System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a price list; means for analyzing the received price list to detect an outlier; and means for notifying a user of an alert if an outlier is detected.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 today's information society, individuals often make a wide variety of mistakes when performing everyday digital tasks. Examples include setting abnormal values ​​in pricing, attaching incorrect files to emails, and making spelling or formatting errors when entering data. These mistakes not only reduce work efficiency but can also lead to serious business problems and information leaks. Therefore, there is a need to detect these mistakes in real time and respond quickly. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: a system that receives and analyzes price lists, detects abnormal values, and notifies the user of an alert; detects specific keywords in document content, checks whether there are any attachments, and displays an alert; and monitors data entry in real time, detects spelling mistakes and formatting errors, and displays an alert to the user. This system allows users to prevent and correct mistakes while performing digital tasks, contributing to improved work efficiency and trouble prevention.

[0006] A "price list" is a collection of information that lists the prices of goods and services.

[0007] An "outlier" is a data value that is significantly outside the normal or expected range.

[0008] "User" refers to any individual or organization that uses a computer system or software.

[0009] An "alert" is a warning message or signal that notifies you of some abnormality or event that requires attention.

[0010] "Document Content" refers to the textual information contained in an email or other digital document.

[0011] "Specific keywords" refer to words or phrases that have predetermined important meanings.

[0012] "Attachment" refers to a data file added in addition to the main message in an email or other digital communication.

[0013] "Data entry" refers to the act of a human entering information into a computer system or software.

[0014] A "spelling error" is when a word is misspelled.

[0015] "Format error" refers to a situation in which the format or structure of data does not conform to expected rules or specifications.

[0016] "Real-time" means that processing and responses are almost immediate. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] DETAILED DESCRIPTION OF THE INVENTION The present invention includes embodiments of a system for preventing pricing errors, misdirected documents, and data entry errors, called DTSAI (Digital Task Safeguard AI).

[0039] Pricing Mistake Detection

[0040] server

[0041] The server processes price lists received from users. These price lists contain prices for goods and services. The server analyzes the price lists and detects outliers that fall outside the normal price range. To do this, it uses machine learning algorithms (e.g., KMeans clustering) to cluster the price lists and automatically identify outliers. When an outlier is detected, the server sends a warning to the user, prompting them to make corrections.

[0042] For example, when a user sets the price of a new product lineup, the price list is sent to the server. For example, if the price list is [500, 520, 510, 490, 1200], the server detects that 1200 is an abnormal value and sends an alert to the user saying, "The price setting of 1200 yen is significantly different from the other prices."

[0043] Preventing documents from being sent to the wrong person

[0044] Terminal

[0045] When a user attempts to send an email, the device analyzes the body of the email. If the body of the email contains specific keywords such as "attachment" or "document," the device checks whether there are any attachments. If there are no attachments, a warning message is displayed to the user to prevent the email from being sent by mistake. The user can check the warning and attach a file or modify the email content as necessary.

[0046] For example, if a user writes "Please see the attached file in this email" but does not actually attach a file, the device will display an alert saying "There is no attachment. Would you like to attach one?" The user will see the warning and attach the file.

[0047] Data entry error detection

[0048] Terminal

[0049] During data entry, the terminal monitors what the user types in real time. It analyzes the text entered and checks for spelling and formatting errors. This includes regular expression and dictionary-based spell checking. If an incorrect entry is detected, the terminal displays an alert to the user immediately and prompts them to correct it.

[0050] For example, if a user enters "example@domain.com" as their email address in an online form, the device will display an alert saying, "There is an error in the email address format. Please check again." The user will then see the warning and correct their email address to "example@domain.com."

[0051] As described above, the DTSAI system of the present invention automatically detects errors in everyday digital tasks such as pricing, document transmission, and data entry, and alerts users in real time, thereby improving work efficiency and accuracy.

[0052] The processing flow will be explained below.

[0053] Pricing Mistake Detection

[0054] server

[0055] Step 1:

[0056] The server receives a price list from the user, the price list containing prices for goods and services.

[0057] Step 2:

[0058] The server converts the received price list into a NumPy array, which is a data preprocessing step to make it suitable for the clustering algorithm.

[0059] Step 3:

[0060] The server applies the KMeans clustering algorithm to divide the price list into two clusters, which distinguishes between normal and abnormal prices.

[0061] Step 4:

[0062] The server calculates cluster centers and detects outliers that deviate significantly from the normal price cluster.

[0063] Step 5:

[0064] If the server detects an abnormal value, it will notify the user in real time as an alert, prompting the user to recheck the price.

[0065] Preventing documents from being sent to the wrong person

[0066] Terminal

[0067] Step 1:

[0068] When a user presses the send button on an email, the device reads the body and subject of the email.

[0069] Step 2:

[0070] The device searches for specific keywords (such as "attachment" or "document") in the email body and checks whether these keywords are included.

[0071] Step 3:

[0072] If a specific keyword is detected, the device checks whether the email has an attachment.

[0073] Step 4:

[0074] If there is no attachment, the device will display an alert to the user saying, "The email contains the word 'attached,' but there is no attachment."

[0075] Step 5:

[0076] The user checks the alert and attaches files or modifies the email content as needed.

[0077] Data entry error detection

[0078] Terminal

[0079] Step 1:

[0080] When a user enters data into an input form, the terminal monitors the input content in real time.

[0081] Step 2:

[0082] The terminal parses the text you enter to detect spelling and formatting errors, using regular expressions and dictionary-based spell checking.

[0083] Step 3:

[0084] If an incorrect input is detected, the device will immediately display an alert to the user saying, "There is an input error. Please check again."

[0085] Step 4:

[0086] The user acknowledges the alert and corrects the data entry.

[0087] The above are the specific processing steps in each module. The DTSAI system of the present invention allows users to quickly detect mistakes during digital tasks and respond in real time.

[0088] Example 1

[0089] 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."

[0090] In today's business environment, pricing errors, mis-sent documents, and data entry errors are commonplace, significantly impacting the efficiency and accuracy of business operations. Preventing these errors requires a comprehensive system that can handle multiple different tasks. However, traditional systems have difficulty resolving these issues consistently, resulting in the cost and effort required to address each issue individually.

[0091] 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.

[0092] In this invention, the server includes means for receiving a price list, means for analyzing the received price list using a machine learning algorithm to detect outliers, means for notifying a user of an alert when an outlier is detected, means for analyzing the content of a document to detect specific keywords, means for checking whether or not an attachment exists when the specific keyword is detected, means for displaying an alert to the user when the attachment does not exist, means for monitoring data entry in real time, means for detecting spelling mistakes and formatting errors, and means for displaying an alert to the user when an error is detected. This makes it possible to automatically detect errors in everyday digital tasks such as pricing, document transmission, and data entry, and to issue alerts in real time, thereby improving work efficiency and accuracy.

[0093] A "price list" is data that compiles price information for products and services in a list format.

[0094] A "machine learning algorithm" is a numerical method that automatically learns patterns based on large amounts of data and makes predictions and classifications.

[0095] "Clustering" is a data analysis technique that divides a dataset into several groups so that data within the same group are similar to each other.

[0096] An "outlier" is a value that deviates significantly from the average trend of the entire data set.

[0097] An "alert" is a warning message that notifies the user when the system detects an abnormality or a situation that requires attention.

[0098] A "specific keyword" is a word or phrase in a document that triggers a specific action (such as checking an attachment).

[0099] An "attachment" is an additional data file included in an email.

[0100] "Real-time monitoring" refers to checking data immediately at the moment the user enters it.

[0101] A "spelling error" is a mistake in which a letter of a word is typed incorrectly.

[0102] A "format error" is a data entry error that does not follow a prescribed format.

[0103] This invention is a system for preventing pricing errors, mis-sent documents, and data entry errors. Specifically, it is an integrated system with multiple functions for analyzing price lists, document content, and monitoring data entry in real time. This system is composed of a server and terminals.

[0104] Pricing Mistake Detection

[0105] server

[0106] The server processes price lists received from users. These price lists contain prices for goods and services. The server analyzes the price lists using machine learning algorithms, specifically KMeans clustering, to detect outliers that fall outside the normal price range. If an outlier is detected, the server sends an alert to the user, prompting them to adjust the pricing.

[0107] Specific examples

[0108] When a user sets the price of a new product lineup, the price list is sent to the server. For example, if the price list is [500 yen, 520 yen, 510 yen, 490 yen, 1200 yen], the server detects that 1200 yen is an abnormal value and sends an alert to the user saying, "The price setting of 1200 yen is significantly different from the other prices."

[0109] Prompt Sentence Examples

[0110] "The price list for the new product lineup contains an outlier at [500, 520, 510, 490, 1200]. Please write a program that detects the outlier and notifies the user."

[0111] Preventing documents from being sent to the wrong person

[0112] Terminal

[0113] When a user attempts to send an email, the device analyzes the body of the email. If the body contains specific keywords such as "attachment" or "document," the device checks whether there are any attachments. If there are no attachments, the device displays a warning message to the user to prevent the email from being sent by mistake.

[0114] Specific examples

[0115] If a user writes "Please see the attachment in this email" but does not actually attach a file, the device will display an alert saying "There is no attachment. Do you want to attach it?" The user will see the warning and attach the file.

[0116] Prompt Sentence Examples

[0117] "Please describe the program's processing to warn when a user sends an email that contains an "attachment" or "document" in the body of the email but the attached file does not exist."

[0118] Data entry error detection

[0119] Terminal

[0120] The terminal monitors what the user types in real time as data is entered. The terminal parses the text entered and checks for spelling and formatting errors using regular expressions and dictionary-based spell checking. If an incorrect entry is detected, the terminal will immediately alert the user and prompt them to correct it.

[0121] Specific examples

[0122] When a user enters an email address in an online form, if the user types "example@domain.com", the device will display an alert saying "There is an error in the email address format. Please check again." The user will then see the warning and correct the email address to "example@domain.com".

[0123] Prompt Sentence Examples

[0124] "When a user enters an email address into an online form, write a program that warns them if the format is invalid."

[0125] In this way, the present invention is a system that automatically detects errors in everyday digital tasks such as pricing, document transmission, and data entry, and provides real-time alerts to improve work efficiency and accuracy.

[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0127] Pricing Mistake Detection

[0128] Step 1:

[0129] The server receives a price list from a user, which includes as input a price list, which contains pricing information for goods and services.

[0130] Step 2:

[0131] The server analyzes the received price list using a machine learning algorithm (e.g., KMeans clustering). First, it stores the price list in a database and then inputs the data into a clustering algorithm. The clustering results show the normal price range and outliers.

[0132] Step 3:

[0133] The server identifies outliers based on the clustering results. If an outlier is detected, it marks it as a flag and prepares to send an alert to the user. As an output, it generates a list of outliers and corresponding warning messages.

[0134] Step 4:

[0135] If an abnormal value is detected, the server will send an alert to the user. The alert will be sent by email or a pop-up notification. For example, a notification such as "The price setting of 1,200 yen is significantly different from the other prices" will be sent.

[0136] Preventing documents from being sent to the wrong person

[0137] Step 1:

[0138] When a user sends an email, the terminal analyzes the content of the email body, which includes the email body as input.

[0139] Step 2:

[0140] The device checks whether specific keywords such as "attachment" or "document" are included in the email body. It performs text analysis and lists the detected keywords. The output shows whether the detected keywords are present or not.

[0141] Step 3:

[0142] When a specific keyword is detected, the terminal checks whether or not there are any attachments. It checks the email attachment list and outputs whether or not there are any attachments.

[0143] Step 4:

[0144] If the attachment does not exist, the terminal will display an alert to the user. Specifically, a warning message such as "There is no attachment. Do you want to attach it?" will be displayed. The user will check this warning and attach the file if necessary.

[0145] Data entry error detection

[0146] Step 1:

[0147] The terminal monitors in real time what the user is entering during data entry. Input includes the data entered by the user.

[0148] Step 2:

[0149] The terminal parses the input text, checking for spelling and formatting errors, applying regular expression and dictionary-based spell checking algorithms, and provides the presence or absence of errors as output.

[0150] Step 3:

[0151] If an incorrect entry is detected, the device will immediately display an alert to the user. Specifically, a warning message such as "There is an error in the email address format. Please check again" will be displayed. The user will then check this warning and correct the entry.

[0152] (Application example 1)

[0153] 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."

[0154] Pricing errors and promotional information errors in physical stores directly lead to sales losses and reduced customer satisfaction. Preventing such errors and detecting and correcting them in real time is a key challenge for improving operational efficiency and customer satisfaction in physical stores. In addition, incorrect transmissions and data entry errors also have a negative impact on operational efficiency, so these issues must also be addressed at the same time.

[0155] 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.

[0156] In this invention, the server includes means for receiving a price list, means for analyzing the received price list and detecting abnormal values, means for notifying a user of an alert when an abnormal value is detected, means for acquiring price information via an electronic device for photographing the price list and analyzing the acquired price information in real time, means for automatically identifying abnormal values ​​in the price information, means for displaying an alert to the user via the electronic device when an abnormal value is detected, and means for prompting the user to reconfirm or correct the abnormal value. This enables errors in pricing and promotion information in physical stores to be detected and corrected in real time, improving business efficiency and customer satisfaction.

[0157] A "price list" is a document or data that lists price information for products or services.

[0158] An "outlier" is any price information that is outside the normal price range and is therefore not valid.

[0159] "User" refers to the person or administrator who uses the system to set prices or view information.

[0160] An "alert" is a warning message that the system sends to the user to notify them of an error or abnormality.

[0161] "Electronic devices" refers to devices used to capture price information and analyze the data, such as smart glasses or smartphones.

[0162] "Real-time" refers to data processing and information notification occurring immediately, without delay.

[0163] "Analysis" refers to analyzing the received data, interpreting its meaning, and detecting specific patterns or anomalies.

[0164] "Revalidation" is the process of re-evaluating the detected discrepancies to check whether they are correct.

[0165] "Correction" refers to changing detected abnormal values ​​or errors into accurate information.

[0166] "Price Information" means price data associated with individual products or services.

[0167] The DTSAI system embodying the present invention is a system that detects pricing errors and promotion information errors in real time in physical stores and notifies users of alerts. The system configuration and processing are described in detail below.

[0168] System Configuration

[0169] 1. Hardware Configuration

[0170] Server: Analyzes the data and detects outliers.

[0171] Terminal (smart glasses, smartphone, etc.): Captures price information and sends it to the server in real time.

[0172] Network: A communication method for linking terminals and servers.

[0173] 2. Software Configuration

[0174] Machine learning algorithm: KMeans clustering is used to analyze price information.

[0175] Data analysis module: a program for analyzing received price lists.

[0176] Alert module: A program that notifies the user when an abnormal value is detected.

[0177] Processing steps

[0178] 1. Obtaining and sending price information

[0179] The user uses smart glasses to take a photo of the product price and transmits the data to the server.

[0180] 2. Analysis of price information

[0181] The server analyzes the received price data in real time and detects outliers that deviate from the normal price range.

[0182] The algorithm used is KMeans clustering, which clusters price data and identifies outliers.

[0183] 3. Alert Notification

[0184] If an abnormal value is detected, the server sends the information to the terminal and displays an alert to the user in real time.

[0185] This allows users to quickly correct pricing errors.

[0186] Specific examples

[0187] For example, if a user sets the price of a new product and the price list includes 500 yen, 520 yen, 510 yen, 490 yen, and 1200 yen, the server will detect that 1200 yen is an abnormal value. The corresponding smart glasses will display an alert saying, "The 1200 yen price setting is significantly different from the other prices. Please check again."

[0188] Prompt Sentence Examples

[0189] Please set a price for your new product. If the prices of other products are around 1000 yen and your set price is 5000 yen, please send an alert as an abnormal value.

[0190] As described above, the DTSAI system of the present invention detects errors in pricing and promotional information in physical stores in real time and promptly notifies users of alerts, thereby improving business efficiency and customer satisfaction.

[0191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0192] Step 1:

[0193] Obtaining and sending price information

[0194] A user captures the price of a product using a device (e.g., smart glasses). The device's built-in camera captures the product's price tag and extracts the price information using OCR (optical character recognition) technology. The device then sends the price information to a server.

[0195] Input: Price tag image

[0196] Output: Extracted price information

[0197] Step 2:

[0198] Receiving price information

[0199] The server receives the price information sent from the terminal and stores it in a database within the server.

[0200] Input: Price information sent from the device

[0201] Output: Price information stored in a database

[0202] Step 3:

[0203] Price information analysis

[0204] The server uses a data analysis module to analyze the received price information in real time. This analysis uses KMeans clustering to classify the price information and detect outliers. The algorithm clusters the price information and identifies the prices detected as outliers.

[0205] Input: Price information stored in a database

[0206] Output: Price information identified as anomalies

[0207] Step 4:

[0208] Alert Generation

[0209] If the server detects an anomaly, it generates an alert based on the price information. The alert message includes details of the anomaly and a recommendation to recheck.

[0210] Input: Price information identified as an outlier

[0211] Output: The generated alert message

[0212] Step 5:

[0213] Alert Notifications

[0214] The server sends the generated alert message to the terminal, which then displays the received alert message on the user's display. The user can then confirm the message and make any necessary adjustments to the pricing.

[0215] Input: The generated alert message

[0216] Output: The alert message displayed on the user's display.

[0217] Specifically, when a user sets a price for a new product, the smart glasses capture the "5,000 yen" price tag and send the price information to the server. The server detects through clustering that "5,000 yen" is an anomaly and generates an alert message saying, "The price of the 5,000 yen product is significantly different from other products. Please check again." This message is displayed on the smart glasses' display. The user can then confirm the alert and make any necessary adjustments to the price setting.

[0218] 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.

[0219] The following describes in detail the mode for carrying out the present invention: The present invention is a system that combines a Digital Task Safeguard AI (DTSAI) system, which prevents pricing errors, incorrect attachments when sending documents, and spelling and formatting errors when entering data, with an emotion engine that recognizes user emotions.

[0220] Mispricing detection and emotional alerts

[0221] server

[0222] The server receives a price list sent by the user. This price list contains the prices of goods and services. The received price list is converted into a NumPy array and analyzed using a clustering algorithm (e.g., KMeans clustering). When an outlier outside the normal price range is detected, the server activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's current emotional state from Japanese chat messages, facial expression recognition, and voice data. Depending on the emotional state, the server notifies the user with an appropriate alert regarding the outlier.

[0223] For example, if a user sets a new product price and sends the price list [500, 520, 510, 490, 1200] to the server, the server will detect 1200 as an abnormal value. If the user is stressed at the time, the server will send a soft-toned alert saying, "This price is significantly different from the other prices. Please check it." On the other hand, if the user is calm, the server will send a direct alert saying, "1200 yen is an abnormal value. Please correct it."

[0224] Preventing mis-sending of documents and emotional response alerts

[0225] Terminal

[0226] When a user attempts to send an email, the device analyzes the content of the email body. If specific keywords (such as "attachment" or "document") are detected, the device checks whether an attachment exists. If no attachment exists, the emotion engine analyzes the user's emotional state. An appropriate alert message is displayed depending on the user's emotional state.

[0227] For example, if a user writes "Please see the attachment in this email" but forgets to include the attachment, the device will detect this. If the user is annoyed, the device will display a gentle alert such as "Attachment missing. Did you forget to attach it?". Conversely, if the user is focused on a task, the device will display a more urgent alert such as "Attachment not found. Please check it immediately."

[0228] Data entry error detection and emotional alerts

[0229] Terminal

[0230] During data entry, the device monitors what the user types in real time. Regular expression and dictionary-based spell checking are used to detect spelling and formatting errors. If an error is detected, an emotion engine analyzes the user's emotional state and displays an alert to the user accordingly.

[0231] For example, if a user types "example@domain.com," the device will detect this and display an alert saying, "The email address format is incorrect. Please check again." If the emotion engine recognizes that the user is tired, it will display an alert with advice such as, "The correct format is example@domain.com. Please correct it." On the other hand, if the user is impatient, it will display a short, concise alert saying, "Please enter your email address in the correct format."

[0232] The combination of the DTSAI system and emotion engine of the present invention allows users to effectively detect mistakes made during digital tasks and receive adaptive responses in real time, greatly improving work efficiency and accuracy.

[0233] The processing flow will be explained below.

[0234] Mispricing detection and emotional alerts

[0235] server

[0236] Step 1:

[0237] The server receives the price list from the user, which is then converted to an appropriate data format (e.g., a NumPy array) when sent to the server.

[0238] Step 2:

[0239] The server applies the KMeans clustering algorithm to the price list and classifies the prices into two clusters: one for normal prices and one for abnormal prices.

[0240] Step 3:

[0241] The server calculates cluster centers of typical prices and identifies outliers based on them. Prices that deviate significantly from the cluster center are considered outliers.

[0242] Step 4:

[0243] If the server detects an anomaly, the emotion engine is activated to analyze the user's current emotional state, which is obtained from text messages, facial recognition, voice data, etc.

[0244] Step 5:

[0245] Based on the analysis results of the emotion engine, the server notifies the user with an appropriate alert. For example, if the user is feeling stressed, the server sends a soft-spoken alert such as "This price is significantly different from other prices. Please check."

[0246] Preventing mis-sending of documents and emotional response alerts

[0247] Terminal

[0248] Step 1:

[0249] When the user clicks the send email button, the terminal reads the email body and subject line.

[0250] Step 2:

[0251] The device searches for specific keywords (such as "attachment" or "document") in the email body. If these keywords are included, it checks whether or not there are any attachments.

[0252] Step 3:

[0253] When a specific keyword is detected, the device checks whether an attachment exists. If an attachment does not exist, the emotion engine is activated to analyze the user's emotional state.

[0254] Step 4:

[0255] The emotion engine analyzes the user's emotional state, which is determined based on real-time data (e.g., facial expressions, voice, etc.).

[0256] Step 5:

[0257] Based on the analysis results of the emotion engine, the device will display appropriate alerts to the user. If the user is annoyed, it will display a gentle alert such as "Attachment missing. Did you forget to attach it?", but if the user is distracted, it will display a more urgent alert such as "Attachment not found. Please check immediately."

[0258] Data entry error detection and emotional alerts

[0259] Terminal

[0260] Step 1:

[0261] As the user enters key data into the input form, the terminal monitors the data in real time.

[0262] Step 2:

[0263] The terminal parses the text entered and uses regular expressions and dictionary-based spell checking to detect spelling and formatting errors.

[0264] Step 3:

[0265] If the device detects an input error, the emotion engine will be activated and analyze the user's emotional state, which can be obtained from text, facial expression analysis, voice analysis, etc.

[0266] Step 4:

[0267] Based on the analysis results of the emotion engine, the device displays appropriate alerts to the user. For example, if the user is tired, it displays an alert with advice such as "The correct format is example@domain.com. Please correct it." If the user is impatient, it displays a simple alert such as "Please enter your email address in the correct format."

[0268] These are the specific processing steps in each module. By combining emotion engines, it is possible to provide appropriate support according to the user's condition, improving the efficiency and accuracy of work.

[0269] Example 2

[0270] 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."

[0271] Conventional digital task management systems have difficulty detecting and notifying users of pricing errors, incorrect attachments when sending documents, and spelling or formatting errors when entering data. Furthermore, they are unable to provide alert messages that take into account the user's emotional state, increasing the risk of user stress and incorrect operation.

[0272] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving a price list; means for converting the received price list into a numerical array, analyzing it using a clustering algorithm, and detecting outliers; means for analyzing the user's emotional state using an emotion analysis engine when an outlier is detected and notifying the user of an appropriate alert for the outlier based on the emotional state; means for analyzing the content of the document and detecting specific keywords; means for checking whether or not an attachment is present when a specific keyword is detected; means for analyzing the user's emotional state using the emotion analysis engine when an attachment is not present and displaying an alert based on the emotional state; means for monitoring data input in real time; means for detecting spelling mistakes and formatting errors; and means for analyzing the user's emotional state using the emotion analysis engine when an error is detected and displaying an appropriate alert for the error based on the emotional state. This enables effective detection of errors during digital tasks and adaptive responses in real time.

[0273] A "price list" is data that lists the prices of products and services.

[0274] A "numeric array" is data with an array structure in which numerical data is arranged in a fixed order.

[0275] A "clustering algorithm" is a computational procedure for classifying data into groups (clusters) based on similarity.

[0276] An "outlier" is a data point that deviates from the normal range and is a value that is significantly different compared to other data.

[0277] An "emotion analysis engine" is a software component that analyzes data such as text, voice, and facial expressions to recognize a user's emotional state.

[0278] An "alert" is a warning message that notifies the user of important information or matters requiring attention.

[0279] "Specific keywords" are predefined important words or phrases that are searched for within a document.

[0280] An "attachment" is an additional file attached to an email or document.

[0281] "Data entry" refers to the operation by which a user inputs information into a system or application.

[0282] A "spelling error" is an error in which a word is spelled incorrectly.

[0283] A "format error" is an error in which the data does not conform to the expected format or structure.

[0284] "Real-time monitoring" refers to the operation of immediately monitoring the contents of data the moment it is entered or updated.

[0285] The following describes in detail the mode for carrying out the present invention. This invention is a system that prevents mistakes in multiple digital tasks and responds adaptively to the user's emotional state. To achieve this, the server, terminal, and user work together.

[0286] Mispricing detection and emotional alerts

[0287] server

[0288] 1. The user sets up a price list and sends it to the server. The sent price list contains the prices of products and services.

[0289] 2. The received price list is converted by the server into a NumPy array. NumPy is a Python library that allows for highly efficient numerical calculations.

[0290] 3. The server analyzes the price list using the clustering algorithm KMeans clustering, which uses the scikit-learn library.

[0291] 4. When an outlier outside the normal price range is detected, the server activates the sentiment analysis engine, which obtains the user's emotional state from data such as text, facial expressions, and voice.

[0292] 5. Depending on the emotional state, generate appropriate alert messages for abnormal values ​​and notify the user.

[0293] Example: If a user sets a new product price and sends the price list [500, 520, 510, 490, 1200] to the server, the server will detect 1200 as an abnormal value. If the user is stressed, the server will send an alert saying "This price is significantly different from other prices. Please check." If the user is calm, the server will send an alert saying "1200 yen is an abnormal value. Please correct it."

[0294] Preventing mis-sending of documents and emotional response alerts

[0295] Terminal

[0296] 1. The user composes an email and clicks the send button.

[0297] 2. When the send button is pressed, the device analyzes the email body and detects the specified specific keywords (e.g., "attachment," "document").

[0298] 3. If the keyword is detected, the device checks whether there is an attachment.

[0299] 4. If there is no attachment, the device runs an emotion analysis engine to analyze the user's emotional state.

[0300] 5. Generate an appropriate alert message according to the emotional state and display it to the user.

[0301] Example: A user tries to send an email saying "Please see the attachment in this email" but forgets to include the attachment. The device will detect this and, if the user is annoyed, will display a gentle alert saying "Attachment missing. Did you forget to attach it?". If the user is distracted, it will display "Attachment not found. Please check it now."

[0302] Data entry error detection and emotional alerts

[0303] Terminal

[0304] 1. A user enters data into a web form, Excel spreadsheet, etc.

[0305] 2. The device monitors what you type in real time and uses dictionary-based spell checking and regular expressions to detect spelling and formatting errors.

[0306] 3. If an error is detected, the device activates an emotion analysis engine to analyze the user's emotional state.

[0307] 4. Generate an appropriate alert message according to the emotional state and display it to the user.

[0308] Example: If a user types "example@domain.com", the device will detect this and display an alert saying "The email address format is incorrect. Please check again." If the sentiment analysis engine recognizes that the user is fatigued, it will display an alert with advice saying "The correct format is example@domain.com. Please correct it." On the other hand, if the user is impatient, it will display a short and concise alert saying "Please enter your email address in the correct format."

[0309] Prompt Sentence Examples

[0310] 1. "Please give me the following price list: [500, 520, 510, 490, 1200]. Detect outliers from this list and generate alert messages based on the emotional state."

[0311] 2. "Analyze the body of the email the user is about to send, and if there is no attachment, generate an appropriate alert message using a sentiment analysis engine."

[0312] 3. "Monitor data entry in real time and detect spelling and formatting errors. Generate appropriate alert messages based on emotional state."

[0313] Through this system, users can quickly detect mistakes made during digital tasks and receive appropriate instructions, which is expected to significantly improve work efficiency and accuracy.

[0314] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0315] Mispricing detection and emotional alerts

[0316] Step 1:

[0317] The user submits a price list to the server.

[0318] Input: The user enters a price list (e.g., [500, 520, 510, 490, 1200]) into the interface and presses the submit button.

[0319] Output: The price list is sent to the server.

[0320] Specific action: A user uses a web interface to enter a price list into a form and presses the submit button.

[0321] Step 2:

[0322] The server receives the price list and converts it into a NumPy array.

[0323] Input: Received price list data.

[0324] Output: Price list as a NumPy array.

[0325] What it does: The server receives the price list and converts it to a numeric array using Python's NumPy library. Example: [500, 520, 510, 490, 1200] -> np.array([500, 520, 510, 490, 1200])

[0326] Step 3:

[0327] The server analyzes the price list using the KMeans clustering algorithm.

[0328] Input: Price list converted to a NumPy array.

[0329] Output: Clustering results and outlier locations.

[0330] Specific operation: The server uses the scikit-learn library to perform KMeans clustering. It sets the number of clusters and initial conditions, clusters the price data, and detects outliers.

[0331] Step 4:

[0332] The server detects outliers.

[0333] Input: Analysis results from the clustering algorithm.

[0334] Output: Data points identified as outliers.

[0335] Specific behavior: From the clustering results, data points in the price list that deviate significantly from the normal range (e.g., 1200) are identified as outliers.

[0336] Step 5:

[0337] The server runs an emotion analysis engine to analyze the emotional state.

[0338] Input: Anomaly detection results, chat messages with users, facial expression data, and voice data.

[0339] Output: The user's emotional state.

[0340] What it does: The server launches an emotion analysis engine that analyzes the user's text messages and other emotional data to determine their current emotional state.

[0341] Step 6:

[0342] The server generates alerts for abnormal values ​​and notifies the user.

[0343] Input: Sentiment analysis results and outliers.

[0344] Output: Appropriate alert message depending on emotional state.

[0345] Specific behavior: Based on the user's emotional state, generate an alert message in a soft or direct tone and display it in the user's interface.

[0346] Preventing mis-sending of documents and emotional response alerts

[0347] Step 1:

[0348] The user composes an email and clicks the send button.

[0349] Input: The email body created by the user.

[0350] Output: The transport request.

[0351] Specific behavior: A user composes an email in an email client (e.g., Outlook, Gmail) and clicks the send button.

[0352] Step 2:

[0353] The device analyzes the email body.

[0354] Input: The email body created by the user.

[0355] Output: Text analysis result.

[0356] What happens: The device reads the email body as a string and begins analyzing it. It performs a regular expression search to find specific keywords (e.g., "attachment").

[0357] Step 3:

[0358] The device detects specific keywords.

[0359] Input: Body parsing result.

[0360] Output: Check for the existence of a specific keyword.

[0361] Specific operation: The device extracts specific keywords such as "attachment" and "document" from the analyzed email body.

[0362] Step 4:

[0363] The device checks for the presence of an attachment.

[0364] Input: Detected results for a specific keyword.

[0365] Output: The result of checking whether the attachment exists.

[0366] Specific operation: The device checks the header information of the email to see if it actually contains an attachment.

[0367] Step 5:

[0368] If there is no attachment, the device runs an emotion analysis engine to analyze the emotional state.

[0369] Input: Attachment check result, user operation data.

[0370] Output: The user's emotional state.

[0371] Specific operation: The device launches an emotion analysis engine and analyzes the user's emotional state from operation data (e.g., keyboard keystroke sounds, keystroke speed).

[0372] Step 6:

[0373] The terminal generates an appropriate alert and displays it to the user.

[0374] Input: Sentiment analysis results, attachment check results.

[0375] Output: An appropriate alert message.

[0376] What it does: Generates a mild or urgent alert message based on the user's emotional state and displays it as a pop-up on the user's screen.

[0377] Data entry error detection and emotional alerts

[0378] Step 1:

[0379] The user enters data into the terminal.

[0380] Input: Data entered by the user.

[0381] Output: Capture of input data.

[0382] Specific action: A user enters data into an Excel spreadsheet or web form.

[0383] Step 2:

[0384] The terminal monitors the input in real time.

[0385] Input: Data that the user is entering.

[0386] Output: Monitoring results (dynamic capture of input data).

[0387] What it does: The device captures data input in real time using JavaScript and keystroke monitoring scripts.

[0388] Step 3:

[0389] The device will detect spelling and formatting errors.

[0390] Input: The monitored input data.

[0391] Output: Detected spelling and formatting errors.

[0392] What it does: The device performs dictionary-based spell checking and regular expression pattern matching to detect spelling and formatting errors.

[0393] Step 4:

[0394] The device runs an emotion analysis engine to analyze the emotional state.

[0395] Input: Results of detection of spelling and formatting errors, user operation data.

[0396] Output: The user's emotional state.

[0397] Specific operation: The device launches an emotion analysis engine and analyzes the user's emotional state based on factors such as typing speed and frequency of input errors.

[0398] Step 5:

[0399] The terminal generates an alert to the error and displays it to the user.

[0400] Input: Sentiment analysis results, error detection results.

[0401] Output: An appropriate alert message.

[0402] Specific behavior: Depending on the emotional state and the error, an advisory or urgent alert message is generated and displayed as a pop-up on the user's screen.

[0403] (Application example 2)

[0404] 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."

[0405] Conventional inventory management and customer support systems have had problems with product pricing errors and data entry errors, which reduce work efficiency. Additionally, the lack of a way to respond appropriately to user emotions has led to stress and impatience, which can lead to increased work errors.

[0406] 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 receiving a price list, means for analyzing the received price list and detecting abnormal values, means for analyzing the user's emotional state in response to the detected abnormal values, and means for notifying an alert with an appropriate tone based on the user's emotional state. This makes it possible to detect pricing errors and notify an appropriate alert according to the user's emotional state.

[0407] A "price list" is a table that lists product price information.

[0408] An "outlier" is a data value that is outside the normal range and is detected by specific criteria or algorithms.

[0409] "Emotional state" refers to the user's psychological and emotional reactions and situations, and is analyzed using voice data and facial expression recognition.

[0410] An "alert" is a notification or warning message sent from the system to the user.

[0411] A "document" refers to text data including text data such as email.

[0412] "Specific keywords" are important words and phrases that are set for the system to search and detect.

[0413] An "attachment" is an additional data file that is added to an email or the like.

[0414] "Data entry" is the act of a user manually entering information into a system.

[0415] "Spelling error" refers to a situation in which a word is misspelled.

[0416] "Format error" refers to a deviation from the specified format when entering data.

[0417] "Real-time monitoring" refers to the instantaneous confirmation and analysis of data and behavior.

[0418] MODE FOR CARRYING OUT THE INVENTION

[0419] This invention is a system that prevents pricing errors and data entry errors when users manage inventory and handle customer service in a physical store, and also provides appropriate alerts based on the user's emotional state. The system receives price lists, detects abnormal values, and notifies the user of alerts based on the user's emotional state.

[0420] System program generation

[0421] The server first receives a price list sent by the user. This price list contains product price information. The received price list is converted into a NumPy array and analyzed using a clustering algorithm (e.g., KMeans clustering). If an outlier outside the normal price range is detected, the server activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's current emotional state using facial recognition, voice data, chat messages, etc.

[0422] Hardware and software used

[0423] Hardware:

[0424] Smartphones, smart glasses, head-mounted displays (HMDs)

[0425] software:

[0426] NumPy: Array manipulation and calculations on data

[0427] scikit-learn: Clustering algorithm implementation

[0428] emotion_recognition:Emotion recognition engine

[0429] The server generates appropriate alerts for outliers based on the user's emotional state. These alerts have different tones depending on the user's emotional state. For example, if the user is stressed, a softer alert such as "This price is significantly different from other prices. Please check it." On the other hand, if the user is calm, a more direct alert such as "1200 yen is an outlier. Please correct it."

[0430] Specific examples

[0431] For example, consider a scenario where a staff member uses smart glasses to manage inventory. If a price list contains the data [500, 520, 510, 490, 1200], the server receives this price list and detects 1200 as an outlier. At this time, the emotion engine analyzes the staff member's emotional state, and if the staff member is feeling stressed, an alert will be displayed saying, "This price is significantly different from the other prices. Please check."

[0432] You can also use the following example prompts to provide appropriate instructions to the generative AI model:

[0433] Prompt Sentence Examples

[0434] User input: Setting stock price. Price list: [500, 520, 510, 490, 1200]

[0435] Emotional state: stressed

[0436] Task: Detect any anomalous prices and generate a customized alert based on the emotion state.

[0437] By implementing this invention, the efficiency and accuracy of inventory management in physical stores can be significantly improved, and flexible responses based on user emotions become possible.

[0438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0439] Step 1:

[0440] The server receives a price list from the user. It takes as input a list containing price information (e.g., [500, 520, 510, 490, 1200]) and stores it for use in the next processing step. The output is the received price list.

[0441] Step 2:

[0442] The server converts the received price list into a NumPy array. Here, the price information in list format is converted into a NumPy array format, making it easier to analyze the data. The input is the price list received in step 1, and the output is the converted NumPy array.

[0443] Step 3:

[0444] The server analyzes the price data using NumPy arrays and applies a clustering algorithm (e.g., KMeans clustering) to detect outliers. The input is the generated NumPy array, and the output is a list of outliers. It evaluates each price cluster and identifies prices outside the normal price range as outliers.

[0445] Step 4:

[0446] The server detects outliers based on the clustering results and then runs an emotion engine to analyze the user's emotional state. The input is a list of outliers, and the output is the user's emotional state (e.g., stressed, calm). Here, the server analyzes the user's emotions from facial recognition data, voice data, chat messages, etc.

[0447] Step 5:

[0448] The server generates an alert with an appropriate tone based on the user's emotional state. The input is the list of abnormal values ​​and the user's emotional state, and the output is the alert message. For example, if the emotional state is "stressed," the server generates a soft-toned alert saying, "This price is significantly different from other prices. Please check."

[0449] 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.

[0450] 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.

[0451] 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.

[0452] [Second embodiment]

[0453] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0454] 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.

[0455] 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).

[0456] 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.

[0457] 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.

[0458] 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).

[0459] 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. 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] In the smart glasses 214, 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.

[0464] 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."

[0465] DETAILED DESCRIPTION OF THE INVENTION The present invention includes embodiments of a system for preventing pricing errors, misdirected documents, and data entry errors, called DTSAI (Digital Task Safeguard AI).

[0466] Pricing Mistake Detection

[0467] server

[0468] The server processes price lists received from users. These price lists contain prices for goods and services. The server analyzes the price lists and detects outliers that fall outside the normal price range. To do this, it uses machine learning algorithms (e.g., KMeans clustering) to cluster the price lists and automatically identify outliers. When an outlier is detected, the server sends a warning to the user, prompting them to make corrections.

[0469] For example, when a user sets the price of a new product lineup, the price list is sent to the server. For example, if the price list is [500, 520, 510, 490, 1200], the server detects that 1200 is an abnormal value and sends an alert to the user saying, "The price setting of 1200 yen is significantly different from the other prices."

[0470] Preventing documents from being sent to the wrong person

[0471] Terminal

[0472] When a user attempts to send an email, the device analyzes the body of the email. If the body of the email contains specific keywords such as "attachment" or "document," the device checks whether there are any attachments. If there are no attachments, a warning message is displayed to the user to prevent the email from being sent by mistake. The user can check the warning and attach a file or modify the email content as necessary.

[0473] For example, if a user writes "Please see the attached file in this email" but does not actually attach a file, the device will display an alert saying "There is no attachment. Would you like to attach one?" The user will see the warning and attach the file.

[0474] Data entry error detection

[0475] Terminal

[0476] During data entry, the terminal monitors what the user types in real time. It analyzes the text entered and checks for spelling and formatting errors. This includes regular expression and dictionary-based spell checking. If an incorrect entry is detected, the terminal displays an alert to the user immediately and prompts them to correct it.

[0477] For example, if a user enters "example@domain.com" as their email address in an online form, the device will display an alert saying, "There is an error in the email address format. Please check again." The user will then see the warning and correct their email address to "example@domain.com."

[0478] As described above, the DTSAI system of the present invention automatically detects errors in everyday digital tasks such as pricing, document transmission, and data entry, and alerts users in real time, thereby improving work efficiency and accuracy.

[0479] The processing flow will be explained below.

[0480] Pricing Mistake Detection

[0481] server

[0482] Step 1:

[0483] The server receives a price list from the user, the price list containing prices for goods and services.

[0484] Step 2:

[0485] The server converts the received price list into a NumPy array, which is a data preprocessing step to make it suitable for the clustering algorithm.

[0486] Step 3:

[0487] The server applies the KMeans clustering algorithm to divide the price list into two clusters, which distinguishes between normal and abnormal prices.

[0488] Step 4:

[0489] The server calculates cluster centers and detects outliers that deviate significantly from the normal price cluster.

[0490] Step 5:

[0491] If the server detects an abnormal value, it will notify the user in real time as an alert, prompting the user to recheck the price.

[0492] Preventing documents from being sent to the wrong person

[0493] Terminal

[0494] Step 1:

[0495] When a user presses the send button on an email, the device reads the body and subject of the email.

[0496] Step 2:

[0497] The device searches for specific keywords (such as "attachment" or "document") in the email body and checks whether these keywords are included.

[0498] Step 3:

[0499] If a specific keyword is detected, the device checks whether the email has an attachment.

[0500] Step 4:

[0501] If there is no attachment, the device will display an alert to the user saying, "The email contains the word 'attached,' but there is no attachment."

[0502] Step 5:

[0503] The user checks the alert and attaches files or modifies the email content as needed.

[0504] Data entry error detection

[0505] Terminal

[0506] Step 1:

[0507] When a user enters data into an input form, the terminal monitors the input content in real time.

[0508] Step 2:

[0509] The terminal parses the text you enter to detect spelling and formatting errors, using regular expressions and dictionary-based spell checking.

[0510] Step 3:

[0511] If an incorrect input is detected, the device will immediately display an alert to the user saying, "There is an input error. Please check again."

[0512] Step 4:

[0513] The user acknowledges the alert and corrects the data entry.

[0514] The above are the specific processing steps in each module. The DTSAI system of the present invention allows users to quickly detect mistakes during digital tasks and respond in real time.

[0515] Example 1

[0516] 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."

[0517] In today's business environment, pricing errors, mis-sent documents, and data entry errors are commonplace, significantly impacting the efficiency and accuracy of business operations. Preventing these errors requires a comprehensive system that can handle multiple different tasks. However, traditional systems have difficulty resolving these issues consistently, resulting in the cost and effort required to address each issue individually.

[0518] 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.

[0519] In this invention, the server includes means for receiving a price list, means for analyzing the received price list using a machine learning algorithm to detect outliers, means for notifying a user of an alert when an outlier is detected, means for analyzing the content of a document to detect specific keywords, means for checking whether or not an attachment exists when the specific keyword is detected, means for displaying an alert to the user when the attachment does not exist, means for monitoring data entry in real time, means for detecting spelling mistakes and formatting errors, and means for displaying an alert to the user when an error is detected. This makes it possible to automatically detect errors in everyday digital tasks such as pricing, document transmission, and data entry, and to issue alerts in real time, thereby improving work efficiency and accuracy.

[0520] A "price list" is data that compiles price information for products and services in a list format.

[0521] A "machine learning algorithm" is a numerical method that automatically learns patterns based on large amounts of data and makes predictions and classifications.

[0522] "Clustering" is a data analysis technique that divides a dataset into several groups so that data within the same group are similar to each other.

[0523] An "outlier" is a value that deviates significantly from the average trend of the entire data set.

[0524] An "alert" is a warning message that notifies the user when the system detects an abnormality or a situation that requires attention.

[0525] A "specific keyword" is a word or phrase in a document that triggers a specific action (such as checking an attachment).

[0526] An "attachment" is an additional data file included in an email.

[0527] "Real-time monitoring" refers to checking data immediately at the moment the user enters it.

[0528] A "spelling error" is a mistake in which a letter of a word is typed incorrectly.

[0529] A "format error" is a data entry error that does not follow a prescribed format.

[0530] This invention is a system for preventing pricing errors, mis-sent documents, and data entry errors. Specifically, it is an integrated system with multiple functions for analyzing price lists, document content, and monitoring data entry in real time. This system is composed of a server and terminals.

[0531] Pricing Mistake Detection

[0532] server

[0533] The server processes price lists received from users. These price lists contain prices for goods and services. The server analyzes the price lists using machine learning algorithms, specifically KMeans clustering, to detect outliers that fall outside the normal price range. If an outlier is detected, the server sends an alert to the user, prompting them to adjust the pricing.

[0534] Specific examples

[0535] When a user sets the price of a new product lineup, the price list is sent to the server. For example, if the price list is [500 yen, 520 yen, 510 yen, 490 yen, 1200 yen], the server detects that 1200 yen is an abnormal value and sends an alert to the user saying, "The price setting of 1200 yen is significantly different from the other prices."

[0536] Prompt Sentence Examples

[0537] "The price list for the new product lineup contains an outlier at [500, 520, 510, 490, 1200]. Please write a program that detects the outlier and notifies the user."

[0538] Preventing documents from being sent to the wrong person

[0539] Terminal

[0540] When a user attempts to send an email, the device analyzes the body of the email. If the body contains specific keywords such as "attachment" or "document," the device checks whether there are any attachments. If there are no attachments, the device displays a warning message to the user to prevent the email from being sent by mistake.

[0541] Specific examples

[0542] If a user writes "Please see the attachment in this email" but does not actually attach a file, the device will display an alert saying "There is no attachment. Do you want to attach it?" The user will see the warning and attach the file.

[0543] Prompt Sentence Examples

[0544] "Please describe the program's processing to warn when a user sends an email that contains an "attachment" or "document" in the body of the email but the attached file does not exist."

[0545] Data entry error detection

[0546] Terminal

[0547] The terminal monitors what the user types in real time as data is entered. The terminal parses the text entered and checks for spelling and formatting errors using regular expressions and dictionary-based spell checking. If an incorrect entry is detected, the terminal will immediately alert the user and prompt them to correct it.

[0548] Specific examples

[0549] When a user enters an email address in an online form, if the user types "example@domain.com", the device will display an alert saying "There is an error in the email address format. Please check again." The user will then see the warning and correct the email address to "example@domain.com".

[0550] Prompt Sentence Examples

[0551] "When a user enters an email address into an online form, write a program that warns them if the format is invalid."

[0552] In this way, the present invention is a system that automatically detects errors in everyday digital tasks such as pricing, document transmission, and data entry, and provides real-time alerts to improve work efficiency and accuracy.

[0553] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0554] Pricing Mistake Detection

[0555] Step 1:

[0556] The server receives a price list from a user, which includes as input a price list, which contains pricing information for goods and services.

[0557] Step 2:

[0558] The server analyzes the received price list using a machine learning algorithm (e.g., KMeans clustering). First, it stores the price list in a database and then inputs the data into a clustering algorithm. The clustering results show the normal price range and outliers.

[0559] Step 3:

[0560] The server identifies outliers based on the clustering results. If an outlier is detected, it marks it as a flag and prepares to send an alert to the user. As an output, it generates a list of outliers and corresponding warning messages.

[0561] Step 4:

[0562] If an abnormal value is detected, the server will send an alert to the user. The alert will be sent by email or a pop-up notification. For example, a notification such as "The price setting of 1,200 yen is significantly different from the other prices" will be sent.

[0563] Preventing documents from being sent to the wrong person

[0564] Step 1:

[0565] When a user sends an email, the terminal analyzes the content of the email body, which includes the email body as input.

[0566] Step 2:

[0567] The device checks whether specific keywords such as "attachment" or "document" are included in the email body. It performs text analysis and lists the detected keywords. The output shows whether the detected keywords are present or not.

[0568] Step 3:

[0569] When a specific keyword is detected, the terminal checks whether or not there are any attachments. It checks the email attachment list and outputs whether or not there are any attachments.

[0570] Step 4:

[0571] If the attachment does not exist, the terminal will display an alert to the user. Specifically, a warning message such as "There is no attachment. Do you want to attach it?" will be displayed. The user will check this warning and attach the file if necessary.

[0572] Data entry error detection

[0573] Step 1:

[0574] The terminal monitors in real time what the user is entering during data entry. Input includes the data entered by the user.

[0575] Step 2:

[0576] The terminal parses the input text, checking for spelling and formatting errors, applying regular expression and dictionary-based spell checking algorithms, and provides the presence or absence of errors as output.

[0577] Step 3:

[0578] If an incorrect entry is detected, the device will immediately display an alert to the user. Specifically, a warning message such as "There is an error in the email address format. Please check again" will be displayed. The user will then check this warning and correct the entry.

[0579] (Application example 1)

[0580] 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."

[0581] Pricing errors and promotional information errors in physical stores directly lead to sales losses and reduced customer satisfaction. Preventing such errors and detecting and correcting them in real time is a key challenge for improving operational efficiency and customer satisfaction in physical stores. In addition, incorrect transmissions and data entry errors also have a negative impact on operational efficiency, so these issues must also be addressed at the same time.

[0582] 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.

[0583] In this invention, the server includes means for receiving a price list, means for analyzing the received price list and detecting abnormal values, means for notifying a user of an alert when an abnormal value is detected, means for acquiring price information via an electronic device for photographing the price list and analyzing the acquired price information in real time, means for automatically identifying abnormal values ​​in the price information, means for displaying an alert to the user via the electronic device when an abnormal value is detected, and means for prompting the user to reconfirm or correct the abnormal value. This enables errors in pricing and promotion information in physical stores to be detected and corrected in real time, improving business efficiency and customer satisfaction.

[0584] A "price list" is a document or data that lists price information for products or services.

[0585] An "outlier" is any price information that is outside the normal price range and is therefore not valid.

[0586] "User" refers to the person or administrator who uses the system to set prices or view information.

[0587] An "alert" is a warning message that the system sends to the user to notify them of an error or abnormality.

[0588] "Electronic devices" refers to devices used to capture price information and analyze the data, such as smart glasses or smartphones.

[0589] "Real-time" refers to data processing and information notification occurring immediately, without delay.

[0590] "Analysis" refers to analyzing the received data, interpreting its meaning, and detecting specific patterns or anomalies.

[0591] "Revalidation" is the process of re-evaluating the detected discrepancies to check whether they are correct.

[0592] "Correction" refers to changing detected abnormal values ​​or errors into accurate information.

[0593] "Price Information" means price data associated with individual products or services.

[0594] The DTSAI system embodying the present invention is a system that detects pricing errors and promotion information errors in real time in physical stores and notifies users of alerts. The system configuration and processing are described in detail below.

[0595] System Configuration

[0596] 1. Hardware Configuration

[0597] Server: Analyzes the data and detects outliers.

[0598] Terminal (smart glasses, smartphone, etc.): Captures price information and sends it to the server in real time.

[0599] Network: A communication method for linking terminals and servers.

[0600] 2. Software Configuration

[0601] Machine learning algorithm: KMeans clustering is used to analyze price information.

[0602] Data analysis module: a program for analyzing received price lists.

[0603] Alert module: A program that notifies the user when an abnormal value is detected.

[0604] Processing steps

[0605] 1. Obtaining and sending price information

[0606] The user uses smart glasses to take a photo of the product price and transmits the data to the server.

[0607] 2. Analysis of price information

[0608] The server analyzes the received price data in real time and detects outliers that deviate from the normal price range.

[0609] The algorithm used is KMeans clustering, which clusters price data and identifies outliers.

[0610] 3. Alert Notification

[0611] If an abnormal value is detected, the server sends the information to the terminal and displays an alert to the user in real time.

[0612] This allows users to quickly correct pricing errors.

[0613] Specific examples

[0614] For example, if a user sets the price of a new product and the price list includes 500 yen, 520 yen, 510 yen, 490 yen, and 1200 yen, the server will detect that 1200 yen is an abnormal value. The corresponding smart glasses will display an alert saying, "The 1200 yen price setting is significantly different from the other prices. Please check again."

[0615] Prompt Sentence Examples

[0616] Please set a price for your new product. If the prices of other products are around 1000 yen and your set price is 5000 yen, please send an alert as an abnormal value.

[0617] As described above, the DTSAI system of the present invention detects errors in pricing and promotional information in physical stores in real time and promptly notifies users of alerts, thereby improving business efficiency and customer satisfaction.

[0618] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0619] Step 1:

[0620] Obtaining and sending price information

[0621] A user captures the price of a product using a device (e.g., smart glasses). The device's built-in camera captures the product's price tag and extracts the price information using OCR (optical character recognition) technology. The device then sends the price information to a server.

[0622] Input: Price tag image

[0623] Output: Extracted price information

[0624] Step 2:

[0625] Receiving price information

[0626] The server receives the price information sent from the terminal and stores it in a database within the server.

[0627] Input: Price information sent from the device

[0628] Output: Price information stored in a database

[0629] Step 3:

[0630] Price information analysis

[0631] The server uses a data analysis module to analyze the received price information in real time. This analysis uses KMeans clustering to classify the price information and detect outliers. The algorithm clusters the price information and identifies the prices detected as outliers.

[0632] Input: Price information stored in a database

[0633] Output: Price information identified as anomalies

[0634] Step 4:

[0635] Alert Generation

[0636] If the server detects an anomaly, it generates an alert based on the price information. The alert message includes details of the anomaly and a recommendation to recheck.

[0637] Input: Price information identified as an outlier

[0638] Output: The generated alert message

[0639] Step 5:

[0640] Alert Notifications

[0641] The server sends the generated alert message to the terminal, which then displays the received alert message on the user's display. The user can then confirm the message and make any necessary adjustments to the pricing.

[0642] Input: The generated alert message

[0643] Output: The alert message displayed on the user's display.

[0644] Specifically, when a user sets a price for a new product, the smart glasses capture the "5,000 yen" price tag and send the price information to the server. The server detects through clustering that "5,000 yen" is an anomaly and generates an alert message saying, "The price of the 5,000 yen product is significantly different from other products. Please check again." This message is displayed on the smart glasses' display. The user can then confirm the alert and make any necessary adjustments to the price setting.

[0645] 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.

[0646] The following describes in detail the mode for carrying out the present invention: The present invention is a system that combines a Digital Task Safeguard AI (DTSAI) system, which prevents pricing errors, incorrect attachments when sending documents, and spelling and formatting errors when entering data, with an emotion engine that recognizes user emotions.

[0647] Mispricing detection and emotional alerts

[0648] server

[0649] The server receives a price list sent by the user. This price list contains the prices of goods and services. The received price list is converted into a NumPy array and analyzed using a clustering algorithm (e.g., KMeans clustering). When an outlier outside the normal price range is detected, the server activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's current emotional state from Japanese chat messages, facial expression recognition, and voice data. Depending on the emotional state, the server notifies the user with an appropriate alert regarding the outlier.

[0650] For example, if a user sets a new product price and sends the price list [500, 520, 510, 490, 1200] to the server, the server will detect 1200 as an abnormal value. If the user is stressed at the time, the server will send a soft-toned alert saying, "This price is significantly different from the other prices. Please check it." On the other hand, if the user is calm, the server will send a direct alert saying, "1200 yen is an abnormal value. Please correct it."

[0651] Preventing mis-sending of documents and emotional response alerts

[0652] Terminal

[0653] When a user attempts to send an email, the device analyzes the content of the email body. If specific keywords (such as "attachment" or "document") are detected, the device checks whether an attachment exists. If no attachment exists, the emotion engine analyzes the user's emotional state. An appropriate alert message is displayed depending on the user's emotional state.

[0654] For example, if a user writes "Please see the attachment in this email" but forgets to include the attachment, the device will detect this. If the user is annoyed, the device will display a gentle alert such as "Attachment missing. Did you forget to attach it?". Conversely, if the user is focused on a task, the device will display a more urgent alert such as "Attachment not found. Please check it immediately."

[0655] Data entry error detection and emotional alerts

[0656] Terminal

[0657] During data entry, the device monitors what the user types in real time. Regular expression and dictionary-based spell checking are used to detect spelling and formatting errors. If an error is detected, an emotion engine analyzes the user's emotional state and displays an alert to the user accordingly.

[0658] For example, if a user types "example@domain.com," the device will detect this and display an alert saying, "The email address format is incorrect. Please check again." If the emotion engine recognizes that the user is tired, it will display an alert with advice such as, "The correct format is example@domain.com. Please correct it." On the other hand, if the user is impatient, it will display a short, concise alert saying, "Please enter your email address in the correct format."

[0659] The combination of the DTSAI system and emotion engine of the present invention allows users to effectively detect mistakes made during digital tasks and receive adaptive responses in real time, greatly improving work efficiency and accuracy.

[0660] The processing flow will be explained below.

[0661] Mispricing detection and emotional alerts

[0662] server

[0663] Step 1:

[0664] The server receives the price list from the user, which is then converted to an appropriate data format (e.g., a NumPy array) when sent to the server.

[0665] Step 2:

[0666] The server applies the KMeans clustering algorithm to the price list and classifies the prices into two clusters: one for normal prices and one for abnormal prices.

[0667] Step 3:

[0668] The server calculates cluster centers of typical prices and identifies outliers based on them. Prices that deviate significantly from the cluster center are considered outliers.

[0669] Step 4:

[0670] If the server detects an anomaly, the emotion engine is activated to analyze the user's current emotional state, which is obtained from text messages, facial recognition, voice data, etc.

[0671] Step 5:

[0672] Based on the analysis results of the emotion engine, the server notifies the user with an appropriate alert. For example, if the user is feeling stressed, the server sends a soft-spoken alert such as "This price is significantly different from other prices. Please check."

[0673] Preventing mis-sending of documents and emotional response alerts

[0674] Terminal

[0675] Step 1:

[0676] When the user clicks the send email button, the terminal reads the email body and subject line.

[0677] Step 2:

[0678] The device searches for specific keywords (such as "attachment" or "document") in the email body. If these keywords are included, it checks whether or not there are any attachments.

[0679] Step 3:

[0680] When a specific keyword is detected, the device checks whether an attachment exists. If an attachment does not exist, the emotion engine is activated to analyze the user's emotional state.

[0681] Step 4:

[0682] The emotion engine analyzes the user's emotional state, which is determined based on real-time data (e.g., facial expressions, voice, etc.).

[0683] Step 5:

[0684] Based on the analysis results of the emotion engine, the device will display appropriate alerts to the user. If the user is annoyed, it will display a gentle alert such as "Attachment missing. Did you forget to attach it?", but if the user is distracted, it will display a more urgent alert such as "Attachment not found. Please check immediately."

[0685] Data entry error detection and emotional alerts

[0686] Terminal

[0687] Step 1:

[0688] As the user enters key data into the input form, the terminal monitors the data in real time.

[0689] Step 2:

[0690] The terminal parses the text entered and uses regular expressions and dictionary-based spell checking to detect spelling and formatting errors.

[0691] Step 3:

[0692] If the device detects an input error, the emotion engine will be activated and analyze the user's emotional state, which can be obtained from text, facial expression analysis, voice analysis, etc.

[0693] Step 4:

[0694] Based on the analysis results of the emotion engine, the device displays appropriate alerts to the user. For example, if the user is tired, it displays an alert with advice such as "The correct format is example@domain.com. Please correct it." If the user is impatient, it displays a simple alert such as "Please enter your email address in the correct format."

[0695] These are the specific processing steps in each module. By combining emotion engines, it is possible to provide appropriate support according to the user's condition, improving the efficiency and accuracy of work.

[0696] Example 2

[0697] 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."

[0698] Conventional digital task management systems have difficulty detecting and notifying users of pricing errors, incorrect attachments when sending documents, and spelling or formatting errors when entering data. Furthermore, they are unable to provide alert messages that take into account the user's emotional state, increasing the risk of user stress and incorrect operation.

[0699] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving a price list; means for converting the received price list into a numerical array, analyzing it using a clustering algorithm, and detecting outliers; means for analyzing the user's emotional state using an emotion analysis engine when an outlier is detected and notifying the user of an appropriate alert for the outlier based on the emotional state; means for analyzing the content of the document and detecting specific keywords; means for checking whether or not an attachment is present when a specific keyword is detected; means for analyzing the user's emotional state using the emotion analysis engine when an attachment is not present and displaying an alert based on the emotional state; means for monitoring data input in real time; means for detecting spelling mistakes and formatting errors; and means for analyzing the user's emotional state using the emotion analysis engine when an error is detected and displaying an appropriate alert for the error based on the emotional state. This enables effective detection of errors during digital tasks and adaptive responses in real time.

[0700] A "price list" is data that lists the prices of products and services.

[0701] A "numeric array" is data with an array structure in which numerical data is arranged in a fixed order.

[0702] A "clustering algorithm" is a computational procedure for classifying data into groups (clusters) based on similarity.

[0703] An "outlier" is a data point that deviates from the normal range and is a value that is significantly different compared to other data.

[0704] An "emotion analysis engine" is a software component that analyzes data such as text, voice, and facial expressions to recognize a user's emotional state.

[0705] An "alert" is a warning message that notifies the user of important information or matters requiring attention.

[0706] "Specific keywords" are predefined important words or phrases that are searched for within a document.

[0707] An "attachment" is an additional file attached to an email or document.

[0708] "Data entry" refers to the operation by which a user inputs information into a system or application.

[0709] A "spelling error" is an error in which a word is spelled incorrectly.

[0710] A "format error" is an error in which the data does not conform to the expected format or structure.

[0711] "Real-time monitoring" refers to the operation of immediately monitoring the contents of data the moment it is entered or updated.

[0712] The following describes in detail the mode for carrying out the present invention. This invention is a system that prevents mistakes in multiple digital tasks and responds adaptively to the user's emotional state. To achieve this, the server, terminal, and user work together.

[0713] Mispricing detection and emotional alerts

[0714] server

[0715] 1. The user sets up a price list and sends it to the server. The sent price list contains the prices of products and services.

[0716] 2. The received price list is converted by the server into a NumPy array. NumPy is a Python library that allows for highly efficient numerical calculations.

[0717] 3. The server analyzes the price list using the clustering algorithm KMeans clustering, which uses the scikit-learn library.

[0718] 4. When an outlier outside the normal price range is detected, the server activates the sentiment analysis engine, which obtains the user's emotional state from data such as text, facial expressions, and voice.

[0719] 5. Depending on the emotional state, generate appropriate alert messages for abnormal values ​​and notify the user.

[0720] Example: If a user sets a new product price and sends the price list [500, 520, 510, 490, 1200] to the server, the server will detect 1200 as an abnormal value. If the user is stressed, the server will send an alert saying "This price is significantly different from other prices. Please check." If the user is calm, the server will send an alert saying "1200 yen is an abnormal value. Please correct it."

[0721] Preventing mis-sending of documents and emotional response alerts

[0722] Terminal

[0723] 1. The user composes an email and clicks the send button.

[0724] 2. When the send button is pressed, the device analyzes the email body and detects the specified specific keywords (e.g., "attachment," "document").

[0725] 3. If the keyword is detected, the device checks whether there is an attachment.

[0726] 4. If there is no attachment, the device runs an emotion analysis engine to analyze the user's emotional state.

[0727] 5. Generate an appropriate alert message according to the emotional state and display it to the user.

[0728] Example: A user tries to send an email saying "Please see the attachment in this email" but forgets to include the attachment. The device will detect this and, if the user is annoyed, will display a gentle alert saying "Attachment missing. Did you forget to attach it?". If the user is distracted, it will display "Attachment not found. Please check it now."

[0729] Data entry error detection and emotional alerts

[0730] Terminal

[0731] 1. A user enters data into a web form, Excel spreadsheet, etc.

[0732] 2. The device monitors what you type in real time and uses dictionary-based spell checking and regular expressions to detect spelling and formatting errors.

[0733] 3. If an error is detected, the device activates an emotion analysis engine to analyze the user's emotional state.

[0734] 4. Generate an appropriate alert message according to the emotional state and display it to the user.

[0735] Example: If a user types "example@domain.com", the device will detect this and display an alert saying "The email address format is incorrect. Please check again." If the sentiment analysis engine recognizes that the user is fatigued, it will display an alert with advice saying "The correct format is example@domain.com. Please correct it." On the other hand, if the user is impatient, it will display a short and concise alert saying "Please enter your email address in the correct format."

[0736] Prompt Sentence Examples

[0737] 1. "Please give me the following price list: [500, 520, 510, 490, 1200]. Detect outliers from this list and generate alert messages based on the emotional state."

[0738] 2. "Analyze the body of the email the user is about to send, and if there is no attachment, generate an appropriate alert message using a sentiment analysis engine."

[0739] 3. "Monitor data entry in real time and detect spelling and formatting errors. Generate appropriate alert messages based on emotional state."

[0740] Through this system, users can quickly detect mistakes made during digital tasks and receive appropriate instructions, which is expected to significantly improve work efficiency and accuracy.

[0741] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0742] Mispricing detection and emotional alerts

[0743] Step 1:

[0744] The user submits a price list to the server.

[0745] Input: The user enters a price list (e.g., [500, 520, 510, 490, 1200]) into the interface and presses the submit button.

[0746] Output: The price list is sent to the server.

[0747] Specific action: A user uses a web interface to enter a price list into a form and presses the submit button.

[0748] Step 2:

[0749] The server receives the price list and converts it into a NumPy array.

[0750] Input: Received price list data.

[0751] Output: Price list as a NumPy array.

[0752] What it does: The server receives the price list and converts it to a numeric array using Python's NumPy library. Example: [500, 520, 510, 490, 1200] -> np.array([500, 520, 510, 490, 1200])

[0753] Step 3:

[0754] The server analyzes the price list using the KMeans clustering algorithm.

[0755] Input: Price list converted to a NumPy array.

[0756] Output: Clustering results and outlier locations.

[0757] Specific operation: The server uses the scikit-learn library to perform KMeans clustering. It sets the number of clusters and initial conditions, clusters the price data, and detects outliers.

[0758] Step 4:

[0759] The server detects outliers.

[0760] Input: Analysis results from the clustering algorithm.

[0761] Output: Data points identified as outliers.

[0762] Specific behavior: From the clustering results, data points in the price list that deviate significantly from the normal range (e.g., 1200) are identified as outliers.

[0763] Step 5:

[0764] The server runs an emotion analysis engine to analyze the emotional state.

[0765] Input: Anomaly detection results, chat messages with users, facial expression data, and voice data.

[0766] Output: The user's emotional state.

[0767] What it does: The server launches an emotion analysis engine that analyzes the user's text messages and other emotional data to determine their current emotional state.

[0768] Step 6:

[0769] The server generates alerts for abnormal values ​​and notifies the user.

[0770] Input: Sentiment analysis results and outliers.

[0771] Output: Appropriate alert message depending on emotional state.

[0772] Specific behavior: Based on the user's emotional state, generate an alert message in a soft or direct tone and display it in the user's interface.

[0773] Preventing mis-sending of documents and emotional response alerts

[0774] Step 1:

[0775] The user composes an email and clicks the send button.

[0776] Input: The email body created by the user.

[0777] Output: The transport request.

[0778] Specific behavior: A user composes an email in an email client (e.g., Outlook, Gmail) and clicks the send button.

[0779] Step 2:

[0780] The device analyzes the email body.

[0781] Input: The email body created by the user.

[0782] Output: Text analysis result.

[0783] What happens: The device reads the email body as a string and begins analyzing it. It performs a regular expression search to find specific keywords (e.g., "attachment").

[0784] Step 3:

[0785] The device detects specific keywords.

[0786] Input: Body parsing result.

[0787] Output: Check for the existence of a specific keyword.

[0788] Specific operation: The device extracts specific keywords such as "attachment" and "document" from the analyzed email body.

[0789] Step 4:

[0790] The device checks for the presence of an attachment.

[0791] Input: Detected results for a specific keyword.

[0792] Output: The result of checking whether the attachment exists.

[0793] Specific operation: The device checks the header information of the email to see if it actually contains an attachment.

[0794] Step 5:

[0795] If there is no attachment, the device runs an emotion analysis engine to analyze the emotional state.

[0796] Input: Attachment check result, user operation data.

[0797] Output: The user's emotional state.

[0798] Specific operation: The device launches an emotion analysis engine and analyzes the user's emotional state from operation data (e.g., keyboard keystroke sounds, keystroke speed).

[0799] Step 6:

[0800] The terminal generates an appropriate alert and displays it to the user.

[0801] Input: Sentiment analysis results, attachment check results.

[0802] Output: An appropriate alert message.

[0803] What it does: Generates a mild or urgent alert message based on the user's emotional state and displays it as a pop-up on the user's screen.

[0804] Data entry error detection and emotional alerts

[0805] Step 1:

[0806] The user enters data into the terminal.

[0807] Input: Data entered by the user.

[0808] Output: Capture of input data.

[0809] Specific action: A user enters data into an Excel spreadsheet or web form.

[0810] Step 2:

[0811] The terminal monitors the input in real time.

[0812] Input: Data that the user is entering.

[0813] Output: Monitoring results (dynamic capture of input data).

[0814] What it does: The device captures data input in real time using JavaScript and keystroke monitoring scripts.

[0815] Step 3:

[0816] The device will detect spelling and formatting errors.

[0817] Input: The monitored input data.

[0818] Output: Detected spelling and formatting errors.

[0819] What it does: The device performs dictionary-based spell checking and regular expression pattern matching to detect spelling and formatting errors.

[0820] Step 4:

[0821] The device runs an emotion analysis engine to analyze the emotional state.

[0822] Input: Results of detection of spelling and formatting errors, user operation data.

[0823] Output: The user's emotional state.

[0824] Specific operation: The device launches an emotion analysis engine and analyzes the user's emotional state based on factors such as typing speed and frequency of input errors.

[0825] Step 5:

[0826] The terminal generates an alert to the error and displays it to the user.

[0827] Input: Sentiment analysis results, error detection results.

[0828] Output: An appropriate alert message.

[0829] Specific behavior: Depending on the emotional state and the error, an advisory or urgent alert message is generated and displayed as a pop-up on the user's screen.

[0830] (Application example 2)

[0831] 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."

[0832] Conventional inventory management and customer support systems have had problems with product pricing errors and data entry errors, which reduce work efficiency. Additionally, the lack of a way to respond appropriately to user emotions has led to stress and impatience, which can lead to increased work errors.

[0833] 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 receiving a price list, means for analyzing the received price list and detecting abnormal values, means for analyzing the user's emotional state in response to the detected abnormal values, and means for notifying an alert with an appropriate tone based on the user's emotional state. This makes it possible to detect pricing errors and notify an appropriate alert according to the user's emotional state.

[0834] A "price list" is a table that lists product price information.

[0835] An "outlier" is a data value that is outside the normal range and is detected by specific criteria or algorithms.

[0836] "Emotional state" refers to the user's psychological and emotional reactions and situations, and is analyzed using voice data and facial expression recognition.

[0837] An "alert" is a notification or warning message sent from the system to the user.

[0838] A "document" refers to text data including text data such as email.

[0839] "Specific keywords" are important words and phrases that are set for the system to search and detect.

[0840] An "attachment" is an additional data file that is added to an email or the like.

[0841] "Data entry" is the act of a user manually entering information into a system.

[0842] "Spelling error" refers to a situation in which a word is misspelled.

[0843] "Format error" refers to a deviation from the specified format when entering data.

[0844] "Real-time monitoring" refers to the instantaneous confirmation and analysis of data and behavior.

[0845] MODE FOR CARRYING OUT THE INVENTION

[0846] This invention is a system that prevents pricing errors and data entry errors when users manage inventory and handle customer service in a physical store, and also provides appropriate alerts based on the user's emotional state. The system receives price lists, detects abnormal values, and notifies the user of alerts based on the user's emotional state.

[0847] System program generation

[0848] The server first receives a price list sent by the user. This price list contains product price information. The received price list is converted into a NumPy array and analyzed using a clustering algorithm (e.g., KMeans clustering). If an outlier outside the normal price range is detected, the server activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's current emotional state using facial recognition, voice data, chat messages, etc.

[0849] Hardware and software used

[0850] Hardware:

[0851] Smartphones, smart glasses, head-mounted displays (HMDs)

[0852] software:

[0853] NumPy: Array manipulation and calculations on data

[0854] scikit-learn: Clustering algorithm implementation

[0855] emotion_recognition:Emotion recognition engine

[0856] The server generates appropriate alerts for outliers based on the user's emotional state. These alerts have different tones depending on the user's emotional state. For example, if the user is stressed, a softer alert such as "This price is significantly different from other prices. Please check it." On the other hand, if the user is calm, a more direct alert such as "1200 yen is an outlier. Please correct it."

[0857] Specific examples

[0858] For example, consider a scenario where a staff member uses smart glasses to manage inventory. If a price list contains the data [500, 520, 510, 490, 1200], the server receives this price list and detects 1200 as an outlier. At this time, the emotion engine analyzes the staff member's emotional state, and if the staff member is feeling stressed, an alert will be displayed saying, "This price is significantly different from the other prices. Please check."

[0859] You can also use the following example prompts to provide appropriate instructions to the generative AI model:

[0860] Prompt Sentence Examples

[0861] User input: Setting stock price. Price list: [500, 520, 510, 490, 1200]

[0862] Emotional state: stressed

[0863] Task: Detect any anomalous prices and generate a customized alert based on the emotion state.

[0864] By implementing this invention, the efficiency and accuracy of inventory management in physical stores can be significantly improved, and flexible responses based on user emotions become possible.

[0865] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0866] Step 1:

[0867] The server receives a price list from the user. It takes as input a list containing price information (e.g., [500, 520, 510, 490, 1200]) and stores it for use in the next processing step. The output is the received price list.

[0868] Step 2:

[0869] The server converts the received price list into a NumPy array. Here, the price information in list format is converted into a NumPy array format, making it easier to analyze the data. The input is the price list received in step 1, and the output is the converted NumPy array.

[0870] Step 3:

[0871] The server analyzes the price data using NumPy arrays and applies a clustering algorithm (e.g., KMeans clustering) to detect outliers. The input is the generated NumPy array, and the output is a list of outliers. It evaluates each price cluster and identifies prices outside the normal price range as outliers.

[0872] Step 4:

[0873] The server detects outliers based on the clustering results and then runs an emotion engine to analyze the user's emotional state. The input is a list of outliers, and the output is the user's emotional state (e.g., stressed, calm). Here, the server analyzes the user's emotions from facial recognition data, voice data, chat messages, etc.

[0874] Step 5:

[0875] The server generates an alert with an appropriate tone based on the user's emotional state. The input is the list of abnormal values ​​and the user's emotional state, and the output is the alert message. For example, if the emotional state is "stressed," the server generates a soft-toned alert saying, "This price is significantly different from other prices. Please check."

[0876] 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.

[0877] 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.

[0878] 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.

[0879] [Third embodiment]

[0880] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0881] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0882] 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).

[0883] 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.

[0884] 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.

[0885] 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).

[0886] 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. 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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."

[0892] DETAILED DESCRIPTION OF THE INVENTION The present invention includes embodiments of a system for preventing pricing errors, misdirected documents, and data entry errors, called DTSAI (Digital Task Safeguard AI).

[0893] Pricing Mistake Detection

[0894] server

[0895] The server processes price lists received from users. These price lists contain prices for goods and services. The server analyzes the price lists and detects outliers that fall outside the normal price range. To do this, it uses machine learning algorithms (e.g., KMeans clustering) to cluster the price lists and automatically identify outliers. When an outlier is detected, the server sends a warning to the user, prompting them to make corrections.

[0896] For example, when a user sets the price of a new product lineup, the price list is sent to the server. For example, if the price list is [500, 520, 510, 490, 1200], the server detects that 1200 is an abnormal value and sends an alert to the user saying, "The price setting of 1200 yen is significantly different from the other prices."

[0897] Preventing documents from being sent to the wrong person

[0898] Terminal

[0899] When a user attempts to send an email, the device analyzes the body of the email. If the body of the email contains specific keywords such as "attachment" or "document," the device checks whether there are any attachments. If there are no attachments, a warning message is displayed to the user to prevent the email from being sent by mistake. The user can check the warning and attach a file or modify the email content as necessary.

[0900] For example, if a user writes "Please see the attached file in this email" but does not actually attach a file, the device will display an alert saying "There is no attachment. Would you like to attach one?" The user will see the warning and attach the file.

[0901] Data entry error detection

[0902] Terminal

[0903] During data entry, the terminal monitors what the user types in real time. It analyzes the text entered and checks for spelling and formatting errors. This includes regular expression and dictionary-based spell checking. If an incorrect entry is detected, the terminal displays an alert to the user immediately and prompts them to correct it.

[0904] For example, if a user enters "example@domain.com" as their email address in an online form, the device will display an alert saying, "There is an error in the email address format. Please check again." The user will then see the warning and correct their email address to "example@domain.com."

[0905] As described above, the DTSAI system of the present invention automatically detects errors in everyday digital tasks such as pricing, document transmission, and data entry, and alerts users in real time, thereby improving work efficiency and accuracy.

[0906] The processing flow will be explained below.

[0907] Pricing Mistake Detection

[0908] server

[0909] Step 1:

[0910] The server receives a price list from the user, the price list containing prices for goods and services.

[0911] Step 2:

[0912] The server converts the received price list into a NumPy array, which is a data preprocessing step to make it suitable for the clustering algorithm.

[0913] Step 3:

[0914] The server applies the KMeans clustering algorithm to divide the price list into two clusters, which distinguishes between normal and abnormal prices.

[0915] Step 4:

[0916] The server calculates cluster centers and detects outliers that deviate significantly from the normal price cluster.

[0917] Step 5:

[0918] If the server detects an abnormal value, it will notify the user in real time as an alert, prompting the user to recheck the price.

[0919] Preventing documents from being sent to the wrong person

[0920] Terminal

[0921] Step 1:

[0922] When a user presses the send button on an email, the device reads the body and subject of the email.

[0923] Step 2:

[0924] The device searches for specific keywords (such as "attachment" or "document") in the email body and checks whether these keywords are included.

[0925] Step 3:

[0926] If a specific keyword is detected, the device checks whether the email has an attachment.

[0927] Step 4:

[0928] If there is no attachment, the device will display an alert to the user saying, "The email contains the word 'attached,' but there is no attachment."

[0929] Step 5:

[0930] The user checks the alert and attaches files or modifies the email content as needed.

[0931] Data entry error detection

[0932] Terminal

[0933] Step 1:

[0934] When a user enters data into an input form, the terminal monitors the input content in real time.

[0935] Step 2:

[0936] The terminal parses the text you enter to detect spelling and formatting errors, using regular expressions and dictionary-based spell checking.

[0937] Step 3:

[0938] If an incorrect input is detected, the device will immediately display an alert to the user saying, "There is an input error. Please check again."

[0939] Step 4:

[0940] The user acknowledges the alert and corrects the data entry.

[0941] The above are the specific processing steps in each module. The DTSAI system of the present invention allows users to quickly detect mistakes during digital tasks and respond in real time.

[0942] Example 1

[0943] 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."

[0944] In today's business environment, pricing errors, mis-sent documents, and data entry errors are commonplace, significantly impacting the efficiency and accuracy of business operations. Preventing these errors requires a comprehensive system that can handle multiple different tasks. However, traditional systems have difficulty resolving these issues consistently, resulting in the cost and effort required to address each issue individually.

[0945] 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.

[0946] In this invention, the server includes means for receiving a price list, means for analyzing the received price list using a machine learning algorithm to detect outliers, means for notifying a user of an alert when an outlier is detected, means for analyzing the content of a document to detect specific keywords, means for checking whether or not an attachment exists when the specific keyword is detected, means for displaying an alert to the user when the attachment does not exist, means for monitoring data entry in real time, means for detecting spelling mistakes and formatting errors, and means for displaying an alert to the user when an error is detected. This makes it possible to automatically detect errors in everyday digital tasks such as pricing, document transmission, and data entry, and to issue alerts in real time, thereby improving work efficiency and accuracy.

[0947] A "price list" is data that compiles price information for products and services in a list format.

[0948] A "machine learning algorithm" is a numerical method that automatically learns patterns based on large amounts of data and makes predictions and classifications.

[0949] "Clustering" is a data analysis technique that divides a dataset into several groups so that data within the same group are similar to each other.

[0950] An "outlier" is a value that deviates significantly from the average trend of the entire data set.

[0951] An "alert" is a warning message that notifies the user when the system detects an abnormality or a situation that requires attention.

[0952] A "specific keyword" is a word or phrase in a document that triggers a specific action (such as checking an attachment).

[0953] An "attachment" is an additional data file included in an email.

[0954] "Real-time monitoring" refers to checking data immediately at the moment the user enters it.

[0955] A "spelling error" is a mistake in which a letter of a word is typed incorrectly.

[0956] A "format error" is a data entry error that does not follow a prescribed format.

[0957] This invention is a system for preventing pricing errors, mis-sent documents, and data entry errors. Specifically, it is an integrated system with multiple functions for analyzing price lists, document content, and monitoring data entry in real time. This system is composed of a server and terminals.

[0958] Pricing Mistake Detection

[0959] server

[0960] The server processes price lists received from users. These price lists contain prices for goods and services. The server analyzes the price lists using machine learning algorithms, specifically KMeans clustering, to detect outliers that fall outside the normal price range. If an outlier is detected, the server sends an alert to the user, prompting them to adjust the pricing.

[0961] Specific examples

[0962] When a user sets the price of a new product lineup, the price list is sent to the server. For example, if the price list is [500 yen, 520 yen, 510 yen, 490 yen, 1200 yen], the server detects that 1200 yen is an abnormal value and sends an alert to the user saying, "The price setting of 1200 yen is significantly different from the other prices."

[0963] Prompt Sentence Examples

[0964] "The price list for the new product lineup contains an outlier at [500, 520, 510, 490, 1200]. Please write a program that detects the outlier and notifies the user."

[0965] Preventing documents from being sent to the wrong person

[0966] Terminal

[0967] When a user attempts to send an email, the device analyzes the body of the email. If the body contains specific keywords such as "attachment" or "document," the device checks whether there are any attachments. If there are no attachments, the device displays a warning message to the user to prevent the email from being sent by mistake.

[0968] Specific examples

[0969] If a user writes "Please see the attachment in this email" but does not actually attach a file, the device will display an alert saying "There is no attachment. Do you want to attach it?" The user will see the warning and attach the file.

[0970] Prompt Sentence Examples

[0971] "Please describe the program's processing to warn when a user sends an email that contains an "attachment" or "document" in the body of the email but the attached file does not exist."

[0972] Data entry error detection

[0973] Terminal

[0974] The terminal monitors what the user types in real time as data is entered. The terminal parses the text entered and checks for spelling and formatting errors using regular expressions and dictionary-based spell checking. If an incorrect entry is detected, the terminal will immediately alert the user and prompt them to correct it.

[0975] Specific examples

[0976] When a user enters an email address in an online form, if the user types "example@domain.com", the device will display an alert saying "There is an error in the email address format. Please check again." The user will then see the warning and correct the email address to "example@domain.com".

[0977] Prompt Sentence Examples

[0978] "When a user enters an email address into an online form, write a program that warns them if the format is invalid."

[0979] In this way, the present invention is a system that automatically detects errors in everyday digital tasks such as pricing, document transmission, and data entry, and provides real-time alerts to improve work efficiency and accuracy.

[0980] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0981] Pricing Mistake Detection

[0982] Step 1:

[0983] The server receives a price list from a user, which includes as input a price list, which contains pricing information for goods and services.

[0984] Step 2:

[0985] The server analyzes the received price list using a machine learning algorithm (e.g., KMeans clustering). First, it stores the price list in a database and then inputs the data into a clustering algorithm. The clustering results show the normal price range and outliers.

[0986] Step 3:

[0987] The server identifies outliers based on the clustering results. If an outlier is detected, it marks it as a flag and prepares to send an alert to the user. As an output, it generates a list of outliers and corresponding warning messages.

[0988] Step 4:

[0989] If an abnormal value is detected, the server will send an alert to the user. The alert will be sent by email or a pop-up notification. For example, a notification such as "The price setting of 1,200 yen is significantly different from the other prices" will be sent.

[0990] Preventing documents from being sent to the wrong person

[0991] Step 1:

[0992] When a user sends an email, the terminal analyzes the content of the email body, which includes the email body as input.

[0993] Step 2:

[0994] The device checks whether specific keywords such as "attachment" or "document" are included in the email body. It performs text analysis and lists the detected keywords. The output shows whether the detected keywords are present or not.

[0995] Step 3:

[0996] When a specific keyword is detected, the terminal checks whether or not there are any attachments. It checks the email attachment list and outputs whether or not there are any attachments.

[0997] Step 4:

[0998] If the attachment does not exist, the terminal will display an alert to the user. Specifically, a warning message such as "There is no attachment. Do you want to attach it?" will be displayed. The user will check this warning and attach the file if necessary.

[0999] Data entry error detection

[1000] Step 1:

[1001] The terminal monitors in real time what the user is entering during data entry. Input includes the data entered by the user.

[1002] Step 2:

[1003] The terminal parses the input text, checking for spelling and formatting errors, applying regular expression and dictionary-based spell checking algorithms, and provides the presence or absence of errors as output.

[1004] Step 3:

[1005] If an incorrect entry is detected, the device will immediately display an alert to the user. Specifically, a warning message such as "There is an error in the email address format. Please check again" will be displayed. The user will then check this warning and correct the entry.

[1006] (Application example 1)

[1007] 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."

[1008] Pricing errors and promotional information errors in physical stores directly lead to sales losses and reduced customer satisfaction. Preventing such errors and detecting and correcting them in real time is a key challenge for improving operational efficiency and customer satisfaction in physical stores. In addition, incorrect transmissions and data entry errors also have a negative impact on operational efficiency, so these issues must also be addressed at the same time.

[1009] 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.

[1010] In this invention, the server includes means for receiving a price list, means for analyzing the received price list and detecting abnormal values, means for notifying a user of an alert when an abnormal value is detected, means for acquiring price information via an electronic device for photographing the price list and analyzing the acquired price information in real time, means for automatically identifying abnormal values ​​in the price information, means for displaying an alert to the user via the electronic device when an abnormal value is detected, and means for prompting the user to reconfirm or correct the abnormal value. This enables errors in pricing and promotion information in physical stores to be detected and corrected in real time, improving business efficiency and customer satisfaction.

[1011] A "price list" is a document or data that lists price information for products or services.

[1012] An "outlier" is any price information that is outside the normal price range and is therefore not valid.

[1013] "User" refers to the person or administrator who uses the system to set prices or view information.

[1014] An "alert" is a warning message that the system sends to the user to notify them of an error or abnormality.

[1015] "Electronic devices" refers to devices used to capture price information and analyze the data, such as smart glasses or smartphones.

[1016] "Real-time" refers to data processing and information notification occurring immediately, without delay.

[1017] "Analysis" refers to analyzing the received data, interpreting its meaning, and detecting specific patterns or anomalies.

[1018] "Revalidation" is the process of re-evaluating the detected discrepancies to check whether they are correct.

[1019] "Correction" refers to changing detected abnormal values ​​or errors into accurate information.

[1020] "Price Information" means price data associated with individual products or services.

[1021] The DTSAI system embodying the present invention is a system that detects pricing errors and promotion information errors in real time in physical stores and notifies users of alerts. The system configuration and processing are described in detail below.

[1022] System Configuration

[1023] 1. Hardware Configuration

[1024] Server: Analyzes the data and detects outliers.

[1025] Terminal (smart glasses, smartphone, etc.): Captures price information and sends it to the server in real time.

[1026] Network: A communication method for linking terminals and servers.

[1027] 2. Software Configuration

[1028] Machine learning algorithm: KMeans clustering is used to analyze price information.

[1029] Data analysis module: a program for analyzing received price lists.

[1030] Alert module: A program that notifies the user when an abnormal value is detected.

[1031] Processing steps

[1032] 1. Obtaining and sending price information

[1033] The user uses smart glasses to take a photo of the product price and transmits the data to the server.

[1034] 2. Analysis of price information

[1035] The server analyzes the received price data in real time and detects outliers that deviate from the normal price range.

[1036] The algorithm used is KMeans clustering, which clusters price data and identifies outliers.

[1037] 3. Alert Notification

[1038] If an abnormal value is detected, the server sends the information to the terminal and displays an alert to the user in real time.

[1039] This allows users to quickly correct pricing errors.

[1040] Specific examples

[1041] For example, if a user sets the price of a new product and the price list includes 500 yen, 520 yen, 510 yen, 490 yen, and 1200 yen, the server will detect that 1200 yen is an abnormal value. The corresponding smart glasses will display an alert saying, "The 1200 yen price setting is significantly different from the other prices. Please check again."

[1042] Prompt Sentence Examples

[1043] Please set a price for your new product. If the prices of other products are around 1000 yen and your set price is 5000 yen, please send an alert as an abnormal value.

[1044] As described above, the DTSAI system of the present invention detects errors in pricing and promotional information in physical stores in real time and promptly notifies users of alerts, thereby improving business efficiency and customer satisfaction.

[1045] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1046] Step 1:

[1047] Obtaining and sending price information

[1048] A user captures the price of a product using a device (e.g., smart glasses). The device's built-in camera captures the product's price tag and extracts the price information using OCR (optical character recognition) technology. The device then sends the price information to a server.

[1049] Input: Price tag image

[1050] Output: Extracted price information

[1051] Step 2:

[1052] Receiving price information

[1053] The server receives the price information sent from the terminal and stores it in a database within the server.

[1054] Input: Price information sent from the device

[1055] Output: Price information stored in a database

[1056] Step 3:

[1057] Price information analysis

[1058] The server uses a data analysis module to analyze the received price information in real time. This analysis uses KMeans clustering to classify the price information and detect outliers. The algorithm clusters the price information and identifies the prices detected as outliers.

[1059] Input: Price information stored in a database

[1060] Output: Price information identified as anomalies

[1061] Step 4:

[1062] Alert Generation

[1063] If the server detects an anomaly, it generates an alert based on the price information. The alert message includes details of the anomaly and a recommendation to recheck.

[1064] Input: Price information identified as an outlier

[1065] Output: The generated alert message

[1066] Step 5:

[1067] Alert Notifications

[1068] The server sends the generated alert message to the terminal, which then displays the received alert message on the user's display. The user can then confirm the message and make any necessary adjustments to the pricing.

[1069] Input: The generated alert message

[1070] Output: The alert message displayed on the user's display.

[1071] Specifically, when a user sets a price for a new product, the smart glasses capture the "5,000 yen" price tag and send the price information to the server. The server detects through clustering that "5,000 yen" is an anomaly and generates an alert message saying, "The price of the 5,000 yen product is significantly different from other products. Please check again." This message is displayed on the smart glasses' display. The user can then confirm the alert and make any necessary adjustments to the price setting.

[1072] 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.

[1073] The following describes in detail the mode for carrying out the present invention: The present invention is a system that combines a Digital Task Safeguard AI (DTSAI) system, which prevents pricing errors, incorrect attachments when sending documents, and spelling and formatting errors when entering data, with an emotion engine that recognizes user emotions.

[1074] Mispricing detection and emotional alerts

[1075] server

[1076] The server receives a price list sent by the user. This price list contains the prices of goods and services. The received price list is converted into a NumPy array and analyzed using a clustering algorithm (e.g., KMeans clustering). When an outlier outside the normal price range is detected, the server activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's current emotional state from Japanese chat messages, facial expression recognition, and voice data. Depending on the emotional state, the server notifies the user with an appropriate alert regarding the outlier.

[1077] For example, if a user sets a new product price and sends the price list [500, 520, 510, 490, 1200] to the server, the server will detect 1200 as an abnormal value. If the user is stressed at the time, the server will send a soft-toned alert saying, "This price is significantly different from the other prices. Please check it." On the other hand, if the user is calm, the server will send a direct alert saying, "1200 yen is an abnormal value. Please correct it."

[1078] Preventing mis-sending of documents and emotional response alerts

[1079] Terminal

[1080] When a user attempts to send an email, the device analyzes the content of the email body. If specific keywords (such as "attachment" or "document") are detected, the device checks whether an attachment exists. If no attachment exists, the emotion engine analyzes the user's emotional state. An appropriate alert message is displayed depending on the user's emotional state.

[1081] For example, if a user writes "Please see the attachment in this email" but forgets to include the attachment, the device will detect this. If the user is annoyed, the device will display a gentle alert such as "Attachment missing. Did you forget to attach it?". Conversely, if the user is focused on a task, the device will display a more urgent alert such as "Attachment not found. Please check it immediately."

[1082] Data entry error detection and emotional alerts

[1083] Terminal

[1084] During data entry, the device monitors what the user types in real time. Regular expression and dictionary-based spell checking are used to detect spelling and formatting errors. If an error is detected, an emotion engine analyzes the user's emotional state and displays an alert to the user accordingly.

[1085] For example, if a user types "example@domain.com," the device will detect this and display an alert saying, "The email address format is incorrect. Please check again." If the emotion engine recognizes that the user is tired, it will display an alert with advice such as, "The correct format is example@domain.com. Please correct it." On the other hand, if the user is impatient, it will display a short, concise alert saying, "Please enter your email address in the correct format."

[1086] The combination of the DTSAI system and emotion engine of the present invention allows users to effectively detect mistakes made during digital tasks and receive adaptive responses in real time, greatly improving work efficiency and accuracy.

[1087] The processing flow will be explained below.

[1088] Mispricing detection and emotional alerts

[1089] server

[1090] Step 1:

[1091] The server receives the price list from the user, which is then converted to an appropriate data format (e.g., a NumPy array) when sent to the server.

[1092] Step 2:

[1093] The server applies the KMeans clustering algorithm to the price list and classifies the prices into two clusters: one for normal prices and one for abnormal prices.

[1094] Step 3:

[1095] The server calculates cluster centers of typical prices and identifies outliers based on them. Prices that deviate significantly from the cluster center are considered outliers.

[1096] Step 4:

[1097] If the server detects an anomaly, the emotion engine is activated to analyze the user's current emotional state, which is obtained from text messages, facial recognition, voice data, etc.

[1098] Step 5:

[1099] Based on the analysis results of the emotion engine, the server notifies the user with an appropriate alert. For example, if the user is feeling stressed, the server sends a soft-spoken alert such as "This price is significantly different from other prices. Please check."

[1100] Preventing mis-sending of documents and emotional response alerts

[1101] Terminal

[1102] Step 1:

[1103] When the user clicks the send email button, the terminal reads the email body and subject line.

[1104] Step 2:

[1105] The device searches for specific keywords (such as "attachment" or "document") in the email body. If these keywords are included, it checks whether or not there are any attachments.

[1106] Step 3:

[1107] When a specific keyword is detected, the device checks whether an attachment exists. If an attachment does not exist, the emotion engine is activated to analyze the user's emotional state.

[1108] Step 4:

[1109] The emotion engine analyzes the user's emotional state, which is determined based on real-time data (e.g., facial expressions, voice, etc.).

[1110] Step 5:

[1111] Based on the analysis results of the emotion engine, the device will display appropriate alerts to the user. If the user is annoyed, it will display a gentle alert such as "Attachment missing. Did you forget to attach it?", but if the user is distracted, it will display a more urgent alert such as "Attachment not found. Please check immediately."

[1112] Data entry error detection and emotional alerts

[1113] Terminal

[1114] Step 1:

[1115] As the user enters key data into the input form, the terminal monitors the data in real time.

[1116] Step 2:

[1117] The terminal parses the text entered and uses regular expressions and dictionary-based spell checking to detect spelling and formatting errors.

[1118] Step 3:

[1119] If the device detects an input error, the emotion engine will be activated and analyze the user's emotional state, which can be obtained from text, facial expression analysis, voice analysis, etc.

[1120] Step 4:

[1121] Based on the analysis results of the emotion engine, the device displays appropriate alerts to the user. For example, if the user is tired, it displays an alert with advice such as "The correct format is example@domain.com. Please correct it." If the user is impatient, it displays a simple alert such as "Please enter your email address in the correct format."

[1122] These are the specific processing steps in each module. By combining emotion engines, it is possible to provide appropriate support according to the user's condition, improving the efficiency and accuracy of work.

[1123] Example 2

[1124] 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."

[1125] Conventional digital task management systems have difficulty detecting and notifying users of pricing errors, incorrect attachments when sending documents, and spelling or formatting errors when entering data. Furthermore, they are unable to provide alert messages that take into account the user's emotional state, increasing the risk of user stress and incorrect operation.

[1126] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving a price list; means for converting the received price list into a numerical array, analyzing it using a clustering algorithm, and detecting outliers; means for analyzing the user's emotional state using an emotion analysis engine when an outlier is detected and notifying the user of an appropriate alert for the outlier based on the emotional state; means for analyzing the content of the document and detecting specific keywords; means for checking whether or not an attachment is present when a specific keyword is detected; means for analyzing the user's emotional state using the emotion analysis engine when an attachment is not present and displaying an alert based on the emotional state; means for monitoring data input in real time; means for detecting spelling mistakes and formatting errors; and means for analyzing the user's emotional state using the emotion analysis engine when an error is detected and displaying an appropriate alert for the error based on the emotional state. This enables effective detection of errors during digital tasks and adaptive responses in real time.

[1127] A "price list" is data that lists the prices of products and services.

[1128] A "numeric array" is data with an array structure in which numerical data is arranged in a fixed order.

[1129] A "clustering algorithm" is a computational procedure for classifying data into groups (clusters) based on similarity.

[1130] An "outlier" is a data point that deviates from the normal range and is a value that is significantly different compared to other data.

[1131] An "emotion analysis engine" is a software component that analyzes data such as text, voice, and facial expressions to recognize a user's emotional state.

[1132] An "alert" is a warning message that notifies the user of important information or matters requiring attention.

[1133] "Specific keywords" are predefined important words or phrases that are searched for within a document.

[1134] An "attachment" is an additional file attached to an email or document.

[1135] "Data entry" refers to the operation by which a user inputs information into a system or application.

[1136] A "spelling error" is an error in which a word is spelled incorrectly.

[1137] A "format error" is an error in which the data does not conform to the expected format or structure.

[1138] "Real-time monitoring" refers to the operation of immediately monitoring the contents of data the moment it is entered or updated.

[1139] The following describes in detail the mode for carrying out the present invention. This invention is a system that prevents mistakes in multiple digital tasks and responds adaptively to the user's emotional state. To achieve this, the server, terminal, and user work together.

[1140] Mispricing detection and emotional alerts

[1141] server

[1142] 1. The user sets up a price list and sends it to the server. The sent price list contains the prices of products and services.

[1143] 2. The received price list is converted by the server into a NumPy array. NumPy is a Python library that allows for highly efficient numerical calculations.

[1144] 3. The server analyzes the price list using the clustering algorithm KMeans clustering, which uses the scikit-learn library.

[1145] 4. When an outlier outside the normal price range is detected, the server activates the sentiment analysis engine, which obtains the user's emotional state from data such as text, facial expressions, and voice.

[1146] 5. Depending on the emotional state, generate appropriate alert messages for abnormal values ​​and notify the user.

[1147] Example: If a user sets a new product price and sends the price list [500, 520, 510, 490, 1200] to the server, the server will detect 1200 as an abnormal value. If the user is stressed, the server will send an alert saying "This price is significantly different from other prices. Please check." If the user is calm, the server will send an alert saying "1200 yen is an abnormal value. Please correct it."

[1148] Preventing mis-sending of documents and emotional response alerts

[1149] Terminal

[1150] 1. The user composes an email and clicks the send button.

[1151] 2. When the send button is pressed, the device analyzes the email body and detects the specified specific keywords (e.g., "attachment," "document").

[1152] 3. If the keyword is detected, the device checks whether there is an attachment.

[1153] 4. If there is no attachment, the device runs an emotion analysis engine to analyze the user's emotional state.

[1154] 5. Generate an appropriate alert message according to the emotional state and display it to the user.

[1155] Example: A user tries to send an email saying "Please see the attachment in this email" but forgets to include the attachment. The device will detect this and, if the user is annoyed, will display a gentle alert saying "Attachment missing. Did you forget to attach it?". If the user is distracted, it will display "Attachment not found. Please check it now."

[1156] Data entry error detection and emotional alerts

[1157] Terminal

[1158] 1. A user enters data into a web form, Excel spreadsheet, etc.

[1159] 2. The device monitors what you type in real time and uses dictionary-based spell checking and regular expressions to detect spelling and formatting errors.

[1160] 3. If an error is detected, the device activates an emotion analysis engine to analyze the user's emotional state.

[1161] 4. Generate an appropriate alert message according to the emotional state and display it to the user.

[1162] Example: If a user types "example@domain.com", the device will detect this and display an alert saying "The email address format is incorrect. Please check again." If the sentiment analysis engine recognizes that the user is fatigued, it will display an alert with advice saying "The correct format is example@domain.com. Please correct it." On the other hand, if the user is impatient, it will display a short and concise alert saying "Please enter your email address in the correct format."

[1163] Prompt Sentence Examples

[1164] 1. "Please give me the following price list: [500, 520, 510, 490, 1200]. Detect outliers from this list and generate alert messages based on the emotional state."

[1165] 2. "Analyze the body of the email the user is about to send, and if there is no attachment, generate an appropriate alert message using a sentiment analysis engine."

[1166] 3. "Monitor data entry in real time and detect spelling and formatting errors. Generate appropriate alert messages based on emotional state."

[1167] Through this system, users can quickly detect mistakes made during digital tasks and receive appropriate instructions, which is expected to significantly improve work efficiency and accuracy.

[1168] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1169] Mispricing detection and emotional alerts

[1170] Step 1:

[1171] The user submits a price list to the server.

[1172] Input: The user enters a price list (e.g., [500, 520, 510, 490, 1200]) into the interface and presses the submit button.

[1173] Output: The price list is sent to the server.

[1174] Specific action: A user uses a web interface to enter a price list into a form and presses the submit button.

[1175] Step 2:

[1176] The server receives the price list and converts it into a NumPy array.

[1177] Input: Received price list data.

[1178] Output: Price list as a NumPy array.

[1179] What it does: The server receives the price list and converts it to a numeric array using Python's NumPy library. Example: [500, 520, 510, 490, 1200] -> np.array([500, 520, 510, 490, 1200])

[1180] Step 3:

[1181] The server analyzes the price list using the KMeans clustering algorithm.

[1182] Input: Price list converted to a NumPy array.

[1183] Output: Clustering results and outlier locations.

[1184] Specific operation: The server uses the scikit-learn library to perform KMeans clustering. It sets the number of clusters and initial conditions, clusters the price data, and detects outliers.

[1185] Step 4:

[1186] The server detects outliers.

[1187] Input: Analysis results from the clustering algorithm.

[1188] Output: Data points identified as outliers.

[1189] Specific behavior: From the clustering results, data points in the price list that deviate significantly from the normal range (e.g., 1200) are identified as outliers.

[1190] Step 5:

[1191] The server runs an emotion analysis engine to analyze the emotional state.

[1192] Input: Anomaly detection results, chat messages with users, facial expression data, and voice data.

[1193] Output: The user's emotional state.

[1194] What it does: The server launches an emotion analysis engine that analyzes the user's text messages and other emotional data to determine their current emotional state.

[1195] Step 6:

[1196] The server generates alerts for abnormal values ​​and notifies the user.

[1197] Input: Sentiment analysis results and outliers.

[1198] Output: Appropriate alert message depending on emotional state.

[1199] Specific behavior: Based on the user's emotional state, generate an alert message in a soft or direct tone and display it in the user's interface.

[1200] Preventing mis-sending of documents and emotional response alerts

[1201] Step 1:

[1202] The user composes an email and clicks the send button.

[1203] Input: The email body created by the user.

[1204] Output: The transport request.

[1205] Specific behavior: A user composes an email in an email client (e.g., Outlook, Gmail) and clicks the send button.

[1206] Step 2:

[1207] The device analyzes the email body.

[1208] Input: The email body created by the user.

[1209] Output: Text analysis result.

[1210] What happens: The device reads the email body as a string and begins analyzing it. It performs a regular expression search to find specific keywords (e.g., "attachment").

[1211] Step 3:

[1212] The device detects specific keywords.

[1213] Input: Body parsing result.

[1214] Output: Check for the existence of a specific keyword.

[1215] Specific operation: The device extracts specific keywords such as "attachment" and "document" from the analyzed email body.

[1216] Step 4:

[1217] The device checks for the presence of an attachment.

[1218] Input: Detected results for a specific keyword.

[1219] Output: The result of checking whether the attachment exists.

[1220] Specific operation: The device checks the header information of the email to see if it actually contains an attachment.

[1221] Step 5:

[1222] If there is no attachment, the device runs an emotion analysis engine to analyze the emotional state.

[1223] Input: Attachment check result, user operation data.

[1224] Output: The user's emotional state.

[1225] Specific operation: The device launches an emotion analysis engine and analyzes the user's emotional state from operation data (e.g., keyboard keystroke sounds, keystroke speed).

[1226] Step 6:

[1227] The terminal generates an appropriate alert and displays it to the user.

[1228] Input: Sentiment analysis results, attachment check results.

[1229] Output: An appropriate alert message.

[1230] What it does: Generates a mild or urgent alert message based on the user's emotional state and displays it as a pop-up on the user's screen.

[1231] Data entry error detection and emotional alerts

[1232] Step 1:

[1233] The user enters data into the terminal.

[1234] Input: Data entered by the user.

[1235] Output: Capture of input data.

[1236] Specific action: A user enters data into an Excel spreadsheet or web form.

[1237] Step 2:

[1238] The terminal monitors the input in real time.

[1239] Input: Data that the user is entering.

[1240] Output: Monitoring results (dynamic capture of input data).

[1241] What it does: The device captures data input in real time using JavaScript and keystroke monitoring scripts.

[1242] Step 3:

[1243] The device will detect spelling and formatting errors.

[1244] Input: The monitored input data.

[1245] Output: Detected spelling and formatting errors.

[1246] What it does: The device performs dictionary-based spell checking and regular expression pattern matching to detect spelling and formatting errors.

[1247] Step 4:

[1248] The device runs an emotion analysis engine to analyze the emotional state.

[1249] Input: Results of detection of spelling and formatting errors, user operation data.

[1250] Output: The user's emotional state.

[1251] Specific operation: The device launches an emotion analysis engine and analyzes the user's emotional state based on factors such as typing speed and frequency of input errors.

[1252] Step 5:

[1253] The terminal generates an alert to the error and displays it to the user.

[1254] Input: Sentiment analysis results, error detection results.

[1255] Output: An appropriate alert message.

[1256] Specific behavior: Depending on the emotional state and the error, an advisory or urgent alert message is generated and displayed as a pop-up on the user's screen.

[1257] (Application example 2)

[1258] 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."

[1259] Conventional inventory management and customer support systems have had problems with product pricing errors and data entry errors, which reduce work efficiency. Additionally, the lack of a way to respond appropriately to user emotions has led to stress and impatience, which can lead to increased work errors.

[1260] 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 receiving a price list, means for analyzing the received price list and detecting abnormal values, means for analyzing the user's emotional state in response to the detected abnormal values, and means for notifying an alert with an appropriate tone based on the user's emotional state. This makes it possible to detect pricing errors and notify an appropriate alert according to the user's emotional state.

[1261] A "price list" is a table that lists product price information.

[1262] An "outlier" is a data value that is outside the normal range and is detected by specific criteria or algorithms.

[1263] "Emotional state" refers to the user's psychological and emotional reactions and situations, and is analyzed using voice data and facial expression recognition.

[1264] An "alert" is a notification or warning message sent from the system to the user.

[1265] A "document" refers to text data including text data such as email.

[1266] "Specific keywords" are important words and phrases that are set for the system to search and detect.

[1267] An "attachment" is an additional data file that is added to an email or the like.

[1268] "Data entry" is the act of a user manually entering information into a system.

[1269] "Spelling error" refers to a situation in which a word is misspelled.

[1270] "Format error" refers to a deviation from the specified format when entering data.

[1271] "Real-time monitoring" refers to the instantaneous confirmation and analysis of data and behavior.

[1272] MODE FOR CARRYING OUT THE INVENTION

[1273] This invention is a system that prevents pricing errors and data entry errors when users manage inventory and handle customer service in a physical store, and also provides appropriate alerts based on the user's emotional state. The system receives price lists, detects abnormal values, and notifies the user of alerts based on the user's emotional state.

[1274] System program generation

[1275] The server first receives a price list sent by the user. This price list contains product price information. The received price list is converted into a NumPy array and analyzed using a clustering algorithm (e.g., KMeans clustering). If an outlier outside the normal price range is detected, the server activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's current emotional state using facial recognition, voice data, chat messages, etc.

[1276] Hardware and software used

[1277] Hardware:

[1278] Smartphones, smart glasses, head-mounted displays (HMDs)

[1279] software:

[1280] NumPy: Array manipulation and calculations on data

[1281] scikit-learn: Clustering algorithm implementation

[1282] emotion_recognition:Emotion recognition engine

[1283] The server generates appropriate alerts for outliers based on the user's emotional state. These alerts have different tones depending on the user's emotional state. For example, if the user is stressed, a softer alert such as "This price is significantly different from other prices. Please check it." On the other hand, if the user is calm, a more direct alert such as "1200 yen is an outlier. Please correct it."

[1284] Specific examples

[1285] For example, consider a scenario where a staff member uses smart glasses to manage inventory. If a price list contains the data [500, 520, 510, 490, 1200], the server receives this price list and detects 1200 as an outlier. At this time, the emotion engine analyzes the staff member's emotional state, and if the staff member is feeling stressed, an alert will be displayed saying, "This price is significantly different from the other prices. Please check."

[1286] You can also use the following example prompts to provide appropriate instructions to the generative AI model:

[1287] Prompt Sentence Examples

[1288] User input: Setting stock price. Price list: [500, 520, 510, 490, 1200]

[1289] Emotional state: stressed

[1290] Task: Detect any anomalous prices and generate a customized alert based on the emotion state.

[1291] By implementing this invention, the efficiency and accuracy of inventory management in physical stores can be significantly improved, and flexible responses based on user emotions become possible.

[1292] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1293] Step 1:

[1294] The server receives a price list from the user. It takes as input a list containing price information (e.g., [500, 520, 510, 490, 1200]) and stores it for use in the next processing step. The output is the received price list.

[1295] Step 2:

[1296] The server converts the received price list into a NumPy array. Here, the price information in list format is converted into a NumPy array format, making it easier to analyze the data. The input is the price list received in step 1, and the output is the converted NumPy array.

[1297] Step 3:

[1298] The server analyzes the price data using NumPy arrays and applies a clustering algorithm (e.g., KMeans clustering) to detect outliers. The input is the generated NumPy array, and the output is a list of outliers. It evaluates each price cluster and identifies prices outside the normal price range as outliers.

[1299] Step 4:

[1300] The server detects outliers based on the clustering results and then runs an emotion engine to analyze the user's emotional state. The input is a list of outliers, and the output is the user's emotional state (e.g., stressed, calm). Here, the server analyzes the user's emotions from facial recognition data, voice data, chat messages, etc.

[1301] Step 5:

[1302] The server generates an alert with an appropriate tone based on the user's emotional state. The input is the list of abnormal values ​​and the user's emotional state, and the output is the alert message. For example, if the emotional state is "stressed," the server generates a soft-toned alert saying, "This price is significantly different from other prices. Please check."

[1303] 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.

[1304] 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.

[1305] 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.

[1306] [Fourth embodiment]

[1307] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1308] 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.

[1309] 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).

[1310] 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.

[1311] 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.

[1312] 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).

[1313] 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. 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.

[1314] 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.

[1315] 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.

[1316] 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.

[1317] 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.

[1318] 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.

[1319] 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."

[1320] DETAILED DESCRIPTION OF THE INVENTION The present invention includes embodiments of a system for preventing pricing errors, misdirected documents, and data entry errors, called DTSAI (Digital Task Safeguard AI).

[1321] Pricing Mistake Detection

[1322] server

[1323] The server processes price lists received from users. These price lists contain prices for goods and services. The server analyzes the price lists and detects outliers that fall outside the normal price range. To do this, it uses machine learning algorithms (e.g., KMeans clustering) to cluster the price lists and automatically identify outliers. When an outlier is detected, the server sends a warning to the user, prompting them to make corrections.

[1324] For example, when a user sets the price of a new product lineup, the price list is sent to the server. For example, if the price list is [500, 520, 510, 490, 1200], the server detects that 1200 is an abnormal value and sends an alert to the user saying, "The price setting of 1200 yen is significantly different from the other prices."

[1325] Preventing documents from being sent to the wrong person

[1326] Terminal

[1327] When a user attempts to send an email, the device analyzes the body of the email. If the body of the email contains specific keywords such as "attachment" or "document," the device checks whether there are any attachments. If there are no attachments, a warning message is displayed to the user to prevent the email from being sent by mistake. The user can check the warning and attach a file or modify the email content as necessary.

[1328] For example, if a user writes "Please see the attached file in this email" but does not actually attach a file, the device will display an alert saying "There is no attachment. Would you like to attach one?" The user will see the warning and attach the file.

[1329] Data entry error detection

[1330] Terminal

[1331] During data entry, the terminal monitors what the user types in real time. It analyzes the text entered and checks for spelling and formatting errors. This includes regular expression and dictionary-based spell checking. If an incorrect entry is detected, the terminal displays an alert to the user immediately and prompts them to correct it.

[1332] For example, if a user enters "example@domain.com" as their email address in an online form, the device will display an alert saying, "There is an error in the email address format. Please check again." The user will then see the warning and correct their email address to "example@domain.com."

[1333] As described above, the DTSAI system of the present invention automatically detects errors in everyday digital tasks such as pricing, document transmission, and data entry, and alerts users in real time, thereby improving work efficiency and accuracy.

[1334] The processing flow will be explained below.

[1335] Pricing Mistake Detection

[1336] server

[1337] Step 1:

[1338] The server receives a price list from the user, the price list containing prices for goods and services.

[1339] Step 2:

[1340] The server converts the received price list into a NumPy array, which is a data preprocessing step to make it suitable for the clustering algorithm.

[1341] Step 3:

[1342] The server applies the KMeans clustering algorithm to divide the price list into two clusters, which distinguishes between normal and abnormal prices.

[1343] Step 4:

[1344] The server calculates cluster centers and detects outliers that deviate significantly from the normal price cluster.

[1345] Step 5:

[1346] If the server detects an abnormal value, it will notify the user in real time as an alert, prompting the user to recheck the price.

[1347] Preventing documents from being sent to the wrong person

[1348] Terminal

[1349] Step 1:

[1350] When a user presses the send button on an email, the device reads the body and subject of the email.

[1351] Step 2:

[1352] The device searches for specific keywords (such as "attachment" or "document") in the email body and checks whether these keywords are included.

[1353] Step 3:

[1354] If a specific keyword is detected, the device checks whether the email has an attachment.

[1355] Step 4:

[1356] If there is no attachment, the device will display an alert to the user saying, "The email contains the word 'attached,' but there is no attachment."

[1357] Step 5:

[1358] The user checks the alert and attaches files or modifies the email content as needed.

[1359] Data entry error detection

[1360] Terminal

[1361] Step 1:

[1362] When a user enters data into an input form, the terminal monitors the input content in real time.

[1363] Step 2:

[1364] The terminal parses the text you enter to detect spelling and formatting errors, using regular expressions and dictionary-based spell checking.

[1365] Step 3:

[1366] If an incorrect input is detected, the device will immediately display an alert to the user saying, "There is an input error. Please check again."

[1367] Step 4:

[1368] The user acknowledges the alert and corrects the data entry.

[1369] The above are the specific processing steps in each module. The DTSAI system of the present invention allows users to quickly detect mistakes during digital tasks and respond in real time.

[1370] Example 1

[1371] 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."

[1372] In today's business environment, pricing errors, mis-sent documents, and data entry errors are commonplace, significantly impacting the efficiency and accuracy of business operations. Preventing these errors requires a comprehensive system that can handle multiple different tasks. However, traditional systems have difficulty resolving these issues consistently, resulting in the cost and effort required to address each issue individually.

[1373] 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.

[1374] In this invention, the server includes means for receiving a price list, means for analyzing the received price list using a machine learning algorithm to detect outliers, means for notifying a user of an alert when an outlier is detected, means for analyzing the content of a document to detect specific keywords, means for checking whether or not an attachment exists when the specific keyword is detected, means for displaying an alert to the user when the attachment does not exist, means for monitoring data entry in real time, means for detecting spelling mistakes and formatting errors, and means for displaying an alert to the user when an error is detected. This makes it possible to automatically detect errors in everyday digital tasks such as pricing, document transmission, and data entry, and to issue alerts in real time, thereby improving work efficiency and accuracy.

[1375] A "price list" is data that compiles price information for products and services in a list format.

[1376] A "machine learning algorithm" is a numerical method that automatically learns patterns based on large amounts of data and makes predictions and classifications.

[1377] "Clustering" is a data analysis technique that divides a dataset into several groups so that data within the same group are similar to each other.

[1378] An "outlier" is a value that deviates significantly from the average trend of the entire data set.

[1379] An "alert" is a warning message that notifies the user when the system detects an abnormality or a situation that requires attention.

[1380] A "specific keyword" is a word or phrase in a document that triggers a specific action (such as checking an attachment).

[1381] An "attachment" is an additional data file included in an email.

[1382] "Real-time monitoring" refers to checking data immediately at the moment the user enters it.

[1383] A "spelling error" is a mistake in which a letter of a word is typed incorrectly.

[1384] A "format error" is a data entry error that does not follow a prescribed format.

[1385] This invention is a system for preventing pricing errors, mis-sent documents, and data entry errors. Specifically, it is an integrated system with multiple functions for analyzing price lists, document content, and monitoring data entry in real time. This system is composed of a server and terminals.

[1386] Pricing Mistake Detection

[1387] server

[1388] The server processes price lists received from users. These price lists contain prices for goods and services. The server analyzes the price lists using machine learning algorithms, specifically KMeans clustering, to detect outliers that fall outside the normal price range. If an outlier is detected, the server sends an alert to the user, prompting them to adjust the pricing.

[1389] Specific examples

[1390] When a user sets the price of a new product lineup, the price list is sent to the server. For example, if the price list is [500 yen, 520 yen, 510 yen, 490 yen, 1200 yen], the server detects that 1200 yen is an abnormal value and sends an alert to the user saying, "The price setting of 1200 yen is significantly different from the other prices."

[1391] Prompt Sentence Examples

[1392] "The price list for the new product lineup contains an outlier at [500, 520, 510, 490, 1200]. Please write a program that detects the outlier and notifies the user."

[1393] Preventing documents from being sent to the wrong person

[1394] Terminal

[1395] When a user attempts to send an email, the device analyzes the body of the email. If the body contains specific keywords such as "attachment" or "document," the device checks whether there are any attachments. If there are no attachments, the device displays a warning message to the user to prevent the email from being sent by mistake.

[1396] Specific examples

[1397] If a user writes "Please see the attachment in this email" but does not actually attach a file, the device will display an alert saying "There is no attachment. Do you want to attach it?" The user will see the warning and attach the file.

[1398] Prompt Sentence Examples

[1399] "Please describe the program's processing to warn when a user sends an email that contains an "attachment" or "document" in the body of the email but the attached file does not exist."

[1400] Data entry error detection

[1401] Terminal

[1402] The terminal monitors what the user types in real time as data is entered. The terminal parses the text entered and checks for spelling and formatting errors using regular expressions and dictionary-based spell checking. If an incorrect entry is detected, the terminal will immediately alert the user and prompt them to correct it.

[1403] Specific examples

[1404] When a user enters an email address in an online form, if the user types "example@domain.com", the device will display an alert saying "There is an error in the email address format. Please check again." The user will then see the warning and correct the email address to "example@domain.com".

[1405] Prompt Sentence Examples

[1406] "When a user enters an email address into an online form, write a program that warns them if the format is invalid."

[1407] In this way, the present invention is a system that automatically detects errors in everyday digital tasks such as pricing, document transmission, and data entry, and provides real-time alerts to improve work efficiency and accuracy.

[1408] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1409] Pricing Mistake Detection

[1410] Step 1:

[1411] The server receives a price list from a user, which includes as input a price list, which contains pricing information for goods and services.

[1412] Step 2:

[1413] The server analyzes the received price list using a machine learning algorithm (e.g., KMeans clustering). First, it stores the price list in a database and then inputs the data into a clustering algorithm. The clustering results show the normal price range and outliers.

[1414] Step 3:

[1415] The server identifies outliers based on the clustering results. If an outlier is detected, it marks it as a flag and prepares to send an alert to the user. As an output, it generates a list of outliers and corresponding warning messages.

[1416] Step 4:

[1417] If an abnormal value is detected, the server will send an alert to the user. The alert will be sent by email or a pop-up notification. For example, a notification such as "The price setting of 1,200 yen is significantly different from the other prices" will be sent.

[1418] Preventing documents from being sent to the wrong person

[1419] Step 1:

[1420] When a user sends an email, the terminal analyzes the content of the email body, which includes the email body as input.

[1421] Step 2:

[1422] The device checks whether specific keywords such as "attachment" or "document" are included in the email body. It performs text analysis and lists the detected keywords. The output shows whether the detected keywords are present or not.

[1423] Step 3:

[1424] When a specific keyword is detected, the terminal checks whether or not there are any attachments. It checks the email attachment list and outputs whether or not there are any attachments.

[1425] Step 4:

[1426] If the attachment does not exist, the terminal will display an alert to the user. Specifically, a warning message such as "There is no attachment. Do you want to attach it?" will be displayed. The user will check this warning and attach the file if necessary.

[1427] Data entry error detection

[1428] Step 1:

[1429] The terminal monitors in real time what the user is entering during data entry. Input includes the data entered by the user.

[1430] Step 2:

[1431] The terminal parses the input text, checking for spelling and formatting errors, applying regular expression and dictionary-based spell checking algorithms, and provides the presence or absence of errors as output.

[1432] Step 3:

[1433] If an incorrect entry is detected, the device will immediately display an alert to the user. Specifically, a warning message such as "There is an error in the email address format. Please check again" will be displayed. The user will then check this warning and correct the entry.

[1434] (Application example 1)

[1435] 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."

[1436] Pricing errors and promotional information errors in physical stores directly lead to sales losses and reduced customer satisfaction. Preventing such errors and detecting and correcting them in real time is a key challenge for improving operational efficiency and customer satisfaction in physical stores. In addition, incorrect transmissions and data entry errors also have a negative impact on operational efficiency, so these issues must also be addressed at the same time.

[1437] 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.

[1438] In this invention, the server includes means for receiving a price list, means for analyzing the received price list and detecting abnormal values, means for notifying a user of an alert when an abnormal value is detected, means for acquiring price information via an electronic device for photographing the price list and analyzing the acquired price information in real time, means for automatically identifying abnormal values ​​in the price information, means for displaying an alert to the user via the electronic device when an abnormal value is detected, and means for prompting the user to reconfirm or correct the abnormal value. This enables errors in pricing and promotion information in physical stores to be detected and corrected in real time, improving business efficiency and customer satisfaction.

[1439] A "price list" is a document or data that lists price information for products or services.

[1440] An "outlier" is any price information that is outside the normal price range and is therefore not valid.

[1441] "User" refers to the person or administrator who uses the system to set prices or view information.

[1442] An "alert" is a warning message that the system sends to the user to notify them of an error or abnormality.

[1443] "Electronic devices" refers to devices used to capture price information and analyze the data, such as smart glasses or smartphones.

[1444] "Real-time" refers to data processing and information notification occurring immediately, without delay.

[1445] "Analysis" refers to analyzing the received data, interpreting its meaning, and detecting specific patterns or anomalies.

[1446] "Revalidation" is the process of re-evaluating the detected discrepancies to check whether they are correct.

[1447] "Correction" refers to changing detected abnormal values ​​or errors into accurate information.

[1448] "Price Information" means price data associated with individual products or services.

[1449] The DTSAI system embodying the present invention is a system that detects pricing errors and promotion information errors in real time in physical stores and notifies users of alerts. The system configuration and processing are described in detail below.

[1450] System Configuration

[1451] 1. Hardware Configuration

[1452] Server: Analyzes the data and detects outliers.

[1453] Terminal (smart glasses, smartphone, etc.): Captures price information and sends it to the server in real time.

[1454] Network: A communication method for linking terminals and servers.

[1455] 2. Software Configuration

[1456] Machine learning algorithm: KMeans clustering is used to analyze price information.

[1457] Data analysis module: a program for analyzing received price lists.

[1458] Alert module: A program that notifies the user when an abnormal value is detected.

[1459] Processing steps

[1460] 1. Obtaining and sending price information

[1461] The user uses smart glasses to take a photo of the product price and transmits the data to the server.

[1462] 2. Analysis of price information

[1463] The server analyzes the received price data in real time and detects outliers that deviate from the normal price range.

[1464] The algorithm used is KMeans clustering, which clusters price data and identifies outliers.

[1465] 3. Alert Notification

[1466] If an abnormal value is detected, the server sends the information to the terminal and displays an alert to the user in real time.

[1467] This allows users to quickly correct pricing errors.

[1468] Specific examples

[1469] For example, if a user sets the price of a new product and the price list includes 500 yen, 520 yen, 510 yen, 490 yen, and 1200 yen, the server will detect that 1200 yen is an abnormal value. The corresponding smart glasses will display an alert saying, "The 1200 yen price setting is significantly different from the other prices. Please check again."

[1470] Prompt Sentence Examples

[1471] Please set a price for your new product. If the prices of other products are around 1000 yen and your set price is 5000 yen, please send an alert as an abnormal value.

[1472] As described above, the DTSAI system of the present invention detects errors in pricing and promotional information in physical stores in real time and promptly notifies users of alerts, thereby improving business efficiency and customer satisfaction.

[1473] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1474] Step 1:

[1475] Obtaining and sending price information

[1476] A user captures the price of a product using a device (e.g., smart glasses). The device's built-in camera captures the product's price tag and extracts the price information using OCR (optical character recognition) technology. The device then sends the price information to a server.

[1477] Input: Price tag image

[1478] Output: Extracted price information

[1479] Step 2:

[1480] Receiving price information

[1481] The server receives the price information sent from the terminal and stores it in a database within the server.

[1482] Input: Price information sent from the device

[1483] Output: Price information stored in a database

[1484] Step 3:

[1485] Price information analysis

[1486] The server uses a data analysis module to analyze the received price information in real time. This analysis uses KMeans clustering to classify the price information and detect outliers. The algorithm clusters the price information and identifies the prices detected as outliers.

[1487] Input: Price information stored in a database

[1488] Output: Price information identified as anomalies

[1489] Step 4:

[1490] Alert Generation

[1491] If the server detects an anomaly, it generates an alert based on the price information. The alert message includes details of the anomaly and a recommendation to recheck.

[1492] Input: Price information identified as an outlier

[1493] Output: The generated alert message

[1494] Step 5:

[1495] Alert Notifications

[1496] The server sends the generated alert message to the terminal, which then displays the received alert message on the user's display. The user can then confirm the message and make any necessary adjustments to the pricing.

[1497] Input: The generated alert message

[1498] Output: The alert message displayed on the user's display.

[1499] Specifically, when a user sets a price for a new product, the smart glasses capture the "5,000 yen" price tag and send the price information to the server. The server detects through clustering that "5,000 yen" is an anomaly and generates an alert message saying, "The price of the 5,000 yen product is significantly different from other products. Please check again." This message is displayed on the smart glasses' display. The user can then confirm the alert and make any necessary adjustments to the price setting.

[1500] 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.

[1501] The following describes in detail the mode for carrying out the present invention: The present invention is a system that combines a Digital Task Safeguard AI (DTSAI) system, which prevents pricing errors, incorrect attachments when sending documents, and spelling and formatting errors when entering data, with an emotion engine that recognizes user emotions.

[1502] Mispricing detection and emotional alerts

[1503] server

[1504] The server receives a price list sent by the user. This price list contains the prices of goods and services. The received price list is converted into a NumPy array and analyzed using a clustering algorithm (e.g., KMeans clustering). When an outlier outside the normal price range is detected, the server activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's current emotional state from Japanese chat messages, facial expression recognition, and voice data. Depending on the emotional state, the server notifies the user with an appropriate alert regarding the outlier.

[1505] For example, if a user sets a new product price and sends the price list [500, 520, 510, 490, 1200] to the server, the server will detect 1200 as an abnormal value. If the user is stressed at the time, the server will send a soft-toned alert saying, "This price is significantly different from the other prices. Please check it." On the other hand, if the user is calm, the server will send a direct alert saying, "1200 yen is an abnormal value. Please correct it."

[1506] Preventing mis-sending of documents and emotional response alerts

[1507] Terminal

[1508] When a user attempts to send an email, the device analyzes the content of the email body. If specific keywords (such as "attachment" or "document") are detected, the device checks whether an attachment exists. If no attachment exists, the emotion engine analyzes the user's emotional state. An appropriate alert message is displayed depending on the user's emotional state.

[1509] For example, if a user writes "Please see the attachment in this email" but forgets to include the attachment, the device will detect this. If the user is annoyed, the device will display a gentle alert such as "Attachment missing. Did you forget to attach it?". Conversely, if the user is focused on a task, the device will display a more urgent alert such as "Attachment not found. Please check it immediately."

[1510] Data entry error detection and emotional alerts

[1511] Terminal

[1512] During data entry, the device monitors what the user types in real time. Regular expression and dictionary-based spell checking are used to detect spelling and formatting errors. If an error is detected, an emotion engine analyzes the user's emotional state and displays an alert to the user accordingly.

[1513] For example, if a user types "example@domain.com," the device will detect this and display an alert saying, "The email address format is incorrect. Please check again." If the emotion engine recognizes that the user is tired, it will display an alert with advice such as, "The correct format is example@domain.com. Please correct it." On the other hand, if the user is impatient, it will display a short, concise alert saying, "Please enter your email address in the correct format."

[1514] The combination of the DTSAI system and emotion engine of the present invention allows users to effectively detect mistakes made during digital tasks and receive adaptive responses in real time, greatly improving work efficiency and accuracy.

[1515] The processing flow will be explained below.

[1516] Mispricing detection and emotional alerts

[1517] server

[1518] Step 1:

[1519] The server receives the price list from the user, which is then converted to an appropriate data format (e.g., a NumPy array) when sent to the server.

[1520] Step 2:

[1521] The server applies the KMeans clustering algorithm to the price list and classifies the prices into two clusters: one for normal prices and one for abnormal prices.

[1522] Step 3:

[1523] The server calculates cluster centers of typical prices and identifies outliers based on them. Prices that deviate significantly from the cluster center are considered outliers.

[1524] Step 4:

[1525] If the server detects an anomaly, the emotion engine is activated to analyze the user's current emotional state, which is obtained from text messages, facial recognition, voice data, etc.

[1526] Step 5:

[1527] Based on the analysis results of the emotion engine, the server notifies the user with an appropriate alert. For example, if the user is feeling stressed, the server sends a soft-spoken alert such as "This price is significantly different from other prices. Please check."

[1528] Preventing mis-sending of documents and emotional response alerts

[1529] Terminal

[1530] Step 1:

[1531] When the user clicks the send email button, the terminal reads the email body and subject line.

[1532] Step 2:

[1533] The device searches for specific keywords (such as "attachment" or "document") in the email body. If these keywords are included, it checks whether or not there are any attachments.

[1534] Step 3:

[1535] When a specific keyword is detected, the device checks whether an attachment exists. If an attachment does not exist, the emotion engine is activated to analyze the user's emotional state.

[1536] Step 4:

[1537] The emotion engine analyzes the user's emotional state, which is determined based on real-time data (e.g., facial expressions, voice, etc.).

[1538] Step 5:

[1539] Based on the analysis results of the emotion engine, the device will display appropriate alerts to the user. If the user is annoyed, it will display a gentle alert such as "Attachment missing. Did you forget to attach it?", but if the user is distracted, it will display a more urgent alert such as "Attachment not found. Please check immediately."

[1540] Data entry error detection and emotional alerts

[1541] Terminal

[1542] Step 1:

[1543] As the user enters key data into the input form, the terminal monitors the data in real time.

[1544] Step 2:

[1545] The terminal parses the text entered and uses regular expressions and dictionary-based spell checking to detect spelling and formatting errors.

[1546] Step 3:

[1547] If the device detects an input error, the emotion engine will be activated and analyze the user's emotional state, which can be obtained from text, facial expression analysis, voice analysis, etc.

[1548] Step 4:

[1549] Based on the analysis results of the emotion engine, the device displays appropriate alerts to the user. For example, if the user is tired, it displays an alert with advice such as "The correct format is example@domain.com. Please correct it." If the user is impatient, it displays a simple alert such as "Please enter your email address in the correct format."

[1550] These are the specific processing steps in each module. By combining emotion engines, it is possible to provide appropriate support according to the user's condition, improving the efficiency and accuracy of work.

[1551] Example 2

[1552] 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."

[1553] Conventional digital task management systems have difficulty detecting and notifying users of pricing errors, incorrect attachments when sending documents, and spelling or formatting errors when entering data. Furthermore, they are unable to provide alert messages that take into account the user's emotional state, increasing the risk of user stress and incorrect operation.

[1554] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for receiving a price list; means for converting the received price list into a numerical array, analyzing it using a clustering algorithm, and detecting outliers; means for analyzing the user's emotional state using an emotion analysis engine when an outlier is detected and notifying the user of an appropriate alert for the outlier based on the emotional state; means for analyzing the content of the document and detecting specific keywords; means for checking whether or not an attachment is present when a specific keyword is detected; means for analyzing the user's emotional state using the emotion analysis engine when an attachment is not present and displaying an alert based on the emotional state; means for monitoring data input in real time; means for detecting spelling mistakes and formatting errors; and means for analyzing the user's emotional state using the emotion analysis engine when an error is detected and displaying an appropriate alert for the error based on the emotional state. This enables effective detection of errors during digital tasks and adaptive responses in real time.

[1555] A "price list" is data that lists the prices of products and services.

[1556] A "numeric array" is data with an array structure in which numerical data is arranged in a fixed order.

[1557] A "clustering algorithm" is a computational procedure for classifying data into groups (clusters) based on similarity.

[1558] An "outlier" is a data point that deviates from the normal range and is a value that is significantly different compared to other data.

[1559] An "emotion analysis engine" is a software component that analyzes data such as text, voice, and facial expressions to recognize a user's emotional state.

[1560] An "alert" is a warning message that notifies the user of important information or matters requiring attention.

[1561] "Specific keywords" are predefined important words or phrases that are searched for within a document.

[1562] An "attachment" is an additional file attached to an email or document.

[1563] "Data entry" refers to the operation by which a user inputs information into a system or application.

[1564] A "spelling error" is an error in which a word is spelled incorrectly.

[1565] A "format error" is an error in which the data does not conform to the expected format or structure.

[1566] "Real-time monitoring" refers to the operation of immediately monitoring the contents of data the moment it is entered or updated.

[1567] The following describes in detail the mode for carrying out the present invention. This invention is a system that prevents mistakes in multiple digital tasks and responds adaptively to the user's emotional state. To achieve this, the server, terminal, and user work together.

[1568] Mispricing detection and emotional alerts

[1569] server

[1570] 1. The user sets up a price list and sends it to the server. The sent price list contains the prices of products and services.

[1571] 2. The received price list is converted by the server into a NumPy array. NumPy is a Python library that allows for highly efficient numerical calculations.

[1572] 3. The server analyzes the price list using the clustering algorithm KMeans clustering, which uses the scikit-learn library.

[1573] 4. When an outlier outside the normal price range is detected, the server activates the sentiment analysis engine, which obtains the user's emotional state from data such as text, facial expressions, and voice.

[1574] 5. Depending on the emotional state, generate appropriate alert messages for abnormal values ​​and notify the user.

[1575] Example: If a user sets a new product price and sends the price list [500, 520, 510, 490, 1200] to the server, the server will detect 1200 as an abnormal value. If the user is stressed, the server will send an alert saying "This price is significantly different from other prices. Please check." If the user is calm, the server will send an alert saying "1200 yen is an abnormal value. Please correct it."

[1576] Preventing mis-sending of documents and emotional response alerts

[1577] Terminal

[1578] 1. The user composes an email and clicks the send button.

[1579] 2. When the send button is pressed, the device analyzes the email body and detects the specified specific keywords (e.g., "attachment," "document").

[1580] 3. If the keyword is detected, the device checks whether there is an attachment.

[1581] 4. If there is no attachment, the device runs an emotion analysis engine to analyze the user's emotional state.

[1582] 5. Generate an appropriate alert message according to the emotional state and display it to the user.

[1583] Example: A user tries to send an email saying "Please see the attachment in this email" but forgets to include the attachment. The device will detect this and, if the user is annoyed, will display a gentle alert saying "Attachment missing. Did you forget to attach it?". If the user is distracted, it will display "Attachment not found. Please check it now."

[1584] Data entry error detection and emotional alerts

[1585] Terminal

[1586] 1. A user enters data into a web form, Excel spreadsheet, etc.

[1587] 2. The device monitors what you type in real time and uses dictionary-based spell checking and regular expressions to detect spelling and formatting errors.

[1588] 3. If an error is detected, the device activates an emotion analysis engine to analyze the user's emotional state.

[1589] 4. Generate an appropriate alert message according to the emotional state and display it to the user.

[1590] Example: If a user types "example@domain.com", the device will detect this and display an alert saying "The email address format is incorrect. Please check again." If the sentiment analysis engine recognizes that the user is fatigued, it will display an alert with advice saying "The correct format is example@domain.com. Please correct it." On the other hand, if the user is impatient, it will display a short and concise alert saying "Please enter your email address in the correct format."

[1591] Prompt Sentence Examples

[1592] 1. "Please give me the following price list: [500, 520, 510, 490, 1200]. Detect outliers from this list and generate alert messages based on the emotional state."

[1593] 2. "Analyze the body of the email the user is about to send, and if there is no attachment, generate an appropriate alert message using a sentiment analysis engine."

[1594] 3. "Monitor data entry in real time and detect spelling and formatting errors. Generate appropriate alert messages based on emotional state."

[1595] Through this system, users can quickly detect mistakes made during digital tasks and receive appropriate instructions, which is expected to significantly improve work efficiency and accuracy.

[1596] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1597] Mispricing detection and emotional alerts

[1598] Step 1:

[1599] The user submits a price list to the server.

[1600] Input: The user enters a price list (e.g., [500, 520, 510, 490, 1200]) into the interface and presses the submit button.

[1601] Output: The price list is sent to the server.

[1602] Specific action: A user uses a web interface to enter a price list into a form and presses the submit button.

[1603] Step 2:

[1604] The server receives the price list and converts it into a NumPy array.

[1605] Input: Received price list data.

[1606] Output: Price list as a NumPy array.

[1607] What it does: The server receives the price list and converts it to a numeric array using Python's NumPy library. Example: [500, 520, 510, 490, 1200] -> np.array([500, 520, 510, 490, 1200])

[1608] Step 3:

[1609] The server analyzes the price list using the KMeans clustering algorithm.

[1610] Input: Price list converted to a NumPy array.

[1611] Output: Clustering results and outlier locations.

[1612] Specific operation: The server uses the scikit-learn library to perform KMeans clustering. It sets the number of clusters and initial conditions, clusters the price data, and detects outliers.

[1613] Step 4:

[1614] The server detects outliers.

[1615] Input: Analysis results from the clustering algorithm.

[1616] Output: Data points identified as outliers.

[1617] Specific behavior: From the clustering results, data points in the price list that deviate significantly from the normal range (e.g., 1200) are identified as outliers.

[1618] Step 5:

[1619] The server runs an emotion analysis engine to analyze the emotional state.

[1620] Input: Anomaly detection results, chat messages with users, facial expression data, and voice data.

[1621] Output: The user's emotional state.

[1622] What it does: The server launches an emotion analysis engine that analyzes the user's text messages and other emotional data to determine their current emotional state.

[1623] Step 6:

[1624] The server generates alerts for abnormal values ​​and notifies the user.

[1625] Input: Sentiment analysis results and outliers.

[1626] Output: Appropriate alert message depending on emotional state.

[1627] Specific behavior: Based on the user's emotional state, generate an alert message in a soft or direct tone and display it in the user's interface.

[1628] Preventing mis-sending of documents and emotional response alerts

[1629] Step 1:

[1630] The user composes an email and clicks the send button.

[1631] Input: The email body created by the user.

[1632] Output: The transport request.

[1633] Specific behavior: A user composes an email in an email client (e.g., Outlook, Gmail) and clicks the send button.

[1634] Step 2:

[1635] The device analyzes the email body.

[1636] Input: The email body created by the user.

[1637] Output: Text analysis result.

[1638] What happens: The device reads the email body as a string and begins analyzing it. It performs a regular expression search to find specific keywords (e.g., "attachment").

[1639] Step 3:

[1640] The device detects specific keywords.

[1641] Input: Body parsing result.

[1642] Output: Check for the existence of a specific keyword.

[1643] Specific operation: The device extracts specific keywords such as "attachment" and "document" from the analyzed email body.

[1644] Step 4:

[1645] The device checks for the presence of an attachment.

[1646] Input: Detected results for a specific keyword.

[1647] Output: The result of checking whether the attachment exists.

[1648] Specific operation: The device checks the header information of the email to see if it actually contains an attachment.

[1649] Step 5:

[1650] If there is no attachment, the device runs an emotion analysis engine to analyze the emotional state.

[1651] Input: Attachment check result, user operation data.

[1652] Output: The user's emotional state.

[1653] Specific operation: The device launches an emotion analysis engine and analyzes the user's emotional state from operation data (e.g., keyboard keystroke sounds, keystroke speed).

[1654] Step 6:

[1655] The terminal generates an appropriate alert and displays it to the user.

[1656] Input: Sentiment analysis results, attachment check results.

[1657] Output: An appropriate alert message.

[1658] What it does: Generates a mild or urgent alert message based on the user's emotional state and displays it as a pop-up on the user's screen.

[1659] Data entry error detection and emotional alerts

[1660] Step 1:

[1661] The user enters data into the terminal.

[1662] Input: Data entered by the user.

[1663] Output: Capture of input data.

[1664] Specific action: A user enters data into an Excel spreadsheet or web form.

[1665] Step 2:

[1666] The terminal monitors the input in real time.

[1667] Input: Data that the user is entering.

[1668] Output: Monitoring results (dynamic capture of input data).

[1669] What it does: The device captures data input in real time using JavaScript and keystroke monitoring scripts.

[1670] Step 3:

[1671] The device will detect spelling and formatting errors.

[1672] Input: The monitored input data.

[1673] Output: Detected spelling and formatting errors.

[1674] What it does: The device performs dictionary-based spell checking and regular expression pattern matching to detect spelling and formatting errors.

[1675] Step 4:

[1676] The device runs an emotion analysis engine to analyze the emotional state.

[1677] Input: Results of detection of spelling and formatting errors, user operation data.

[1678] Output: The user's emotional state.

[1679] Specific operation: The device launches an emotion analysis engine and analyzes the user's emotional state based on factors such as typing speed and frequency of input errors.

[1680] Step 5:

[1681] The terminal generates an alert to the error and displays it to the user.

[1682] Input: Sentiment analysis results, error detection results.

[1683] Output: An appropriate alert message.

[1684] Specific behavior: Depending on the emotional state and the error, an advisory or urgent alert message is generated and displayed as a pop-up on the user's screen.

[1685] (Application example 2)

[1686] 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."

[1687] Conventional inventory management and customer support systems have had problems with product pricing errors and data entry errors, which reduce work efficiency. Additionally, the lack of a way to respond appropriately to user emotions has led to stress and impatience, which can lead to increased work errors.

[1688] 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 receiving a price list, means for analyzing the received price list and detecting abnormal values, means for analyzing the user's emotional state in response to the detected abnormal values, and means for notifying an alert with an appropriate tone based on the user's emotional state. This makes it possible to detect pricing errors and notify an appropriate alert according to the user's emotional state.

[1689] A "price list" is a table that lists product price information.

[1690] An "outlier" is a data value that is outside the normal range and is detected by specific criteria or algorithms.

[1691] "Emotional state" refers to the user's psychological and emotional reactions and situations, and is analyzed using voice data and facial expression recognition.

[1692] An "alert" is a notification or warning message sent from the system to the user.

[1693] A "document" refers to text data including text data such as email.

[1694] "Specific keywords" are important words and phrases that are set for the system to search and detect.

[1695] An "attachment" is an additional data file that is added to an email or the like.

[1696] "Data entry" is the act of a user manually entering information into a system.

[1697] "Spelling error" refers to a situation in which a word is misspelled.

[1698] "Format error" refers to a deviation from the specified format when entering data.

[1699] "Real-time monitoring" refers to the instantaneous confirmation and analysis of data and behavior.

[1700] MODE FOR CARRYING OUT THE INVENTION

[1701] This invention is a system that prevents pricing errors and data entry errors when users manage inventory and handle customer service in a physical store, and also provides appropriate alerts based on the user's emotional state. The system receives price lists, detects abnormal values, and notifies the user of alerts based on the user's emotional state.

[1702] System program generation

[1703] The server first receives a price list sent by the user. This price list contains product price information. The received price list is converted into a NumPy array and analyzed using a clustering algorithm (e.g., KMeans clustering). If an outlier outside the normal price range is detected, the server activates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the user's current emotional state using facial recognition, voice data, chat messages, etc.

[1704] Hardware and software used

[1705] Hardware:

[1706] Smartphones, smart glasses, head-mounted displays (HMDs)

[1707] software:

[1708] NumPy: Array manipulation and calculations on data

[1709] scikit-learn: Clustering algorithm implementation

[1710] emotion_recognition:Emotion recognition engine

[1711] The server generates appropriate alerts for outliers based on the user's emotional state. These alerts have different tones depending on the user's emotional state. For example, if the user is stressed, a softer alert such as "This price is significantly different from other prices. Please check it." On the other hand, if the user is calm, a more direct alert such as "1200 yen is an outlier. Please correct it."

[1712] Specific examples

[1713] For example, consider a scenario where a staff member uses smart glasses to manage inventory. If a price list contains the data [500, 520, 510, 490, 1200], the server receives this price list and detects 1200 as an outlier. At this time, the emotion engine analyzes the staff member's emotional state, and if the staff member is feeling stressed, an alert will be displayed saying, "This price is significantly different from the other prices. Please check."

[1714] You can also use the following example prompts to provide appropriate instructions to the generative AI model:

[1715] Prompt Sentence Examples

[1716] User input: Setting stock price. Price list: [500, 520, 510, 490, 1200]

[1717] Emotional state: stressed

[1718] Task: Detect any anomalous prices and generate a customized alert based on the emotion state.

[1719] By implementing this invention, the efficiency and accuracy of inventory management in physical stores can be significantly improved, and flexible responses based on user emotions become possible.

[1720] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1721] Step 1:

[1722] The server receives a price list from the user. It takes as input a list containing price information (e.g., [500, 520, 510, 490, 1200]) and stores it for use in the next processing step. The output is the received price list.

[1723] Step 2:

[1724] The server converts the received price list into a NumPy array. Here, the price information in list format is converted into a NumPy array format, making it easier to analyze the data. The input is the price list received in step 1, and the output is the converted NumPy array.

[1725] Step 3:

[1726] The server analyzes the price data using NumPy arrays and applies a clustering algorithm (e.g., KMeans clustering) to detect outliers. The input is the generated NumPy array, and the output is a list of outliers. It evaluates each price cluster and identifies prices outside the normal price range as outliers.

[1727] Step 4:

[1728] The server detects outliers based on the clustering results and then runs an emotion engine to analyze the user's emotional state. The input is a list of outliers, and the output is the user's emotional state (e.g., stressed, calm). Here, the server analyzes the user's emotions from facial recognition data, voice data, chat messages, etc.

[1729] Step 5:

[1730] The server generates an alert with an appropriate tone based on the user's emotional state. The input is the list of abnormal values ​​and the user's emotional state, and the output is the alert message. For example, if the emotional state is "stressed," the server generates a soft-toned alert saying, "This price is significantly different from other prices. Please check."

[1731] 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.

[1732] 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.

[1733] 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.

[1734] 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.

[1735] 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.

[1736] 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.

[1737] 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).

[1738] 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.

[1739] 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."

[1740] 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.

[1741] 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).

[1742] 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.

[1743] 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.

[1744] 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.

[1745] 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.

[1746] 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.

[1747] 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.

[1748] 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.

[1749] 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.

[1750] 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, in order to avoid confusion and to 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.

[1751] 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.

[1752] The following is further disclosed regarding the above embodiment.

[1753] (Claim 1)

[1754] means for receiving a price list;

[1755] means for analyzing the received price list and detecting outliers;

[1756] a means for notifying a user of an alert when an abnormal value is detected;

[1757] A system including:

[1758] (Claim 2)

[1759] a means for analyzing the content of a document and detecting specific keywords;

[1760] A means to check for the presence of attachments when specific keywords are detected;

[1761] a means for alerting the user if the attachment does not exist;

[1762] A system including:

[1763] (Claim 3)

[1764] a means of monitoring data entry in real time;

[1765] a means of detecting spelling and formatting errors;

[1766] means for displaying an alert to a user when an error is detected;

[1767] A system including:

[1768] (Claim 4)

[1769] means for receiving a price list;

[1770] means for analyzing the received price list and detecting outliers;

[1771] a means for notifying a user of an alert when an abnormal value is detected;

[1772] a means for analyzing the content of a document and detecting specific keywords;

[1773] A means to check for the presence of attachments when specific keywords are detected;

[1774] a means for alerting the user if the attachment does not exist;

[1775] 10. The system of claim 1, comprising:

[1776] (Claim 5)

[1777] means for receiving a price list;

[1778] means for analyzing the received price list and detecting outliers;

[1779] a means for notifying a user of an alert when an abnormal value is detected;

[1780] a means for analyzing the content of a document and detecting specific keywords;

[1781] A means to check for the presence of attachments when specific keywords are detected;

[1782] a means for alerting the user if the attachment does not exist;

[1783] a means of monitoring data entry in real time;

[1784] a means of detecting spelling and formatting errors;

[1785] means for displaying an alert to a user when an error is detected;

[1786] 10. The system of claim 1, comprising:

[1787] (Claim 6)

[1788] a means for analyzing the content of a document and detecting specific keywords;

[1789] A means to check for the presence of attachments when specific keywords are detected;

[1790] a means for alerting the user if the attachment does not exist;

[1791] a means of monitoring data entry in real time;

[1792] a means of detecting spelling and formatting errors;

[1793] means for displaying an alert to a user when an error is detected;

[1794] 3. The system of claim 2, comprising:

[1795] "Example 1"

[1796] (Claim 1)

[1797] means for receiving a price list;

[1798] means for analyzing the received price list using a machine learning algorithm to detect outliers;

[1799] a means for notifying a user of an alert when an abnormal value is detected;

[1800] a means for analyzing the content of a document and detecting specific keywords;

[1801] A means to check for the presence of attachments when specific keywords are detected;

[1802] a means for alerting the user if the attachment does not exist;

[1803] a means of monitoring data entry in real time;

[1804] a means of detecting spelling and formatting errors;

[1805] means for displaying an alert to a user when an error is detected;

[1806] A system including:

[1807] (Claim 2)

[1808] 10. The system of claim 1, wherein a machine learning algorithm is used to cluster the price list and automatically identify outliers.

[1809] (Claim 3)

[1810] The system according to claim 1, further comprising a function to check whether or not a file is attached when a specific keyword is detected in the contents of a document, and to display a warning message to the user if the file is not attached.

[1811] "Application Example 1"

[1812] (Claim 1)

[1813] means for receiving a price list;

[1814] means for analyzing the received price list and detecting outliers;

[1815] a means for notifying a user of an alert when an abnormal value is detected;

[1816] Obtaining price information through electronic devices for photographing price lists;

[1817] A means of analyzing the acquired price information in real time,

[1818] means for automatically identifying outliers in the price information;

[1819] means for displaying an alert to a user via an electronic device when an abnormal value is detected;

[1820] Measures to encourage reconfirmation and correction of abnormal values,

[1821] A system including:

[1822] (Claim 2)

[1823] a means for analyzing the content of a document and detecting specific keywords;

[1824] A means to check for the presence of attachments when specific keywords are detected;

[1825] a means for alerting the user if the attachment does not exist;

[1826] 10. The system of claim 1, comprising:

[1827] (Claim 3)

[1828] a means of monitoring data entry in real time;

[1829] a means of detecting spelling and formatting errors;

[1830] means for displaying an alert to a user when an error is detected;

[1831] 10. The system of claim 1, comprising:

[1832] "Example 2: Combining Emotion Engines"

[1833] (Claim 1)

[1834] means for receiving a price list;

[1835] means for converting the received price list into a numerical array and analyzing it using a clustering algorithm to detect outliers;

[1836] means for analyzing the emotional state of a user using an emotion analysis engine when an abnormal value is detected, and notifying the user of an appropriate alert regarding the abnormal value according to the emotional state;

[1837] a means for analyzing the content of a document and detecting specific keywords;

[1838] A means to check for the presence of attachments when specific keywords are detected;

[1839] means for analyzing the emotional state of a user using an emotion analysis engine when there is no attachment, and displaying an alert according to the emotional state;

[1840] a means of monitoring data entry in real time;

[1841] a means of detecting spelling and formatting errors;

[1842] a means for analyzing the emotional state of the user using an emotion analysis engine when an error is detected, and displaying an appropriate alert for the error according to the emotional state;

[1843] A system including:

[1844] (Claim 2)

[1845] 10. The system of claim 1, wherein the sentiment analysis engine generates an appropriate alert based on the results of the sentiment analysis.

[1846] (Claim 3)

[1847] 10. The system of claim 1, wherein the system adaptively responds in real time to the detection of outliers, mistransmissions, and misspellings.

[1848] "Application example 2 when combining emotion engines"

[1849] (Claim 1)

[1850] means for receiving a price list;

[1851] means for analyzing the received price list and detecting outliers;

[1852] means for analyzing the user's emotional state in response to the detected abnormal value;

[1853] means for issuing an alert with an appropriate tone based on the user's emotional state;

[1854] A system including:

[1855] (Claim 2)

[1856] a means for analyzing the content of a document and detecting specific keywords;

[1857] A means to check for the presence of attachments when specific keywords are detected;

[1858] means for analyzing a user's emotional state when no attachment is present;

[1859] means for displaying an alert with an appropriate tone based on the user's emotional state;

[1860] 10. The system of claim 1, comprising:

[1861] (Claim 3)

[1862] a means of monitoring data entry in real time;

[1863] a means of detecting spelling and formatting errors;

[1864] means for analyzing the emotional state of the user when an error is detected;

[1865] means for displaying an alert with an appropriate tone based on the user's emotional state;

[1866] 10. The system of claim 1, comprising: [Explanation of symbols]

[1867] 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. means for receiving a price list; means for analyzing the received price list and detecting outliers; a means for notifying a user of an alert when an abnormal value is detected; A system including:

2. a means for analyzing the content of a document and detecting specific keywords; A means to check for the presence of attachments when specific keywords are detected; a means for alerting the user if the attachment does not exist; A system including:

3. a means of monitoring data entry in real time; a means of detecting spelling and formatting errors; means for displaying an alert to a user when an error is detected; A system including:

4. means for receiving a price list; means for analyzing the received price list and detecting outliers; a means for notifying a user of an alert when an abnormal value is detected; a means for analyzing the content of a document and detecting specific keywords; A means to check for the presence of attachments when specific keywords are detected; a means for alerting the user if the attachment does not exist; The system of claim 1 , comprising:

5. means for receiving a price list; means for analyzing the received price list and detecting outliers; a means for notifying a user of an alert when an abnormal value is detected; a means for analyzing the content of a document and detecting specific keywords; A means to check for the presence of attachments when specific keywords are detected; a means for alerting the user if the attachment does not exist; a means of monitoring data entry in real time; a means of detecting spelling and formatting errors; means for displaying an alert to a user when an error is detected; The system of claim 1 , comprising:

6. a means for analyzing the content of a document and detecting specific keywords; A means to check for the presence of attachments when specific keywords are detected; a means for alerting the user if the attachment does not exist; a means of monitoring data entry in real time; a means of detecting spelling and formatting errors; means for displaying an alert to a user when an error is detected; The system of claim 2 , comprising:

Images