accurately evaluate the appropriateness and urgency of purchases, thereby improving the speed and reliability of the entire process.

[0632] (Example 2)

[0633] 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".

[0634] The approval process for purchase requests within companies and organizations is often manual, which can lead to delays in decision-making and errors. Furthermore, because it proceeds formally without considering user emotions or urgency, it fails to respond quickly to urgent requests. Traditional systems lacked effective solutions to these problems.

[0635] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring purchase requests and sentiment information from a database, means for assessing the acquired purchase requests and sentiment information using an artificial intelligence tool and a sentiment engine, and means for storing the assessment results in the database. This makes it possible to comprehensively judge the validity of purchase requests and the emotional state of the user, and to quickly approve payment requests when prior consultation on purchases is not required.

[0636] A "purchase request" is an application submitted by a user to purchase a specific product or service.

[0637] "Emotional information" refers to data that indicates a user's emotional state, and is expressed through text messages, voice input, and other means.

[0638] A "database" is a system that centrally stores and manages data such as purchase requests, sentiment information, and appraisal results.

[0639] An "artificial intelligence tool" is software that uses machine learning algorithms and data analysis techniques to evaluate the validity of purchase requests.

[0640] An "emotion engine" is software that analyzes emotional information provided by the user and recognizes and evaluates that emotional state.

[0641] "Assessment results" refer to information regarding the validity and emotional state of a purchase request, as evaluated by artificial intelligence tools and an emotion engine.

[0642] "Pre-purchase consultation" refers to the detailed review and discussion process that takes place before a purchase request is approved.

[0643] A "payment approval request" is an approval process related to the payment procedures for expenses that are carried out after a purchase request has been finally approved.

[0644] A "server" is a central computer system that retrieves, analyzes, stores, and evaluates purchase requests.

[0645] A "terminal" is a device used by a user to input purchase requests or emotional information, and includes computers, smartphones, and other similar devices.

[0646] This invention relates to a system for streamlining the payment approval process within companies and organizations.

[0647] System Configuration

[0648] This system consists of the following main components:

[0649] 1. User terminal (terminal)

[0650] An interface for users to input purchase requests and sentiment information. Specifically, this includes devices such as computers and smartphones.

[0651] 2. Server

[0652] It has central functions for acquiring purchase requests, assessing them using artificial intelligence tools and an emotion engine, saving assessment results, determining their validity, and notifying users of the need for payment approval or pre-purchase consultation.

[0653] 3. Artificial Intelligence Tools

[0654] Software that automatically assesses purchase requests and evaluates their validity. Specifically, it operates using machine learning algorithms and data analysis techniques.

[0655] 4. Emotional Engine

[0656] Software that recognizes emotions from user input and uses the analysis results to assess purchase requests. It includes text and voice analysis algorithms.

[0657] Detailed explanation of the program's processing

[0658] Retrieving purchase requests

[0659] The user enters a purchase request for a new computer or other item from their terminal, and also provides emotional information (e.g., text message, voice input) along with the request. The server retrieves this request and emotional information from its database. The data is transmitted and stored in JSON format or another appropriate data format.

[0660] Purchase request assessment

[0661] The server passes the acquired purchase request content and sentiment information to artificial intelligence tools and sentiment engines for assessment. The artificial intelligence tools evaluate the validity based on price, specifications, past purchase history, etc. Meanwhile, the sentiment engine analyzes the sentiment information and identifies the user's emotional state (e.g., urgency, reassurance, anxiety). Machine learning models and natural language processing (NLP) algorithms are used in this process.

[0662] Saving of assessment results

[0663] The server stores assessment results from artificial intelligence tools and emotion engines in a database. The retrieved results are written to the database in JSON format or another appropriate data format and used later for reference.

[0664] Evaluation and determination of assessment results

[0665] The server determines whether the assessment results received from the artificial intelligence tools and the sentiment engine are valid. Specifically, it decides whether the request can be approved based on the "is_approved" flag and the sentiment analysis results.

[0666] Notification of the result of the payment approval request

[0667] The server will either approve the payment request based on the final evaluation, or notify the user that pre-purchase consultation is required. If approved, it will send an "Approved" result to the user's terminal, and the process will be complete. If not approved, it will send a "Needs Pre-purchase Approval" result, and request pre-purchase consultation.

[0668] Specific example

[0669] For example, if a user wants to buy a new computer, the following steps are taken:

[0670] 1. The user enters a request to purchase a new computer from their device, and at the same time, includes the emotional information "I need this urgently" as a text message.

[0671] 2. The server retrieves the purchase request and sentiment information from the database.

[0672] 3. The server passes the acquired requests to artificial intelligence tools and an emotion engine for assessment.

[0673] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[0674] 5. The emotion engine analyzes the emotional information provided by the user and evaluates the user's emotional state (in this case, "urgency").

[0675] 6. The server stores the assessment results from the artificial intelligence tools and emotion engine in a database.

[0676] 7. The server evaluates the assessment results and, if deemed appropriate, approves the payment request and returns "Approved". If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[0677] Example of a prompt:

[0678] "I have submitted a request to purchase a new computer. I need it urgently. Please use an AI tool to evaluate its feasibility, taking into account my past purchase history, current price, and specifications. Also, please use an emotion engine to analyze my emotional information and make a final decision on payment approval."

[0679] In this way, the system of the present invention can streamline the pre-purchase consultation process and enable rapid payment approval processing that takes user sentiment into consideration.

[0680] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0681] Step 1: The user enters a purchase request and sentiment information into the terminal.

[0682] The user uses a terminal to enter a purchase request (e.g., a desire to purchase a new computer) and sentiment information (e.g., a text message saying "I need this urgently"). The entered data is sent to the server when the user presses the submit button.

[0683] Input: Purchase request, sentiment information

[0684] Output: Sending request data

[0685] Step 2: The server receives the purchase request and sentiment information and stores it in the database.

[0686] The server receives purchase requests and sentiment information sent by users. The received data is converted to JSON format or an appropriate data format and stored in the database.

[0687] Input: User request data

[0688] Output: Saving data to the database

[0689] Step 3: The server retrieves and processes the request data from the database.

[0690] The server retrieves purchase requests and sentiment information from the database and processes it into a data format for passing to artificial intelligence tools and sentiment engines. Specifically, it converts the data into the appropriate JSON format.

[0691] Input: Request data from the database

[0692] Output: Processed data

[0693] Step 4: The server passes the request data to the AI ​​tool and emotion engine and requests an assessment.

[0694] The server passes the processed data to an artificial intelligence tool and an emotion engine. The AI ​​tool evaluates the validity of the purchase request based on price, specifications, and past purchase history, while the emotion engine analyzes emotional information to determine the user's urgency and stress level.

[0695] Input: Processed data

[0696] Output: Assessment results from AI tools and emotion engine

[0697] Step 5: The server saves the assessment results to the database.

[0698] The server stores assessment results received from artificial intelligence tools and emotion engines in a database. This stored data is then used for future processing and reference.

[0699] Input: Assessment result

[0700] Output: Save to database

[0701] Step 6: The server evaluates the assessment results and determines their validity.

[0702] The server refers to the assessment results stored in the database and comprehensively evaluates their validity. In particular, it decides whether to approve or reject the purchase request based on the "is_approved" flag and the sentiment analysis results.

[0703] Input: Assessment results from the database

[0704] Output: Evaluation result (Approval / Rejection)

[0705] Step 7: The server notifies the user of the approval result.

[0706] Based on the final evaluation, the server will either approve the payment request or notify the user that pre-purchase consultation is required. If approved, it will return "Approved"; if not approved, it will return "Needs Pre-purchase Approval" and notify the user's terminal.

[0707] Input: Evaluation result

[0708] Output: Notification to user terminal

[0709] (Application Example 2)

[0710] 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."

[0711] Traditional purchasing approval systems failed to adequately consider user emotions and urgency when evaluating the validity of purchase requests. As a result, even highly urgent purchase requests could experience delays, potentially disrupting business operations. Furthermore, the inability to provide personalized content recommendations that reflected user emotions made improving user satisfaction difficult.

[0712] 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. In this invention, the server includes means for acquiring purchase requests from a database, means for evaluating the acquired purchase requests using an artificial intelligence tool, means for storing the evaluation results in a database, means including an emotion engine that acquires and analyzes user emotion information, and means for determining the urgency and priority of purchase requests based on emotion information and reflecting this in the evaluation. This enables rapid approval processing that takes into account the urgency of purchase requests and user emotions. Furthermore, it is possible to recommend the most suitable content based on user viewing requests and emotion information, thereby improving user satisfaction.

[0713] A "purchase request" refers to a request or application submitted by a user when they wish to purchase a new product or service.

[0714] A "database" is a repository of information that stores information in an efficient and organized manner, making it easy to search and retrieve.

[0715] An "artificial intelligence tool" is a computer program that uses technologies such as machine learning and neural networks to analyze data and make predictions and judgments.

[0716] "Assessment" is the process of evaluating and judging the validity and appropriateness of a purchase request.

[0717] "Emotional information" refers to data that represents a user's psychological state and emotions, and is obtained from sources such as text, voice, and facial expressions.

[0718] An "emotion engine" is software that analyzes a user's emotional information and identifies their emotional state.

[0719] "Urgency" refers to the degree to which a particular purchase request or task is urgent.

[0720] "Priority" is an indicator that shows which of several tasks or requests is more important than others.

[0721] A "pre-purchase consultation" is a meeting or discussion held to confirm necessary information and conditions before formally approving a purchase request.

[0722] "Rin-gi" refers to the process of seeking approval or decision-making within a company, and often specifically refers to the approval process for payments.

[0723] "Assessment results" refer to the results after evaluating the validity and urgency of a purchase request using artificial intelligence tools and emotion engines.

[0724] "Relevance" is an evaluation criterion that indicates whether a purchase request is feasible and conforms to the company's policies and standards.

[0725] "Recommendation" refers to suggesting the most suitable products or services based on the user's past behavior, preferences, and emotional information.

[0726] "Viewing trend data" refers to data that shows information about user and market viewing trends and popular content.

[0727] To implement this invention, the following system configuration and processing flow are used. The system consists of a user terminal, a server, an artificial intelligence tool, an emotion engine, and a database. The specific hardware used is a smartphone, smart glasses, and a server, and the software includes a user interface, an artificial intelligence tool (e.g., TensorFlow, PyTorch), and an emotion engine (e.g., Emotion API, Facial Recognition API).

[0728] System components

[0729] User terminal

[0730] The user terminal consists of a smartphone or smart glasses and provides an interface for users to input emotional information and content viewing requests. This ensures smooth user operation.

[0731] server

[0732] The server plays a central role in the system, retrieving purchase requests and sentiment information from the database and analyzing them using artificial intelligence tools and a sentiment engine. The analysis results are then evaluated again by the server and stored in the database. Furthermore, based on the results, it either notifies the customer of the need for pre-purchase consultation or approves the payment request.

[0733] Artificial intelligence tools

[0734] Artificial intelligence tools are software that evaluates the validity of purchase requests. They analyze and evaluate requests based on price, specifications, past purchase history, and viewing trend data. Specifically, they use TensorFlow and PyTorch to build machine learning models and make purchase requests and content recommendations.

[0735] Emotional Engine

[0736] An emotion engine is software that analyzes a user's emotional information. It analyzes text messages and voice data acquired from the device to identify the user's emotional state. For example, the Emotion API and Facial Recognition API are used for emotion analysis.

[0737] database

[0738] The database is an information management system for storing purchase requests, sentiment information, analysis results, past purchase and viewing history, and viewing trend data. This makes the data available for later analysis and reference.

[0739] Add specific examples to the description.

[0740] Examples of content recommendations

[0741] For example, a user might type "I want to watch a relaxing movie" on their smartphone and also voice-input "I'm a little tired." The server passes this information to an artificial intelligence tool and an emotion engine for analysis. The AI ​​tool analyzes past viewing history and trends in relaxing movies, while the emotion engine determines the user's emotions from the voice input "I'm a little tired." Finally, the server recommends and notifies the user of the most suitable content.

[0742] Examples of prompts for generative AI models

[0743] The following are examples of prompts for a generative AI model:

[0744] Point down

[0745] A user types "I want to watch a relaxing movie" on their smartphone and also voice-inputs "I'm a little tired." An emotion engine analyzes the user's voice information, and an artificial intelligence tool recommends the most suitable content based on past viewing history and trends in relaxing movies. What models or APIs should I use to achieve this?

[0746] By implementing this invention, personalized content recommendations that take into account the user's emotions and past viewing history become possible, which is expected to improve user satisfaction. Furthermore, rapid processing of purchase requests can also be achieved simultaneously.

[0747] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0748] Step 1:

[0749] Users use their smartphones or smart glasses to input viewing requests and emotional information. Specifically, they launch the application and input text such as "I want to watch a relaxing movie" and voice information such as "I'm a little tired." The input data is stored on the device and sent to the server.

[0750] Step 2:

[0751] The server retrieves the received viewing requests and sentiment information from the database. Specifically, data sent to the server in the form of "purchase requests" and "sentiment information" retrieves information from the database and passes it on to the next processing step.

[0752] Step 3:

[0753] The server passes the content of the acquired viewing request to an artificial intelligence tool, and then passes the emotional information to an emotion engine. The artificial intelligence tool uses past viewing history and viewing trend data to analyze the data and evaluate the validity of the request and recommend content. The emotion engine analyzes the emotional state from the audio data and derives the result "slightly tired."

[0754] Step 4:

[0755] The server integrates analysis results from artificial intelligence tools and an emotion engine. Specifically, it combines a list of relaxing movies recommended by the AI ​​tool with the user's emotional state analyzed by the emotion engine to select the most suitable content. For example, it selects the content with the highest "relaxation level" and "viewing recommendation level" from the list of relaxing movies.

[0756] Step 5:

[0757] The server notifies the user of the most suitable content it has selected. Specifically, it sends a message to the user's device saying, "Here is the best movie for you: XXXXX," along with a link to view the content.

[0758] Step 6:

[0759] Users can start watching by checking the notification they receive and clicking the provided link. This makes it easy for users to watch the relaxing movie they want.

[0760] The specific flow and processing steps enable personalized content recommendations based on user viewing requests and sentiment information.

[0761] 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.

[0762] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One 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.

[0763] 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.

[0764] [Third Embodiment]

[0765] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0766] 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.

[0767] 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).

[0768] 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.

[0769] 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.

[0770] 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).

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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".

[0777] This invention relates to a system for streamlining the payment approval process within companies and organizations. This system automates the assessment of purchase requests using artificial intelligence and, when necessary, skips pre-purchase consultations, thereby accelerating the approval process.

[0778] System Overview

[0779] This system consists of the following main components:

[0780] 1. User terminal (terminal): An interface for users to enter purchase requests.

[0781] 2. Server: This server has the central functions of acquiring purchase requests, performing AI-based assessments, saving assessment results, determining appropriateness, and notifying users of the need for payment approval or pre-purchase consultation.

[0782] 3. Artificial intelligence tools: Software for automatically assessing purchase requests and evaluating their validity.

[0783] Program processing

[0784] Retrieving purchase requests

[0785] The user enters a purchase request for a computer or other item from their terminal. The server retrieves this request from the database. For example, it searches the database using the purchase request ID (purchase_request_id) and retrieves the corresponding request.

[0786] Purchase request assessment

[0787] The server passes the acquired purchase request details to an artificial intelligence tool for assessment. The AI ​​tool evaluates the validity of the request based on price, specifications, past purchase history, and other factors. This makes it possible to quickly and objectively determine the appropriateness of the purchase request.

[0788] Saving of assessment results

[0789] The server stores the assessment results from the artificial intelligence tool in a database. These assessment results are stored appropriately as they may be used for reference later.

[0790] Assessment results and next steps

[0791] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result. If it is deemed valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the server that a pre-purchase consultation is required.

[0792] Return of the payment approval result

[0793] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[0794] Specific example

[0795] For example, suppose a user wants to buy a new computer. In that case, the following flow would be executed:

[0796] 1. The user enters a request to purchase a new computer from their device.

[0797] 2. The server retrieves the purchase request from the database.

[0798] 3. The server passes the acquired requests to an artificial intelligence tool for assessment.

[0799] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[0800] 5. The server saves the assessment results from the artificial intelligence tool to the database.

[0801] 6. The server evaluates the assessment results and, if deemed appropriate, skips the pre-purchase consultation and approves the payment request, returning "Approved" as the final result. If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[0802] In this way, the system of the present invention can streamline the pre-purchase consultation process and expedite the processing of payment approval requests.

[0803] The following describes the processing flow.

[0804] Step 1:

[0805] The user enters a request to purchase a new computer from their device.

[0806] Step 2:

[0807] The server retrieves purchase requests submitted by users from the database. Specifically, it searches the database using the purchase request ID (e.g., purchase_request_id) and retrieves the corresponding requests.

[0808] Step 3:

[0809] The server passes the acquired purchase request details to the artificial intelligence tool. At this time, it provides the AI ​​tool with detailed information about the purchase request (price, specifications, quantity, etc.).

[0810] Step 4:

[0811] The artificial intelligence tool performs an assessment based on the provided purchase request information. Specifically, it evaluates the following items:

[0812] Comparison with market price

[0813] Compatibility of specifications and specs

[0814] Comparison with past similar purchase history

[0815] Step 5:

[0816] The server receives the assessment results from the artificial intelligence tool. It is expected that the assessment results will be returned in JSON format or other data formats, as is typical.

[0817] Step 6:

[0818] The server saves the received assessment results to a database. This data is stored in an appropriate format so that it can be referenced later.

[0819] Step 7:

[0820] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result.

[0821] Step 8:

[0822] If the "is_approved" flag is true, the server skips the pre-purchase consultation and proceeds directly to approving the payment request. Specifically, it triggers the purchase approval flow in its internal system, which returns "Approved" as a result.

[0823] Step 9:

[0824] If the "is_approved" flag is false, the server will notify that pre-purchase consultation is necessary. In this case, it will send a message to the purchasing officer or relevant department stating "Needs Pre-purchase Approval".

[0825] The above steps ensure efficient assessment and approval of purchase requests. If pre-purchase consultations can be skipped, the overall process speed increases significantly, improving operational efficiency.

[0826] (Example 1)

[0827] 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."

[0828] The purchasing approval process within companies and organizations often requires manual evaluation and consultation, which is time-consuming and labor-intensive. Furthermore, unclear evaluation criteria create a risk of erroneous approvals or rejections based on subjective judgments. There is a need to resolve these issues and achieve a swift and fair purchasing approval process.

[0829] 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.

[0830] In this invention, the server includes means for recording the details of a purchase request, means for retrieving the recorded purchase request from a database, means for evaluating the retrieved purchase request using an artificial intelligence tool, means for storing the evaluation results in a database, means for determining whether the evaluation results are valid, means for skipping the pre-purchase review and completing the approval process if the results are deemed valid, and means for notifying the server of the need for a pre-purchase review if the results are not valid. This automates the evaluation and approval process of purchase requests, enabling them to be processed quickly and fairly.

[0831] A "purchase request" is a request document that includes details of a desire to purchase goods or services.

[0832] A "database" is a digital information repository used to systematically store purchase requests and related information.

[0833] An "artificial intelligence tool" is a program or algorithm that uses machine learning and data analysis techniques to automatically evaluate the content of a purchase request.

[0834] "Evaluation results" refer to information indicating the validity and appropriateness of a purchase request, calculated by an artificial intelligence tool.

[0835] A "Request ID" is an identification number used to uniquely identify a purchase request within the database.

[0836] "Recording means" refers to a mechanism or program for saving the details of a purchase request in a database.

[0837] "Acquisition method" refers to the process or program used to retrieve a specific purchase request from a database.

[0838] "Evaluation method" refers to the process of analyzing the content of purchase requests using artificial intelligence tools and evaluating their validity.

[0839] A "determination method" refers to a process or program used to determine whether or not to approve a purchase request based on the evaluation results.

[0840] A "notification mechanism" is a mechanism or program that informs the user if a purchase request is invalid.

[0841] This invention relates to a system for effectively managing purchase requests and automating the approval process. The system includes a user terminal, a server for processing and storing data, and an artificial intelligence tool for evaluating purchase requests. Specific embodiments of the invention are described below.

[0842] System Configuration

[0843] The user terminal has an interface for entering purchase requests. The user uses a dedicated application or web browser to enter details of the required products (e.g., name, quantity, budget) into a form and presses the submit button. This information is sent to the server in real time.

[0844] The server has the function of saving received purchase requests to a database. Each request is assigned a unique request ID, which is recorded in the database. The server uses a SQL database or similar to efficiently store and retrieve data.

[0845] The server then retrieves new purchase requests from the database and passes the data to an artificial intelligence tool. The AI ​​tool evaluates the validity of the purchase request based on its price, specifications, and past purchase history. This evaluation uses machine learning algorithms such as random forests and neural networks.

[0846] The evaluation results returned by the artificial intelligence tool are again stored in the database by the server. These results include flags indicating whether the purchase request is valid and detailed evaluation information.

[0847] Next, the server determines the validity of the request based on the evaluation results. If the evaluation results are deemed valid, the server skips the pre-purchase review and approves the direct payment request. In this case, the user receives a notification that it has been approved. On the other hand, if the evaluation results are deemed invalid, the server notifies the user of the need for pre-purchase review, displaying the message "Needs Pre-purchase Approval".

[0848] Specific example

[0849] For example, let's specifically describe the flow when a user requests the purchase of a new computer (e.g., a laptop):

[0850] 1. The user enters a purchase request for a "laptop (specs: 16GB RAM, 512GB SSD, 13-inch)" from their terminal and presses the submit button. This sends the request to the server.

[0851] 2. The server saves this request in the database and generates a request ID (e.g., ID 101).

[0852] 3. The server retrieves the details of request ID 101 from the database and passes the data to the artificial intelligence tool. The artificial intelligence tool evaluates the validity of this request by comparing it with past purchase history and returns a "yes" or "no" flag.

[0853] 4. The server saves the evaluation results to the database and updates the status of the corresponding request.

[0854] 5. If the evaluation result is "yes," the server approves the payment request and notifies the user with "Approved." If the evaluation result is "no," the server notifies the user with "Needs Pre-purchase Approval."

[0855] In this way, the system streamlines purchasing operations within companies and organizations by conducting the assessment and approval process of purchase requests efficiently and fairly.

[0856] Specific examples of input prompts for generative AI models

[0857] When requesting a system description from a generative AI model, you can use prompt statements like the following:

[0858] "Please describe in detail a system that automates the processing of purchase requests within a company. Explain the specific steps involved in how this system uses artificial intelligence to evaluate the validity of requests and expedite the approval process."

[0859] This prompt allows you to obtain a detailed and specific system description from the generated AI model.

[0860] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0861] Step 1:

[0862] The user enters a purchase request using a terminal. The user enters detailed information such as the name of the item to be purchased, quantity, desired delivery date, and budget into a form in a dedicated application or web browser, and then presses the submit button. The input data includes specific request details, and the terminal sends this information to the server.

[0863] Input: Detailed information of the purchase request entered by the user (name, quantity, desired delivery date, budget).

[0864] Output: Sending purchase request data from the terminal to the server.

[0865] Step 2:

[0866] The server saves purchase requests received from terminals to a database. When saving, it generates a unique request ID for each purchase request and saves it along with the request information. Specifically, it adds data to the SQL database using an INSERT statement.

[0867] Input: Purchase request data sent from the terminal.

[0868] Output: Save purchase request information to the database and generate a request ID.

[0869] Step 3:

[0870] The server retrieves new purchase requests from the database. Specifically, it searches for requests with a status of "pending" using an SQL query and retrieves their detailed information. For example, it executes a query like SELECT FROM purchase_requests WHERE status = 'pending'.

[0871] Input: Purchase request information stored in the database.

[0872] Output: Retrieved purchase request information.

[0873] Step 4:

[0874] The server passes the acquired purchase request information to an artificial intelligence tool for evaluation. This evaluation uses data such as past purchase history, price, and specifications. The artificial intelligence tool calculates the validity of the purchase request using machine learning algorithms such as random forests and neural networks.

[0875] Input: Purchase request information provided by the server, as well as past purchase history, price, and specification data.

[0876] Output: Validity results of purchase requests evaluated by an artificial intelligence tool.

[0877] Step 5:

[0878] The server stores the evaluation results returned by the artificial intelligence tool in a database. The evaluation results include flags indicating the validity of the purchase request and evaluation details. Saving is performed using an SQL statement such as UPDATE purchase_requests SET ai_result = 'result', is_approved = 'yes / no' WHERE purchase_request_id = 'id'.

[0879] Input: Evaluation results provided by an artificial intelligence tool.

[0880] Output: Saving evaluation results to the database.

[0881] Step 6:

[0882] The server determines the validity of the purchase request based on the stored evaluation results. Specifically, it checks the `is_approved` flag in the evaluation results. If the flag is "yes", it skips the pre-purchase review and approves the direct payment request. If the flag is "no", it notifies the server that a pre-purchase review is necessary.

[0883] Input: Evaluation results stored in the database.

[0884] Output: Approval of purchase request or notification of the need for pre-purchase review.

[0885] Step 7:

[0886] The server sends a notification to the user based on the decision. The notification will include messages such as "Approved" if the purchase request is approved, or "Needs Pre-purchase Approval" if pre-purchase review is required. The notification will be sent via email or the company's internal messaging system.

[0887] Input: Approval or pre-purchase review decision result.

[0888] Output: Sending a notification to the user.

[0889] In this way, this system can efficiently evaluate and approve purchase requests, enabling faster progress in purchasing operations within a company.

[0890] (Application Example 1)

[0891] 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."

[0892] Many factories face problems with time-consuming purchasing request processing and inefficient pre-purchase consultation and payment approval processes. Furthermore, manual verification processes are cumbersome and can lack consistency and objectivity in decision-making. This results in wasted costs and time, leading to decreased operational efficiency.

[0893] 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.

[0894] In this invention, the server includes means for obtaining purchase requests from a database, means for assessing the obtained purchase requests using an artificial intelligence tool, means for storing the assessment results in the database, means for determining whether the assessment results are appropriate, means for skipping pre-purchase consultation and approving the payment request if it is determined to be appropriate, means for notifying the need for pre-purchase consultation if it is not appropriate, means for receiving input of purchase requests from factory robots within the factory, and means for rapidly processing the assessment results by the factory robots. As a result, the processing of purchase requests is accelerated, enabling improved operational efficiency and cost reduction.

[0895] A "purchase request" refers to a request to buy goods or services needed within a factory.

[0896] A "database" is an organized collection used to store, search, and manage information such as purchase requests and appraisal results.

[0897] An "artificial intelligence tool" is software or hardware that evaluates the validity of a purchase request based on factors such as price, specifications, and past purchase history.

[0898] "Assessment result" refers to the judgment made after the validity of a purchase request has been evaluated by an artificial intelligence tool.

[0899] A "factory robot" refers to a machine or device that automatically processes requests for the purchase of goods or services within a factory.

[0900] "Prior purchase consultation" refers to the necessary approval process that takes place in advance of a purchase request.

[0901] "Payment approval process" refers to the payment procedure carried out after a purchase request has been approved.

[0902] "Terminal" refers to input devices such as computers and tablets used by operators within a factory.

[0903] This invention relates to a system for efficiently processing purchase requests within a factory. The system aims to expedite the approval process by automating the assessment of purchase requests using artificial intelligence and skipping pre-purchase consultations as needed.

[0904] System Overview

[0905] This system consists of the following main components:

[0906] 1. Terminal

[0907] These are input devices such as computers and tablets used by operators within a factory, and they provide an input interface for purchase requests.

[0908] 2. Server

[0909] It plays a central role in acquiring purchase requests, conducting AI-powered assessments, saving assessment results, determining their validity, and notifying users of the need for payment approval or pre-purchase consultation.

[0910] 3. Artificial Intelligence Tools

[0911] This software automatically assesses purchase requests and evaluates their validity. It makes its determination based on factors such as price, specifications, and past purchase history.

[0912] Program processing and detailed description

[0913] Retrieving purchase requests

[0914] The user, acting as an operator within the factory, enters a purchase request from a terminal. Specifically, they enter details such as the name, price, specifications, and quantity of the goods or services they wish to purchase. The server retrieves this request from the database. For example, it searches the database using the purchase request ID and retrieves the corresponding request.

[0915] Purchase request assessment

[0916] The server passes the acquired purchase request details to an artificial intelligence tool for assessment. The AI ​​tool evaluates the validity of the request based on data such as price, specifications, and past purchase history. This makes it possible to quickly and objectively determine the appropriateness of the purchase request.

[0917] Saving of assessment results

[0918] The server stores the assessment results from the artificial intelligence tool in a database. These assessment results are stored appropriately as they may be used for reference later.

[0919] Assessment results and next steps

[0920] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result. If it is deemed valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the server that a pre-purchase consultation is required.

[0921] Return of the payment approval result

[0922] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[0923] Hardware and software to be used

[0924] Hardware:

[0925] Tablets and dedicated terminals installed on factory robots.

[0926] software:

[0927] An artificial intelligence tool using Python, pandas, and the scikit-learn library.

[0928] Specific example

[0929] For example, if an operator wants to purchase a new machine tool, they would enter the following into a terminal in the factory:

[0930] "I would like to purchase a new machine tool. The price is 500,000 yen, the specifications are CNC 5-axis, and the quantity is 1 unit."

[0931] This system receives the request, performs an assessment based on past data, and returns either an "Approved" or "Needs Pre-purchase Approval" result. Through this specific example, applying the system of the present invention to factory robots not only streamlines the purchasing process within the factory but also enables quick and objective decision-making.

[0932] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0933] Step 1:

[0934] Users enter purchase requests using terminals within the factory. The information entered includes the name of the item or service, price, specifications, and quantity. This input data is sent to a server, which stores the received data in a database.

[0935] Step 2:

[0936] The server retrieves newly saved purchase requests from the database. Based on identification information such as the ID used for retrieval, it extracts detailed information about the associated purchase requests. The retrieved data is used in the next processing step.

[0937] Step 3:

[0938] The server passes the acquired purchase request data to an artificial intelligence tool for assessment. Specifically, the AI ​​model evaluates the validity of the purchase based on data such as price, specifications, and past purchase history. Price, specifications, and past data are provided as input data, and the AI ​​model outputs the evaluation result of the validity.

[0939] Step 4:

[0940] The server saves the assessment results generated by the artificial intelligence tool back into the database. This makes it possible to reuse the assessment results in the future. When saving the data, appropriate identification information (such as a purchase request ID) is used.

[0941] Step 5:

[0942] The server determines whether the saved assessment results are valid. Specifically, it checks the status of the "is_approved" flag included in the assessment results. Depending on whether the flag indicates "valid" or "not valid," the next action is determined accordingly.

[0943] Step 6:

[0944] If the server determines that the assessment results are reasonable, it skips the pre-purchase consultation and proceeds with approving the payment request. It returns an "Approved" result as the final outcome, completing the process. This expedites the purchasing process.

[0945] Step 7:

[0946] If the server determines that the assessment result is unsatisfactory, it will notify the user that pre-purchase consultation is required. This notification will include a result of "Needs Pre-purchase Approval" and will proceed to another pre-purchase consultation step. The notification will be displayed on the device.

[0947] In this way, the roles of the server, terminal, and user are clearly defined in each processing step, ensuring that purchase requests are processed quickly and efficiently.

[0948] 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.

[0949] This invention relates to a system for streamlining the payment approval process within companies and organizations. In particular, it automates the assessment of purchase requests using artificial intelligence, combines this with an emotion engine that recognizes user emotions, and skips pre-purchase consultations as needed, thereby enabling rapid approval processing.

[0950] System Overview

[0951] This system consists of the following main components:

[0952] 1. User terminal (terminal): An interface for users to input purchase requests and their emotional information at that time.

[0953] 2. Server: Has the central functions of acquiring purchase requests, conducting assessments using artificial intelligence and emotion engines, saving assessment results, determining appropriateness, and notifying of the need for payment approval or pre-purchase consultation.

[0954] 3. Artificial intelligence tools: Software for automatically assessing purchase requests and evaluating their validity.

[0955] 4. Emotion Engine: Software that recognizes emotions from user input and reflects the analysis results in the assessment of purchase requests.

[0956] Program processing

[0957] Retrieving purchase requests

[0958] The user enters a purchase request for a new computer or other device from their terminal, and also provides emotional information (e.g., text message, voice input) along with the request. The server retrieves this request and emotional information from its database.

[0959] Purchase request assessment

[0960] The server passes the acquired purchase request content and emotional information to the artificial intelligence tool and emotion engine for assessment. The artificial intelligence tool evaluates the appropriateness based on price, specifications, past purchase history, etc. Meanwhile, the emotion engine analyzes the emotional information and identifies the user's emotional state (e.g., urgency, reassurance, anxiety, etc.).

[0961] Saving of assessment results

[0962] The server stores assessment results from artificial intelligence tools and emotion engines in a database. These assessment results are stored appropriately as they will be used later for reference.

[0963] Assessment results and next steps

[0964] The server determines whether the assessment results received from the artificial intelligence tools and the sentiment engine are valid. Specifically, it comprehensively evaluates the "is_approved" flag in the assessment results and the sentiment analysis results. If it is determined to be valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the user that a pre-purchase consultation is required.

[0965] Return of the payment approval result

[0966] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[0967] Specific example

[0968] For example, suppose a user wants to buy a new computer. In that case, the following flow would be executed:

[0969] 1. The user enters a request to purchase a new computer from their device, and at the same time, includes the emotional information "I need this urgently" as a text message.

[0970] 2. The server retrieves the purchase request and sentiment information from the database.

[0971] 3. The server passes the acquired requests to artificial intelligence tools and an emotion engine for assessment.

[0972] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[0973] 5. The emotion engine analyzes the emotional information provided by the user and evaluates the user's emotional state (in this case, "urgency").

[0974] 6. The server stores the assessment results from the artificial intelligence tools and emotion engine in a database.

[0975] 7. The server evaluates the assessment results, and if deemed appropriate, it skips the pre-purchase consultation and approves the payment request, returning "Approved" as the final result. If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[0976] In this way, the system of the present invention can streamline the pre-purchase consultation process and enable rapid payment approval processing that takes user sentiment into consideration.

[0977] The following describes the processing flow.

[0978] Step 1:

[0979] A user enters a request to purchase a new computer via a terminal. At the same time, the user sends emotional information (for example, a message such as "I need this urgently").

[0980] Step 2:

[0981] The server retrieves purchase requests and sentiment information sent by users from the database. Specifically, it searches the database using the purchase request ID (e.g., purchase_request_id) and retrieves the corresponding request and sentiment information.

[0982] Step 3:

[0983] The server separates the acquired purchase request from the sentiment information, passes the purchase request content to an artificial intelligence tool, and passes the sentiment information to the sentiment engine.

[0984] Step 4:

[0985] The artificial intelligence tool assesses the content of the provided purchase request. Specifically, it evaluates the following items:

[0986] Comparison with market price

[0987] Compatibility of specifications and specs

[0988] Comparison with past similar purchase history

[0989] Step 5:

[0990] The emotion engine analyzes the provided emotional information and evaluates the user's emotional state (e.g., "urgency" or "sense of security"). An emotion recognition algorithm is used to ensure accurate analysis results.

[0991] Step 6:

[0992] The server retrieves evaluation results obtained from artificial intelligence tools and emotion engines.

[0993] Step 7:

[0994] The server stores the assessment results of the artificial intelligence tool and the evaluation results of the emotion engine in a database. This ensures that each evaluation result is accurately recorded so that it can be referenced in the future.

[0995] Step 8:

[0996] The server determines whether the assessment results are valid. This determination includes the "is_approved" flag from the artificial intelligence tool and the evaluation results from the sentiment engine.

[0997] Step 9:

[0998] If the "is_approved" flag is true and the sentiment engine's analysis results support the need for purchase, the server skips the pre-purchase consultation and proceeds directly to approving the payment request. In this case, it returns the result "Approved".

[0999] Step 10:

[1000] If the "is_approved" flag is false, or if the sentiment engine's analysis does not support the need for purchase, the server will notify the server of the need for pre-purchase consultation. In this case, it will return the result "Needs Pre-purchase Approval".

[1001] The above steps enable efficient assessment and approval of purchase requests. By considering user sentiment information, it becomes possible to more accurately evaluate the appropriateness and urgency of purchases, thereby improving the speed and reliability of the entire process.

[1002] (Example 2)

[1003] 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."

[1004] The approval process for purchase requests within companies and organizations is often manual, which can lead to delays in decision-making and errors. Furthermore, because it proceeds formally without considering user emotions or urgency, it fails to respond quickly to urgent requests. Traditional systems lacked effective solutions to these problems.

[1005] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring purchase requests and sentiment information from a database, means for assessing the acquired purchase requests and sentiment information using an artificial intelligence tool and a sentiment engine, and means for storing the assessment results in the database. This makes it possible to comprehensively judge the validity of purchase requests and the emotional state of the user, and to quickly approve payment requests when prior consultation on purchases is not required.

[1006] A "purchase request" is an application submitted by a user to purchase a specific product or service.

[1007] "Emotional information" refers to data that indicates a user's emotional state, and is expressed through text messages, voice input, and other means.

[1008] A "database" is a system that centrally stores and manages data such as purchase requests, sentiment information, and appraisal results.

[1009] An "artificial intelligence tool" is software that uses machine learning algorithms and data analysis techniques to evaluate the validity of purchase requests.

[1010] An "emotion engine" is software that analyzes emotional information provided by the user and recognizes and evaluates that emotional state.

[1011] "Assessment results" refer to information regarding the validity and emotional state of a purchase request, as evaluated by artificial intelligence tools and an emotion engine.

[1012] "Pre-purchase consultation" refers to the detailed review and discussion process that takes place before a purchase request is approved.

[1013] A "payment approval request" is an approval process related to the payment procedures for expenses that are carried out after a purchase request has been finally approved.

[1014] A "server" is a central computer system that retrieves, analyzes, stores, and evaluates purchase requests.

[1015] A "terminal" is a device used by a user to input purchase requests or emotional information, and includes computers, smartphones, and other similar devices.

[1016] This invention relates to a system for streamlining the payment approval process within companies and organizations.

[1017] System Configuration

[1018] This system consists of the following main components:

[1019] 1. User terminal (terminal)

[1020] An interface for users to input purchase requests and sentiment information. Specifically, this includes devices such as computers and smartphones.

[1021] 2. Server

[1022] It has central functions for acquiring purchase requests, assessing them using artificial intelligence tools and an emotion engine, saving assessment results, determining their validity, and notifying users of the need for payment approval or pre-purchase consultation.

[1023] 3. Artificial Intelligence Tools

[1024] Software that automatically assesses purchase requests and evaluates their validity. Specifically, it operates using machine learning algorithms and data analysis techniques.

[1025] 4. Emotional Engine

[1026] Software that recognizes emotions from user input and uses the analysis results to assess purchase requests. It includes text and voice analysis algorithms.

[1027] Detailed explanation of the program's processing

[1028] Retrieving purchase requests

[1029] The user enters a purchase request for a new computer or other item from their terminal, and also provides emotional information (e.g., text message, voice input) along with the request. The server retrieves this request and emotional information from its database. The data is transmitted and stored in JSON format or another appropriate data format.

[1030] Purchase request assessment

[1031] The server passes the acquired purchase request content and sentiment information to artificial intelligence tools and sentiment engines for assessment. The artificial intelligence tools evaluate the validity based on price, specifications, past purchase history, etc. Meanwhile, the sentiment engine analyzes the sentiment information and identifies the user's emotional state (e.g., urgency, reassurance, anxiety). Machine learning models and natural language processing (NLP) algorithms are used in this process.

[1032] Saving of assessment results

[1033] The server stores assessment results from artificial intelligence tools and emotion engines in a database. The retrieved results are written to the database in JSON format or another appropriate data format and used later for reference.

[1034] Evaluation and determination of assessment results

[1035] The server determines whether the assessment results received from the artificial intelligence tools and the sentiment engine are valid. Specifically, it decides whether the request can be approved based on the "is_approved" flag and the sentiment analysis results.

[1036] Notification of the result of the payment approval request

[1037] The server will either approve the payment request based on the final evaluation, or notify the user that pre-purchase consultation is required. If approved, it will send an "Approved" result to the user's terminal, and the process will be complete. If not approved, it will send a "Needs Pre-purchase Approval" result, and request pre-purchase consultation.

[1038] Specific example

[1039] For example, if a user wants to buy a new computer, the following steps are taken:

[1040] 1. The user enters a request to purchase a new computer from their device, and at the same time, includes the emotional information "I need this urgently" as a text message.

[1041] 2. The server retrieves the purchase request and sentiment information from the database.

[1042] 3. The server passes the acquired requests to artificial intelligence tools and an emotion engine for assessment.

[1043] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[1044] 5. The emotion engine analyzes the emotional information provided by the user and evaluates the user's emotional state (in this case, "urgency").

[1045] 6. The server stores the assessment results from the artificial intelligence tools and emotion engine in a database.

[1046] 7. The server evaluates the assessment results and, if deemed appropriate, approves the payment request and returns "Approved". If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[1047] Example of a prompt:

[1048] "I have submitted a request to purchase a new computer. I need it urgently. Please use an AI tool to evaluate its feasibility, taking into account my past purchase history, current price, and specifications. Also, please use an emotion engine to analyze my emotional information and make a final decision on payment approval."

[1049] In this way, the system of the present invention can streamline the pre-purchase consultation process and enable rapid payment approval processing that takes user sentiment into consideration.

[1050] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1051] Step 1: The user enters a purchase request and sentiment information into the terminal.

[1052] The user uses a terminal to enter a purchase request (e.g., a desire to purchase a new computer) and sentiment information (e.g., a text message saying "I need this urgently"). The entered data is sent to the server when the user presses the submit button.

[1053] Input: Purchase request, sentiment information

[1054] Output: Sending request data

[1055] Step 2: The server receives the purchase request and sentiment information and stores it in the database.

[1056] The server receives purchase requests and sentiment information sent by users. The received data is converted to JSON format or an appropriate data format and stored in the database.

[1057] Input: User request data

[1058] Output: Saving data to the database

[1059] Step 3: The server retrieves and processes the request data from the database.

[1060] The server retrieves purchase requests and sentiment information from the database and processes it into a data format for passing to artificial intelligence tools and sentiment engines. Specifically, it converts the data into the appropriate JSON format.

[1061] Input: Request data from the database

[1062] Output: Processed data

[1063] Step 4: The server passes the request data to the AI ​​tool and emotion engine and requests an assessment.

[1064] The server passes the processed data to an artificial intelligence tool and an emotion engine. The AI ​​tool evaluates the validity of the purchase request based on price, specifications, and past purchase history, while the emotion engine analyzes emotional information to determine the user's urgency and stress level.

[1065] Input: Processed data

[1066] Output: Assessment results from AI tools and emotion engine

[1067] Step 5: The server saves the assessment results to the database.

[1068] The server stores assessment results received from artificial intelligence tools and emotion engines in a database. This stored data is then used for future processing and reference.

[1069] Input: Assessment result

[1070] Output: Save to database

[1071] Step 6: The server evaluates the assessment results and determines their validity.

[1072] The server refers to the assessment results stored in the database and comprehensively evaluates their validity. In particular, it decides whether to approve or reject the purchase request based on the "is_approved" flag and the sentiment analysis results.

[1073] Input: Assessment results from the database

[1074] Output: Evaluation result (Approval / Rejection)

[1075] Step 7: The server notifies the user of the approval result.

[1076] Based on the final evaluation, the server will either approve the payment request or notify the user that pre-purchase consultation is required. If approved, it will return "Approved"; if not approved, it will return "Needs Pre-purchase Approval" and notify the user's terminal.

[1077] Input: Evaluation result

[1078] Output: Notification to user terminal

[1079] (Application Example 2)

[1080] 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."

[1081] Traditional purchasing approval systems failed to adequately consider user emotions and urgency when evaluating the validity of purchase requests. As a result, even highly urgent purchase requests could experience delays, potentially disrupting business operations. Furthermore, the inability to provide personalized content recommendations that reflected user emotions made improving user satisfaction difficult.

[1082] 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. In this invention, the server includes means for acquiring purchase requests from a database, means for evaluating the acquired purchase requests using an artificial intelligence tool, means for storing the evaluation results in a database, means including an emotion engine that acquires and analyzes user emotion information, and means for determining the urgency and priority of purchase requests based on emotion information and reflecting this in the evaluation. This enables rapid approval processing that takes into account the urgency of purchase requests and user emotions. Furthermore, it is possible to recommend the most suitable content based on user viewing requests and emotion information, thereby improving user satisfaction.

[1083] A "purchase request" refers to a request or application submitted by a user when they wish to purchase a new product or service.

[1084] A "database" is a repository of information that stores information in an efficient and organized manner, making it easy to search and retrieve.

[1085] An "artificial intelligence tool" is a computer program that uses technologies such as machine learning and neural networks to analyze data and make predictions and judgments.

[1086] "Assessment" is the process of evaluating and judging the validity and appropriateness of a purchase request.

[1087] "Emotional information" refers to data that represents a user's psychological state and emotions, and is obtained from sources such as text, voice, and facial expressions.

[1088] An "emotion engine" is software that analyzes a user's emotional information and identifies their emotional state.

[1089] "Urgency" refers to the degree to which a particular purchase request or task is urgent.

[1090] "Priority" is an indicator that shows which of several tasks or requests is more important than others.

[1091] A "pre-purchase consultation" is a meeting or discussion held to confirm necessary information and conditions before formally approving a purchase request.

[1092] "Rin-gi" refers to the process of seeking approval or decision-making within a company, and often specifically refers to the approval process for payments.

[1093] "Assessment results" refer to the results after evaluating the validity and urgency of a purchase request using artificial intelligence tools and emotion engines.

[1094] "Relevance" is an evaluation criterion that indicates whether a purchase request is feasible and conforms to the company's policies and standards.

[1095] "Recommendation" refers to suggesting the most suitable products or services based on the user's past behavior, preferences, and emotional information.

[1096] "Viewing trend data" refers to data that shows information about user and market viewing trends and popular content.

[1097] To implement this invention, the following system configuration and processing flow are used. The system consists of a user terminal, a server, an artificial intelligence tool, an emotion engine, and a database. The specific hardware used is a smartphone, smart glasses, and a server, and the software includes a user interface, an artificial intelligence tool (e.g., TensorFlow, PyTorch), and an emotion engine (e.g., Emotion API, Facial Recognition API).

[1098] System components

[1099] User terminal

[1100] The user terminal consists of a smartphone or smart glasses and provides an interface for users to input emotional information and content viewing requests. This ensures smooth user operation.

[1101] server

[1102] The server plays a central role in the system, retrieving purchase requests and sentiment information from the database and analyzing them using artificial intelligence tools and a sentiment engine. The analysis results are then evaluated again by the server and stored in the database. Furthermore, based on the results, it either notifies the customer of the need for pre-purchase consultation or approves the payment request.

[1103] Artificial intelligence tools

[1104] Artificial intelligence tools are software that evaluates the validity of purchase requests. They analyze and evaluate requests based on price, specifications, past purchase history, and viewing trend data. Specifically, they use TensorFlow and PyTorch to build machine learning models and make purchase requests and content recommendations.

[1105] Emotional Engine

[1106] An emotion engine is software that analyzes a user's emotional information. It analyzes text messages and voice data acquired from the device to identify the user's emotional state. For example, the Emotion API and Facial Recognition API are used for emotion analysis.

[1107] database

[1108] The database is an information management system for storing purchase requests, sentiment information, analysis results, past purchase and viewing history, and viewing trend data. This makes the data available for later analysis and reference.

[1109] Add specific examples to the description.

[1110] Examples of content recommendations

[1111] For example, a user might type "I want to watch a relaxing movie" on their smartphone and also voice-input "I'm a little tired." The server passes this information to an artificial intelligence tool and an emotion engine for analysis. The AI ​​tool analyzes past viewing history and trends in relaxing movies, while the emotion engine determines the user's emotions from the voice input "I'm a little tired." Finally, the server recommends and notifies the user of the most suitable content.

[1112] Examples of prompts for generative AI models

[1113] The following are examples of prompts for a generative AI model:

[1114] Point down

[1115] A user types "I want to watch a relaxing movie" on their smartphone and also voice-inputs "I'm a little tired." An emotion engine analyzes the user's voice information, and an artificial intelligence tool recommends the most suitable content based on past viewing history and trends in relaxing movies. What models or APIs should I use to achieve this?

[1116] By implementing this invention, personalized content recommendations that take into account the user's emotions and past viewing history become possible, which is expected to improve user satisfaction. Furthermore, rapid processing of purchase requests can also be achieved simultaneously.

[1117] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1118] Step 1:

[1119] Users use their smartphones or smart glasses to input viewing requests and emotional information. Specifically, they launch the application and input text such as "I want to watch a relaxing movie" and voice information such as "I'm a little tired." The input data is stored on the device and sent to the server.

[1120] Step 2:

[1121] The server retrieves the received viewing requests and sentiment information from the database. Specifically, data sent to the server in the form of "purchase requests" and "sentiment information" retrieves information from the database and passes it on to the next processing step.

[1122] Step 3:

[1123] The server passes the content of the acquired viewing request to an artificial intelligence tool, and then passes the emotional information to an emotion engine. The artificial intelligence tool uses past viewing history and viewing trend data to analyze the data and evaluate the validity of the request and recommend content. The emotion engine analyzes the emotional state from the audio data and derives the result "slightly tired."

[1124] Step 4:

[1125] The server integrates analysis results from artificial intelligence tools and an emotion engine. Specifically, it combines a list of relaxing movies recommended by the AI ​​tool with the user's emotional state analyzed by the emotion engine to select the most suitable content. For example, it selects the content with the highest "relaxation level" and "viewing recommendation level" from the list of relaxing movies.

[1126] Step 5:

[1127] The server notifies the user of the most suitable content it has selected. Specifically, it sends a message to the user's device saying, "Here is the best movie for you: XXXXX," along with a link to view the content.

[1128] Step 6:

[1129] Users can start watching by checking the notification they receive and clicking the provided link. This makes it easy for users to watch the relaxing movie they want.

[1130] The specific flow and processing steps enable personalized content recommendations based on user viewing requests and sentiment information.

[1131] 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.

[1132] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One 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.

[1133] 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.

[1134] [Fourth Embodiment]

[1135] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1136] 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.

[1137] 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).

[1138] 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.

[1139] 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.

[1140] 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).

[1141] 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.

[1142] 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.

[1143] 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.

[1144] 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.

[1145] 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.

[1146] 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.

[1147] 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".

[1148] This invention relates to a system for streamlining the payment approval process within companies and organizations. This system automates the assessment of purchase requests using artificial intelligence and, when necessary, skips pre-purchase consultations, thereby accelerating the approval process.

[1149] System Overview

[1150] This system consists of the following main components:

[1151] 1. User terminal (terminal): An interface for users to enter purchase requests.

[1152] 2. Server: This server has the central functions of acquiring purchase requests, performing AI-based assessments, saving assessment results, determining appropriateness, and notifying users of the need for payment approval or pre-purchase consultation.

[1153] 3. Artificial intelligence tools: Software for automatically assessing purchase requests and evaluating their validity.

[1154] Program processing

[1155] Retrieving purchase requests

[1156] The user enters a purchase request for a computer or other item from their terminal. The server retrieves this request from the database. For example, it searches the database using the purchase request ID (purchase_request_id) and retrieves the corresponding request.

[1157] Purchase request assessment

[1158] The server passes the acquired purchase request details to an artificial intelligence tool for assessment. The AI ​​tool evaluates the validity of the request based on price, specifications, past purchase history, and other factors. This makes it possible to quickly and objectively determine the appropriateness of the purchase request.

[1159] Saving of assessment results

[1160] The server stores the assessment results from the artificial intelligence tool in a database. These assessment results are stored appropriately as they may be used for reference later.

[1161] Assessment results and next steps

[1162] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result. If it is deemed valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the server that a pre-purchase consultation is required.

[1163] Return of the payment approval result

[1164] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[1165] Specific example

[1166] For example, suppose a user wants to buy a new computer. In that case, the following flow would be executed:

[1167] 1. The user enters a request to purchase a new computer from their device.

[1168] 2. The server retrieves the purchase request from the database.

[1169] 3. The server passes the acquired requests to an artificial intelligence tool for assessment.

[1170] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[1171] 5. The server saves the assessment results from the artificial intelligence tool to the database.

[1172] 6. The server evaluates the assessment results and, if deemed appropriate, skips the pre-purchase consultation and approves the payment request, returning "Approved" as the final result. If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[1173] In this way, the system of the present invention can streamline the pre-purchase consultation process and expedite the processing of payment approval requests.

[1174] The following describes the processing flow.

[1175] Step 1:

[1176] The user enters a request to purchase a new computer from their device.

[1177] Step 2:

[1178] The server retrieves purchase requests submitted by users from the database. Specifically, it searches the database using the purchase request ID (e.g., purchase_request_id) and retrieves the corresponding requests.

[1179] Step 3:

[1180] The server passes the acquired purchase request details to the artificial intelligence tool. At this time, it provides the AI ​​tool with detailed information about the purchase request (price, specifications, quantity, etc.).

[1181] Step 4:

[1182] The artificial intelligence tool performs an assessment based on the provided purchase request information. Specifically, it evaluates the following items:

[1183] Comparison with market price

[1184] Compatibility of specifications and specs

[1185] Comparison with past similar purchase history

[1186] Step 5:

[1187] The server receives the assessment results from the artificial intelligence tool. It is expected that the assessment results will be returned in JSON format or other data formats, as is typical.

[1188] Step 6:

[1189] The server saves the received assessment results to a database. This data is stored in an appropriate format so that it can be referenced later.

[1190] Step 7:

[1191] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result.

[1192] Step 8:

[1193] If the "is_approved" flag is true, the server skips the pre-purchase consultation and proceeds directly to approving the payment request. Specifically, it triggers the purchase approval flow in its internal system, which returns "Approved" as a result.

[1194] Step 9:

[1195] If the "is_approved" flag is false, the server will notify that pre-purchase consultation is necessary. In this case, it will send a message to the purchasing officer or relevant department stating "Needs Pre-purchase Approval".

[1196] The above steps ensure efficient assessment and approval of purchase requests. If pre-purchase consultations can be skipped, the overall process speed increases significantly, improving operational efficiency.

[1197] (Example 1)

[1198] 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".

[1199] The purchasing approval process within companies and organizations often requires manual evaluation and consultation, which is time-consuming and labor-intensive. Furthermore, unclear evaluation criteria create a risk of erroneous approvals or rejections based on subjective judgments. There is a need to resolve these issues and achieve a swift and fair purchasing approval process.

[1200] 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.

[1201] In this invention, the server includes means for recording the details of a purchase request, means for retrieving the recorded purchase request from a database, means for evaluating the retrieved purchase request using an artificial intelligence tool, means for storing the evaluation results in a database, means for determining whether the evaluation results are valid, means for skipping the pre-purchase review and completing the approval process if the results are deemed valid, and means for notifying the server of the need for a pre-purchase review if the results are not valid. This automates the evaluation and approval process of purchase requests, enabling them to be processed quickly and fairly.

[1202] A "purchase request" is a request document that includes details of a desire to purchase goods or services.

[1203] A "database" is a digital information repository used to systematically store purchase requests and related information.

[1204] An "artificial intelligence tool" is a program or algorithm that uses machine learning and data analysis techniques to automatically evaluate the content of a purchase request.

[1205] "Evaluation results" refer to information indicating the validity and appropriateness of a purchase request, calculated by an artificial intelligence tool.

[1206] A "Request ID" is an identification number used to uniquely identify a purchase request within the database.

[1207] "Recording means" refers to a mechanism or program for saving the details of a purchase request in a database.

[1208] "Acquisition method" refers to the process or program used to retrieve a specific purchase request from a database.

[1209] "Evaluation method" refers to the process of analyzing the content of purchase requests using artificial intelligence tools and evaluating their validity.

[1210] A "determination method" refers to a process or program used to determine whether or not to approve a purchase request based on the evaluation results.

[1211] A "notification mechanism" is a mechanism or program that informs the user if a purchase request is invalid.

[1212] This invention relates to a system for effectively managing purchase requests and automating the approval process. The system includes a user terminal, a server for processing and storing data, and an artificial intelligence tool for evaluating purchase requests. Specific embodiments of the invention are described below.

[1213] System Configuration

[1214] The user terminal has an interface for entering purchase requests. The user uses a dedicated application or web browser to enter details of the required products (e.g., name, quantity, budget) into a form and presses the submit button. This information is sent to the server in real time.

[1215] The server has the function of saving received purchase requests to a database. Each request is assigned a unique request ID, which is recorded in the database. The server uses a SQL database or similar to efficiently store and retrieve data.

[1216] The server then retrieves new purchase requests from the database and passes the data to an artificial intelligence tool. The AI ​​tool evaluates the validity of the purchase request based on its price, specifications, and past purchase history. This evaluation uses machine learning algorithms such as random forests and neural networks.

[1217] The evaluation results returned by the artificial intelligence tool are again stored in the database by the server. These results include flags indicating whether the purchase request is valid and detailed evaluation information.

[1218] Next, the server determines the validity of the request based on the evaluation results. If the evaluation results are deemed valid, the server skips the pre-purchase review and approves the direct payment request. In this case, the user receives a notification that it has been approved. On the other hand, if the evaluation results are deemed invalid, the server notifies the user of the need for pre-purchase review, displaying the message "Needs Pre-purchase Approval".

[1219] Specific example

[1220] For example, let's specifically describe the flow when a user requests the purchase of a new computer (e.g., a laptop):

[1221] 1. The user enters a purchase request for a "laptop (specs: 16GB RAM, 512GB SSD, 13-inch)" from their terminal and presses the submit button. This sends the request to the server.

[1222] 2. The server saves this request in the database and generates a request ID (e.g., ID 101).

[1223] 3. The server retrieves the details of request ID 101 from the database and passes the data to the artificial intelligence tool. The artificial intelligence tool evaluates the validity of this request by comparing it with past purchase history and returns a "yes" or "no" flag.

[1224] 4. The server saves the evaluation results to the database and updates the status of the corresponding request.

[1225] 5. If the evaluation result is "yes," the server approves the payment request and notifies the user with "Approved." If the evaluation result is "no," the server notifies the user with "Needs Pre-purchase Approval."

[1226] In this way, the system streamlines purchasing operations within companies and organizations by conducting the assessment and approval process of purchase requests efficiently and fairly.

[1227] Specific examples of input prompts for generative AI models

[1228] When requesting a system description from a generative AI model, you can use prompt statements like the following:

[1229] "Please describe in detail a system that automates the processing of purchase requests within a company. Explain the specific steps involved in how this system uses artificial intelligence to evaluate the validity of requests and expedite the approval process."

[1230] This prompt allows you to obtain a detailed and specific system description from the generated AI model.

[1231] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1232] Step 1:

[1233] The user enters a purchase request using a terminal. The user enters detailed information such as the name of the item to be purchased, quantity, desired delivery date, and budget into a form in a dedicated application or web browser, and then presses the submit button. The input data includes specific request details, and the terminal sends this information to the server.

[1234] Input: Detailed information of the purchase request entered by the user (name, quantity, desired delivery date, budget).

[1235] Output: Sending purchase request data from the terminal to the server.

[1236] Step 2:

[1237] The server saves purchase requests received from terminals to a database. When saving, it generates a unique request ID for each purchase request and saves it along with the request information. Specifically, it adds data to the SQL database using an INSERT statement.

[1238] Input: Purchase request data sent from the terminal.

[1239] Output: Save purchase request information to the database and generate a request ID.

[1240] Step 3:

[1241] The server retrieves new purchase requests from the database. Specifically, it searches for requests with a status of "pending" using an SQL query and retrieves their detailed information. For example, it executes a query like SELECT FROM purchase_requests WHERE status = 'pending'.

[1242] Input: Purchase request information stored in the database.

[1243] Output: Retrieved purchase request information.

[1244] Step 4:

[1245] The server passes the acquired purchase request information to an artificial intelligence tool for evaluation. This evaluation uses data such as past purchase history, price, and specifications. The artificial intelligence tool calculates the validity of the purchase request using machine learning algorithms such as random forests and neural networks.

[1246] Input: Purchase request information provided by the server, as well as past purchase history, price, and specification data.

[1247] Output: Validity results of purchase requests evaluated by an artificial intelligence tool.

[1248] Step 5:

[1249] The server stores the evaluation results returned by the artificial intelligence tool in a database. The evaluation results include flags indicating the validity of the purchase request and evaluation details. Saving is performed using an SQL statement such as UPDATE purchase_requests SET ai_result = 'result', is_approved = 'yes / no' WHERE purchase_request_id = 'id'.

[1250] Input: Evaluation results provided by an artificial intelligence tool.

[1251] Output: Saving evaluation results to the database.

[1252] Step 6:

[1253] The server determines the validity of the purchase request based on the stored evaluation results. Specifically, it checks the `is_approved` flag in the evaluation results. If the flag is "yes", it skips the pre-purchase review and approves the direct payment request. If the flag is "no", it notifies the server that a pre-purchase review is necessary.

[1254] Input: Evaluation results stored in the database.

[1255] Output: Approval of purchase request or notification of the need for pre-purchase review.

[1256] Step 7:

[1257] The server sends a notification to the user based on the decision. The notification will include messages such as "Approved" if the purchase request is approved, or "Needs Pre-purchase Approval" if pre-purchase review is required. The notification will be sent via email or the company's internal messaging system.

[1258] Input: Approval or pre-purchase review decision result.

[1259] Output: Sending a notification to the user.

[1260] In this way, this system can efficiently evaluate and approve purchase requests, enabling faster progress in purchasing operations within a company.

[1261] (Application Example 1)

[1262] 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".

[1263] Many factories face problems with time-consuming purchasing request processing and inefficient pre-purchase consultation and payment approval processes. Furthermore, manual verification processes are cumbersome and can lack consistency and objectivity in decision-making. This results in wasted costs and time, leading to decreased operational efficiency.

[1264] 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.

[1265] In this invention, the server includes means for obtaining purchase requests from a database, means for assessing the obtained purchase requests using an artificial intelligence tool, means for storing the assessment results in the database, means for determining whether the assessment results are appropriate, means for skipping pre-purchase consultation and approving the payment request if it is determined to be appropriate, means for notifying the need for pre-purchase consultation if it is not appropriate, means for receiving input of purchase requests from factory robots within the factory, and means for rapidly processing the assessment results by the factory robots. As a result, the processing of purchase requests is accelerated, enabling improved operational efficiency and cost reduction.

[1266] A "purchase request" refers to a request to buy goods or services needed within a factory.

[1267] A "database" is an organized collection used to store, search, and manage information such as purchase requests and appraisal results.

[1268] An "artificial intelligence tool" is software or hardware that evaluates the validity of a purchase request based on factors such as price, specifications, and past purchase history.

[1269] "Assessment result" refers to the judgment made after the validity of a purchase request has been evaluated by an artificial intelligence tool.

[1270] A "factory robot" refers to a machine or device that automatically processes requests for the purchase of goods or services within a factory.

[1271] "Prior purchase consultation" refers to the necessary approval process that takes place in advance of a purchase request.

[1272] "Payment approval process" refers to the payment procedure carried out after a purchase request has been approved.

[1273] "Terminal" refers to input devices such as computers and tablets used by operators within a factory.

[1274] This invention relates to a system for efficiently processing purchase requests within a factory. The system aims to expedite the approval process by automating the assessment of purchase requests using artificial intelligence and skipping pre-purchase consultations as needed.

[1275] System Overview

[1276] This system consists of the following main components:

[1277] 1. Terminal

[1278] These are input devices such as computers and tablets used by operators within a factory, and they provide an input interface for purchase requests.

[1279] 2. Server

[1280] It plays a central role in acquiring purchase requests, conducting AI-powered assessments, saving assessment results, determining their validity, and notifying users of the need for payment approval or pre-purchase consultation.

[1281] 3. Artificial Intelligence Tools

[1282] This software automatically assesses purchase requests and evaluates their validity. It makes its determination based on factors such as price, specifications, and past purchase history.

[1283] Program processing and detailed description

[1284] Retrieving purchase requests

[1285] The user, acting as an operator within the factory, enters a purchase request from a terminal. Specifically, they enter details such as the name, price, specifications, and quantity of the goods or services they wish to purchase. The server retrieves this request from the database. For example, it searches the database using the purchase request ID and retrieves the corresponding request.

[1286] Purchase request assessment

[1287] The server passes the acquired purchase request details to an artificial intelligence tool for assessment. The AI ​​tool evaluates the validity of the request based on data such as price, specifications, and past purchase history. This makes it possible to quickly and objectively determine the appropriateness of the purchase request.

[1288] Saving of assessment results

[1289] The server stores the assessment results from the artificial intelligence tool in a database. These assessment results are stored appropriately as they may be used for reference later.

[1290] Assessment results and next steps

[1291] The server determines whether the assessment result is valid. Specifically, it checks the "is_approved" flag within the assessment result. If it is deemed valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the server that a pre-purchase consultation is required.

[1292] Return of the payment approval result

[1293] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[1294] Hardware and software to be used

[1295] Hardware:

[1296] Tablets and dedicated terminals installed on factory robots.

[1297] software:

[1298] An artificial intelligence tool using Python, pandas, and the scikit-learn library.

[1299] Specific example

[1300] For example, if an operator wants to purchase a new machine tool, they would enter the following into a terminal in the factory:

[1301] "I would like to purchase a new machine tool. The price is 500,000 yen, the specifications are CNC 5-axis, and the quantity is 1 unit."

[1302] This system receives the request, performs an assessment based on past data, and returns either an "Approved" or "Needs Pre-purchase Approval" result. Through this specific example, applying the system of the present invention to factory robots not only streamlines the purchasing process within the factory but also enables quick and objective decision-making.

[1303] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1304] Step 1:

[1305] Users enter purchase requests using terminals within the factory. The information entered includes the name of the item or service, price, specifications, and quantity. This input data is sent to a server, which stores the received data in a database.

[1306] Step 2:

[1307] The server retrieves newly saved purchase requests from the database. Based on identification information such as the ID used for retrieval, it extracts detailed information about the associated purchase requests. The retrieved data is used in the next processing step.

[1308] Step 3:

[1309] The server passes the acquired purchase request data to an artificial intelligence tool for assessment. Specifically, the AI ​​model evaluates the validity of the purchase based on data such as price, specifications, and past purchase history. Price, specifications, and past data are provided as input data, and the AI ​​model outputs the evaluation result of the validity.

[1310] Step 4:

[1311] The server saves the assessment results generated by the artificial intelligence tool back into the database. This makes it possible to reuse the assessment results in the future. When saving the data, appropriate identification information (such as a purchase request ID) is used.

[1312] Step 5:

[1313] The server determines whether the saved assessment results are valid. Specifically, it checks the status of the "is_approved" flag included in the assessment results. Depending on whether the flag indicates "valid" or "not valid," the next action is determined accordingly.

[1314] Step 6:

[1315] If the server determines that the assessment results are reasonable, it skips the pre-purchase consultation and proceeds with approving the payment request. It returns an "Approved" result as the final outcome, completing the process. This expedites the purchasing process.

[1316] Step 7:

[1317] If the server determines that the assessment result is unsatisfactory, it will notify the user that pre-purchase consultation is required. This notification will include a result of "Needs Pre-purchase Approval" and will proceed to another pre-purchase consultation step. The notification will be displayed on the device.

[1318] In this way, the roles of the server, terminal, and user are clearly defined in each processing step, ensuring that purchase requests are processed quickly and efficiently.

[1319] 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.

[1320] This invention relates to a system for streamlining the payment approval process within companies and organizations. In particular, it automates the assessment of purchase requests using artificial intelligence, combines this with an emotion engine that recognizes user emotions, and skips pre-purchase consultations as needed, thereby enabling rapid approval processing.

[1321] System Overview

[1322] This system consists of the following main components:

[1323] 1. User terminal (terminal): An interface for users to input purchase requests and their emotional information at that time.

[1324] 2. Server: Has the central functions of acquiring purchase requests, conducting assessments using artificial intelligence and emotion engines, saving assessment results, determining appropriateness, and notifying of the need for payment approval or pre-purchase consultation.

[1325] 3. Artificial intelligence tools: Software for automatically assessing purchase requests and evaluating their validity.

[1326] 4. Emotion Engine: Software that recognizes emotions from user input and reflects the analysis results in the assessment of purchase requests.

[1327] Program processing

[1328] Retrieving purchase requests

[1329] The user enters a purchase request for a new computer or other device from their terminal, and also provides emotional information (e.g., text message, voice input) along with the request. The server retrieves this request and emotional information from its database.

[1330] Purchase request assessment

[1331] The server passes the acquired purchase request content and emotional information to the artificial intelligence tool and emotion engine for assessment. The artificial intelligence tool evaluates the appropriateness based on price, specifications, past purchase history, etc. Meanwhile, the emotion engine analyzes the emotional information and identifies the user's emotional state (e.g., urgency, reassurance, anxiety, etc.).

[1332] Saving of assessment results

[1333] The server stores assessment results from artificial intelligence tools and emotion engines in a database. These assessment results are stored appropriately as they will be used later for reference.

[1334] Assessment results and next steps

[1335] The server determines whether the assessment results received from the artificial intelligence tools and the sentiment engine are valid. Specifically, it comprehensively evaluates the "is_approved" flag in the assessment results and the sentiment analysis results. If it is determined to be valid, it skips the pre-purchase consultation and proceeds to the process of directly approving the payment request. Conversely, if the result is not valid, it notifies the user that a pre-purchase consultation is required.

[1336] Return of the payment approval result

[1337] If the server determines that the assessment result is reasonable, it approves the payment request. In this case, it returns an "Approved" result and the process is complete. If it is not reasonable, it returns an "Needs Pre-purchase Approval" result and proceeds to another pre-purchase consultation step.

[1338] Specific example

[1339] For example, suppose a user wants to buy a new computer. In that case, the following flow would be executed:

[1340] 1. The user enters a request to purchase a new computer from their device, and at the same time, includes the emotional information "I need this urgently" as a text message.

[1341] 2. The server retrieves the purchase request and sentiment information from the database.

[1342] 3. The server passes the acquired requests to artificial intelligence tools and an emotion engine for assessment.

[1343] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[1344] 5. The emotion engine analyzes the emotional information provided by the user and evaluates the user's emotional state (in this case, "urgency").

[1345] 6. The server stores the assessment results from the artificial intelligence tools and emotion engine in a database.

[1346] 7. The server evaluates the assessment results, and if deemed appropriate, it skips the pre-purchase consultation and approves the payment request, returning "Approved" as the final result. If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[1347] In this way, the system of the present invention can streamline the pre-purchase consultation process and enable rapid payment approval processing that takes user sentiment into consideration.

[1348] The following describes the processing flow.

[1349] Step 1:

[1350] A user enters a request to purchase a new computer via a terminal. At the same time, the user sends emotional information (for example, a message such as "I need this urgently").

[1351] Step 2:

[1352] The server retrieves purchase requests and sentiment information sent by users from the database. Specifically, it searches the database using the purchase request ID (e.g., purchase_request_id) and retrieves the corresponding request and sentiment information.

[1353] Step 3:

[1354] The server separates the acquired purchase request from the sentiment information, passes the purchase request content to an artificial intelligence tool, and passes the sentiment information to the sentiment engine.

[1355] Step 4:

[1356] The artificial intelligence tool assesses the content of the provided purchase request. Specifically, it evaluates the following items:

[1357] Comparison with market price

[1358] Compatibility of specifications and specs

[1359] Comparison with past similar purchase history

[1360] Step 5:

[1361] The emotion engine analyzes the provided emotional information and evaluates the user's emotional state (e.g., "urgency" or "sense of security"). An emotion recognition algorithm is used to ensure accurate analysis results.

[1362] Step 6:

[1363] The server retrieves evaluation results obtained from artificial intelligence tools and emotion engines.

[1364] Step 7:

[1365] The server stores the assessment results of the artificial intelligence tool and the evaluation results of the emotion engine in a database. This ensures that each evaluation result is accurately recorded so that it can be referenced in the future.

[1366] Step 8:

[1367] The server determines whether the assessment results are valid. This determination includes the "is_approved" flag from the artificial intelligence tool and the evaluation results from the sentiment engine.

[1368] Step 9:

[1369] If the "is_approved" flag is true and the sentiment engine's analysis results support the need for purchase, the server skips the pre-purchase consultation and proceeds directly to approving the payment request. In this case, it returns the result "Approved".

[1370] Step 10:

[1371] If the "is_approved" flag is false, or if the sentiment engine's analysis does not support the need for purchase, the server will notify the server of the need for pre-purchase consultation. In this case, it will return the result "Needs Pre-purchase Approval".

[1372] The above steps enable efficient assessment and approval of purchase requests. By considering user sentiment information, it becomes possible to more accurately evaluate the appropriateness and urgency of purchases, thereby improving the speed and reliability of the entire process.

[1373] (Example 2)

[1374] 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".

[1375] The approval process for purchase requests within companies and organizations is often manual, which can lead to delays in decision-making and errors. Furthermore, because it proceeds formally without considering user emotions or urgency, it fails to respond quickly to urgent requests. Traditional systems lacked effective solutions to these problems.

[1376] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring purchase requests and sentiment information from a database, means for assessing the acquired purchase requests and sentiment information using an artificial intelligence tool and a sentiment engine, and means for storing the assessment results in the database. This makes it possible to comprehensively judge the validity of purchase requests and the emotional state of the user, and to quickly approve payment requests when prior consultation on purchases is not required.

[1377] A "purchase request" is an application submitted by a user to purchase a specific product or service.

[1378] "Emotional information" refers to data that indicates a user's emotional state, and is expressed through text messages, voice input, and other means.

[1379] A "database" is a system that centrally stores and manages data such as purchase requests, sentiment information, and appraisal results.

[1380] An "artificial intelligence tool" is software that uses machine learning algorithms and data analysis techniques to evaluate the validity of purchase requests.

[1381] An "emotion engine" is software that analyzes emotional information provided by the user and recognizes and evaluates that emotional state.

[1382] "Assessment results" refer to information regarding the validity and emotional state of a purchase request, as evaluated by artificial intelligence tools and an emotion engine.

[1383] "Pre-purchase consultation" refers to the detailed review and discussion process that takes place before a purchase request is approved.

[1384] A "payment approval request" is an approval process related to the payment procedures for expenses that are carried out after a purchase request has been finally approved.

[1385] A "server" is a central computer system that retrieves, analyzes, stores, and evaluates purchase requests.

[1386] A "terminal" is a device used by a user to input purchase requests or emotional information, and includes computers, smartphones, and other similar devices.

[1387] This invention relates to a system for streamlining the payment approval process within companies and organizations.

[1388] System Configuration

[1389] This system consists of the following main components:

[1390] 1. User terminal (terminal)

[1391] An interface for users to input purchase requests and sentiment information. Specifically, this includes devices such as computers and smartphones.

[1392] 2. Server

[1393] It has central functions for acquiring purchase requests, assessing them using artificial intelligence tools and an emotion engine, saving assessment results, determining their validity, and notifying users of the need for payment approval or pre-purchase consultation.

[1394] 3. Artificial Intelligence Tools

[1395] Software that automatically assesses purchase requests and evaluates their validity. Specifically, it operates using machine learning algorithms and data analysis techniques.

[1396] 4. Emotional Engine

[1397] Software that recognizes emotions from user input and uses the analysis results to assess purchase requests. It includes text and voice analysis algorithms.

[1398] Detailed explanation of the program's processing

[1399] Retrieving purchase requests

[1400] The user enters a purchase request for a new computer or other item from their terminal, and also provides emotional information (e.g., text message, voice input) along with the request. The server retrieves this request and emotional information from its database. The data is transmitted and stored in JSON format or another appropriate data format.

[1401] Purchase request assessment

[1402] The server passes the acquired purchase request content and sentiment information to artificial intelligence tools and sentiment engines for assessment. The artificial intelligence tools evaluate the validity based on price, specifications, past purchase history, etc. Meanwhile, the sentiment engine analyzes the sentiment information and identifies the user's emotional state (e.g., urgency, reassurance, anxiety). Machine learning models and natural language processing (NLP) algorithms are used in this process.

[1403] Saving of assessment results

[1404] The server stores assessment results from artificial intelligence tools and emotion engines in a database. The retrieved results are written to the database in JSON format or another appropriate data format and used later for reference.

[1405] Evaluation and determination of assessment results

[1406] The server determines whether the assessment results received from the artificial intelligence tools and the sentiment engine are valid. Specifically, it decides whether the request can be approved based on the "is_approved" flag and the sentiment analysis results.

[1407] Notification of the result of the payment approval request

[1408] The server will either approve the payment request based on the final evaluation, or notify the user that pre-purchase consultation is required. If approved, it will send an "Approved" result to the user's terminal, and the process will be complete. If not approved, it will send a "Needs Pre-purchase Approval" result, and request pre-purchase consultation.

[1409] Specific example

[1410] For example, if a user wants to buy a new computer, the following steps are taken:

[1411] 1. The user enters a request to purchase a new computer from their device, and at the same time, includes the emotional information "I need this urgently" as a text message.

[1412] 2. The server retrieves the purchase request and sentiment information from the database.

[1413] 3. The server passes the acquired requests to artificial intelligence tools and an emotion engine for assessment.

[1414] 4. An artificial intelligence tool evaluates the validity of the request based on price, specifications, and past purchase history.

[1415] 5. The emotion engine analyzes the emotional information provided by the user and evaluates the user's emotional state (in this case, "urgency").

[1416] 6. The server stores the assessment results from the artificial intelligence tools and emotion engine in a database.

[1417] 7. The server evaluates the assessment results and, if deemed appropriate, approves the payment request and returns "Approved". If deemed inappropriate, it returns "Needs Pre-purchase Approval".

[1418] Example of a prompt:

[1419] "I have submitted a request to purchase a new computer. I need it urgently. Please use an AI tool to evaluate its feasibility, taking into account my past purchase history, current price, and specifications. Also, please use an emotion engine to analyze my emotional information and make a final decision on payment approval."

[1420] In this way, the system of the present invention can streamline the pre-purchase consultation process and enable rapid payment approval processing that takes user sentiment into consideration.

[1421] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1422] Step 1: The user enters a purchase request and sentiment information into the terminal.

[1423] The user uses a terminal to enter a purchase request (e.g., a desire to purchase a new computer) and sentiment information (e.g., a text message saying "I need this urgently"). The entered data is sent to the server when the user presses the submit button.

[1424] Input: Purchase request, sentiment information

[1425] Output: Sending request data

[1426] Step 2: The server receives the purchase request and sentiment information and stores it in the database.

[1427] The server receives purchase requests and sentiment information sent by users. The received data is converted to JSON format or an appropriate data format and stored in the database.

[1428] Input: User request data

[1429] Output: Saving data to the database

[1430] Step 3: The server retrieves and processes the request data from the database.

[1431] The server retrieves purchase requests and sentiment information from the database and processes it into a data format for passing to artificial intelligence tools and sentiment engines. Specifically, it converts the data into the appropriate JSON format.

[1432] Input: Request data from the database

[1433] Output: Processed data

[1434] Step 4: The server passes the request data to the AI ​​tool and emotion engine and requests an assessment.

[1435] The server passes the processed data to an artificial intelligence tool and an emotion engine. The AI ​​tool evaluates the validity of the purchase request based on price, specifications, and past purchase history, while the emotion engine analyzes emotional information to determine the user's urgency and stress level.

[1436] Input: Processed data

[1437] Output: Assessment results from AI tools and emotion engine

[1438] Step 5: The server saves the assessment results to the database.

[1439] The server stores assessment results received from artificial intelligence tools and emotion engines in a database. This stored data is then used for future processing and reference.

[1440] Input: Assessment result

[1441] Output: Save to database

[1442] Step 6: The server evaluates the assessment results and determines their validity.

[1443] The server refers to the assessment results stored in the database and comprehensively evaluates their validity. In particular, it decides whether to approve or reject the purchase request based on the "is_approved" flag and the sentiment analysis results.

[1444] Input: Assessment results from the database

[1445] Output: Evaluation result (Approval / Rejection)

[1446] Step 7: The server notifies the user of the approval result.

[1447] Based on the final evaluation, the server will either approve the payment request or notify the user that pre-purchase consultation is required. If approved, it will return "Approved"; if not approved, it will return "Needs Pre-purchase Approval" and notify the user's terminal.

[1448] Input: Evaluation result

[1449] Output: Notification to user terminal

[1450] (Application Example 2)

[1451] 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".

[1452] Traditional purchasing approval systems failed to adequately consider user emotions and urgency when evaluating the validity of purchase requests. As a result, even highly urgent purchase requests could experience delays, potentially disrupting business operations. Furthermore, the inability to provide personalized content recommendations that reflected user emotions made improving user satisfaction difficult.

[1453] 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. In this invention, the server includes means for acquiring purchase requests from a database, means for evaluating the acquired purchase requests using an artificial intelligence tool, means for storing the evaluation results in a database, means including an emotion engine that acquires and analyzes user emotion information, and means for determining the urgency and priority of purchase requests based on emotion information and reflecting this in the evaluation. This enables rapid approval processing that takes into account the urgency of purchase requests and user emotions. Furthermore, it is possible to recommend the most suitable content based on user viewing requests and emotion information, thereby improving user satisfaction.

[1454] A "purchase request" refers to a request or application submitted by a user when they wish to purchase a new product or service.

[1455] A "database" is a repository of information that stores information in an efficient and organized manner, making it easy to search and retrieve.

[1456] An "artificial intelligence tool" is a computer program that uses technologies such as machine learning and neural networks to analyze data and make predictions and judgments.

[1457] "Assessment" is the process of evaluating and judging the validity and appropriateness of a purchase request.

[1458] "Emotional information" refers to data that represents a user's psychological state and emotions, and is obtained from sources such as text, voice, and facial expressions.

[1459] An "emotion engine" is software that analyzes a user's emotional information and identifies their emotional state.

[1460] "Urgency" refers to the degree to which a particular purchase request or task is urgent.

[1461] "Priority" is an indicator that shows which of several tasks or requests is more important than others.

[1462] A "pre-purchase consultation" is a meeting or discussion held to confirm necessary information and conditions before formally approving a purchase request.

[1463] "Rin-gi" refers to the process of seeking approval or decision-making within a company, and often specifically refers to the approval process for payments.

[1464] "Assessment results" refer to the results after evaluating the validity and urgency of a purchase request using artificial intelligence tools and emotion engines.

[1465] "Relevance" is an evaluation criterion that indicates whether a purchase request is feasible and conforms to the company's policies and standards.

[1466] "Recommendation" refers to suggesting the most suitable products or services based on the user's past behavior, preferences, and emotional information.

[1467] "Viewing trend data" refers to data that shows information about user and market viewing trends and popular content.

[1468] To implement this invention, the following system configuration and processing flow are used. The system consists of a user terminal, a server, an artificial intelligence tool, an emotion engine, and a database. The specific hardware used is a smartphone, smart glasses, and a server, and the software includes a user interface, an artificial intelligence tool (e.g., TensorFlow, PyTorch), and an emotion engine (e.g., Emotion API, Facial Recognition API).

[1469] System components

[1470] User terminal

[1471] The user terminal consists of a smartphone or smart glasses and provides an interface for users to input emotional information and content viewing requests. This ensures smooth user operation.

[1472] server

[1473] The server plays a central role in the system, retrieving purchase requests and sentiment information from the database and analyzing them using artificial intelligence tools and a sentiment engine. The analysis results are then evaluated again by the server and stored in the database. Furthermore, based on the results, it either notifies the customer of the need for pre-purchase consultation or approves the payment request.

[1474] Artificial intelligence tools

[1475] Artificial intelligence tools are software that evaluates the validity of purchase requests. They analyze and evaluate requests based on price, specifications, past purchase history, and viewing trend data. Specifically, they use TensorFlow and PyTorch to build machine learning models and make purchase requests and content recommendations.

[1476] Emotional Engine

[1477] An emotion engine is software that analyzes a user's emotional information. It analyzes text messages and voice data acquired from the device to identify the user's emotional state. For example, the Emotion API and Facial Recognition API are used for emotion analysis.

[1478] database

[1479] The database is an information management system for storing purchase requests, sentiment information, analysis results, past purchase and viewing history, and viewing trend data. This makes the data available for later analysis and reference.

[1480] Add specific examples to the description.

[1481] Examples of content recommendations

[1482] For example, a user might type "I want to watch a relaxing movie" on their smartphone and also voice-input "I'm a little tired." The server passes this information to an artificial intelligence tool and an emotion engine for analysis. The AI ​​tool analyzes past viewing history and trends in relaxing movies, while the emotion engine determines the user's emotions from the voice input "I'm a little tired." Finally, the server recommends and notifies the user of the most suitable content.

[1483] Examples of prompts for generative AI models

[1484] The following are examples of prompts for a generative AI model:

[1485] Point down

[1486] A user types "I want to watch a relaxing movie" on their smartphone and also voice-inputs "I'm a little tired." An emotion engine analyzes the user's voice information, and an artificial intelligence tool recommends the most suitable content based on past viewing history and trends in relaxing movies. What models or APIs should I use to achieve this?

[1487] By implementing this invention, personalized content recommendations that take into account the user's emotions and past viewing history become possible, which is expected to improve user satisfaction. Furthermore, rapid processing of purchase requests can also be achieved simultaneously.

[1488] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1489] Step 1:

[1490] Users use their smartphones or smart glasses to input viewing requests and emotional information. Specifically, they launch the application and input text such as "I want to watch a relaxing movie" and voice information such as "I'm a little tired." The input data is stored on the device and sent to the server.

[1491] Step 2:

[1492] The server retrieves the received viewing requests and sentiment information from the database. Specifically, data sent to the server in the form of "purchase requests" and "sentiment information" retrieves information from the database and passes it on to the next processing step.

[1493] Step 3:

[1494] The server passes the content of the acquired viewing request to an artificial intelligence tool, and then passes the emotional information to an emotion engine. The artificial intelligence tool uses past viewing history and viewing trend data to analyze the data and evaluate the validity of the request and recommend content. The emotion engine analyzes the emotional state from the audio data and derives the result "slightly tired."

[1495] Step 4:

[1496] The server integrates analysis results from artificial intelligence tools and an emotion engine. Specifically, it combines a list of relaxing movies recommended by the AI ​​tool with the user's emotional state analyzed by the emotion engine to select the most suitable content. For example, it selects the content with the highest "relaxation level" and "viewing recommendation level" from the list of relaxing movies.

[1497] Step 5:

[1498] The server notifies the user of the most suitable content it has selected. Specifically, it sends a message to the user's device saying, "Here is the best movie for you: XXXXX," along with a link to view the content.

[1499] Step 6:

[1500] Users can start watching by checking the notification they receive and clicking the provided link. This makes it easy for users to watch the relaxing movie they want.

[1501] The specific flow and processing steps enable personalized content recommendations based on user viewing requests and sentiment information.

[1502] 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.

[1503] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One 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.

[1504] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1505] 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.

[1506] 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.

[1507] 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.

[1508] 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.

[1509] 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.

[1510] 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."

[1511] 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.

[1512] 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.

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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.

[1519] 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.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] The following is further disclosed regarding the embodiments described above.

[1524] (Claim 1)

[1525] A means of retrieving purchase requests from the database,

[1526] A method for evaluating acquired purchase requests using an artificial intelligence tool,

[1527] A means of saving the assessment results to a database,

[1528] A means of determining whether the assessment results are appropriate,

[1529] A means of skipping pre-purchase consultations and approving payment requests if deemed appropriate,

[1530] A system that includes means for notifying the need for pre-purchase consultation if it is deemed inappropriate.

[1531] (Claim 2)

[1532] The system according to claim 1, comprising an artificial intelligence tool for assessing a purchase request based on price, specifications, and past purchase history.

[1533] (Claim 3)

[1534] The system according to claim 1, comprising means for receiving purchase requests from a terminal.

[1535] "Example 1"

[1536] (Claim 1)

[1537] A means of recording the details of a purchase request,

[1538] A means of retrieving recorded purchase requests from a database,

[1539] A means of evaluating acquired purchase requests using an artificial intelligence tool,

[1540] A means of saving the evaluation results to a database,

[1541] A means of determining whether the evaluation results are valid,

[1542] A means to skip the pre-purchase review and complete the approval process if it is deemed appropriate,

[1543] A system that includes means for notifying the need for prior consideration of a purchase if it is deemed inappropriate.

[1544] (Claim 2)

[1545] The system according to claim 1, comprising an artificial intelligence tool for evaluating purchase requests based on price, performance, and past transaction records.

[1546] (Claim 3)

[1547] The system according to claim 1, comprising means for receiving input of a purchase request from an input device.

[1548] "Application Example 1"

[1549] (Claim 1)

[1550] A means of retrieving purchase requests from the database,

[1551] A method for evaluating acquired purchase requests using an artificial intelligence tool,

[1552] A means of saving the assessment results to a database,

[1553] A means of determining whether the assessment results are appropriate,

[1554] A means of skipping pre-purchase consultations and approving payment requests if deemed appropriate,

[1555] A means of notifying the need for pre-purchase consultation if it is not appropriate,

[1556] A method for receiving purchase requests from factory robots within the factory,

[1557] A system that includes means for rapidly processing assessment results using factory robots.

[1558] (Claim 2)

[1559] The system according to claim 1, comprising an artificial intelligence tool for assessing a purchase request based on price, specifications, and past purchase history.

[1560] (Claim 3)

[1561] The system according to claim 1, comprising means for receiving input from a terminal used by an operator in a factory.

[1562] "Example 2 of combining an emotion engine"

[1563] (Claim 1)

[1564] A means of obtaining purchase requests and sentiment information from a database,

[1565] A means for assessing acquired purchase requests and sentiment information using artificial intelligence tools and sentiment engines,

[1566] A means of saving the assessment results to a database,

[1567] A means of determining whether the assessment results are appropriate,

[1568] A means of skipping pre-purchase consultations and approving payment requests if deemed appropriate,

[1569] A system that includes means for notifying the need for pre-purchase consultation if it is deemed inappropriate.

[1570] (Claim 2)

[1571] The system according to claim 1, comprising an artificial intelligence tool for assessing a purchase request based on price, specifications, and past purchase history.

[1572] (Claim 3)

[1573] The system according to claim 1, comprising means for receiving purchase requests and emotional information input from a terminal.

[1574] "Application example 2 when combining with an emotional engine"

[1575] (Claim 1)

[1576] A means of retrieving purchase requests from the database,

[1577] A method for evaluating acquired purchase requests using an artificial intelligence tool,

[1578] A means of saving the assessment results to a database,

[1579] A means of determining whether the assessment results are appropriate,

[1580] A means of skipping pre-purchase consultations and approving payment requests if deemed appropriate,

[1581] A means of notifying the need for pre-purchase consultation if it is not appropriate,

[1582] A means including an emotion engine that acquires and analyzes user emotion information,

[1583] A system that includes means to determine the urgency and priority of purchase requests based on emotional information and reflect this in the assessment.

[1584] (Claim 2)

[1585] The system according to claim 1, comprising an artificial intelligence tool that provides means for assessing purchase requests based on price, specifications, and past purchase history, and further providing means for recommending optimal content based on past viewing history and viewing trend data.

[1586] (Claim 3)

[1587] The system according to claim 1, further comprising means for receiving purchase requests from a terminal and for receiving user viewing requests and emotional information from the terminal. [Explanation of Symbols]

[1588] 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

1. A means of retrieving purchase requests from the database, A method for evaluating acquired purchase requests using an artificial intelligence tool, A means of saving the assessment results to a database, A means of determining whether the assessment results are appropriate, A means of skipping pre-purchase consultations and approving payment requests if deemed appropriate, A system that includes means for notifying the need for pre-purchase consultation if it is deemed inappropriate.

2. The system according to claim 1, comprising an artificial intelligence tool for assessing a purchase request based on price, specifications, and past purchase history.

3. The system according to claim 1, comprising means for receiving purchase requests from a terminal.

Images