System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining sales price data; means for training an unsupervised learning algorithm based on historical sales price data; and means for performing an anomaly detection algorithm on current sales price data and outputting a determination result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In an environment where sales prices fluctuate frequently due to factors such as exchange rates, it is necessary to accurately reflect the price at the time of creating a quote using a uniform nationwide standard. However, with conventional methods, there is a high risk of creating inaccurate quotes due to price fluctuations. In addition, manual price checking requires a great deal of effort and is not efficient. For this reason, an automated system is needed to create quotes accurately and efficiently. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system that includes a means for acquiring sales price data, a means for training an unsupervised learning algorithm based on past sales price data, and a means for executing an anomaly detection algorithm on current sales price data and outputting the determination result.

[0006] Specifically, the system periodically retrieves the latest price information from a sales price database and uses this information to train an unsupervised learning algorithm (e.g., Isolation Forest). The trained model is used to run an anomaly detection algorithm to determine whether the price at the time of creating the quote is within a normal range. If an abnormal price is detected, a warning message is generated to notify the user, preventing the creation of quotes with incorrect prices. This system makes it possible to create accurate quotes based on uniform standards across the country.

[0007] "Sales Price Data" refers to information regarding the current selling price of a product.

[0008] An "unsupervised learning algorithm" is an algorithm that automatically learns patterns and structures in data based on data that has not been pre-labeled.

[0009] An "anomaly detection algorithm" is an algorithm for detecting anomalies or abnormal patterns in data.

[0010] The "judgment result" refers to the result obtained after the anomaly detection algorithm is executed, indicating whether the data is normal or abnormal.

[0011] "Quotation" means a document that specifies the price and terms for the provision of goods or services.

[0012] A "warning message" is a message that notifies the user when the system detects an abnormality.

[0013] A "request" refers to a request from a terminal or system to a server for information or processing.

[0014] "Response" refers to a response that a server sends to a terminal or system in response to a request. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention relates to a system that generates accurate quotations based on a nationwide standard, taking into account fluctuations in sales prices at the time of creation of the quotation. The system automatically acquires sales price data, trains an unsupervised learning algorithm, performs anomaly detection, outputs the results, and generates warning messages as needed.

[0037] Explanation of program processing

[0038] Obtaining sales price data

[0039] The server periodically retrieves the latest price information from the sales price database and stores it in memory or cache. The server also returns the latest sales price data in response to a request from a terminal.

[0040] When a user creates a new quotation, the terminal requests the current sales price data from the server and receives the latest sales price data as a response from the server.

[0041] Examples:

[0042] The server retrieves the price data by executing an SQL query such as SELECT product_id, current_price, timestamp FROM price_data;

[0043] The device sends an HTTP request such as GET / api / current_prices to the server, and the server returns {"product_id": 123, "current_price": 1500} as a response.

[0044] Identifying price fluctuations

[0045] The server trains an unsupervised learning algorithm based on historical sales price data, and the trained model is used for anomaly detection to determine whether a normal price exists within the range of price data.

[0046] The terminal sends a request to the server to determine if the current sale price is within a range.

[0047] Examples:

[0048] The server analyzes and trains past data using algorithms such as Isolation Forest.

[0049] The terminal sends the current price to the server and makes a request such as POST / api / detect_anomaly. The server determines the price and returns {"status": "normal"} in the response.

[0050] Detecting abnormal prices

[0051] The server runs an anomaly detection algorithm against current price data to determine anomalous prices, and if an anomalous price is detected, the server generates a warning message.

[0052] The terminal receives a response from the server stating the abnormality, and if an abnormality is detected, displays a warning message to the user.

[0053] Examples:

[0054] The server runs an anomaly detection algorithm and returns {"status": "abnormal"} as the result in case of abnormal prices.

[0055] The terminal receives the response indicating the abnormality and notifies the user that an abnormal price has been detected.

[0056] Create and save quotes

[0057] The user creates a quote based on the pricing information provided. Once the quote is complete, the user clicks the "Save" button to save the quote.

[0058] The terminal sends the created quotation data to the server and requests that it be saved. The server saves the quotation data in a database.

[0059] Examples:

[0060] The user creates a quote using the terminal interface and clicks the "Save" button.

[0061] The terminal sends a request, POST / api / save_estimate, along with the data to the server, and the server saves the estimate data in the database with a query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0062] The processing flow will be explained below.

[0063] Program processing steps

[0064] Obtaining sales price data

[0065] Step 1:

[0066] The server periodically retrieves the latest price information from the sales price database. For example, it executes the following SQL query to retrieve sales price data: SELECT product_id, current_price, timestamp FROM price_data;

[0067] Step 2:

[0068] The server stores the obtained price data in memory or cache for quick access.

[0069] Step 3:

[0070] When a user opens a screen to create a new quote, the terminal automatically requests sales price data from the server by sending an HTTP request such as GET / api / current_prices.

[0071] Step 4:

[0072] The server receives the request from the device, retrieves the latest sales price data from memory or cache, and returns it as an HTTP response. Response example: {"product_id": 123, "current_price": 1500}

[0073] Identifying price fluctuations

[0074] Step 5:

[0075] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. Through this training, it learns the normal price range.

[0076] Step 6:

[0077] The server stores the trained model and waits for the next request.

[0078] Step 7:

[0079] The device sends a request to the server to perform anomaly detection based on the current selling price. For example, send data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly.

[0080] Step 8:

[0081] The server runs an anomaly detection algorithm on the received data to determine whether it is normal or abnormal. The result is returned as an HTTP response. Example response: {"status": "normal"}

[0082] Detecting abnormal prices

[0083] Step 9:

[0084] The server determines whether the price is within the normal range or is abnormal based on the results of the anomaly detection algorithm, and if it is abnormal, generates a warning message.

[0085] Step 10:

[0086] The terminal receives the response from the server, and if it is within the normal range, it notifies the user and allows them to continue. If it is within the abnormal range, a warning message is displayed to the user. Example of display: "An abnormal price has been detected. Please check again."

[0087] Create and save quotes

[0088] Step 11:

[0089] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button.

[0090] Step 12:

[0091] The terminal sends the created estimate data to the server and requests that it be saved. For example, send data such as {"estimate_id": 456, "product_id": 123, "price": 1500} to the endpoint POST / api / save_estimate.

[0092] Step 13:

[0093] The server saves the received quote data in the database by executing the following SQL query: INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0094] Step 14:

[0095] The server returns a response to the terminal indicating that the save was successful. Example response: {"status": "success", "message": "The quote has been saved"}

[0096] The above are the specific processing steps in the embodiment for carrying out the invention.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] With the previous quotation creation system, it was difficult to reflect fluctuations in sales prices in real time, making it impossible to create accurate quotation. Furthermore, there was a lack of functionality to respond immediately when abnormal prices were detected, which created a risk of submitting inaccurate quotation. Furthermore, the process of saving quotation was often done manually, which reduced work efficiency.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0101] In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for requesting the latest sales price data when a user creates a new estimate, means for providing the sales price data as a response, means for generating and outputting a warning message when an abnormal price is detected, and means for creating and saving estimate data. This enables accurate and prompt creation of estimates while taking into account fluctuations in sales prices and immediate response to abnormal prices.

[0102] "Sales price data" is data that records price information for products and services, including product ID, current price, timestamp, etc.

[0103] An "unsupervised learning algorithm" is a type of machine learning algorithm that finds patterns and relationships from unlabeled data and is used for model training.

[0104] An "anomaly detection algorithm" is an algorithm that detects unusual patterns or exceptions in data, identifying data that falls outside of the normal range.

[0105] A "quote" is a document that details the products or services to be provided and their prices, and is used to make a formal price proposal to a customer.

[0106] A "server" is a computer system that is connected to a network and provides data and resources to other computer systems (clients).

[0107] A "terminal" is a computer system that is operated by a user and communicates with a server, and data is input and results are received via a user interface.

[0108] "User" means any person or entity that operates the System and utilizes its functions, such as generating quotes.

[0109] The system of this invention is a system for creating accurate quotations that reflect changes in sales prices in real time. Specifically, it includes a series of processes, such as acquiring sales price data, training an unsupervised learning algorithm, performing anomaly detection, outputting the judgment results, generating warning messages, and saving quotations.

[0110] Obtaining sales price data

[0111] The server accesses the sales price database at regular intervals to obtain the latest price information. For example, it periodically executes an SQL query such as SELECT product_id, current_price, timestamp FROM price_data; to obtain price data. The obtained data is then stored in memory or cache. When a user creates a new quote, the terminal sends an HTTP request, GET / api / current_prices, to the server, and the server provides the latest sales price data as a response. For example, it returns data in the format {"product_id": 123, "current_price": 1500}.

[0112] Training unsupervised learning algorithms

[0113] The server collects historical sales price data and trains an unsupervised learning algorithm. Specifically, it analyzes the data using algorithms such as Isolation Forest to train a model for anomaly detection. The trained model is then stored in storage.

[0114] Determining current price data

[0115] The user's device sends current price data to the server for a decision. For example, a request such as POST / api / detect_anomaly is sent to the endpoint. The server uses a trained anomaly detection model to judge the received price data and returns the result. Examples of responses include {"status": "normal"} and {"status": "abnormal"}.

[0116] Detecting abnormal prices

[0117] After receiving the current price data, the server runs an anomaly detection algorithm to determine whether the price is abnormal. For example, it can generate a warning message such as {"status": "abnormal", "message": "Price is abnormal"}. The terminal receives this warning message and notifies the user, displaying a message such as "An abnormal price has been detected."

[0118] Create and save quotes

[0119] The user uses the terminal interface to create a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button. The terminal sends the quote data to the server via a POST / api / save_estimate request. The server then saves the received quote data to the database. For example, it does so by executing an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0120] As described above, the system of the present invention is designed to reflect fluctuations in selling prices in real time, thereby creating accurate and up-to-date estimates and responding immediately to abnormal prices.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1: Obtaining sales price data

[0123] The server periodically accesses the sales price database to obtain the latest price information. Specifically, the server executes the SQL query SELECT product_id, current_price, timestamp FROM price_data; to extract price data. This extracted data is temporarily stored in memory or cache and used in subsequent processes. When a user creates a new quote, the terminal sends an HTTP request, GET / api / current_prices, to the server to request sales price data. The server returns the latest sales price data in JSON format as a response.

[0124] Input: Request price information from sales price database

[0125] Output: Latest price information stored in memory or cache, and sales price data as a response to the terminal

[0126] Step 2: Training the unsupervised learning algorithm

[0127] The server performs unsupervised learning using algorithms such as the Isolation Forest algorithm based on past sales price data. The server extracts past price data from the database and inputs it into the algorithm. This algorithm learns patterns in the price data and generates a model that identifies outliers. The trained model is saved in storage and can be reused in subsequent anomaly detection processes.

[0128] Input: Historical sales price data

[0129] Output: A trained anomaly detection model

[0130] Step 3: Determine current price data

[0131] When a user performs a price data judgment, the terminal sends the current price data to the server. For example, price data is sent to the endpoint POST / api / detect_anomaly. The server analyzes the received current price data using a trained anomaly detection model and judges whether it is an anomaly. The server returns the judgment result in JSON format to the terminal. For example, a response such as {"status": "normal"} or {"status": "abnormal"} is possible.

[0132] Input: Current price data

[0133] Output: Abnormality judgment result

[0134] Step 4: Detecting price anomalies

[0135] The server runs an anomaly detection algorithm on the current price data it receives to determine whether the price is abnormal. If an abnormal price is detected, the server generates a warning message. For example, the message is generated in the format {"status": "abnormal", "message": "The price is abnormal"}. The terminal receives the response from the server and displays the warning message to the user.

[0136] Input: Current price data

[0137] Output: Abnormal price warning message

[0138] Step 5: Create and save a quote

[0139] The user uses the terminal interface to create a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button. The terminal sends the created quote data to the server with the request POST / api / save_estimate. The server saves the received quote data in the database. For example, it saves it in the database using an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0140] Input: Quotation data

[0141] Output: Quote saved in database

[0142] The above is the specific processing flow of the program for this system.

[0143] (Application example 1)

[0144] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0145] In conventional quotation creation systems, it was difficult to reflect fluctuations in sales price data in real time, detect abnormal prices, and take appropriate measures. Furthermore, when abnormal prices occurred, warnings had to be issued manually, which was inefficient. Furthermore, creating and saving quotations was often done manually, which required time and effort. The present invention aims to solve these problems and provide a system that automatically and efficiently creates quotations and responds to price fluctuations.

[0146] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0147] In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for issuing a warning signal when an anomaly is detected, means for automatically creating an estimate based on normal price data, means for saving the created estimate and making it accessible later, and means for executing the above series of processes using a robot, thereby enabling real-time acquisition of sales price data, anomaly detection, warning function, and automatic estimate creation and saving.

[0148] The "means for acquiring sales price data" is a function that allows a server or robot to acquire the latest sales price data from the server and store it in a usable format.

[0149] "Means for training an unsupervised learning algorithm based on past sales price data" refers to a function that uses past price data to train an unsupervised learning algorithm for detecting abnormal prices using a server or computer, and creates a model of the algorithm.

[0150] "Means for executing an anomaly detection algorithm on current sales price data and outputting the determination results" is a function for executing an anomaly detection algorithm based on the latest price data to determine price anomalies and output the results.

[0151] The "means for issuing a warning signal when an abnormality is detected" is a function for issuing a warning signal such as sound or light when price data is determined to be abnormal.

[0152] The "means for automatically creating a quotation based on normal price data" is a function for automatically creating a required quotation based on normal price data.

[0153] "Means for saving the created estimate and making it accessible later" is a function for saving automatically created estimate data and making it possible to access or refer to it in the future.

[0154] The "means for executing the series of processes using a robot" is a function that enables a robot to execute a series of processes including obtaining sales price data, detecting abnormalities, issuing warning signals, and automatically creating and saving estimates.

[0155] This invention is a system consisting of the following processing steps: First, the server periodically obtains the latest sales price data and stores it in memory or cache. This sales price data is for later use by the robot. The server also trains an unsupervised learning algorithm based on the past sales price data to generate an anomaly detection model. This model is implemented using an algorithm such as Isolation Forest.

[0156] The robot retrieves the latest sales price data from the server and requests an anomaly detection algorithm from the server to determine whether the current sales price is within the normal range. If an abnormality is detected, the server has the function of issuing a warning signal. This warning is issued by sound or light, and notifies the worker visually or audibly of the existence of an abnormal price.

[0157] Furthermore, if valid price data is obtained, the robot automatically creates a quote. This quote is sent to the server and saved in the database. The saved quote data is kept in a state that can be accessed later. This process automates and efficiently performs the entire process from creating to saving quotes.

[0158] For example, if a robot obtains the price of a specific part and the price exceeds the normal range, the server will immediately detect the abnormality and send a warning signal to the worker. In addition, a delivery quotation will be automatically created based on the normal price data and saved on the server.

[0159] Below is an example of a textual input prompt for a generative AI model:

[0160] "Design an anomaly detection system for part price data obtained by a factory robot. The following requirements must be met: 1. The robot periodically retrieves the latest price data from the server. 2. Implement an anomaly detection algorithm based on past price data. 3. Implement a function to issue a warning if an abnormal price is detected. 4. Automatically create a quote based on normal price data and save it on the server. Example: Price data: [

[0100] ,

[0150] ,

[0200] ,

[0120] ,

[0160] ,

[0210] ,

[0140] ,

[0170] ,

[0220] ,

[0180] ] Abnormal price: 200 Warning method: Speaker, flashing light Quote data: {"part_id": 123, "quantity": 10, "total_price": 1500}"

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1:

[0163] The server periodically retrieves the latest price information from the sales price database. This information is stored in memory or cache. Specifically, the server retrieves the latest sales price data by executing the SQL query SELECT product_id, current_price, timestamp FROM price_data; The input is the query result from the price database, and the output is the latest price information stored in memory or cache.

[0164] Step 2:

[0165] When a user creates a new quote, the terminal requests current sales price data from the server. The server receives an HTTP request, GET / api / current_prices, and returns the latest sales price data as a response. The input is the HTTP request, and the output is a JSON-formatted response containing the current sales price data.

[0166] Step 3:

[0167] The server trains a model using an unsupervised learning algorithm such as Isolation Forest based on past sales price data. The input is the past sales price data, and the output is an anomaly detection model. This model is used to determine whether there is a normal price within the range of price data.

[0168] Step 4:

[0169] The device sends a request to the server to determine whether the current selling price is within a range. Specifically, it makes a request called POST / api / detect_anomaly and sends the current price. The server inputs this price into an anomaly detection model to determine whether it is an anomaly. The output is a response that stores the status of an anomaly or normal.

[0170] Step 5:

[0171] Based on the results of the anomaly determination, the server generates a warning message if an abnormal price is detected. The terminal receives this response and issues a warning to the user saying, "An abnormal price has been detected." The input is the result of the anomaly determination, and the output is a warning message to the user. Specifically, a warning signal is emitted using sound or light.

[0172] Step 6:

[0173] The user creates a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button to save the quote. The terminal sends the created quote data to the server and requests it to be saved. The input is the quote data created by the user, and the output is the quote saved on the server. The server executes the query INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500); to save it in the database.

[0174] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0175] This invention relates to a system that generates accurate quotations based on a uniform standard nationwide, taking into account fluctuations in sales prices at the time of creation of the quotation. This system includes functions for automatically acquiring sales price data, training unsupervised learning algorithms, performing anomaly detection, outputting the results, and generating warning messages as necessary. Furthermore, it incorporates an emotion engine that recognizes user emotions, and adds a function for providing appropriate feedback to the user.

[0176] Explanation of program processing

[0177] Obtaining sales price data

[0178] The server periodically retrieves the latest price information from the sales price database. The retrieved data is stored in memory or cache for quick access. When a user opens a screen for creating a new quote, the terminal requests the current sales price data from the server. The server returns the latest sales price data to the terminal.

[0179] Examples:

[0180] The server retrieves the price data by executing an SQL query such as SELECT product_id, current_price, timestamp FROM price_data;

[0181] The device sends an HTTP request such as GET / api / current_prices to the server, and the server returns {"product_id": 123, "current_price": 1500} as a response.

[0182] Identifying price fluctuations

[0183] Next, the server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. The trained model is used for anomaly detection to determine whether there is a normal price within the range of price data. The device sends a request to the server to perform anomaly detection based on the current sales price. The server runs the anomaly detection algorithm and returns the results.

[0184] Examples:

[0185] The server trains the unsupervised learning algorithm and generates the model.

[0186] The device sends data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly. The server determines the price and returns a response with {"status": "normal"}.

[0187] Detecting abnormal prices

[0188] The server runs an anomaly detection algorithm on the current price data to determine if a price is abnormal. If an abnormal price is detected, it generates a warning message. The terminal receives the response from the server and displays a warning message to the user if an abnormality is detected.

[0189] Examples:

[0190] The server runs an anomaly detection algorithm and returns the result {"status": "abnormal"} in case of abnormal prices.

[0191] The terminal receives the response indicating the abnormality detection and notifies the user with a warning message saying "An abnormal price has been detected."

[0192] Create and save quotes

[0193] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button. The device sends the created quote data to the server and requests that it be saved. The server saves the received quote data in its database.

[0194] Examples:

[0195] The user creates a quote using the terminal interface and clicks the "Save" button.

[0196] The device sends a POST / api / save_estimate request with the data to the server, which saves it to the database with the SQL query INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0197] Emotion engine integration

[0198] The device uses a camera and microphone to recognize the user's emotions while the user is operating the device. The emotion data is sent to the server in real time. The server then uses an emotion engine to analyze the emotion data and generate appropriate feedback based on the user's emotional state.

[0199] Examples:

[0200] The device uses a camera and microphone to capture the user's facial expressions and voice, and sends the emotion data to the server using the endpoint POST / api / analyze_emotion.

[0201] The server analyzes the data using an emotion engine, and if it determines, for example, that the user is in a state of stress, it generates a message encouraging relaxation and returns the response {"message": "Please take a short break"}.

[0202] The above is a concrete example of how to implement the invention by combining an emotion engine. This system combines accurate reflection of sales price information with feedback based on the user's emotions, enabling more efficient and user-friendly quotation creation.

[0203] The processing flow will be explained below.

[0204] Obtaining sales price data

[0205] Step 1:

[0206] The server periodically retrieves the latest price information from the sales price database. For example, it executes the following SQL query to retrieve sales price data: SELECT product_id, current_price, timestamp FROM price_data;

[0207] Step 2:

[0208] The server stores the obtained price data in memory or cache for quick access.

[0209] Step 3:

[0210] When a user opens a screen to create a new quote, the terminal automatically requests sales price data from the server by sending an HTTP request such as GET / api / current_prices.

[0211] Step 4:

[0212] The server receives the request from the device, retrieves the latest sales price data from memory or cache, and returns it as an HTTP response. Response example: {"product_id": 123, "current_price": 1500}

[0213] Identifying price fluctuations

[0214] Step 5:

[0215] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. Through this training, it learns the normal price range.

[0216] Step 6:

[0217] The server stores the trained model and waits for the next request.

[0218] Step 7:

[0219] The device sends a request to the server to perform anomaly detection based on the current selling price. For example, send data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly.

[0220] Step 8:

[0221] The server runs an anomaly detection algorithm on the received data to determine whether it is normal or abnormal. The result is returned as an HTTP response. Example response: {"status": "normal"}

[0222] Detecting abnormal prices

[0223] Step 9:

[0224] The server determines whether the price is within the normal range or is abnormal based on the results of the anomaly detection algorithm, and if it is abnormal, generates a warning message.

[0225] Step 10:

[0226] The terminal receives the response from the server, and if it is within the normal range, it notifies the user and allows them to continue. If it is within the abnormal range, a warning message is displayed to the user. Example of display: "An abnormal price has been detected. Please check again."

[0227] Create and save quotes

[0228] Step 11:

[0229] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button.

[0230] Step 12:

[0231] The terminal sends the created estimate data to the server and requests that it be saved. For example, send data such as {"estimate_id": 456, "product_id": 123, "price": 1500} to the endpoint POST / api / save_estimate.

[0232] Step 13:

[0233] The server saves the received estimate data in the database by executing an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0234] Step 14:

[0235] The server returns a response to the terminal indicating that the save was successful. Example response: {"status": "success", "message": "The quote has been saved"}

[0236] Emotion engine integration

[0237] Step 15:

[0238] The device uses a camera and microphone to recognize the user's emotions while the user is operating the device, and the emotion data is sent to the server in real time.

[0239] Step 16:

[0240] The server uses an emotion engine to analyze the emotion data and generate appropriate feedback based on the user's emotional state.

[0241] Step 17:

[0242] The server generates a feedback message for the user based on the emotion analysis results and sends it to the terminal. For example, if the server determines that the user is in a "stressed state," it generates a message saying, "Please take a short break."

[0243] Step 18:

[0244] The terminal receives the feedback message sent from the server and displays it to the user. Example: "Your current work seems stressful. Please take a short break."

[0245] The above are the specific processing steps for implementing the invention that combines an emotion engine. This system achieves more efficient and user-friendly quotation creation by combining accurate reflection of sales price information with feedback based on the user's emotions.

[0246] Example 2

[0247] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0248] Conventional quotation creation systems do not adequately consider fluctuations in sales prices or the detection of abnormal prices, making it difficult to create accurate quotation documents. Furthermore, they lack feedback that takes into account the user's emotional state, resulting in a lack of improvement in the user experience.

[0249] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting a determination result, means for acquiring and analyzing emotion data, and means for generating appropriate feedback based on the user's emotional state. This not only makes it possible to create accurate estimates that take into account fluctuations in sales prices and abnormal prices, but also makes it possible to provide feedback according to the user's emotional state, improving the user experience.

[0250] "Sales Price Data" means information about the selling price of a product, obtained from a database or other source.

[0251] "Unsupervised learning algorithms" is a general term for algorithms used to train models using unlabeled data to perform tasks such as classification and clustering.

[0252] An "anomaly detection algorithm" is an algorithm that detects data points in a dataset that do not fit a normal pattern.

[0253] The "judgment result" is the conclusion obtained after executing the anomaly detection algorithm, whether the data is normal or abnormal.

[0254] "Emotional data" is information that indicates the user's emotional state and is collected through sensors such as cameras and microphones.

[0255] "Analytical means" are technical devices and algorithms used to process collected data and extract useful information.

[0256] "Feedback" refers to the responses or instructions that a system provides to a user, based on the user's emotional state and operational status.

[0257] This invention relates to a system for creating accurate quotations that take into account fluctuations in sales prices. The system has the functions of automatically acquiring sales price data, training unsupervised learning algorithms, performing anomaly detection, outputting judgment results, and analyzing emotion data and generating feedback.

[0258] Obtaining sales price data

[0259] The server retrieves the latest price information from the sales price database at a fixed time. This task is performed by a scheduled job, for example, at 2:00 AM every day. The specific software used is a database management system (for example, MySQL), which retrieves price data by executing the SQL query SELECT product_id, current_price, timestamp FROM price_data;. The retrieved data is stored in memory or cached for quick access.

[0260] When a user opens a screen for creating a new quote, the terminal requests the latest sales price data from the server. The request from the terminal is sent using the HTTP protocol in the format GET / api / current_prices. The server receives the request and returns the latest price data it has saved in JSON format to the terminal.

[0261] Identifying price fluctuations

[0262] Next, the server trains a model using an unsupervised learning algorithm (e.g., Isolation Forest) based on the collected historical sales price data. The model is generated using a Python machine learning library (e.g., scikit-learn). The trained model is saved and later used for anomaly detection.

[0263] The terminal sends an anomaly detection request to the server based on the current selling price entered by the user. The request format is POST / api / detect_anomaly, and sends data such as {"product_id": 123, "price": 1500}. The server runs the anomaly detection algorithm based on this data and returns the results to the terminal. If the result is normal, it is returned as {"status": "normal"}, and if it is an abnormal value, it is returned as {"status": "abnormal"}.

[0264] Detecting abnormal prices

[0265] The server runs an anomaly detection algorithm against the current price data to determine if a price is abnormal. If an abnormal price is detected, it generates a warning message. The generated warning message has the format {"message": "An abnormal price has been detected"}.

[0266] The terminal displays the received warning message to the user, who can then quickly respond by checking the on-screen warning that "an abnormal price has been detected."

[0267] Create and save quotes

[0268] The user creates a quote using the device interface, entering product information and pricing and clicking the "Save" button.

[0269] The terminal sends the created estimate data to the server and requests that it be saved. The request format is POST / api / save_estimate, and sends the following data, for example: {"estimate_id": 456, "product_id": 123, "price": 1500}.

[0270] The server saves the received estimate data in the database by executing the following SQL query: INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0271] Emotion engine integration

[0272] The device uses the camera and microphone to recognize the user's emotions while the user is operating the device. Emotion data is collected in real time and sent to the server. The sending format is POST / api / analyze_emotion, and data such as {"emotion": "sad", "intensity": 0.8} is sent.

[0273] The server analyzes the data collected by the emotion engine and generates appropriate feedback based on the user's emotional state. For example, if the server determines that the user is in a stressful state, it generates a message encouraging relaxation and sends the response {"message": "Please take a short break"} to the device.

[0274] The above describes a specific embodiment of the present invention. This system combines accurate reflection of sales price information with feedback based on the user's emotions to create more efficient and user-friendly estimates.

[0275] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0276] Specific flow of program processing

[0277] Step 1: Obtaining sales price data

[0278] The server periodically retrieves the latest price information from the sales price database. The input is a database query (e.g. SELECT product_id, current_price, timestamp FROM price_data;) and the output is the latest sales price data. Specifically, it executes an SQL query from the database and stores the price data in memory or cache, making it readily accessible.

[0279] Step 2: User Request

[0280] When a user opens the screen for creating a new quote, the terminal sends a request to the server to obtain current sales price data. The input is the user's operation, and the output is an HTTP request (e.g., GET / api / current_prices). Based on this request, the server retrieves the latest price information from memory or cache and returns it to the terminal in JSON format (e.g., {"product_id": 123, "current_price": 1500}).

[0281] Step 3: Determine price fluctuations

[0282] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. The input is past sales price data, and the output is the trained model. Specifically, it trains the algorithm using a Python machine learning library (e.g., scikit-learn) and saves the generated model.

[0283] Step 4: Anomaly detection request

[0284] The terminal sends an anomaly detection request to the server based on the current sales price. The input is the current sales price data (e.g., {"product_id": 123, "price": 1500}), and the output is an HTTP request (e.g., POST / api / detect_anomaly). After receiving the request, the server runs the anomaly detection algorithm and outputs the results.

[0285] Step 5: Detecting price anomalies

[0286] The server runs an anomaly detection algorithm to determine whether a price is abnormal. The input is the data of the anomaly detection request, and the output is the anomaly determination result (e.g., {"status": "abnormal"}). If an anomaly is detected, a warning message (e.g., {"message": "An abnormal price has been detected"}) is generated.

[0287] Step 6: Displaying warning messages

[0288] The terminal receives the abnormality determination result and warning message from the server and displays them to the user. The input is the response data from the server, and the output is the display of the warning message to the user. The user can see the message "An abnormal price has been detected" on the terminal screen.

[0289] Step 7: Create and save a quote

[0290] The user creates a quote using the terminal. The input is product information and price data, and the output is the quote data. After completing the quote, the user clicks the "Save" button. The terminal sends this save request to the server (e.g., POST / api / save_estimate). The server saves the received quote data in the database (e.g., INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);).

[0291] Step 8: Capturing Emotional Data

[0292] The device collects user emotional data in real time using a camera and microphone while the user is operating the device. The input is captured data from the sensors, and the output is emotional data. The emotional data is sent to the server in real time (e.g., POST / api / analyze_emotion).

[0293] Step 9: Analyze emotion data and generate feedback

[0294] The server analyzes the emotion data using an emotion engine. The input is emotion data (e.g., {"emotion": "sad", "intensity": 0.8}), and the output is a feedback message. For example, if the server determines that the user is in a "stressed" state based on the analysis results, it generates a message encouraging relaxation and sends it to the device as feedback (e.g., {"message": "Please take a short break"}).

[0295] The above is the specific processing flow of the program for this system. At each step, data processing and calculation are performed based on the input, and the results are output.

[0296] (Application example 2)

[0297] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0298] In modern stores, it is difficult to provide appropriate service based on the customer's emotional state while taking into account fluctuations in sales prices at the time of creating a quote. Conventional systems not only provide accurate price information in real time, but also lack the ability to recognize and respond to customer emotions, which means that the customer experience is not fully improved.

[0299] The identification process by the identification 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 sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for recognizing customer emotions and providing appropriate feedback, and means for creating product quotations. This makes it possible to create accurate and fair quotations in real time and to provide services that take into account the emotional state of the customer.

[0300] "Sales price data" is data that indicates the latest price information related to the selling price of a product.

[0301] An "unsupervised learning algorithm" is an algorithm that performs pattern detection and clustering using unlabeled data.

[0302] An "anomaly detection algorithm" is an algorithm for detecting anomalous patterns or values ​​in data.

[0303] The "determination result" indicates whether the data obtained using the anomaly detection algorithm is correct or incorrect.

[0304] "Recognizing customer emotions" means using a camera or microphone to analyze the customer's facial expressions and voice to determine their emotional state.

[0305] "Appropriate feedback" refers to information and actions that provide messages and support to promote relaxation based on the customer's emotional state.

[0306] A "product quotation" is a document created based on price information about a product, and indicates the conditions for purchase.

[0307] A system for implementing the present invention is constructed based on the following elements.

[0308] The server periodically retrieves the latest price information from the sales price database. The retrieved data is stored in memory or cache for quick access. This price data is provided by the server when requested by the terminal when creating a quote.

[0309] The server trains an anomaly detection model using an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. This model is then used to detect anomalies based on new sales price data. The anomaly detection algorithm generates a judgment result, and a warning message is generated if an anomaly is detected.

[0310] The device is also equipped with a camera and microphone, which are used to recognize the user's emotions. Emotional data is sent to the server in real time, and the server analyzes it using an emotion engine. Appropriate feedback based on the user's emotional state is generated and sent to the device.

[0311] As a concrete example, when a salesperson in a physical store prepares a product quotation, the terminal retrieves the latest sales price data from the server and prepares the quotation. The prepared quotation data is sent to the server and saved. If the emotion engine determines that the customer is feeling stressed at this time, a message such as "Please take a short break" will be displayed.

[0312] The following specific technical elements are used to realize this system:

[0313] Hardware: Smartphone, smart glasses or tablet, camera, microphone installed in a physical store

[0314] Software: Python, sklearn (running unsupervised learning algorithms), opencv (image processing), emotion_recognition (emotion engine)

[0315] As an example of an application of a generative AI model, the following prompt sentence predicts market price data.

[0316] "Given current market price data, what is your predicted price for next month?"

[0317] The system enables accurate and fair quotes that take customer sentiment into account, improving the customer experience.

[0318] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0319] Step 1:

[0320] The server periodically retrieves the latest price information from a sales price database. This database contains information such as product ID, current price, and timestamp. The retrieved data is stored in memory or cache for quick access. Specifically, the server executes an SQL query (e.g., SELECT product_id, current_price, timestamp FROM price_data;) and stores the results in memory.

[0321] Input: Sales price database

[0322] Output: Latest sales price data

[0323] Step 2:

[0324] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) on historical sales price data, which generates an anomaly detection model. Unsupervised learning is used to cluster historical data and identify anomalous data points.

[0325] Input: Historical sales price data

[0326] Output: A trained model

[0327] Step 3:

[0328] When a user opens the screen to create a new quote, the terminal requests the current sales price data from the server. The server returns the latest sales price data to the terminal. Specifically, the terminal sends an HTTP request (e.g., GET / api / current_prices) to the server, and the server returns data in JSON format.

[0329] Input: A request from the user

[0330] Output: Current sales price data

[0331] Step 4:

[0332] The terminal sends an anomaly detection request to the server based on the current sales price data. The server runs the anomaly detection algorithm and returns the result to the terminal. Specifically, the terminal sends a request including the price data (e.g., POST / api / detect_anomaly), and the server determines whether there is an anomaly and returns a response.

[0333] Input: Current sales price data

[0334] Output: Anomaly detection result

[0335] Step 5:

[0336] If an abnormal price is detected, the server generates and sends a warning message to the terminal, a specific example of which is the message "An abnormal price has been detected."

[0337] Input: Anomaly detection result

[0338] Output: Warning message

[0339] Step 6:

[0340] The user creates a quote based on the provided price information. After completing the quote, the user clicks the save button, and the device sends the quote data to the server and requests that it be saved. The server then saves the received quote data in a database.

[0341] Input: Quotation data

[0342] Output: Quote saved in database

[0343] Step 7:

[0344] The device recognizes the user's emotions using a camera and microphone while the user is operating the device. The emotion data is sent to the server in real time, and the server analyzes the emotion data using an emotion engine. Appropriate feedback is generated based on the analysis results and sent to the device.

[0345] Input: User emotion data

[0346] Output: Sentiment analysis results and feedback

[0347] Specifically, the device captures emotional data using a camera and microphone and sends it to the server. The server then analyzes the data using its emotion engine, and if it determines that the user is in a state of stress, it generates and returns a message saying, "Please take a short break."

[0348] In this way, a system will be built that provides accurate price information in real time and delivers services based on customer sentiment.

[0349] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0350] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0351] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0352] [Second embodiment]

[0353] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0354] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0355] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0356] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0357] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0358] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0359] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0360] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0361] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0362] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0363] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0364] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0365] This invention relates to a system that generates accurate quotations based on a nationwide standard, taking into account fluctuations in sales prices at the time of creation of the quotation. The system automatically acquires sales price data, trains an unsupervised learning algorithm, performs anomaly detection, outputs the results, and generates warning messages as needed.

[0366] Explanation of program processing

[0367] Obtaining sales price data

[0368] The server periodically retrieves the latest price information from the sales price database and stores it in memory or cache. The server also returns the latest sales price data in response to a request from a terminal.

[0369] When a user creates a new quotation, the terminal requests the current sales price data from the server and receives the latest sales price data as a response from the server.

[0370] Examples:

[0371] The server retrieves the price data by executing an SQL query such as SELECT product_id, current_price, timestamp FROM price_data;

[0372] The device sends an HTTP request such as GET / api / current_prices to the server, and the server returns {"product_id": 123, "current_price": 1500} as a response.

[0373] Identifying price fluctuations

[0374] The server trains an unsupervised learning algorithm based on historical sales price data, and the trained model is used for anomaly detection to determine whether a normal price exists within the range of price data.

[0375] The terminal sends a request to the server to determine if the current sale price is within a range.

[0376] Examples:

[0377] The server analyzes and trains past data using algorithms such as Isolation Forest.

[0378] The terminal sends the current price to the server and makes a request such as POST / api / detect_anomaly. The server determines the price and returns {"status": "normal"} in the response.

[0379] Detecting abnormal prices

[0380] The server runs an anomaly detection algorithm against current price data to determine anomalous prices, and if an anomalous price is detected, the server generates a warning message.

[0381] The terminal receives a response from the server stating the abnormality, and if an abnormality is detected, displays a warning message to the user.

[0382] Examples:

[0383] The server runs an anomaly detection algorithm and returns {"status": "abnormal"} as the result in case of abnormal prices.

[0384] The terminal receives the response indicating the abnormality and notifies the user that an abnormal price has been detected.

[0385] Create and save quotes

[0386] The user creates a quote based on the pricing information provided. Once the quote is complete, the user clicks the "Save" button to save the quote.

[0387] The terminal sends the created quotation data to the server and requests that it be saved. The server saves the quotation data in a database.

[0388] Examples:

[0389] The user creates a quote using the terminal interface and clicks the "Save" button.

[0390] The terminal sends a request, POST / api / save_estimate, along with the data to the server, and the server saves the estimate data in the database with a query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0391] The processing flow will be explained below.

[0392] Program processing steps

[0393] Obtaining sales price data

[0394] Step 1:

[0395] The server periodically retrieves the latest price information from the sales price database. For example, it executes the following SQL query to retrieve sales price data: SELECT product_id, current_price, timestamp FROM price_data;

[0396] Step 2:

[0397] The server stores the obtained price data in memory or cache for quick access.

[0398] Step 3:

[0399] When a user opens a screen to create a new quote, the terminal automatically requests sales price data from the server by sending an HTTP request such as GET / api / current_prices.

[0400] Step 4:

[0401] The server receives the request from the device, retrieves the latest sales price data from memory or cache, and returns it as an HTTP response. Response example: {"product_id": 123, "current_price": 1500}

[0402] Identifying price fluctuations

[0403] Step 5:

[0404] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. Through this training, it learns the normal price range.

[0405] Step 6:

[0406] The server stores the trained model and waits for the next request.

[0407] Step 7:

[0408] The device sends a request to the server to perform anomaly detection based on the current selling price. For example, send data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly.

[0409] Step 8:

[0410] The server runs an anomaly detection algorithm on the received data to determine whether it is normal or abnormal. The result is returned as an HTTP response. Example response: {"status": "normal"}

[0411] Detecting abnormal prices

[0412] Step 9:

[0413] The server determines whether the price is within the normal range or is abnormal based on the results of the anomaly detection algorithm, and if it is abnormal, generates a warning message.

[0414] Step 10:

[0415] The terminal receives the response from the server, and if it is within the normal range, it notifies the user and allows them to continue. If it is within the abnormal range, a warning message is displayed to the user. Example of display: "An abnormal price has been detected. Please check again."

[0416] Create and save quotes

[0417] Step 11:

[0418] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button.

[0419] Step 12:

[0420] The terminal sends the created estimate data to the server and requests that it be saved. For example, send data such as {"estimate_id": 456, "product_id": 123, "price": 1500} to the endpoint POST / api / save_estimate.

[0421] Step 13:

[0422] The server saves the received quote data in the database by executing the following SQL query: INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0423] Step 14:

[0424] The server returns a response to the terminal indicating that the save was successful. Example response: {"status": "success", "message": "The quote has been saved"}

[0425] The above are the specific processing steps in the embodiment for carrying out the invention.

[0426] Example 1

[0427] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0428] With the previous quotation creation system, it was difficult to reflect fluctuations in sales prices in real time, making it impossible to create accurate quotation. Furthermore, there was a lack of functionality to respond immediately when abnormal prices were detected, which created a risk of submitting inaccurate quotation. Furthermore, the process of saving quotation was often done manually, which reduced work efficiency.

[0429] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0430] In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for requesting the latest sales price data when a user creates a new estimate, means for providing the sales price data as a response, means for generating and outputting a warning message when an abnormal price is detected, and means for creating and saving estimate data. This enables accurate and prompt creation of estimates while taking into account fluctuations in sales prices and immediate response to abnormal prices.

[0431] "Sales price data" is data that records price information for products and services, including product ID, current price, timestamp, etc.

[0432] An "unsupervised learning algorithm" is a type of machine learning algorithm that finds patterns and relationships from unlabeled data and is used for model training.

[0433] An "anomaly detection algorithm" is an algorithm that detects unusual patterns or exceptions in data, identifying data that falls outside of the normal range.

[0434] A "quote" is a document that details the products or services to be provided and their prices, and is used to make a formal price proposal to a customer.

[0435] A "server" is a computer system that is connected to a network and provides data and resources to other computer systems (clients).

[0436] A "terminal" is a computer system that is operated by a user and communicates with a server, and data is input and results are received via a user interface.

[0437] "User" means any person or entity that operates the System and utilizes its functions, such as generating quotes.

[0438] The system of this invention is a system for creating accurate quotations that reflect changes in sales prices in real time. Specifically, it includes a series of processes, such as acquiring sales price data, training an unsupervised learning algorithm, performing anomaly detection, outputting the judgment results, generating warning messages, and saving quotations.

[0439] Obtaining sales price data

[0440] The server accesses the sales price database at regular intervals to obtain the latest price information. For example, it periodically executes an SQL query such as SELECT product_id, current_price, timestamp FROM price_data; to obtain price data. The obtained data is then stored in memory or cache. When a user creates a new quote, the terminal sends an HTTP request, GET / api / current_prices, to the server, and the server provides the latest sales price data as a response. For example, it returns data in the format {"product_id": 123, "current_price": 1500}.

[0441] Training unsupervised learning algorithms

[0442] The server collects historical sales price data and trains an unsupervised learning algorithm. Specifically, it analyzes the data using algorithms such as Isolation Forest to train a model for anomaly detection. The trained model is then stored in storage.

[0443] Determining current price data

[0444] The user's device sends current price data to the server for a decision. For example, a request such as POST / api / detect_anomaly is sent to the endpoint. The server uses a trained anomaly detection model to judge the received price data and returns the result. Examples of responses include {"status": "normal"} and {"status": "abnormal"}.

[0445] Detecting abnormal prices

[0446] After receiving the current price data, the server runs an anomaly detection algorithm to determine whether the price is abnormal. For example, it can generate a warning message such as {"status": "abnormal", "message": "Price is abnormal"}. The terminal receives this warning message and notifies the user, displaying a message such as "An abnormal price has been detected."

[0447] Create and save quotes

[0448] The user uses the terminal interface to create a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button. The terminal sends the quote data to the server via a POST / api / save_estimate request. The server then saves the received quote data to the database. For example, it does so by executing an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0449] As described above, the system of the present invention is designed to reflect fluctuations in selling prices in real time, thereby creating accurate and up-to-date estimates and responding immediately to abnormal prices.

[0450] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0451] Step 1: Obtaining sales price data

[0452] The server periodically accesses the sales price database to obtain the latest price information. Specifically, the server executes the SQL query SELECT product_id, current_price, timestamp FROM price_data; to extract price data. This extracted data is temporarily stored in memory or cache and used in subsequent processes. When a user creates a new quote, the terminal sends an HTTP request, GET / api / current_prices, to the server to request sales price data. The server returns the latest sales price data in JSON format as a response.

[0453] Input: Request price information from sales price database

[0454] Output: Latest price information stored in memory or cache, and sales price data as a response to the terminal

[0455] Step 2: Training the unsupervised learning algorithm

[0456] The server performs unsupervised learning using algorithms such as the Isolation Forest algorithm based on past sales price data. The server extracts past price data from the database and inputs it into the algorithm. This algorithm learns patterns in the price data and generates a model that identifies outliers. The trained model is saved in storage and can be reused in subsequent anomaly detection processes.

[0457] Input: Historical sales price data

[0458] Output: A trained anomaly detection model

[0459] Step 3: Determine current price data

[0460] When a user performs a price data judgment, the terminal sends the current price data to the server. For example, price data is sent to the endpoint POST / api / detect_anomaly. The server analyzes the received current price data using a trained anomaly detection model and judges whether it is an anomaly. The server returns the judgment result in JSON format to the terminal. For example, a response such as {"status": "normal"} or {"status": "abnormal"} is possible.

[0461] Input: Current price data

[0462] Output: Abnormality judgment result

[0463] Step 4: Detecting price anomalies

[0464] The server runs an anomaly detection algorithm on the current price data it receives to determine whether the price is abnormal. If an abnormal price is detected, the server generates a warning message. For example, the message is generated in the format {"status": "abnormal", "message": "The price is abnormal"}. The terminal receives the response from the server and displays the warning message to the user.

[0465] Input: Current price data

[0466] Output: Abnormal price warning message

[0467] Step 5: Create and save a quote

[0468] The user uses the terminal interface to create a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button. The terminal sends the created quote data to the server with the request POST / api / save_estimate. The server saves the received quote data in the database. For example, it saves it in the database using an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0469] Input: Quotation data

[0470] Output: Quote saved in database

[0471] The above is the specific processing flow of the program for this system.

[0472] (Application example 1)

[0473] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0474] In conventional quotation creation systems, it was difficult to reflect fluctuations in sales price data in real time, detect abnormal prices, and take appropriate measures. Furthermore, when abnormal prices occurred, warnings had to be issued manually, which was inefficient. Furthermore, creating and saving quotations was often done manually, which required time and effort. The present invention aims to solve these problems and provide a system that automatically and efficiently creates quotations and responds to price fluctuations.

[0475] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0476] In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for issuing a warning signal when an anomaly is detected, means for automatically creating an estimate based on normal price data, means for saving the created estimate and making it accessible later, and means for executing the above series of processes using a robot, thereby enabling real-time acquisition of sales price data, anomaly detection, warning function, and automatic estimate creation and saving.

[0477] The "means for acquiring sales price data" is a function that allows a server or robot to acquire the latest sales price data from the server and store it in a usable format.

[0478] "Means for training an unsupervised learning algorithm based on past sales price data" refers to a function that uses past price data to train an unsupervised learning algorithm for detecting abnormal prices using a server or computer, and creates a model of the algorithm.

[0479] "Means for executing an anomaly detection algorithm on current sales price data and outputting the determination results" is a function for executing an anomaly detection algorithm based on the latest price data to determine price anomalies and output the results.

[0480] The "means for issuing a warning signal when an abnormality is detected" is a function for issuing a warning signal such as sound or light when price data is determined to be abnormal.

[0481] The "means for automatically creating a quotation based on normal price data" is a function for automatically creating a required quotation based on normal price data.

[0482] "Means for saving the created estimate and making it accessible later" is a function for saving automatically created estimate data and making it possible to access or refer to it in the future.

[0483] The "means for executing the series of processes using a robot" is a function that enables a robot to execute a series of processes including obtaining sales price data, detecting abnormalities, issuing warning signals, and automatically creating and saving estimates.

[0484] This invention is a system consisting of the following processing steps: First, the server periodically obtains the latest sales price data and stores it in memory or cache. This sales price data is for later use by the robot. The server also trains an unsupervised learning algorithm based on the past sales price data to generate an anomaly detection model. This model is implemented using an algorithm such as Isolation Forest.

[0485] The robot retrieves the latest sales price data from the server and requests an anomaly detection algorithm from the server to determine whether the current sales price is within the normal range. If an abnormality is detected, the server has the function of issuing a warning signal. This warning is issued by sound or light, and notifies the worker visually or audibly of the existence of an abnormal price.

[0486] Furthermore, if valid price data is obtained, the robot automatically creates a quote. This quote is sent to the server and saved in the database. The saved quote data is kept in a state that can be accessed later. This process automates and efficiently performs the entire process from creating to saving quotes.

[0487] For example, if a robot obtains the price of a specific part and the price exceeds the normal range, the server will immediately detect the abnormality and send a warning signal to the worker. In addition, a delivery quotation will be automatically created based on the normal price data and saved on the server.

[0488] Below is an example of a textual input prompt for a generative AI model:

[0489] "Design an anomaly detection system for part price data obtained by a factory robot. The following requirements must be met: 1. The robot periodically retrieves the latest price data from the server. 2. Implement an anomaly detection algorithm based on past price data. 3. Implement a function to issue a warning if an abnormal price is detected. 4. Automatically create a quote based on normal price data and save it on the server. Example: Price data: [

[0100] ,

[0150] ,

[0200] ,

[0120] ,

[0160] ,

[0210] ,

[0140] ,

[0170] ,

[0220] ,

[0180] ] Abnormal price: 200 Warning method: Speaker, flashing light Quote data: {"part_id": 123, "quantity": 10, "total_price": 1500}"

[0490] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0491] Step 1:

[0492] The server periodically retrieves the latest price information from the sales price database. This information is stored in memory or cache. Specifically, the server retrieves the latest sales price data by executing the SQL query SELECT product_id, current_price, timestamp FROM price_data; The input is the query result from the price database, and the output is the latest price information stored in memory or cache.

[0493] Step 2:

[0494] When a user creates a new quote, the terminal requests current sales price data from the server. The server receives an HTTP request, GET / api / current_prices, and returns the latest sales price data as a response. The input is the HTTP request, and the output is a JSON-formatted response containing the current sales price data.

[0495] Step 3:

[0496] The server trains a model using an unsupervised learning algorithm such as Isolation Forest based on past sales price data. The input is the past sales price data, and the output is an anomaly detection model. This model is used to determine whether there is a normal price within the range of price data.

[0497] Step 4:

[0498] The device sends a request to the server to determine whether the current selling price is within a range. Specifically, it makes a request called POST / api / detect_anomaly and sends the current price. The server inputs this price into an anomaly detection model to determine whether it is an anomaly. The output is a response that stores the status of an anomaly or normal.

[0499] Step 5:

[0500] Based on the results of the anomaly determination, the server generates a warning message if an abnormal price is detected. The terminal receives this response and issues a warning to the user saying, "An abnormal price has been detected." The input is the result of the anomaly determination, and the output is a warning message to the user. Specifically, a warning signal is emitted using sound or light.

[0501] Step 6:

[0502] The user creates a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button to save the quote. The terminal sends the created quote data to the server and requests it to be saved. The input is the quote data created by the user, and the output is the quote saved on the server. The server executes the query INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500); to save it in the database.

[0503] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0504] This invention relates to a system that generates accurate quotations based on a uniform standard nationwide, taking into account fluctuations in sales prices at the time of creation of the quotation. This system includes functions for automatically acquiring sales price data, training unsupervised learning algorithms, performing anomaly detection, outputting the results, and generating warning messages as necessary. Furthermore, it incorporates an emotion engine that recognizes user emotions, and adds a function for providing appropriate feedback to the user.

[0505] Explanation of program processing

[0506] Obtaining sales price data

[0507] The server periodically retrieves the latest price information from the sales price database. The retrieved data is stored in memory or cache for quick access. When a user opens a screen for creating a new quote, the terminal requests the current sales price data from the server. The server returns the latest sales price data to the terminal.

[0508] Examples:

[0509] The server retrieves the price data by executing an SQL query such as SELECT product_id, current_price, timestamp FROM price_data;

[0510] The device sends an HTTP request such as GET / api / current_prices to the server, and the server returns {"product_id": 123, "current_price": 1500} as a response.

[0511] Identifying price fluctuations

[0512] Next, the server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. The trained model is used for anomaly detection to determine whether there is a normal price within the range of price data. The device sends a request to the server to perform anomaly detection based on the current sales price. The server runs the anomaly detection algorithm and returns the results.

[0513] Examples:

[0514] The server trains the unsupervised learning algorithm and generates the model.

[0515] The device sends data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly. The server determines the price and returns a response with {"status": "normal"}.

[0516] Detecting abnormal prices

[0517] The server runs an anomaly detection algorithm on the current price data to determine if a price is abnormal. If an abnormal price is detected, it generates a warning message. The terminal receives the response from the server and displays a warning message to the user if an abnormality is detected.

[0518] Examples:

[0519] The server runs an anomaly detection algorithm and returns the result {"status": "abnormal"} in case of abnormal prices.

[0520] The terminal receives the response indicating the abnormality detection and notifies the user with a warning message saying "An abnormal price has been detected."

[0521] Create and save quotes

[0522] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button. The device sends the created quote data to the server and requests that it be saved. The server saves the received quote data in its database.

[0523] Examples:

[0524] The user creates a quote using the terminal interface and clicks the "Save" button.

[0525] The device sends a POST / api / save_estimate request with the data to the server, which saves it to the database with the SQL query INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0526] Emotion engine integration

[0527] The device uses a camera and microphone to recognize the user's emotions while the user is operating the device. The emotion data is sent to the server in real time. The server then uses an emotion engine to analyze the emotion data and generate appropriate feedback based on the user's emotional state.

[0528] Examples:

[0529] The device uses a camera and microphone to capture the user's facial expressions and voice, and sends the emotion data to the server using the endpoint POST / api / analyze_emotion.

[0530] The server analyzes the data using an emotion engine, and if it determines, for example, that the user is in a state of stress, it generates a message encouraging relaxation and returns the response {"message": "Please take a short break"}.

[0531] The above is a concrete example of how to implement the invention by combining an emotion engine. This system combines accurate reflection of sales price information with feedback based on the user's emotions, enabling more efficient and user-friendly quotation creation.

[0532] The processing flow will be explained below.

[0533] Obtaining sales price data

[0534] Step 1:

[0535] The server periodically retrieves the latest price information from the sales price database. For example, it executes the following SQL query to retrieve sales price data: SELECT product_id, current_price, timestamp FROM price_data;

[0536] Step 2:

[0537] The server stores the obtained price data in memory or cache for quick access.

[0538] Step 3:

[0539] When a user opens a screen to create a new quote, the terminal automatically requests sales price data from the server by sending an HTTP request such as GET / api / current_prices.

[0540] Step 4:

[0541] The server receives the request from the device, retrieves the latest sales price data from memory or cache, and returns it as an HTTP response. Response example: {"product_id": 123, "current_price": 1500}

[0542] Identifying price fluctuations

[0543] Step 5:

[0544] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. Through this training, it learns the normal price range.

[0545] Step 6:

[0546] The server stores the trained model and waits for the next request.

[0547] Step 7:

[0548] The device sends a request to the server to perform anomaly detection based on the current selling price. For example, send data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly.

[0549] Step 8:

[0550] The server runs an anomaly detection algorithm on the received data to determine whether it is normal or abnormal. The result is returned as an HTTP response. Example response: {"status": "normal"}

[0551] Detecting abnormal prices

[0552] Step 9:

[0553] The server determines whether the price is within the normal range or is abnormal based on the results of the anomaly detection algorithm, and if it is abnormal, generates a warning message.

[0554] Step 10:

[0555] The terminal receives the response from the server, and if it is within the normal range, it notifies the user and allows them to continue. If it is within the abnormal range, a warning message is displayed to the user. Example of display: "An abnormal price has been detected. Please check again."

[0556] Create and save quotes

[0557] Step 11:

[0558] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button.

[0559] Step 12:

[0560] The terminal sends the created estimate data to the server and requests that it be saved. For example, send data such as {"estimate_id": 456, "product_id": 123, "price": 1500} to the endpoint POST / api / save_estimate.

[0561] Step 13:

[0562] The server saves the received estimate data in the database by executing an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0563] Step 14:

[0564] The server returns a response to the terminal indicating that the save was successful. Example response: {"status": "success", "message": "The quote has been saved"}

[0565] Emotion engine integration

[0566] Step 15:

[0567] The device uses a camera and microphone to recognize the user's emotions while the user is operating the device, and the emotion data is sent to the server in real time.

[0568] Step 16:

[0569] The server uses an emotion engine to analyze the emotion data and generate appropriate feedback based on the user's emotional state.

[0570] Step 17:

[0571] The server generates a feedback message for the user based on the emotion analysis results and sends it to the terminal. For example, if the server determines that the user is in a "stressed state," it generates a message saying, "Please take a short break."

[0572] Step 18:

[0573] The terminal receives the feedback message sent from the server and displays it to the user. Example: "Your current work seems stressful. Please take a short break."

[0574] The above are the specific processing steps for implementing the invention that combines an emotion engine. This system achieves more efficient and user-friendly quotation creation by combining accurate reflection of sales price information with feedback based on the user's emotions.

[0575] Example 2

[0576] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0577] Conventional quotation creation systems do not adequately consider fluctuations in sales prices or the detection of abnormal prices, making it difficult to create accurate quotation documents. Furthermore, they lack feedback that takes into account the user's emotional state, resulting in a lack of improvement in the user experience.

[0578] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting a determination result, means for acquiring and analyzing emotion data, and means for generating appropriate feedback based on the user's emotional state. This not only makes it possible to create accurate estimates that take into account fluctuations in sales prices and abnormal prices, but also makes it possible to provide feedback according to the user's emotional state, improving the user experience.

[0579] "Sales Price Data" means information about the selling price of a product, obtained from a database or other source.

[0580] "Unsupervised learning algorithms" is a general term for algorithms used to train models using unlabeled data to perform tasks such as classification and clustering.

[0581] An "anomaly detection algorithm" is an algorithm that detects data points in a dataset that do not fit a normal pattern.

[0582] The "judgment result" is the conclusion obtained after executing the anomaly detection algorithm, whether the data is normal or abnormal.

[0583] "Emotional data" is information that indicates the user's emotional state and is collected through sensors such as cameras and microphones.

[0584] "Analytical means" are technical devices and algorithms used to process collected data and extract useful information.

[0585] "Feedback" refers to the responses or instructions that a system provides to a user, based on the user's emotional state and operational status.

[0586] This invention relates to a system for creating accurate quotations that take into account fluctuations in sales prices. The system has the functions of automatically acquiring sales price data, training unsupervised learning algorithms, performing anomaly detection, outputting judgment results, and analyzing emotion data and generating feedback.

[0587] Obtaining sales price data

[0588] The server retrieves the latest price information from the sales price database at a fixed time. This task is performed by a scheduled job, for example, at 2:00 AM every day. The specific software used is a database management system (for example, MySQL), which retrieves price data by executing the SQL query SELECT product_id, current_price, timestamp FROM price_data;. The retrieved data is stored in memory or cached for quick access.

[0589] When a user opens a screen for creating a new quote, the terminal requests the latest sales price data from the server. The request from the terminal is sent using the HTTP protocol in the format GET / api / current_prices. The server receives the request and returns the latest price data it has saved in JSON format to the terminal.

[0590] Identifying price fluctuations

[0591] Next, the server trains a model using an unsupervised learning algorithm (e.g., Isolation Forest) based on the collected historical sales price data. The model is generated using a Python machine learning library (e.g., scikit-learn). The trained model is saved and later used for anomaly detection.

[0592] The terminal sends an anomaly detection request to the server based on the current selling price entered by the user. The request format is POST / api / detect_anomaly, and sends data such as {"product_id": 123, "price": 1500}. The server runs the anomaly detection algorithm based on this data and returns the results to the terminal. If the result is normal, it is returned as {"status": "normal"}, and if it is an abnormal value, it is returned as {"status": "abnormal"}.

[0593] Detecting abnormal prices

[0594] The server runs an anomaly detection algorithm against the current price data to determine if a price is abnormal. If an abnormal price is detected, it generates a warning message. The generated warning message has the format {"message": "An abnormal price has been detected"}.

[0595] The terminal displays the received warning message to the user, who can then quickly respond by checking the on-screen warning that "an abnormal price has been detected."

[0596] Create and save quotes

[0597] The user creates a quote using the device interface, entering product information and pricing and clicking the "Save" button.

[0598] The terminal sends the created estimate data to the server and requests that it be saved. The request format is POST / api / save_estimate, and sends the following data, for example: {"estimate_id": 456, "product_id": 123, "price": 1500}.

[0599] The server saves the received estimate data in the database by executing the following SQL query: INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0600] Emotion engine integration

[0601] The device uses the camera and microphone to recognize the user's emotions while the user is operating the device. Emotion data is collected in real time and sent to the server. The sending format is POST / api / analyze_emotion, and data such as {"emotion": "sad", "intensity": 0.8} is sent.

[0602] The server analyzes the data collected by the emotion engine and generates appropriate feedback based on the user's emotional state. For example, if the server determines that the user is in a stressful state, it generates a message encouraging relaxation and sends the response {"message": "Please take a short break"} to the device.

[0603] The above describes a specific embodiment of the present invention. This system combines accurate reflection of sales price information with feedback based on the user's emotions to create more efficient and user-friendly estimates.

[0604] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0605] Specific flow of program processing

[0606] Step 1: Obtaining sales price data

[0607] The server periodically retrieves the latest price information from the sales price database. The input is a database query (e.g. SELECT product_id, current_price, timestamp FROM price_data;) and the output is the latest sales price data. Specifically, it executes an SQL query from the database and stores the price data in memory or cache, making it readily accessible.

[0608] Step 2: User Request

[0609] When a user opens the screen for creating a new quote, the terminal sends a request to the server to obtain current sales price data. The input is the user's operation, and the output is an HTTP request (e.g., GET / api / current_prices). Based on this request, the server retrieves the latest price information from memory or cache and returns it to the terminal in JSON format (e.g., {"product_id": 123, "current_price": 1500}).

[0610] Step 3: Determine price fluctuations

[0611] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. The input is past sales price data, and the output is the trained model. Specifically, it trains the algorithm using a Python machine learning library (e.g., scikit-learn) and saves the generated model.

[0612] Step 4: Anomaly detection request

[0613] The terminal sends an anomaly detection request to the server based on the current sales price. The input is the current sales price data (e.g., {"product_id": 123, "price": 1500}), and the output is an HTTP request (e.g., POST / api / detect_anomaly). After receiving the request, the server runs the anomaly detection algorithm and outputs the results.

[0614] Step 5: Detecting price anomalies

[0615] The server runs an anomaly detection algorithm to determine whether a price is abnormal. The input is the data of the anomaly detection request, and the output is the anomaly determination result (e.g., {"status": "abnormal"}). If an anomaly is detected, a warning message (e.g., {"message": "An abnormal price has been detected"}) is generated.

[0616] Step 6: Displaying warning messages

[0617] The terminal receives the abnormality determination result and warning message from the server and displays them to the user. The input is the response data from the server, and the output is the display of the warning message to the user. The user can see the message "An abnormal price has been detected" on the terminal screen.

[0618] Step 7: Create and save a quote

[0619] The user creates a quote using the terminal. The input is product information and price data, and the output is the quote data. After completing the quote, the user clicks the "Save" button. The terminal sends this save request to the server (e.g., POST / api / save_estimate). The server saves the received quote data in the database (e.g., INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);).

[0620] Step 8: Capturing Emotional Data

[0621] The device collects user emotional data in real time using a camera and microphone while the user is operating the device. The input is captured data from the sensors, and the output is emotional data. The emotional data is sent to the server in real time (e.g., POST / api / analyze_emotion).

[0622] Step 9: Analyze emotion data and generate feedback

[0623] The server analyzes the emotion data using an emotion engine. The input is emotion data (e.g., {"emotion": "sad", "intensity": 0.8}), and the output is a feedback message. For example, if the server determines that the user is in a "stressed" state based on the analysis results, it generates a message encouraging relaxation and sends it to the device as feedback (e.g., {"message": "Please take a short break"}).

[0624] The above is the specific processing flow of the program for this system. At each step, data processing and calculation are performed based on the input, and the results are output.

[0625] (Application example 2)

[0626] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0627] In modern stores, it is difficult to provide appropriate service based on the customer's emotional state while taking into account fluctuations in sales prices at the time of creating a quote. Conventional systems not only provide accurate price information in real time, but also lack the ability to recognize and respond to customer emotions, which means that the customer experience is not fully improved.

[0628] The identification process by the identification 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 sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for recognizing customer emotions and providing appropriate feedback, and means for creating product quotations. This makes it possible to create accurate and fair quotations in real time and to provide services that take into account the emotional state of the customer.

[0629] "Sales price data" is data that indicates the latest price information related to the selling price of a product.

[0630] An "unsupervised learning algorithm" is an algorithm that performs pattern detection and clustering using unlabeled data.

[0631] An "anomaly detection algorithm" is an algorithm for detecting anomalous patterns or values ​​in data.

[0632] The "determination result" indicates whether the data obtained using the anomaly detection algorithm is correct or incorrect.

[0633] "Recognizing customer emotions" means using a camera or microphone to analyze the customer's facial expressions and voice to determine their emotional state.

[0634] "Appropriate feedback" refers to information and actions that provide messages and support to promote relaxation based on the customer's emotional state.

[0635] A "product quotation" is a document created based on price information about a product, and indicates the conditions for purchase.

[0636] A system for implementing the present invention is constructed based on the following elements.

[0637] The server periodically retrieves the latest price information from the sales price database. The retrieved data is stored in memory or cache for quick access. This price data is provided by the server when requested by the terminal when creating a quote.

[0638] The server trains an anomaly detection model using an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. This model is then used to detect anomalies based on new sales price data. The anomaly detection algorithm generates a judgment result, and a warning message is generated if an anomaly is detected.

[0639] The device is also equipped with a camera and microphone, which are used to recognize the user's emotions. Emotional data is sent to the server in real time, and the server analyzes it using an emotion engine. Appropriate feedback based on the user's emotional state is generated and sent to the device.

[0640] As a concrete example, when a salesperson in a physical store prepares a product quotation, the terminal retrieves the latest sales price data from the server and prepares the quotation. The prepared quotation data is sent to the server and saved. If the emotion engine determines that the customer is feeling stressed at this time, a message such as "Please take a short break" will be displayed.

[0641] The following specific technical elements are used to realize this system:

[0642] Hardware: Smartphone, smart glasses or tablet, camera, microphone installed in a physical store

[0643] Software: Python, sklearn (running unsupervised learning algorithms), opencv (image processing), emotion_recognition (emotion engine)

[0644] As an example of an application of a generative AI model, the following prompt sentence predicts market price data.

[0645] "Given current market price data, what is your predicted price for next month?"

[0646] The system enables accurate and fair quotes that take customer sentiment into account, improving the customer experience.

[0647] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0648] Step 1:

[0649] The server periodically retrieves the latest price information from a sales price database. This database contains information such as product ID, current price, and timestamp. The retrieved data is stored in memory or cache for quick access. Specifically, the server executes an SQL query (e.g., SELECT product_id, current_price, timestamp FROM price_data;) and stores the results in memory.

[0650] Input: Sales price database

[0651] Output: Latest sales price data

[0652] Step 2:

[0653] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) on historical sales price data, which generates an anomaly detection model. Unsupervised learning is used to cluster historical data and identify anomalous data points.

[0654] Input: Historical sales price data

[0655] Output: A trained model

[0656] Step 3:

[0657] When a user opens the screen to create a new quote, the terminal requests the current sales price data from the server. The server returns the latest sales price data to the terminal. Specifically, the terminal sends an HTTP request (e.g., GET / api / current_prices) to the server, and the server returns data in JSON format.

[0658] Input: A request from the user

[0659] Output: Current sales price data

[0660] Step 4:

[0661] The terminal sends an anomaly detection request to the server based on the current sales price data. The server runs the anomaly detection algorithm and returns the result to the terminal. Specifically, the terminal sends a request including the price data (e.g., POST / api / detect_anomaly), and the server determines whether there is an anomaly and returns a response.

[0662] Input: Current sales price data

[0663] Output: Anomaly detection result

[0664] Step 5:

[0665] If an abnormal price is detected, the server generates and sends a warning message to the terminal, a specific example of which is the message "An abnormal price has been detected."

[0666] Input: Anomaly detection result

[0667] Output: Warning message

[0668] Step 6:

[0669] The user creates a quote based on the provided price information. After completing the quote, the user clicks the save button, and the device sends the quote data to the server and requests that it be saved. The server then saves the received quote data in a database.

[0670] Input: Quotation data

[0671] Output: Quote saved in database

[0672] Step 7:

[0673] The device recognizes the user's emotions using a camera and microphone while the user is operating the device. The emotion data is sent to the server in real time, and the server analyzes the emotion data using an emotion engine. Appropriate feedback is generated based on the analysis results and sent to the device.

[0674] Input: User emotion data

[0675] Output: Sentiment analysis results and feedback

[0676] Specifically, the device captures emotional data using a camera and microphone and sends it to the server. The server then analyzes the data using its emotion engine, and if it determines that the user is in a state of stress, it generates and returns a message saying, "Please take a short break."

[0677] In this way, a system will be built that provides accurate price information in real time and delivers services based on customer sentiment.

[0678] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0679] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0680] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0681] [Third embodiment]

[0682] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0683] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0684] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0685] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0686] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0687] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0688] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0689] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0690] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0691] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0692] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0693] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0694] This invention relates to a system that generates accurate quotations based on a nationwide standard, taking into account fluctuations in sales prices at the time of creation of the quotation. The system automatically acquires sales price data, trains an unsupervised learning algorithm, performs anomaly detection, outputs the results, and generates warning messages as needed.

[0695] Explanation of program processing

[0696] Obtaining sales price data

[0697] The server periodically retrieves the latest price information from the sales price database and stores it in memory or cache. The server also returns the latest sales price data in response to a request from a terminal.

[0698] When a user creates a new quotation, the terminal requests the current sales price data from the server and receives the latest sales price data as a response from the server.

[0699] Examples:

[0700] The server retrieves the price data by executing an SQL query such as SELECT product_id, current_price, timestamp FROM price_data;

[0701] The device sends an HTTP request such as GET / api / current_prices to the server, and the server returns {"product_id": 123, "current_price": 1500} as a response.

[0702] Identifying price fluctuations

[0703] The server trains an unsupervised learning algorithm based on historical sales price data, and the trained model is used for anomaly detection to determine whether a normal price exists within the range of price data.

[0704] The terminal sends a request to the server to determine if the current sale price is within a range.

[0705] Examples:

[0706] The server analyzes and trains past data using algorithms such as Isolation Forest.

[0707] The terminal sends the current price to the server and makes a request such as POST / api / detect_anomaly. The server determines the price and returns {"status": "normal"} in the response.

[0708] Detecting abnormal prices

[0709] The server runs an anomaly detection algorithm against current price data to determine anomalous prices, and if an anomalous price is detected, the server generates a warning message.

[0710] The terminal receives a response from the server stating the abnormality, and if an abnormality is detected, displays a warning message to the user.

[0711] Examples:

[0712] The server runs an anomaly detection algorithm and returns {"status": "abnormal"} as the result in case of abnormal prices.

[0713] The terminal receives the response indicating the abnormality and notifies the user that an abnormal price has been detected.

[0714] Create and save quotes

[0715] The user creates a quote based on the pricing information provided. Once the quote is complete, the user clicks the "Save" button to save the quote.

[0716] The terminal sends the created quotation data to the server and requests that it be saved. The server saves the quotation data in a database.

[0717] Examples:

[0718] The user creates a quote using the terminal interface and clicks the "Save" button.

[0719] The terminal sends a request, POST / api / save_estimate, along with the data to the server, and the server saves the estimate data in the database with a query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0720] The processing flow will be explained below.

[0721] Program processing steps

[0722] Obtaining sales price data

[0723] Step 1:

[0724] The server periodically retrieves the latest price information from the sales price database. For example, it executes the following SQL query to retrieve sales price data: SELECT product_id, current_price, timestamp FROM price_data;

[0725] Step 2:

[0726] The server stores the obtained price data in memory or cache for quick access.

[0727] Step 3:

[0728] When a user opens a screen to create a new quote, the terminal automatically requests sales price data from the server by sending an HTTP request such as GET / api / current_prices.

[0729] Step 4:

[0730] The server receives the request from the device, retrieves the latest sales price data from memory or cache, and returns it as an HTTP response. Response example: {"product_id": 123, "current_price": 1500}

[0731] Identifying price fluctuations

[0732] Step 5:

[0733] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. Through this training, it learns the normal price range.

[0734] Step 6:

[0735] The server stores the trained model and waits for the next request.

[0736] Step 7:

[0737] The device sends a request to the server to perform anomaly detection based on the current selling price. For example, send data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly.

[0738] Step 8:

[0739] The server runs an anomaly detection algorithm on the received data to determine whether it is normal or abnormal. The result is returned as an HTTP response. Example response: {"status": "normal"}

[0740] Detecting abnormal prices

[0741] Step 9:

[0742] The server determines whether the price is within the normal range or is abnormal based on the results of the anomaly detection algorithm, and if it is abnormal, generates a warning message.

[0743] Step 10:

[0744] The terminal receives the response from the server, and if it is within the normal range, it notifies the user and allows them to continue. If it is within the abnormal range, a warning message is displayed to the user. Example of display: "An abnormal price has been detected. Please check again."

[0745] Create and save quotes

[0746] Step 11:

[0747] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button.

[0748] Step 12:

[0749] The terminal sends the created estimate data to the server and requests that it be saved. For example, send data such as {"estimate_id": 456, "product_id": 123, "price": 1500} to the endpoint POST / api / save_estimate.

[0750] Step 13:

[0751] The server saves the received quote data in the database by executing the following SQL query: INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0752] Step 14:

[0753] The server returns a response to the terminal indicating that the save was successful. Example response: {"status": "success", "message": "The quote has been saved"}

[0754] The above are the specific processing steps in the embodiment for carrying out the invention.

[0755] Example 1

[0756] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0757] With the previous quotation creation system, it was difficult to reflect fluctuations in sales prices in real time, making it impossible to create accurate quotation. Furthermore, there was a lack of functionality to respond immediately when abnormal prices were detected, which created a risk of submitting inaccurate quotation. Furthermore, the process of saving quotation was often done manually, which reduced work efficiency.

[0758] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0759] In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for requesting the latest sales price data when a user creates a new estimate, means for providing the sales price data as a response, means for generating and outputting a warning message when an abnormal price is detected, and means for creating and saving estimate data. This enables accurate and prompt creation of estimates while taking into account fluctuations in sales prices and immediate response to abnormal prices.

[0760] "Sales price data" is data that records price information for products and services, including product ID, current price, timestamp, etc.

[0761] An "unsupervised learning algorithm" is a type of machine learning algorithm that finds patterns and relationships from unlabeled data and is used for model training.

[0762] An "anomaly detection algorithm" is an algorithm that detects unusual patterns or exceptions in data, identifying data that falls outside of the normal range.

[0763] A "quote" is a document that details the products or services to be provided and their prices, and is used to make a formal price proposal to a customer.

[0764] A "server" is a computer system that is connected to a network and provides data and resources to other computer systems (clients).

[0765] A "terminal" is a computer system that is operated by a user and communicates with a server, and data is input and results are received via a user interface.

[0766] "User" means any person or entity that operates the System and utilizes its functions, such as generating quotes.

[0767] The system of this invention is a system for creating accurate quotations that reflect changes in sales prices in real time. Specifically, it includes a series of processes, such as acquiring sales price data, training an unsupervised learning algorithm, performing anomaly detection, outputting the judgment results, generating warning messages, and saving quotations.

[0768] Obtaining sales price data

[0769] The server accesses the sales price database at regular intervals to obtain the latest price information. For example, it periodically executes an SQL query such as SELECT product_id, current_price, timestamp FROM price_data; to obtain price data. The obtained data is then stored in memory or cache. When a user creates a new quote, the terminal sends an HTTP request, GET / api / current_prices, to the server, and the server provides the latest sales price data as a response. For example, it returns data in the format {"product_id": 123, "current_price": 1500}.

[0770] Training unsupervised learning algorithms

[0771] The server collects historical sales price data and trains an unsupervised learning algorithm. Specifically, it analyzes the data using algorithms such as Isolation Forest to train a model for anomaly detection. The trained model is then stored in storage.

[0772] Determining current price data

[0773] The user's device sends current price data to the server for a decision. For example, a request such as POST / api / detect_anomaly is sent to the endpoint. The server uses a trained anomaly detection model to judge the received price data and returns the result. Examples of responses include {"status": "normal"} and {"status": "abnormal"}.

[0774] Detecting abnormal prices

[0775] After receiving the current price data, the server runs an anomaly detection algorithm to determine whether the price is abnormal. For example, it can generate a warning message such as {"status": "abnormal", "message": "Price is abnormal"}. The terminal receives this warning message and notifies the user, displaying a message such as "An abnormal price has been detected."

[0776] Create and save quotes

[0777] The user uses the terminal interface to create a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button. The terminal sends the quote data to the server via a POST / api / save_estimate request. The server then saves the received quote data to the database. For example, it does so by executing an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0778] As described above, the system of the present invention is designed to reflect fluctuations in selling prices in real time, thereby creating accurate and up-to-date estimates and responding immediately to abnormal prices.

[0779] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0780] Step 1: Obtaining sales price data

[0781] The server periodically accesses the sales price database to obtain the latest price information. Specifically, the server executes the SQL query SELECT product_id, current_price, timestamp FROM price_data; to extract price data. This extracted data is temporarily stored in memory or cache and used in subsequent processes. When a user creates a new quote, the terminal sends an HTTP request, GET / api / current_prices, to the server to request sales price data. The server returns the latest sales price data in JSON format as a response.

[0782] Input: Request price information from sales price database

[0783] Output: Latest price information stored in memory or cache, and sales price data as a response to the terminal

[0784] Step 2: Training the unsupervised learning algorithm

[0785] The server performs unsupervised learning using algorithms such as the Isolation Forest algorithm based on past sales price data. The server extracts past price data from the database and inputs it into the algorithm. This algorithm learns patterns in the price data and generates a model that identifies outliers. The trained model is saved in storage and can be reused in subsequent anomaly detection processes.

[0786] Input: Historical sales price data

[0787] Output: A trained anomaly detection model

[0788] Step 3: Determine current price data

[0789] When a user performs a price data judgment, the terminal sends the current price data to the server. For example, price data is sent to the endpoint POST / api / detect_anomaly. The server analyzes the received current price data using a trained anomaly detection model and judges whether it is an anomaly. The server returns the judgment result in JSON format to the terminal. For example, a response such as {"status": "normal"} or {"status": "abnormal"} is possible.

[0790] Input: Current price data

[0791] Output: Abnormality judgment result

[0792] Step 4: Detecting price anomalies

[0793] The server runs an anomaly detection algorithm on the current price data it receives to determine whether the price is abnormal. If an abnormal price is detected, the server generates a warning message. For example, the message is generated in the format {"status": "abnormal", "message": "The price is abnormal"}. The terminal receives the response from the server and displays the warning message to the user.

[0794] Input: Current price data

[0795] Output: Abnormal price warning message

[0796] Step 5: Create and save a quote

[0797] The user uses the terminal interface to create a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button. The terminal sends the created quote data to the server with the request POST / api / save_estimate. The server saves the received quote data in the database. For example, it saves it in the database using an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0798] Input: Quotation data

[0799] Output: Quote saved in database

[0800] The above is the specific processing flow of the program for this system.

[0801] (Application example 1)

[0802] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0803] In conventional quotation creation systems, it was difficult to reflect fluctuations in sales price data in real time, detect abnormal prices, and take appropriate measures. Furthermore, when abnormal prices occurred, warnings had to be issued manually, which was inefficient. Furthermore, creating and saving quotations was often done manually, which required time and effort. The present invention aims to solve these problems and provide a system that automatically and efficiently creates quotations and responds to price fluctuations.

[0804] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0805] In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for issuing a warning signal when an anomaly is detected, means for automatically creating an estimate based on normal price data, means for saving the created estimate and making it accessible later, and means for executing the above series of processes using a robot, thereby enabling real-time acquisition of sales price data, anomaly detection, warning function, and automatic estimate creation and saving.

[0806] The "means for acquiring sales price data" is a function that allows a server or robot to acquire the latest sales price data from the server and store it in a usable format.

[0807] "Means for training an unsupervised learning algorithm based on past sales price data" refers to a function that uses past price data to train an unsupervised learning algorithm for detecting abnormal prices using a server or computer, and creates a model of the algorithm.

[0808] "Means for executing an anomaly detection algorithm on current sales price data and outputting the determination results" is a function for executing an anomaly detection algorithm based on the latest price data to determine price anomalies and output the results.

[0809] The "means for issuing a warning signal when an abnormality is detected" is a function for issuing a warning signal such as sound or light when price data is determined to be abnormal.

[0810] The "means for automatically creating a quotation based on normal price data" is a function for automatically creating a required quotation based on normal price data.

[0811] "Means for saving the created estimate and making it accessible later" is a function for saving automatically created estimate data and making it possible to access or refer to it in the future.

[0812] The "means for executing the series of processes using a robot" is a function that enables a robot to execute a series of processes including obtaining sales price data, detecting abnormalities, issuing warning signals, and automatically creating and saving estimates.

[0813] This invention is a system consisting of the following processing steps: First, the server periodically obtains the latest sales price data and stores it in memory or cache. This sales price data is for later use by the robot. The server also trains an unsupervised learning algorithm based on the past sales price data to generate an anomaly detection model. This model is implemented using an algorithm such as Isolation Forest.

[0814] The robot retrieves the latest sales price data from the server and requests an anomaly detection algorithm from the server to determine whether the current sales price is within the normal range. If an abnormality is detected, the server has the function of issuing a warning signal. This warning is issued by sound or light, and notifies the worker visually or audibly of the existence of an abnormal price.

[0815] Furthermore, if valid price data is obtained, the robot automatically creates a quote. This quote is sent to the server and saved in the database. The saved quote data is kept in a state that can be accessed later. This process automates and efficiently performs the entire process from creating to saving quotes.

[0816] For example, if a robot obtains the price of a specific part and the price exceeds the normal range, the server will immediately detect the abnormality and send a warning signal to the worker. In addition, a delivery quotation will be automatically created based on the normal price data and saved on the server.

[0817] Below is an example of a textual input prompt for a generative AI model:

[0818] "Design an anomaly detection system for part price data obtained by a factory robot. The following requirements must be met: 1. The robot periodically retrieves the latest price data from the server. 2. Implement an anomaly detection algorithm based on past price data. 3. Implement a function to issue a warning if an abnormal price is detected. 4. Automatically create a quote based on normal price data and save it on the server. Example: Price data: [

[0100] ,

[0150] ,

[0200] ,

[0120] ,

[0160] ,

[0210] ,

[0140] ,

[0170] ,

[0220] ,

[0180] ] Abnormal price: 200 Warning method: Speaker, flashing light Quote data: {"part_id": 123, "quantity": 10, "total_price": 1500}"

[0819] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0820] Step 1:

[0821] The server periodically retrieves the latest price information from the sales price database. This information is stored in memory or cache. Specifically, the server retrieves the latest sales price data by executing the SQL query SELECT product_id, current_price, timestamp FROM price_data; The input is the query result from the price database, and the output is the latest price information stored in memory or cache.

[0822] Step 2:

[0823] When a user creates a new quote, the terminal requests current sales price data from the server. The server receives an HTTP request, GET / api / current_prices, and returns the latest sales price data as a response. The input is the HTTP request, and the output is a JSON-formatted response containing the current sales price data.

[0824] Step 3:

[0825] The server trains a model using an unsupervised learning algorithm such as Isolation Forest based on past sales price data. The input is the past sales price data, and the output is an anomaly detection model. This model is used to determine whether there is a normal price within the range of price data.

[0826] Step 4:

[0827] The device sends a request to the server to determine whether the current selling price is within a range. Specifically, it makes a request called POST / api / detect_anomaly and sends the current price. The server inputs this price into an anomaly detection model to determine whether it is an anomaly. The output is a response that stores the status of an anomaly or normal.

[0828] Step 5:

[0829] Based on the results of the anomaly determination, the server generates a warning message if an abnormal price is detected. The terminal receives this response and issues a warning to the user saying, "An abnormal price has been detected." The input is the result of the anomaly determination, and the output is a warning message to the user. Specifically, a warning signal is emitted using sound or light.

[0830] Step 6:

[0831] The user creates a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button to save the quote. The terminal sends the created quote data to the server and requests it to be saved. The input is the quote data created by the user, and the output is the quote saved on the server. The server executes the query INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500); to save it in the database.

[0832] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0833] This invention relates to a system that generates accurate quotations based on a uniform standard nationwide, taking into account fluctuations in sales prices at the time of creation of the quotation. This system includes functions for automatically acquiring sales price data, training unsupervised learning algorithms, performing anomaly detection, outputting the results, and generating warning messages as necessary. Furthermore, it incorporates an emotion engine that recognizes user emotions, and adds a function for providing appropriate feedback to the user.

[0834] Explanation of program processing

[0835] Obtaining sales price data

[0836] The server periodically retrieves the latest price information from the sales price database. The retrieved data is stored in memory or cache for quick access. When a user opens a screen for creating a new quote, the terminal requests the current sales price data from the server. The server returns the latest sales price data to the terminal.

[0837] Examples:

[0838] The server retrieves the price data by executing an SQL query such as SELECT product_id, current_price, timestamp FROM price_data;

[0839] The device sends an HTTP request such as GET / api / current_prices to the server, and the server returns {"product_id": 123, "current_price": 1500} as a response.

[0840] Identifying price fluctuations

[0841] Next, the server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. The trained model is used for anomaly detection to determine whether there is a normal price within the range of price data. The device sends a request to the server to perform anomaly detection based on the current sales price. The server runs the anomaly detection algorithm and returns the results.

[0842] Examples:

[0843] The server trains the unsupervised learning algorithm and generates the model.

[0844] The device sends data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly. The server determines the price and returns a response with {"status": "normal"}.

[0845] Detecting abnormal prices

[0846] The server runs an anomaly detection algorithm on the current price data to determine if a price is abnormal. If an abnormal price is detected, it generates a warning message. The terminal receives the response from the server and displays a warning message to the user if an abnormality is detected.

[0847] Examples:

[0848] The server runs an anomaly detection algorithm and returns the result {"status": "abnormal"} in case of abnormal prices.

[0849] The terminal receives the response indicating the abnormality detection and notifies the user with a warning message saying "An abnormal price has been detected."

[0850] Create and save quotes

[0851] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button. The device sends the created quote data to the server and requests that it be saved. The server saves the received quote data in its database.

[0852] Examples:

[0853] The user creates a quote using the terminal interface and clicks the "Save" button.

[0854] The device sends a POST / api / save_estimate request with the data to the server, which saves it to the database with the SQL query INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0855] Emotion engine integration

[0856] The device uses a camera and microphone to recognize the user's emotions while the user is operating the device. The emotion data is sent to the server in real time. The server then uses an emotion engine to analyze the emotion data and generate appropriate feedback based on the user's emotional state.

[0857] Examples:

[0858] The device uses a camera and microphone to capture the user's facial expressions and voice, and sends the emotion data to the server using the endpoint POST / api / analyze_emotion.

[0859] The server analyzes the data using an emotion engine, and if it determines, for example, that the user is in a state of stress, it generates a message encouraging relaxation and returns the response {"message": "Please take a short break"}.

[0860] The above is a concrete example of how to implement the invention by combining an emotion engine. This system combines accurate reflection of sales price information with feedback based on the user's emotions, enabling more efficient and user-friendly quotation creation.

[0861] The processing flow will be explained below.

[0862] Obtaining sales price data

[0863] Step 1:

[0864] The server periodically retrieves the latest price information from the sales price database. For example, it executes the following SQL query to retrieve sales price data: SELECT product_id, current_price, timestamp FROM price_data;

[0865] Step 2:

[0866] The server stores the obtained price data in memory or cache for quick access.

[0867] Step 3:

[0868] When a user opens a screen to create a new quote, the terminal automatically requests sales price data from the server by sending an HTTP request such as GET / api / current_prices.

[0869] Step 4:

[0870] The server receives the request from the device, retrieves the latest sales price data from memory or cache, and returns it as an HTTP response. Response example: {"product_id": 123, "current_price": 1500}

[0871] Identifying price fluctuations

[0872] Step 5:

[0873] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. Through this training, it learns the normal price range.

[0874] Step 6:

[0875] The server stores the trained model and waits for the next request.

[0876] Step 7:

[0877] The device sends a request to the server to perform anomaly detection based on the current selling price. For example, send data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly.

[0878] Step 8:

[0879] The server runs an anomaly detection algorithm on the received data to determine whether it is normal or abnormal. The result is returned as an HTTP response. Example response: {"status": "normal"}

[0880] Detecting abnormal prices

[0881] Step 9:

[0882] The server determines whether the price is within the normal range or is abnormal based on the results of the anomaly detection algorithm, and if it is abnormal, generates a warning message.

[0883] Step 10:

[0884] The terminal receives the response from the server, and if it is within the normal range, it notifies the user and allows them to continue. If it is within the abnormal range, a warning message is displayed to the user. Example of display: "An abnormal price has been detected. Please check again."

[0885] Create and save quotes

[0886] Step 11:

[0887] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button.

[0888] Step 12:

[0889] The terminal sends the created estimate data to the server and requests that it be saved. For example, send data such as {"estimate_id": 456, "product_id": 123, "price": 1500} to the endpoint POST / api / save_estimate.

[0890] Step 13:

[0891] The server saves the received estimate data in the database by executing an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0892] Step 14:

[0893] The server returns a response to the terminal indicating that the save was successful. Example response: {"status": "success", "message": "The quote has been saved"}

[0894] Emotion engine integration

[0895] Step 15:

[0896] The device uses a camera and microphone to recognize the user's emotions while the user is operating the device, and the emotion data is sent to the server in real time.

[0897] Step 16:

[0898] The server uses an emotion engine to analyze the emotion data and generate appropriate feedback based on the user's emotional state.

[0899] Step 17:

[0900] The server generates a feedback message for the user based on the emotion analysis results and sends it to the terminal. For example, if the server determines that the user is in a "stressed state," it generates a message saying, "Please take a short break."

[0901] Step 18:

[0902] The terminal receives the feedback message sent from the server and displays it to the user. Example: "Your current work seems stressful. Please take a short break."

[0903] The above are the specific processing steps for implementing the invention that combines an emotion engine. This system achieves more efficient and user-friendly quotation creation by combining accurate reflection of sales price information with feedback based on the user's emotions.

[0904] Example 2

[0905] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0906] Conventional quotation creation systems do not adequately consider fluctuations in sales prices or the detection of abnormal prices, making it difficult to create accurate quotation documents. Furthermore, they lack feedback that takes into account the user's emotional state, resulting in a lack of improvement in the user experience.

[0907] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting a determination result, means for acquiring and analyzing emotion data, and means for generating appropriate feedback based on the user's emotional state. This not only makes it possible to create accurate estimates that take into account fluctuations in sales prices and abnormal prices, but also makes it possible to provide feedback according to the user's emotional state, improving the user experience.

[0908] "Sales Price Data" means information about the selling price of a product, obtained from a database or other source.

[0909] "Unsupervised learning algorithms" is a general term for algorithms used to train models using unlabeled data to perform tasks such as classification and clustering.

[0910] An "anomaly detection algorithm" is an algorithm that detects data points in a dataset that do not fit a normal pattern.

[0911] The "judgment result" is the conclusion obtained after executing the anomaly detection algorithm, whether the data is normal or abnormal.

[0912] "Emotional data" is information that indicates the user's emotional state and is collected through sensors such as cameras and microphones.

[0913] "Analytical means" are technical devices and algorithms used to process collected data and extract useful information.

[0914] "Feedback" refers to the responses or instructions that a system provides to a user, based on the user's emotional state and operational status.

[0915] This invention relates to a system for creating accurate quotations that take into account fluctuations in sales prices. The system has the functions of automatically acquiring sales price data, training unsupervised learning algorithms, performing anomaly detection, outputting judgment results, and analyzing emotion data and generating feedback.

[0916] Obtaining sales price data

[0917] The server retrieves the latest price information from the sales price database at a fixed time. This task is performed by a scheduled job, for example, at 2:00 AM every day. The specific software used is a database management system (for example, MySQL), which retrieves price data by executing the SQL query SELECT product_id, current_price, timestamp FROM price_data;. The retrieved data is stored in memory or cached for quick access.

[0918] When a user opens a screen for creating a new quote, the terminal requests the latest sales price data from the server. The request from the terminal is sent using the HTTP protocol in the format GET / api / current_prices. The server receives the request and returns the latest price data it has saved in JSON format to the terminal.

[0919] Identifying price fluctuations

[0920] Next, the server trains a model using an unsupervised learning algorithm (e.g., Isolation Forest) based on the collected historical sales price data. The model is generated using a Python machine learning library (e.g., scikit-learn). The trained model is saved and later used for anomaly detection.

[0921] The terminal sends an anomaly detection request to the server based on the current selling price entered by the user. The request format is POST / api / detect_anomaly, and sends data such as {"product_id": 123, "price": 1500}. The server runs the anomaly detection algorithm based on this data and returns the results to the terminal. If the result is normal, it is returned as {"status": "normal"}, and if it is an abnormal value, it is returned as {"status": "abnormal"}.

[0922] Detecting abnormal prices

[0923] The server runs an anomaly detection algorithm against the current price data to determine if a price is abnormal. If an abnormal price is detected, it generates a warning message. The generated warning message has the format {"message": "An abnormal price has been detected"}.

[0924] The terminal displays the received warning message to the user, who can then quickly respond by checking the on-screen warning that "an abnormal price has been detected."

[0925] Create and save quotes

[0926] The user creates a quote using the device interface, entering product information and pricing and clicking the "Save" button.

[0927] The terminal sends the created estimate data to the server and requests that it be saved. The request format is POST / api / save_estimate, and sends the following data, for example: {"estimate_id": 456, "product_id": 123, "price": 1500}.

[0928] The server saves the received estimate data in the database by executing the following SQL query: INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[0929] Emotion engine integration

[0930] The device uses the camera and microphone to recognize the user's emotions while the user is operating the device. Emotion data is collected in real time and sent to the server. The sending format is POST / api / analyze_emotion, and data such as {"emotion": "sad", "intensity": 0.8} is sent.

[0931] The server analyzes the data collected by the emotion engine and generates appropriate feedback based on the user's emotional state. For example, if the server determines that the user is in a stressful state, it generates a message encouraging relaxation and sends the response {"message": "Please take a short break"} to the device.

[0932] The above describes a specific embodiment of the present invention. This system combines accurate reflection of sales price information with feedback based on the user's emotions to create more efficient and user-friendly estimates.

[0933] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0934] Specific flow of program processing

[0935] Step 1: Obtaining sales price data

[0936] The server periodically retrieves the latest price information from the sales price database. The input is a database query (e.g. SELECT product_id, current_price, timestamp FROM price_data;) and the output is the latest sales price data. Specifically, it executes an SQL query from the database and stores the price data in memory or cache, making it readily accessible.

[0937] Step 2: User Request

[0938] When a user opens the screen for creating a new quote, the terminal sends a request to the server to obtain current sales price data. The input is the user's operation, and the output is an HTTP request (e.g., GET / api / current_prices). Based on this request, the server retrieves the latest price information from memory or cache and returns it to the terminal in JSON format (e.g., {"product_id": 123, "current_price": 1500}).

[0939] Step 3: Determine price fluctuations

[0940] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. The input is past sales price data, and the output is the trained model. Specifically, it trains the algorithm using a Python machine learning library (e.g., scikit-learn) and saves the generated model.

[0941] Step 4: Anomaly detection request

[0942] The terminal sends an anomaly detection request to the server based on the current sales price. The input is the current sales price data (e.g., {"product_id": 123, "price": 1500}), and the output is an HTTP request (e.g., POST / api / detect_anomaly). After receiving the request, the server runs the anomaly detection algorithm and outputs the results.

[0943] Step 5: Detecting price anomalies

[0944] The server runs an anomaly detection algorithm to determine whether a price is abnormal. The input is the data of the anomaly detection request, and the output is the anomaly determination result (e.g., {"status": "abnormal"}). If an anomaly is detected, a warning message (e.g., {"message": "An abnormal price has been detected"}) is generated.

[0945] Step 6: Displaying warning messages

[0946] The terminal receives the abnormality determination result and warning message from the server and displays them to the user. The input is the response data from the server, and the output is the display of the warning message to the user. The user can see the message "An abnormal price has been detected" on the terminal screen.

[0947] Step 7: Create and save a quote

[0948] The user creates a quote using the terminal. The input is product information and price data, and the output is the quote data. After completing the quote, the user clicks the "Save" button. The terminal sends this save request to the server (e.g., POST / api / save_estimate). The server saves the received quote data in the database (e.g., INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);).

[0949] Step 8: Capturing Emotional Data

[0950] The device collects user emotional data in real time using a camera and microphone while the user is operating the device. The input is captured data from the sensors, and the output is emotional data. The emotional data is sent to the server in real time (e.g., POST / api / analyze_emotion).

[0951] Step 9: Analyze emotion data and generate feedback

[0952] The server analyzes the emotion data using an emotion engine. The input is emotion data (e.g., {"emotion": "sad", "intensity": 0.8}), and the output is a feedback message. For example, if the server determines that the user is in a "stressed" state based on the analysis results, it generates a message encouraging relaxation and sends it to the device as feedback (e.g., {"message": "Please take a short break"}).

[0953] The above is the specific processing flow of the program for this system. At each step, data processing and calculation are performed based on the input, and the results are output.

[0954] (Application example 2)

[0955] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0956] In modern stores, it is difficult to provide appropriate service based on the customer's emotional state while taking into account fluctuations in sales prices at the time of creating a quote. Conventional systems not only provide accurate price information in real time, but also lack the ability to recognize and respond to customer emotions, which means that the customer experience is not fully improved.

[0957] The identification process by the identification 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 sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for recognizing customer emotions and providing appropriate feedback, and means for creating product quotations. This makes it possible to create accurate and fair quotations in real time and to provide services that take into account the emotional state of the customer.

[0958] "Sales price data" is data that indicates the latest price information related to the selling price of a product.

[0959] An "unsupervised learning algorithm" is an algorithm that performs pattern detection and clustering using unlabeled data.

[0960] An "anomaly detection algorithm" is an algorithm for detecting anomalous patterns or values ​​in data.

[0961] The "determination result" indicates whether the data obtained using the anomaly detection algorithm is correct or incorrect.

[0962] "Recognizing customer emotions" means using a camera or microphone to analyze the customer's facial expressions and voice to determine their emotional state.

[0963] "Appropriate feedback" refers to information and actions that provide messages and support to promote relaxation based on the customer's emotional state.

[0964] A "product quotation" is a document created based on price information about a product, and indicates the conditions for purchase.

[0965] A system for implementing the present invention is constructed based on the following elements.

[0966] The server periodically retrieves the latest price information from the sales price database. The retrieved data is stored in memory or cache for quick access. This price data is provided by the server when requested by the terminal when creating a quote.

[0967] The server trains an anomaly detection model using an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. This model is then used to detect anomalies based on new sales price data. The anomaly detection algorithm generates a judgment result, and a warning message is generated if an anomaly is detected.

[0968] The device is also equipped with a camera and microphone, which are used to recognize the user's emotions. Emotional data is sent to the server in real time, and the server analyzes it using an emotion engine. Appropriate feedback based on the user's emotional state is generated and sent to the device.

[0969] As a concrete example, when a salesperson in a physical store prepares a product quotation, the terminal retrieves the latest sales price data from the server and prepares the quotation. The prepared quotation data is sent to the server and saved. If the emotion engine determines that the customer is feeling stressed at this time, a message such as "Please take a short break" will be displayed.

[0970] The following specific technical elements are used to realize this system:

[0971] Hardware: Smartphone, smart glasses or tablet, camera, microphone installed in a physical store

[0972] Software: Python, sklearn (running unsupervised learning algorithms), opencv (image processing), emotion_recognition (emotion engine)

[0973] As an example of an application of a generative AI model, the following prompt sentence predicts market price data.

[0974] "Given current market price data, what is your predicted price for next month?"

[0975] The system enables accurate and fair quotes that take customer sentiment into account, improving the customer experience.

[0976] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0977] Step 1:

[0978] The server periodically retrieves the latest price information from a sales price database. This database contains information such as product ID, current price, and timestamp. The retrieved data is stored in memory or cache for quick access. Specifically, the server executes an SQL query (e.g., SELECT product_id, current_price, timestamp FROM price_data;) and stores the results in memory.

[0979] Input: Sales price database

[0980] Output: Latest sales price data

[0981] Step 2:

[0982] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) on historical sales price data, which generates an anomaly detection model. Unsupervised learning is used to cluster historical data and identify anomalous data points.

[0983] Input: Historical sales price data

[0984] Output: A trained model

[0985] Step 3:

[0986] When a user opens the screen to create a new quote, the terminal requests the current sales price data from the server. The server returns the latest sales price data to the terminal. Specifically, the terminal sends an HTTP request (e.g., GET / api / current_prices) to the server, and the server returns data in JSON format.

[0987] Input: A request from the user

[0988] Output: Current sales price data

[0989] Step 4:

[0990] The terminal sends an anomaly detection request to the server based on the current sales price data. The server runs the anomaly detection algorithm and returns the result to the terminal. Specifically, the terminal sends a request including the price data (e.g., POST / api / detect_anomaly), and the server determines whether there is an anomaly and returns a response.

[0991] Input: Current sales price data

[0992] Output: Anomaly detection result

[0993] Step 5:

[0994] If an abnormal price is detected, the server generates and sends a warning message to the terminal, a specific example of which is the message "An abnormal price has been detected."

[0995] Input: Anomaly detection result

[0996] Output: Warning message

[0997] Step 6:

[0998] The user creates a quote based on the provided price information. After completing the quote, the user clicks the save button, and the device sends the quote data to the server and requests that it be saved. The server then saves the received quote data in a database.

[0999] Input: Quotation data

[1000] Output: Quote saved in database

[1001] Step 7:

[1002] The device recognizes the user's emotions using a camera and microphone while the user is operating the device. The emotion data is sent to the server in real time, and the server analyzes the emotion data using an emotion engine. Appropriate feedback is generated based on the analysis results and sent to the device.

[1003] Input: User emotion data

[1004] Output: Sentiment analysis results and feedback

[1005] Specifically, the device captures emotional data using a camera and microphone and sends it to the server. The server then analyzes the data using its emotion engine, and if it determines that the user is in a state of stress, it generates and returns a message saying, "Please take a short break."

[1006] In this way, a system will be built that provides accurate price information in real time and delivers services based on customer sentiment.

[1007] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1008] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1009] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1010] [Fourth embodiment]

[1011] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1012] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1013] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1014] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1015] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1016] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1017] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1018] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1019] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1020] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1021] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1022] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1023] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1024] This invention relates to a system that generates accurate quotations based on a nationwide standard, taking into account fluctuations in sales prices at the time of creation of the quotation. The system automatically acquires sales price data, trains an unsupervised learning algorithm, performs anomaly detection, outputs the results, and generates warning messages as needed.

[1025] Explanation of program processing

[1026] Obtaining sales price data

[1027] The server periodically retrieves the latest price information from the sales price database and stores it in memory or cache. The server also returns the latest sales price data in response to a request from a terminal.

[1028] When a user creates a new quotation, the terminal requests the current sales price data from the server and receives the latest sales price data as a response from the server.

[1029] Examples:

[1030] The server retrieves the price data by executing an SQL query such as SELECT product_id, current_price, timestamp FROM price_data;

[1031] The device sends an HTTP request such as GET / api / current_prices to the server, and the server returns {"product_id": 123, "current_price": 1500} as a response.

[1032] Identifying price fluctuations

[1033] The server trains an unsupervised learning algorithm based on historical sales price data, and the trained model is used for anomaly detection to determine whether a normal price exists within the range of price data.

[1034] The terminal sends a request to the server to determine if the current sale price is within a range.

[1035] Examples:

[1036] The server analyzes and trains past data using algorithms such as Isolation Forest.

[1037] The terminal sends the current price to the server and makes a request such as POST / api / detect_anomaly. The server determines the price and returns {"status": "normal"} in the response.

[1038] Detecting abnormal prices

[1039] The server runs an anomaly detection algorithm against current price data to determine anomalous prices, and if an anomalous price is detected, the server generates a warning message.

[1040] The terminal receives a response from the server stating the abnormality, and if an abnormality is detected, displays a warning message to the user.

[1041] Examples:

[1042] The server runs an anomaly detection algorithm and returns {"status": "abnormal"} as the result in case of abnormal prices.

[1043] The terminal receives the response indicating the abnormality and notifies the user that an abnormal price has been detected.

[1044] Create and save quotes

[1045] The user creates a quote based on the pricing information provided. Once the quote is complete, the user clicks the "Save" button to save the quote.

[1046] The terminal sends the created quotation data to the server and requests that it be saved. The server saves the quotation data in a database.

[1047] Examples:

[1048] The user creates a quote using the terminal interface and clicks the "Save" button.

[1049] The terminal sends a request, POST / api / save_estimate, along with the data to the server, and the server saves the estimate data in the database with a query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[1050] The processing flow will be explained below.

[1051] Program processing steps

[1052] Obtaining sales price data

[1053] Step 1:

[1054] The server periodically retrieves the latest price information from the sales price database. For example, it executes the following SQL query to retrieve sales price data: SELECT product_id, current_price, timestamp FROM price_data;

[1055] Step 2:

[1056] The server stores the obtained price data in memory or cache for quick access.

[1057] Step 3:

[1058] When a user opens a screen to create a new quote, the terminal automatically requests sales price data from the server by sending an HTTP request such as GET / api / current_prices.

[1059] Step 4:

[1060] The server receives the request from the device, retrieves the latest sales price data from memory or cache, and returns it as an HTTP response. Response example: {"product_id": 123, "current_price": 1500}

[1061] Identifying price fluctuations

[1062] Step 5:

[1063] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. Through this training, it learns the normal price range.

[1064] Step 6:

[1065] The server stores the trained model and waits for the next request.

[1066] Step 7:

[1067] The device sends a request to the server to perform anomaly detection based on the current selling price. For example, send data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly.

[1068] Step 8:

[1069] The server runs an anomaly detection algorithm on the received data to determine whether it is normal or abnormal. The result is returned as an HTTP response. Example response: {"status": "normal"}

[1070] Detecting abnormal prices

[1071] Step 9:

[1072] The server determines whether the price is within the normal range or is abnormal based on the results of the anomaly detection algorithm, and if it is abnormal, generates a warning message.

[1073] Step 10:

[1074] The terminal receives the response from the server, and if it is within the normal range, it notifies the user and allows them to continue. If it is within the abnormal range, a warning message is displayed to the user. Example of display: "An abnormal price has been detected. Please check again."

[1075] Create and save quotes

[1076] Step 11:

[1077] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button.

[1078] Step 12:

[1079] The terminal sends the created estimate data to the server and requests that it be saved. For example, send data such as {"estimate_id": 456, "product_id": 123, "price": 1500} to the endpoint POST / api / save_estimate.

[1080] Step 13:

[1081] The server saves the received quote data in the database by executing the following SQL query: INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[1082] Step 14:

[1083] The server returns a response to the terminal indicating that the save was successful. Example response: {"status": "success", "message": "The quote has been saved"}

[1084] The above are the specific processing steps in the embodiment for carrying out the invention.

[1085] Example 1

[1086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1087] With the previous quotation creation system, it was difficult to reflect fluctuations in sales prices in real time, making it impossible to create accurate quotation. Furthermore, there was a lack of functionality to respond immediately when abnormal prices were detected, which created a risk of submitting inaccurate quotation. Furthermore, the process of saving quotation was often done manually, which reduced work efficiency.

[1088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1089] In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for requesting the latest sales price data when a user creates a new estimate, means for providing the sales price data as a response, means for generating and outputting a warning message when an abnormal price is detected, and means for creating and saving estimate data. This enables accurate and prompt creation of estimates while taking into account fluctuations in sales prices and immediate response to abnormal prices.

[1090] "Sales price data" is data that records price information for products and services, including product ID, current price, timestamp, etc.

[1091] An "unsupervised learning algorithm" is a type of machine learning algorithm that finds patterns and relationships from unlabeled data and is used for model training.

[1092] An "anomaly detection algorithm" is an algorithm that detects unusual patterns or exceptions in data, identifying data that falls outside of the normal range.

[1093] A "quote" is a document that details the products or services to be provided and their prices, and is used to make a formal price proposal to a customer.

[1094] A "server" is a computer system that is connected to a network and provides data and resources to other computer systems (clients).

[1095] A "terminal" is a computer system that is operated by a user and communicates with a server, and data is input and results are received via a user interface.

[1096] "User" means any person or entity that operates the System and utilizes its functions, such as generating quotes.

[1097] The system of this invention is a system for creating accurate quotations that reflect changes in sales prices in real time. Specifically, it includes a series of processes, such as acquiring sales price data, training an unsupervised learning algorithm, performing anomaly detection, outputting the judgment results, generating warning messages, and saving quotations.

[1098] Obtaining sales price data

[1099] The server accesses the sales price database at regular intervals to obtain the latest price information. For example, it periodically executes an SQL query such as SELECT product_id, current_price, timestamp FROM price_data; to obtain price data. The obtained data is then stored in memory or cache. When a user creates a new quote, the terminal sends an HTTP request, GET / api / current_prices, to the server, and the server provides the latest sales price data as a response. For example, it returns data in the format {"product_id": 123, "current_price": 1500}.

[1100] Training unsupervised learning algorithms

[1101] The server collects historical sales price data and trains an unsupervised learning algorithm. Specifically, it analyzes the data using algorithms such as Isolation Forest to train a model for anomaly detection. The trained model is then stored in storage.

[1102] Determining current price data

[1103] The user's device sends current price data to the server for a decision. For example, a request such as POST / api / detect_anomaly is sent to the endpoint. The server uses a trained anomaly detection model to judge the received price data and returns the result. Examples of responses include {"status": "normal"} and {"status": "abnormal"}.

[1104] Detecting abnormal prices

[1105] After receiving the current price data, the server runs an anomaly detection algorithm to determine whether the price is abnormal. For example, it can generate a warning message such as {"status": "abnormal", "message": "Price is abnormal"}. The terminal receives this warning message and notifies the user, displaying a message such as "An abnormal price has been detected."

[1106] Create and save quotes

[1107] The user uses the terminal interface to create a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button. The terminal sends the quote data to the server via a POST / api / save_estimate request. The server then saves the received quote data to the database. For example, it does so by executing an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[1108] As described above, the system of the present invention is designed to reflect fluctuations in selling prices in real time, thereby creating accurate and up-to-date estimates and responding immediately to abnormal prices.

[1109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1110] Step 1: Obtaining sales price data

[1111] The server periodically accesses the sales price database to obtain the latest price information. Specifically, the server executes the SQL query SELECT product_id, current_price, timestamp FROM price_data; to extract price data. This extracted data is temporarily stored in memory or cache and used in subsequent processes. When a user creates a new quote, the terminal sends an HTTP request, GET / api / current_prices, to the server to request sales price data. The server returns the latest sales price data in JSON format as a response.

[1112] Input: Request price information from sales price database

[1113] Output: Latest price information stored in memory or cache, and sales price data as a response to the terminal

[1114] Step 2: Training the unsupervised learning algorithm

[1115] The server performs unsupervised learning using algorithms such as the Isolation Forest algorithm based on past sales price data. The server extracts past price data from the database and inputs it into the algorithm. This algorithm learns patterns in the price data and generates a model that identifies outliers. The trained model is saved in storage and can be reused in subsequent anomaly detection processes.

[1116] Input: Historical sales price data

[1117] Output: A trained anomaly detection model

[1118] Step 3: Determine current price data

[1119] When a user performs a price data judgment, the terminal sends the current price data to the server. For example, price data is sent to the endpoint POST / api / detect_anomaly. The server analyzes the received current price data using a trained anomaly detection model and judges whether it is an anomaly. The server returns the judgment result in JSON format to the terminal. For example, a response such as {"status": "normal"} or {"status": "abnormal"} is possible.

[1120] Input: Current price data

[1121] Output: Abnormality judgment result

[1122] Step 4: Detecting price anomalies

[1123] The server runs an anomaly detection algorithm on the current price data it receives to determine whether the price is abnormal. If an abnormal price is detected, the server generates a warning message. For example, the message is generated in the format {"status": "abnormal", "message": "The price is abnormal"}. The terminal receives the response from the server and displays the warning message to the user.

[1124] Input: Current price data

[1125] Output: Abnormal price warning message

[1126] Step 5: Create and save a quote

[1127] The user uses the terminal interface to create a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button. The terminal sends the created quote data to the server with the request POST / api / save_estimate. The server saves the received quote data in the database. For example, it saves it in the database using an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[1128] Input: Quotation data

[1129] Output: Quote saved in database

[1130] The above is the specific processing flow of the program for this system.

[1131] (Application example 1)

[1132] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1133] In conventional quotation creation systems, it was difficult to reflect fluctuations in sales price data in real time, detect abnormal prices, and take appropriate measures. Furthermore, when abnormal prices occurred, warnings had to be issued manually, which was inefficient. Furthermore, creating and saving quotations was often done manually, which required time and effort. The present invention aims to solve these problems and provide a system that automatically and efficiently creates quotations and responds to price fluctuations.

[1134] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1135] In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for issuing a warning signal when an anomaly is detected, means for automatically creating an estimate based on normal price data, means for saving the created estimate and making it accessible later, and means for executing the above series of processes using a robot, thereby enabling real-time acquisition of sales price data, anomaly detection, warning function, and automatic estimate creation and saving.

[1136] The "means for acquiring sales price data" is a function that allows a server or robot to acquire the latest sales price data from the server and store it in a usable format.

[1137] "Means for training an unsupervised learning algorithm based on past sales price data" refers to a function that uses past price data to train an unsupervised learning algorithm for detecting abnormal prices using a server or computer, and creates a model of the algorithm.

[1138] "Means for executing an anomaly detection algorithm on current sales price data and outputting the determination results" is a function for executing an anomaly detection algorithm based on the latest price data to determine price anomalies and output the results.

[1139] The "means for issuing a warning signal when an abnormality is detected" is a function for issuing a warning signal such as sound or light when price data is determined to be abnormal.

[1140] The "means for automatically creating a quotation based on normal price data" is a function for automatically creating a required quotation based on normal price data.

[1141] "Means for saving the created estimate and making it accessible later" is a function for saving automatically created estimate data and making it possible to access or refer to it in the future.

[1142] The "means for executing the series of processes using a robot" is a function that enables a robot to execute a series of processes including obtaining sales price data, detecting abnormalities, issuing warning signals, and automatically creating and saving estimates.

[1143] This invention is a system consisting of the following processing steps: First, the server periodically obtains the latest sales price data and stores it in memory or cache. This sales price data is for later use by the robot. The server also trains an unsupervised learning algorithm based on the past sales price data to generate an anomaly detection model. This model is implemented using an algorithm such as Isolation Forest.

[1144] The robot retrieves the latest sales price data from the server and requests an anomaly detection algorithm from the server to determine whether the current sales price is within the normal range. If an abnormality is detected, the server has the function of issuing a warning signal. This warning is issued by sound or light, and notifies the worker visually or audibly of the existence of an abnormal price.

[1145] Furthermore, if valid price data is obtained, the robot automatically creates a quote. This quote is sent to the server and saved in the database. The saved quote data is kept in a state that can be accessed later. This process automates and efficiently performs the entire process from creating to saving quotes.

[1146] For example, if a robot obtains the price of a specific part and the price exceeds the normal range, the server will immediately detect the abnormality and send a warning signal to the worker. In addition, a delivery quotation will be automatically created based on the normal price data and saved on the server.

[1147] Below is an example of a textual input prompt for a generative AI model:

[1148] "Design an anomaly detection system for part price data obtained by a factory robot. The following requirements must be met: 1. The robot periodically retrieves the latest price data from the server. 2. Implement an anomaly detection algorithm based on past price data. 3. Implement a function to issue a warning if an abnormal price is detected. 4. Automatically create a quote based on normal price data and save it on the server. Example: Price data: [

[0100] ,

[0150] ,

[0200] ,

[0120] ,

[0160] ,

[0210] ,

[0140] ,

[0170] ,

[0220] ,

[0180] ] Abnormal price: 200 Warning method: Speaker, flashing light Quote data: {"part_id": 123, "quantity": 10, "total_price": 1500}"

[1149] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1150] Step 1:

[1151] The server periodically retrieves the latest price information from the sales price database. This information is stored in memory or cache. Specifically, the server retrieves the latest sales price data by executing the SQL query SELECT product_id, current_price, timestamp FROM price_data; The input is the query result from the price database, and the output is the latest price information stored in memory or cache.

[1152] Step 2:

[1153] When a user creates a new quote, the terminal requests current sales price data from the server. The server receives an HTTP request, GET / api / current_prices, and returns the latest sales price data as a response. The input is the HTTP request, and the output is a JSON-formatted response containing the current sales price data.

[1154] Step 3:

[1155] The server trains a model using an unsupervised learning algorithm such as Isolation Forest based on past sales price data. The input is the past sales price data, and the output is an anomaly detection model. This model is used to determine whether there is a normal price within the range of price data.

[1156] Step 4:

[1157] The device sends a request to the server to determine whether the current selling price is within a range. Specifically, it makes a request called POST / api / detect_anomaly and sends the current price. The server inputs this price into an anomaly detection model to determine whether it is an anomaly. The output is a response that stores the status of an anomaly or normal.

[1158] Step 5:

[1159] Based on the results of the anomaly determination, the server generates a warning message if an abnormal price is detected. The terminal receives this response and issues a warning to the user saying, "An abnormal price has been detected." The input is the result of the anomaly determination, and the output is a warning message to the user. Specifically, a warning signal is emitted using sound or light.

[1160] Step 6:

[1161] The user creates a quote based on the provided price information. When the quote is complete, the user clicks the "Save" button to save the quote. The terminal sends the created quote data to the server and requests it to be saved. The input is the quote data created by the user, and the output is the quote saved on the server. The server executes the query INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500); to save it in the database.

[1162] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1163] This invention relates to a system that generates accurate quotations based on a uniform standard nationwide, taking into account fluctuations in sales prices at the time of creation of the quotation. This system includes functions for automatically acquiring sales price data, training unsupervised learning algorithms, performing anomaly detection, outputting the results, and generating warning messages as necessary. Furthermore, it incorporates an emotion engine that recognizes user emotions, and adds a function for providing appropriate feedback to the user.

[1164] Explanation of program processing

[1165] Obtaining sales price data

[1166] The server periodically retrieves the latest price information from the sales price database. The retrieved data is stored in memory or cache for quick access. When a user opens a screen for creating a new quote, the terminal requests the current sales price data from the server. The server returns the latest sales price data to the terminal.

[1167] Examples:

[1168] The server retrieves the price data by executing an SQL query such as SELECT product_id, current_price, timestamp FROM price_data;

[1169] The device sends an HTTP request such as GET / api / current_prices to the server, and the server returns {"product_id": 123, "current_price": 1500} as a response.

[1170] Identifying price fluctuations

[1171] Next, the server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. The trained model is used for anomaly detection to determine whether there is a normal price within the range of price data. The device sends a request to the server to perform anomaly detection based on the current sales price. The server runs the anomaly detection algorithm and returns the results.

[1172] Examples:

[1173] The server trains the unsupervised learning algorithm and generates the model.

[1174] The device sends data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly. The server determines the price and returns a response with {"status": "normal"}.

[1175] Detecting abnormal prices

[1176] The server runs an anomaly detection algorithm on the current price data to determine if a price is abnormal. If an abnormal price is detected, it generates a warning message. The terminal receives the response from the server and displays a warning message to the user if an abnormality is detected.

[1177] Examples:

[1178] The server runs an anomaly detection algorithm and returns the result {"status": "abnormal"} in case of abnormal prices.

[1179] The terminal receives the response indicating the abnormality detection and notifies the user with a warning message saying "An abnormal price has been detected."

[1180] Create and save quotes

[1181] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button. The device sends the created quote data to the server and requests that it be saved. The server saves the received quote data in its database.

[1182] Examples:

[1183] The user creates a quote using the terminal interface and clicks the "Save" button.

[1184] The device sends a POST / api / save_estimate request with the data to the server, which saves it to the database with the SQL query INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[1185] Emotion engine integration

[1186] The device uses a camera and microphone to recognize the user's emotions while the user is operating the device. The emotion data is sent to the server in real time. The server then uses an emotion engine to analyze the emotion data and generate appropriate feedback based on the user's emotional state.

[1187] Examples:

[1188] The device uses a camera and microphone to capture the user's facial expressions and voice, and sends the emotion data to the server using the endpoint POST / api / analyze_emotion.

[1189] The server analyzes the data using an emotion engine, and if it determines, for example, that the user is in a state of stress, it generates a message encouraging relaxation and returns the response {"message": "Please take a short break"}.

[1190] The above is a concrete example of how to implement the invention by combining an emotion engine. This system combines accurate reflection of sales price information with feedback based on the user's emotions, enabling more efficient and user-friendly quotation creation.

[1191] The processing flow will be explained below.

[1192] Obtaining sales price data

[1193] Step 1:

[1194] The server periodically retrieves the latest price information from the sales price database. For example, it executes the following SQL query to retrieve sales price data: SELECT product_id, current_price, timestamp FROM price_data;

[1195] Step 2:

[1196] The server stores the obtained price data in memory or cache for quick access.

[1197] Step 3:

[1198] When a user opens a screen to create a new quote, the terminal automatically requests sales price data from the server by sending an HTTP request such as GET / api / current_prices.

[1199] Step 4:

[1200] The server receives the request from the device, retrieves the latest sales price data from memory or cache, and returns it as an HTTP response. Response example: {"product_id": 123, "current_price": 1500}

[1201] Identifying price fluctuations

[1202] Step 5:

[1203] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. Through this training, it learns the normal price range.

[1204] Step 6:

[1205] The server stores the trained model and waits for the next request.

[1206] Step 7:

[1207] The device sends a request to the server to perform anomaly detection based on the current selling price. For example, send data such as {"product_id": 123, "price": 1500} to the endpoint POST / api / detect_anomaly.

[1208] Step 8:

[1209] The server runs an anomaly detection algorithm on the received data to determine whether it is normal or abnormal. The result is returned as an HTTP response. Example response: {"status": "normal"}

[1210] Detecting abnormal prices

[1211] Step 9:

[1212] The server determines whether the price is within the normal range or is abnormal based on the results of the anomaly detection algorithm, and if it is abnormal, generates a warning message.

[1213] Step 10:

[1214] The terminal receives the response from the server, and if it is within the normal range, it notifies the user and allows them to continue. If it is within the abnormal range, a warning message is displayed to the user. Example of display: "An abnormal price has been detected. Please check again."

[1215] Create and save quotes

[1216] Step 11:

[1217] The user creates a quote based on the provided price information. After completing the quote, the user clicks the "Save" button.

[1218] Step 12:

[1219] The terminal sends the created estimate data to the server and requests that it be saved. For example, send data such as {"estimate_id": 456, "product_id": 123, "price": 1500} to the endpoint POST / api / save_estimate.

[1220] Step 13:

[1221] The server saves the received estimate data in the database by executing an SQL query such as INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[1222] Step 14:

[1223] The server returns a response to the terminal indicating that the save was successful. Example response: {"status": "success", "message": "The quote has been saved"}

[1224] Emotion engine integration

[1225] Step 15:

[1226] The device uses a camera and microphone to recognize the user's emotions while the user is operating the device, and the emotion data is sent to the server in real time.

[1227] Step 16:

[1228] The server uses an emotion engine to analyze the emotion data and generate appropriate feedback based on the user's emotional state.

[1229] Step 17:

[1230] The server generates a feedback message for the user based on the emotion analysis results and sends it to the terminal. For example, if the server determines that the user is in a "stressed state," it generates a message saying, "Please take a short break."

[1231] Step 18:

[1232] The terminal receives the feedback message sent from the server and displays it to the user. Example: "Your current work seems stressful. Please take a short break."

[1233] The above are the specific processing steps for implementing the invention that combines an emotion engine. This system achieves more efficient and user-friendly quotation creation by combining accurate reflection of sales price information with feedback based on the user's emotions.

[1234] Example 2

[1235] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1236] Conventional quotation creation systems do not adequately consider fluctuations in sales prices or the detection of abnormal prices, making it difficult to create accurate quotation documents. Furthermore, they lack feedback that takes into account the user's emotional state, resulting in a lack of improvement in the user experience.

[1237] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting a determination result, means for acquiring and analyzing emotion data, and means for generating appropriate feedback based on the user's emotional state. This not only makes it possible to create accurate estimates that take into account fluctuations in sales prices and abnormal prices, but also makes it possible to provide feedback according to the user's emotional state, improving the user experience.

[1238] "Sales Price Data" means information about the selling price of a product, obtained from a database or other source.

[1239] "Unsupervised learning algorithms" is a general term for algorithms used to train models using unlabeled data to perform tasks such as classification and clustering.

[1240] An "anomaly detection algorithm" is an algorithm that detects data points in a dataset that do not fit a normal pattern.

[1241] The "judgment result" is the conclusion obtained after executing the anomaly detection algorithm, whether the data is normal or abnormal.

[1242] "Emotional data" is information that indicates the user's emotional state and is collected through sensors such as cameras and microphones.

[1243] "Analytical means" are technical devices and algorithms used to process collected data and extract useful information.

[1244] "Feedback" refers to the responses or instructions that a system provides to a user, based on the user's emotional state and operational status.

[1245] This invention relates to a system for creating accurate quotations that take into account fluctuations in sales prices. The system has the functions of automatically acquiring sales price data, training unsupervised learning algorithms, performing anomaly detection, outputting judgment results, and analyzing emotion data and generating feedback.

[1246] Obtaining sales price data

[1247] The server retrieves the latest price information from the sales price database at a fixed time. This task is performed by a scheduled job, for example, at 2:00 AM every day. The specific software used is a database management system (for example, MySQL), which retrieves price data by executing the SQL query SELECT product_id, current_price, timestamp FROM price_data;. The retrieved data is stored in memory or cached for quick access.

[1248] When a user opens a screen for creating a new quote, the terminal requests the latest sales price data from the server. The request from the terminal is sent using the HTTP protocol in the format GET / api / current_prices. The server receives the request and returns the latest price data it has saved in JSON format to the terminal.

[1249] Identifying price fluctuations

[1250] Next, the server trains a model using an unsupervised learning algorithm (e.g., Isolation Forest) based on the collected historical sales price data. The model is generated using a Python machine learning library (e.g., scikit-learn). The trained model is saved and later used for anomaly detection.

[1251] The terminal sends an anomaly detection request to the server based on the current selling price entered by the user. The request format is POST / api / detect_anomaly, and sends data such as {"product_id": 123, "price": 1500}. The server runs the anomaly detection algorithm based on this data and returns the results to the terminal. If the result is normal, it is returned as {"status": "normal"}, and if it is an abnormal value, it is returned as {"status": "abnormal"}.

[1252] Detecting abnormal prices

[1253] The server runs an anomaly detection algorithm against the current price data to determine if a price is abnormal. If an abnormal price is detected, it generates a warning message. The generated warning message has the format {"message": "An abnormal price has been detected"}.

[1254] The terminal displays the received warning message to the user, who can then quickly respond by checking the on-screen warning that "an abnormal price has been detected."

[1255] Create and save quotes

[1256] The user creates a quote using the device interface, entering product information and pricing and clicking the "Save" button.

[1257] The terminal sends the created estimate data to the server and requests that it be saved. The request format is POST / api / save_estimate, and sends the following data, for example: {"estimate_id": 456, "product_id": 123, "price": 1500}.

[1258] The server saves the received estimate data in the database by executing the following SQL query: INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);

[1259] Emotion engine integration

[1260] The device uses the camera and microphone to recognize the user's emotions while the user is operating the device. Emotion data is collected in real time and sent to the server. The sending format is POST / api / analyze_emotion, and data such as {"emotion": "sad", "intensity": 0.8} is sent.

[1261] The server analyzes the data collected by the emotion engine and generates appropriate feedback based on the user's emotional state. For example, if the server determines that the user is in a stressful state, it generates a message encouraging relaxation and sends the response {"message": "Please take a short break"} to the device.

[1262] The above describes a specific embodiment of the present invention. This system combines accurate reflection of sales price information with feedback based on the user's emotions to create more efficient and user-friendly estimates.

[1263] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1264] Specific flow of program processing

[1265] Step 1: Obtaining sales price data

[1266] The server periodically retrieves the latest price information from the sales price database. The input is a database query (e.g. SELECT product_id, current_price, timestamp FROM price_data;) and the output is the latest sales price data. Specifically, it executes an SQL query from the database and stores the price data in memory or cache, making it readily accessible.

[1267] Step 2: User Request

[1268] When a user opens the screen for creating a new quote, the terminal sends a request to the server to obtain current sales price data. The input is the user's operation, and the output is an HTTP request (e.g., GET / api / current_prices). Based on this request, the server retrieves the latest price information from memory or cache and returns it to the terminal in JSON format (e.g., {"product_id": 123, "current_price": 1500}).

[1269] Step 3: Determine price fluctuations

[1270] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. The input is past sales price data, and the output is the trained model. Specifically, it trains the algorithm using a Python machine learning library (e.g., scikit-learn) and saves the generated model.

[1271] Step 4: Anomaly detection request

[1272] The terminal sends an anomaly detection request to the server based on the current sales price. The input is the current sales price data (e.g., {"product_id": 123, "price": 1500}), and the output is an HTTP request (e.g., POST / api / detect_anomaly). After receiving the request, the server runs the anomaly detection algorithm and outputs the results.

[1273] Step 5: Detecting price anomalies

[1274] The server runs an anomaly detection algorithm to determine whether a price is abnormal. The input is the data of the anomaly detection request, and the output is the anomaly determination result (e.g., {"status": "abnormal"}). If an anomaly is detected, a warning message (e.g., {"message": "An abnormal price has been detected"}) is generated.

[1275] Step 6: Displaying warning messages

[1276] The terminal receives the abnormality determination result and warning message from the server and displays them to the user. The input is the response data from the server, and the output is the display of the warning message to the user. The user can see the message "An abnormal price has been detected" on the terminal screen.

[1277] Step 7: Create and save a quote

[1278] The user creates a quote using the terminal. The input is product information and price data, and the output is the quote data. After completing the quote, the user clicks the "Save" button. The terminal sends this save request to the server (e.g., POST / api / save_estimate). The server saves the received quote data in the database (e.g., INSERT INTO estimates (estimate_id, product_id, price) VALUES (456, 123, 1500);).

[1279] Step 8: Capturing Emotional Data

[1280] The device collects user emotional data in real time using a camera and microphone while the user is operating the device. The input is captured data from the sensors, and the output is emotional data. The emotional data is sent to the server in real time (e.g., POST / api / analyze_emotion).

[1281] Step 9: Analyze emotion data and generate feedback

[1282] The server analyzes the emotion data using an emotion engine. The input is emotion data (e.g., {"emotion": "sad", "intensity": 0.8}), and the output is a feedback message. For example, if the server determines that the user is in a "stressed" state based on the analysis results, it generates a message encouraging relaxation and sends it to the device as feedback (e.g., {"message": "Please take a short break"}).

[1283] The above is the specific processing flow of the program for this system. At each step, data processing and calculation are performed based on the input, and the results are output.

[1284] (Application example 2)

[1285] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1286] In modern stores, it is difficult to provide appropriate service based on the customer's emotional state while taking into account fluctuations in sales prices at the time of creating a quote. Conventional systems not only provide accurate price information in real time, but also lack the ability to recognize and respond to customer emotions, which means that the customer experience is not fully improved.

[1287] The identification process by the identification 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 sales price data, means for training an unsupervised learning algorithm based on past sales price data, means for executing an anomaly detection algorithm on current sales price data and outputting the determination result, means for recognizing customer emotions and providing appropriate feedback, and means for creating product quotations. This makes it possible to create accurate and fair quotations in real time and to provide services that take into account the emotional state of the customer.

[1288] "Sales price data" is data that indicates the latest price information related to the selling price of a product.

[1289] An "unsupervised learning algorithm" is an algorithm that performs pattern detection and clustering using unlabeled data.

[1290] An "anomaly detection algorithm" is an algorithm for detecting anomalous patterns or values ​​in data.

[1291] The "determination result" indicates whether the data obtained using the anomaly detection algorithm is correct or incorrect.

[1292] "Recognizing customer emotions" means using a camera or microphone to analyze the customer's facial expressions and voice to determine their emotional state.

[1293] "Appropriate feedback" refers to information and actions that provide messages and support to promote relaxation based on the customer's emotional state.

[1294] A "product quotation" is a document created based on price information about a product, and indicates the conditions for purchase.

[1295] A system for implementing the present invention is constructed based on the following elements.

[1296] The server periodically retrieves the latest price information from the sales price database. The retrieved data is stored in memory or cache for quick access. This price data is provided by the server when requested by the terminal when creating a quote.

[1297] The server trains an anomaly detection model using an unsupervised learning algorithm (e.g., Isolation Forest) based on past sales price data. This model is then used to detect anomalies based on new sales price data. The anomaly detection algorithm generates a judgment result, and a warning message is generated if an anomaly is detected.

[1298] The device is also equipped with a camera and microphone, which are used to recognize the user's emotions. Emotional data is sent to the server in real time, and the server analyzes it using an emotion engine. Appropriate feedback based on the user's emotional state is generated and sent to the device.

[1299] As a concrete example, when a salesperson in a physical store prepares a product quotation, the terminal retrieves the latest sales price data from the server and prepares the quotation. The prepared quotation data is sent to the server and saved. If the emotion engine determines that the customer is feeling stressed at this time, a message such as "Please take a short break" will be displayed.

[1300] The following specific technical elements are used to realize this system:

[1301] Hardware: Smartphone, smart glasses or tablet, camera, microphone installed in a physical store

[1302] Software: Python, sklearn (running unsupervised learning algorithms), opencv (image processing), emotion_recognition (emotion engine)

[1303] As an example of an application of a generative AI model, the following prompt sentence predicts market price data.

[1304] "Given current market price data, what is your predicted price for next month?"

[1305] The system enables accurate and fair quotes that take customer sentiment into account, improving the customer experience.

[1306] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1307] Step 1:

[1308] The server periodically retrieves the latest price information from a sales price database. This database contains information such as product ID, current price, and timestamp. The retrieved data is stored in memory or cache for quick access. Specifically, the server executes an SQL query (e.g., SELECT product_id, current_price, timestamp FROM price_data;) and stores the results in memory.

[1309] Input: Sales price database

[1310] Output: Latest sales price data

[1311] Step 2:

[1312] The server trains an unsupervised learning algorithm (e.g., Isolation Forest) on historical sales price data, which generates an anomaly detection model. Unsupervised learning is used to cluster historical data and identify anomalous data points.

[1313] Input: Historical sales price data

[1314] Output: A trained model

[1315] Step 3:

[1316] When a user opens the screen to create a new quote, the terminal requests the current sales price data from the server. The server returns the latest sales price data to the terminal. Specifically, the terminal sends an HTTP request (e.g., GET / api / current_prices) to the server, and the server returns data in JSON format.

[1317] Input: A request from the user

[1318] Output: Current sales price data

[1319] Step 4:

[1320] The terminal sends an anomaly detection request to the server based on the current sales price data. The server runs the anomaly detection algorithm and returns the result to the terminal. Specifically, the terminal sends a request including the price data (e.g., POST / api / detect_anomaly), and the server determines whether there is an anomaly and returns a response.

[1321] Input: Current sales price data

[1322] Output: Anomaly detection result

[1323] Step 5:

[1324] If an abnormal price is detected, the server generates and sends a warning message to the terminal, a specific example of which is the message "An abnormal price has been detected."

[1325] Input: Anomaly detection result

[1326] Output: Warning message

[1327] Step 6:

[1328] The user creates a quote based on the provided price information. After completing the quote, the user clicks the save button, and the device sends the quote data to the server and requests that it be saved. The server then saves the received quote data in a database.

[1329] Input: Quotation data

[1330] Output: Quote saved in database

[1331] Step 7:

[1332] The device recognizes the user's emotions using a camera and microphone while the user is operating the device. The emotion data is sent to the server in real time, and the server analyzes the emotion data using an emotion engine. Appropriate feedback is generated based on the analysis results and sent to the device.

[1333] Input: User emotion data

[1334] Output: Sentiment analysis results and feedback

[1335] Specifically, the device captures emotional data using a camera and microphone and sends it to the server. The server then analyzes the data using its emotion engine, and if it determines that the user is in a state of stress, it generates and returns a message saying, "Please take a short break."

[1336] In this way, a system will be built that provides accurate price information in real time and delivers services based on customer sentiment.

[1337] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1338] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1339] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1340] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1341] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1342] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1343] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1344] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1345] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1346] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1347] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1348] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1349] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1350] 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.

[1351] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1352] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1353] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1354] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1355] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1356] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1357] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1358] The following is further disclosed regarding the above embodiment.

[1359] (Claim 1)

[1360] a means for obtaining sales price data;

[1361] a means of training an unsupervised learning algorithm based on historical sales price data;

[1362] means for executing an anomaly detection algorithm on current sales price data and outputting a determination result;

[1363] A system including:

[1364] (Claim 2)

[1365] 10. The system of claim 1, further comprising: means for generating and outputting a warning message when the sales price data is abnormal.

[1366] (Claim 3)

[1367] 10. The system of claim 1, further comprising means for creating and storing quote data.

[1368] "Example 1"

[1369] (Claim 1)

[1370] a means for obtaining sales price data;

[1371] a means of training an unsupervised learning algorithm based on historical sales price data;

[1372] means for executing an anomaly detection algorithm on current sales price data and outputting a determination result;

[1373] A way for users to request the latest sales price data when creating a new quote;

[1374] a means for providing sales price data in response;

[1375] means for generating and outputting a warning message when an abnormal price is detected;

[1376] A means for creating and saving quotation data;

[1377] A system including:

[1378] (Claim 2)

[1379] 10. The system of claim 1, further comprising: means for generating and outputting a warning message when the sales price data is abnormal.

[1380] (Claim 3)

[1381] 10. The system of claim 1, further comprising means for creating and storing quote data.

[1382] "Application Example 1"

[1383] (Claim 1)

[1384] a means for obtaining sales price data;

[1385] a means of training an unsupervised learning algorithm based on historical sales price data;

[1386] means for executing an anomaly detection algorithm on current sales price data and outputting a determination result;

[1387] means for issuing a warning signal if an abnormality is detected;

[1388] A means to automatically generate quotes based on valid price data,

[1389] A means to store the generated quotes and make them accessible at a later date;

[1390] means for executing the series of processes using a robot;

[1391] ...

[1392] A system including:

[1393] (Claim 2)

[1394] 10. The system of claim 1, further comprising means for performing anomaly detection based on the price data and issuing a visual or audio warning signal when an anomaly is detected.

[1395] (Claim 3)

[1396] 10. The system of claim 1, further comprising means for automatically generating and storing quotes in a database based on valid price data.

[1397] "Example 2: Combining Emotion Engines"

[1398] (Claim 1)

[1399] a means for obtaining sales price data;

[1400] a means of training an unsupervised learning algorithm based on historical sales price data;

[1401] means for executing an anomaly detection algorithm on current sales price data and outputting a determination result;

[1402] A means for acquiring and analyzing emotion data;

[1403] means for generating appropriate feedback based on the user's emotional state;

[1404] A system including:

[1405] (Claim 2)

[1406] 10. The system of claim 1, further comprising means for generating and outputting a warning message when abnormal sales price data is detected.

[1407] (Claim 3)

[1408] 10. The system of claim 1, further comprising means for creating and storing quote data.

[1409] "Application example 2 when combining emotion engines"

[1410] (Claim 1)

[1411] a means for obtaining sales price data;

[1412] a means of training an unsupervised learning algorithm based on historical sales price data;

[1413] means for executing an anomaly detection algorithm on current sales price data and outputting a determination result;

[1414] A means of recognizing customer emotions and providing appropriate feedback;

[1415] A means of creating product quotes;

[1416] A system including:

[1417] (Claim 2)

[1418] 10. The system of claim 1, further comprising: means for generating and outputting a warning message when the sales price data is abnormal.

[1419] (Claim 3)

[1420] 10. The system of claim 1, further comprising means for storing data of the generated estimate. [Explanation of symbols]

[1421] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for obtaining sales price data; a means of training an unsupervised learning algorithm based on historical sales price data; means for executing an anomaly detection algorithm on current sales price data and outputting a determination result; A system including:

2. The system of claim 1 , further comprising means for generating and outputting a warning message when the sales price data is abnormal.

3. The system of claim 1 further comprising means for creating and storing quote data.

Images