system

Abstract

Provide a system. A means for reading data on the frequency of use of a specific name; a means for transposing each name in reverse order; a means of investigating the frequency of use of the transposed names; means for calculating a ranking based on the frequency of use of the original name and the transposed name; a means for identifying names that are lower in ranking than the original name and generating a warning list; an interface means for displaying the alert list; A system including:

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] When calling a patient's name in a hospital or medical facility, the patient's last name may be mispronounced. This mispronunciation not only causes confusion for the patient and medical staff, but may also lead to serious medical accidents in some cases. The purpose of this invention is to prevent mispronunciation of last names and ensure accurate calling. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means: Reading usage frequency data for specific names, transposing each name in reverse order, and investigating the usage frequency of the transposed names. Next, calculating a ranking based on the usage frequency of the original names and the transposed names, identifying names with lower rankings among the original names, and generating a warning list. Then, providing an interface for displaying the warning list encourages users at hospitals and other facilities to make accurate calls and prevent misdialing. The system also includes a means for treating the usage frequency as zero if no transposed names exist, and a communication means for transmitting the warning list to a terminal, thereby enhancing the system's practicality and accuracy.

[0006] "Data on the frequency of use of specific names" is statistical data that shows how frequently a specific name or title is used in a certain period or area.

[0007] "Reading means" refers to a method or function for inputting data on the frequency of use of a specific name into the system.

[0008] A "transposition means" is a method or function that rearranges the original name string in reverse order.

[0009] "Means of investigation" refers to methods or functions for checking whether the transposed name is used in the same way as the original name and how frequently it is used.

[0010] A "means for calculating rankings" is a method or function for ranking names in order of popularity based on frequency of use data.

[0011] The "means for generating a warning list" refers to a method or function for creating a list of names that are likely to be mispronounced based on specific criteria.

[0012] The "interface means for displaying" refers to a method or function for displaying the generated warning list so that the user can check it.

[0013] "Communication means" refers to the method or function for transmitting information such as a warning list to a terminal. [Brief explanation of the drawings]

[0014] [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 illustrating 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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention is a system for preventing mispronunciation of specific names. This system uses data on the frequency of use of specific names to calculate name transpositions and usage frequency rankings, and generates and displays a warning list. This system is intended for use in situations such as calling out the names of patients in hospitals and medical facilities.

[0036] System Overview

[0037] The system is controlled by a server and has the following main functions:

[0038] 1. Loading name frequency data

[0039] The server reads name frequency data, which indicates how often each name is used.

[0040] 2. Transposition of names

[0041] The server reverses and transposes each name, preparing to identify names that are likely to be mispronounced.

[0042] 3. Frequency of use of transposed names

[0043] The server checks the frequency of the inverted name. If the inverted name exists, it retrieves its frequency data; if it does not exist, it treats the frequency as zero.

[0044] 4. Ranking Calculation

[0045] The server calculates a ranking based on the frequency of use of the names and their inverted names, thereby ranking each name in descending order of popularity.

[0046] 5. Generate a warning list

[0047] The server identifies names that rank lower than the original name and generates a warning list, which lists names that are likely to be mispronounced.

[0048] 6. Display by Interface Means

[0049] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[0050] Specific explanation of program processing

[0051] 1. The server reads the name frequency data

[0052] The server inputs pre-prepared name frequency data into the system, which is in dictionary format and includes information on the names and the number of households where they are used.

[0053] 2. The server performs a transpose operation on each name.

[0054] The server performs string manipulation to reverse each name to generate the inverted name.

[0055] 3. The server checks the frequency of use of the inverted name

[0056] The server checks whether the inverted name exists and obtains the frequency data. If it does not exist, it treats the frequency as zero.

[0057] 4. The server calculates the ranking

[0058] The server calculates a ranking for each name and transposed name based on frequency of use data, with the rankings sorted from highest to lowest frequency of use.

[0059] 5. The server generates a warning list

[0060] The server identifies names that rank lower than the original name and adds them to the warning list.

[0061] 6. The server sends the alert list to the terminal and displays it.

[0062] The server transmits the generated warning list to the terminal, which displays the list, thereby warning the user.

[0063] Specific examples

[0064] For example, if the name data includes "Tanaka," the server reads "Tanaka" and reverse-sorts "Tanaka" to generate "Nakata." It then checks the frequency of use of "Nakata" and calculates the ranking of both names. If "Tanaka" is ranked low, it is added to a warning list. Finally, the server sends this list to the terminal and displays a warning message to the user to avoid accidentally calling "Tanaka" "Nakata."

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The server reads name frequency data.

[0068] The server inputs pre-prepared name frequency data into the system. This data contains names and their frequency of use in dictionary format. For example, there are 75,000 households with the name "Tanaka" and 2,000 households with the name "Nakata."

[0069] Step 2:

[0070] The server converts the data into a data frame.

[0071] The server converts the name frequency data it has read into a Pandas data frame, which has each name and its number of households as a row.

[0072] Step 3:

[0073] The server performs the transposition of each name.

[0074] The server reverses each name to generate a transposed name. For example, reverse "Tanaka" to create "Nakatana." This operation is performed for all names.

[0075] Step 4:

[0076] The server checks the frequency of use of the inverted name.

[0077] The server checks the existence of the transposed name and checks its frequency of use. If the transposed name exists, it adds its frequency of use to the data frame; if it does not exist, it treats the frequency of use as zero.

[0078] Step 5:

[0079] The server calculates the ranking.

[0080] The server calculates the ranking of each name, from highest to lowest, based on the frequency of use data for the name and the transposed name. The rankings for the original name and the transposed name are added to a data frame.

[0081] Step 6:

[0082] The server generates a reminder list.

[0083] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to a warning list, which contains names that are prone to mispronunciation based on certain criteria.

[0084] Step 7:

[0085] The server sends the warning list to the terminal and displays it.

[0086] The server sends the generated warning list to the terminal. The terminal receives the list and displays messages and information to warn the user. This allows the user to recognize the risk of mispronouncing names in advance.

[0087] Example 1

[0088] 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."

[0089] When calling patients by name in hospitals and medical facilities, mispronunciations between patients with similar names are common. Such mispronunciations can lead to medical accidents and confusion, and are a major obstacle to providing safe and efficient medical services. The present invention aims to provide a system that calculates name transpositions and rankings based on data on the frequency of use of specific names, and generates and displays a warning list to prevent mispronunciations.

[0090] 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.

[0091] In this invention, the server includes means for reading name usage frequency data, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for acquiring name usage frequency data from a database, means for acquiring the usage frequency of the transposed names from the database, and means for sorting the names in descending order of usage frequency, thereby making it possible to prevent names from being mispronounced.

[0092] "Name usage frequency data" is data that numerically indicates how frequently a particular name is used.

[0093] "Reading means" refers to a function or method by which a server obtains specific data from a database, storage, etc., and makes it available within the system.

[0094] A "transposition means" is a function or method for rearranging a specific string of characters in reverse order. For example, "Tanaka" is converted to "Nakada."

[0095] A "means for investigating frequency of use" is a function or method for obtaining the frequency of use of a specific name from a database or the like.

[0096] The "means for calculating rankings" is a function or method that calculates the ranking of each name based on the collected usage frequency data and rearranges them in descending order of frequency of use.

[0097] The "means for generating a warning list" is a function or method for identifying names that are likely to be mispronounced based on the ranking results and listing them.

[0098] The "interface means" is a function or method for visually displaying the generated reminder list to the user.

[0099] "Means for retrieving from a database" refers to a function or method for searching and retrieving specific data from a database.

[0100] The "means for sorting names in descending order of frequency of use" is a function or method for performing an operation to sort names in descending order of frequency of use based on the data on the frequency of use of the names.

[0101] "Communication means" refers to the method or technology used by the server to transmit data to the terminal, which allows the generated reminder list to be displayed on the terminal.

[0102] The present invention is a system for preventing mispronunciation of specific names. This system has the function of calculating name transpositions and usage frequency rankings based on name usage frequency data, and generating and displaying a warning list. A specific embodiment of this system is described below.

[0103] This system operates among the server, terminals, and users as follows.

[0104] 1. Loading name usage frequency data

[0105] The server retrieves pre-prepared name usage frequency data from a database. The name usage frequency data is stored in a MySQL (registered trademark) database, and by importing this data, the server can determine how frequently each name is used. For example, this data is recorded as "Tanaka" 30 times and "Nakata" 20 times.

[0106] 2. Name transposition operation

[0107] The server uses string manipulation to reverse the order of each name. For example, "Tanaka" is reversed to become "Nakata." This operation is realized using Python's string manipulation functions.

[0108] 3. Frequency of use of transposed names

[0109] The server retrieves the frequency of use of the transposed name from the database again. For example, it checks whether the transposed name "Nakata" exists and retrieves its frequency of use. If it does not exist, it treats the frequency of use as zero.

[0110] 4. Ranking Calculation

[0111] The server calculates the ranking of each name based on the frequency of use of the original name and the transposed name. The ranking is sorted by frequency of use. The calculation is done using Python's pandas library or similar to sort the data.

[0112] 5. Generate a warning list

[0113] The server then uses the ranking results to identify names that rank lower than the original name and adds them to a warning list, which is used to identify names that are prone to being mispronounced.

[0114] 6. Display of warning list

[0115] The server sends the generated warning list to the terminal, which displays it. The terminal is equipped with a web browser, and data is sent from the server via an HTTP request and displayed in HTML format. This allows the user to visually receive the warning message.

[0116] Specific examples

[0117] For example, if the name data includes "Tanaka," the server reads "Tanaka" and rearranges "Tanaka" in reverse order to generate "Nakata." The server then investigates the frequency of use of "Nakata," and assumes that "Tanaka" is used 30 times and "Nakata" is used 20 times. A ranking is calculated based on this data, and if "Tanaka" is ranked low, it is added to a warning list. Finally, the server sends this list to the device, which displays a warning message to prevent the device from mistakenly calling "Tanaka" "Nakata."

[0118] Examples of prompt statements

[0119] The following are examples of prompts used to test the operation of a system using a generative AI model:

[0120] Enter the name "Tanaka" into the system. Then, obtain the frequency of use data for the transposed name "Nakata" in the same way and calculate the ranking. Finally, if the name "Tanaka" is ranked low, add it to a warning list and display it to the user.

[0121] The present invention provides a system that prevents mispronunciation of names, thereby improving patient safety and quality of service, particularly in hospitals and medical facilities.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] The server reads name frequency data. The server retrieves frequency data for specific names from the database. This data contains information on how frequently each name is used. The input is the names stored in the database and their frequency of use, and the output is the frequency data for names loaded into the server's internal memory. As a specific example of how this works, the server uses a SELECT statement from the MySQL database to retrieve the names and their corresponding frequency of use.

[0125] Step 2:

[0126] The server performs a transposition operation on each name. The server rearranges the names in reverse order to generate a new transposed name. The input is the read name, and the output is the transposed version of each name. As a specific example of how it works, the server reverses the names using Python's string manipulation functions.

[0127] Step 3:

[0128] The server checks the frequency of use of the inverted name. The server again retrieves the frequency data of the inverted name from the database. The inverted name is the input, and the frequency data of the inverted name is obtained as the output. If it does not exist, the frequency is treated as zero. As a specific example of operation, the server retrieves the frequency of use of the inverted name from the MySQL database using a SELECT statement, and if it does not exist, it sets it to 0.

[0129] Step 4:

[0130] The server calculates the rankings based on the usage frequency data of the original names and transposed names. The input is the usage frequency data of the original names and transposed names, and the output is the ranking of each name. As a specific example of how it works, the server uses Python's pandas library to sort the usage frequency data and create a ranking.

[0131] Step 5:

[0132] The server generates a warning list. The server identifies the original names that are at the bottom of the rankings and adds them to the warning list. The generated rankings are the input, and the warning list is the output. As a specific example of operation, the server adds names that are at the bottom of the rankings to the list based on a specific threshold.

[0133] Step 6:

[0134] The server sends the warning list to the terminal and displays it. The server sends the generated warning list to the terminal, and the terminal displays it. The input is the generated warning list, and the output is the warning message displayed on the terminal. As a specific example of operation, the server sends the warning list to the terminal using an HTTP request, and the terminal displays the list in HTML format using a web browser.

[0135] (Application example 1)

[0136] 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."

[0137] Mispronouncing certain names can cause confusion and inconvenience to users. In particular, in physical stores, where employees need to efficiently serve many customers in a short amount of time, mispronouncing names can lead to lower customer satisfaction and complaints. Furthermore, with the spread of wearable information devices, there is a demand for dynamic provision of this information.

[0138] 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.

[0139] In this invention, the server includes means for reading usage frequency data of specific names, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, and means for displaying the warning list on a mobile information terminal or wearable information terminal and notifying the user by audio or visual content. This makes it possible to prevent customers from being mispronounced by name and improve the quality of service in physical stores.

[0140] "Data on the frequency of use of a particular name" is statistical data that indicates how frequently a particular name is used.

[0141] The "means for reversing each name" is a process or algorithm for reversing the strings of each name.

[0142] A "means for investigating the frequency of use of a transposed name" is a mechanism for investigating how frequently a transposed name is used.

[0143] A "means for calculating rankings" is an algorithm or system that determines rankings based on frequency of use of the original and transposed names.

[0144] The "means for identifying low-ranking names and generating a warning list" is a process for listing less frequently used names and warning them.

[0145] An "interface means for displaying the reminder list" is a device or software for visually or audibly presenting the reminder list to a user.

[0146] "Means for displaying the warning list on a mobile information terminal or wearable information terminal and notifying the user with audio or visual content" refers to a mechanism for displaying the warning list on a device such as a smartphone or smart glasses and alerting the user with audio or visual messages.

[0147] This invention is a system that prevents mispronouncing specific names. This system is intended for use in brick-and-mortar stores, and generates and displays a list of reminders to prevent employees from mispronouncing customers' names.

[0148] System Configuration

[0149] This system consists of a server, a mobile information terminal (smartphone), and a wearable information terminal (smart glasses or head-mounted display). Each device plays the following role:

[0150] 1. Server

[0151] Loading name frequency data: The server loads the frequency data for a specific name from the database and imports it into the system.

[0152] Transpose each name: The server reverses each name using string manipulation.

[0153] Checking the frequency of use of the transposed name: The server checks the frequency of use of the transposed name from the database and obtains the frequency data if it exists.

[0154] Calculating Ranking: The server calculates a ranking based on the name and inverted name to assess the popularity of the name.

[0155] Generate a warning list: The server identifies names that are ranked lower than the original name and generates a warning list.

[0156] Communication means: The server transmits the generated alert list to the mobile information terminal or wearable information terminal.

[0157] 2. Portable and wearable information terminals

[0158] Interface means: The mobile information terminal or wearable information terminal displays the alert list and notifies the user with audio or visual content.

[0159] Specific explanation of the process

[0160] 1. Loading name frequency data: The server loads name frequency data from the database. This data is stored in a dictionary format, with the key being the name and the value being the frequency of use.

[0161] 2. Generate a transposed version of each name: The server applies an algorithm to reverse the names and generates the transposed version. This is done using a programming language such as Python.

[0162] 3. Frequency check of transposed name: Check whether the transposed name exists in the database and get its frequency of use. If it does not exist, treat the frequency as zero.

[0163] 4. Calculate Ranking: The server calculates the ranking based on the frequency of use of the names and transposed names. This ranking is generated by sorting the frequency of use of each name from most to least frequent.

[0164] 5. Generate Reminder List: The server identifies less frequently used names and adds them to the reminder list.

[0165] 6. Displaying the list on the device and notifying users: The alert list is sent to smartphones or smart glasses, and these devices notify users with voice messages and visual content.

[0166] Specific examples

[0167] For example, suppose the names of customers waiting at a store are "Tanaka" (used 50 times), "Yamada" (used 30 times), "Nakata" (used 20 times), and "Sato" (used 60 times). The server reverses "Tanaka" to generate "Nakata" and adds up the frequency of both (70 times). Ultimately, "Tanaka" is not included in the warning list because it is ranked high.

[0168] Prompt Sentence Examples

[0169] Create a reminder system to prevent mispronunciation of names. Name data is provided in the following format: "Tanaka": 50, "Yamada": 30, "Nakata": 20, "Sato": 60. Sort the names in reverse order, investigate the frequency of their transpositions, and generate a reminder list based on the frequency of each name and its transpositions. The list should contain names that are used 10 times or less.

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] The server reads name frequency data. This data is retrieved from the database and stored in dictionary format. The input is the database connection information and query, and the output is dictionary data of names and their frequency of use. Specifically, the server connects to the database and retrieves the data by executing an SQL query such as "SELECT name, frequency FROM name_data".

[0173] Step 2:

[0174] The server transposes each name in reverse order. The input is the dictionary of name data obtained in step 1, and the output is the dictionary data of the transposed names. Specifically, each name is reversed using string manipulation and stored as a transposed name in a new dictionary. For example, "Tanaka" is transposed to "Nakata."

[0175] Step 3:

[0176] The server checks the frequency of the inverted name. The input is the dictionary of the inverted names from step 2, and the output is a dictionary with the frequency of the inverted name added. Specifically, it checks whether the inverted name exists in the database, and if so, obtains its frequency; if not, it sets the frequency to zero.

[0177] Step 4:

[0178] The server calculates the ranking based on the frequency of use of the name and transposed name. The input is the frequency data of the name and transposed name obtained in step 3, and the output is a ranking list based on frequency. Specifically, an algorithm is applied to sort the names in descending order of frequency to generate the ranking list.

[0179] Step 5:

[0180] The server identifies the names with low rankings and generates a warning list. The input is the ranking list from step 4, and the output is the warning list. Specifically, it lists names whose frequency of use is below a certain threshold and adds them to the warning list.

[0181] Step 6:

[0182] The server sends the alert list to the mobile or wearable information terminal. The input is the alert list from step 5, and the output is a message to be displayed on the user's device. Specifically, the generated alert list is distributed to smartphones or smart glasses, and these devices notify the user with audio or visual messages.

[0183] Step 7:

[0184] The user checks the warning list through a mobile information terminal or wearable information terminal. The input is the warning list sent to the terminal, and the output is the displayed list and the notification message. Specifically, the user can check the list by operating a smartphone or smart glasses and take measures to prevent mispronunciation of names.

[0185] 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.

[0186] This invention is a system for preventing mispronunciation of specific names, and also includes an emotion engine that recognizes the user's emotions and optimizes alerts. This system uses data on the frequency of use of specific names to calculate name transpositions and usage frequency rankings, and generates and displays an alert list. This system is intended for use in situations where patients are called by name in hospitals, medical facilities, etc.

[0187] System Overview

[0188] The system is controlled by a server and has the following main functions:

[0189] 1. Loading name usage frequency data

[0190] The server reads data on the frequency of name usage. For example, the statistical data shows that "Tanaka" is used in 75,000 households and "Nakata" in 2,000 households.

[0191] 2. Transposition of names

[0192] The server reverses each name to generate the transposed name. For example, "Tanaka" is reversed to become "Nakata."

[0193] 3. Frequency of use of transposed names

[0194] The server checks the frequency of use of the transposed name. If the transposed name exists, it obtains its frequency data; if it does not exist, it treats the frequency as zero.

[0195] 4. Ranking Calculation

[0196] The server calculates the ranking based on the frequency of use data for names and transposed names, thereby ranking each name in descending order of popularity.

[0197] 5. Generate a warning list

[0198] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to the warning list.

[0199] 6. Display by Interface Means

[0200] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[0201] Additional features of the Emotion Engine

[0202] In addition, the present invention is equipped with an emotion engine that analyzes the user's emotions, optimizing the effectiveness of the alert.

[0203] 7. Emotion engine that recognizes user emotions

[0204] The server analyzes voice and facial expression data to recognize the user's emotional state, and the results are used to emphasize alerts.

[0205] 8. Interface adjustment based on emotional state

[0206] If the user is feeling stressed, the device will display a warning message more prominently, by increasing the font size or changing the color.

[0207] 9. Recording emotional data and optimizing future alerts

[0208] The server records the user's emotional state and optimizes future reminders based on past emotional data. This record is used to understand the user's preferences and tendencies.

[0209] Specific explanation of program processing

[0210] 1. The server reads the name frequency data

[0211] The server reads pre-prepared name usage frequency data and inputs it into the system.

[0212] 2. The server converts the data into a data frame

[0213] Convert the read data into a Pandas data frame, with each name and its frequency as a row.

[0214] 3. The server performs a transposition operation on each name.

[0215] Using string manipulation, each name is rearranged in reverse order to generate the transposed name.

[0216] 4. The server checks the frequency of use of the inverted name

[0217] The server checks whether the transposed name exists and obtains its frequency of use data. If it does not exist, it treats the frequency of use as zero.

[0218] 5. The server calculates the ranking

[0219] Based on the frequency of use data, calculate the ranking of each name and add it to the data frame.

[0220] 6. The server generates a warning list

[0221] Identify names with lower rankings and add them to a warning list.

[0222] 7. The server sends the alert list to the device and displays it.

[0223] The server sends the reminder list to the terminal, which displays it.

[0224] Explanation of how the emotion engine works

[0225] 8. The server recognizes the user's emotions

[0226] The server analyzes voice and facial expression data to recognize the user's emotional state.

[0227] For example: If the user is feeling stressed, the system will recognize this.

[0228] 9. Devices will adjust their interfaces based on user emotions

[0229] If the user is feeling stressed, the device will display a message to alert them by highlighting it, for example by making the text larger or adding a warning sound.

[0230] 10. The server records emotional data and optimizes future reminders based on that data.

[0231] The system records past emotional data and adjusts future alert methods based on that data, allowing it to provide alerts that best suit the user's emotions.

[0232] The processing flow will be explained below.

[0233] Step 1:

[0234] The server reads name frequency data.

[0235] The server reads the frequency data for specific names from a pre-prepared data file and inputs it into the system as a large dictionary-style data set, which includes each name and its frequency of use.

[0236] Step 2:

[0237] The server converts the data into a data frame.

[0238] The server converts the data it reads into a Pandas data frame, which stores each name and its frequency as a row. This operation makes it easier to process the data.

[0239] Step 3:

[0240] The server performs the transposition of each name.

[0241] The server generates the inverted name by reversing each name, e.g., changing "Tanaka" to "Nakada." This operation is performed for every name in the data frame, and a new inverted name column is added.

[0242] Step 4:

[0243] The server checks the frequency of use of the inverted name.

[0244] The server checks the frequency of use of the generated inverted name. If the inverted name does not exist, the frequency of use is treated as zero. The frequency of use of the inverted name is added to the data frame.

[0245] Step 5:

[0246] The server calculates the ranking.

[0247] The server calculates the ranking based on the frequency of use data for the original and transposed names. This results in the names being ranked in order of most or least frequently used. Add a ranking column to the data frame.

[0248] Step 6:

[0249] The server generates a reminder list.

[0250] The server identifies names that rank lower than the original name and generates a warning list. Specifically, it lists names that rank in the top 75% or higher of the total. This list includes names that are prone to being mispronounced.

[0251] Step 7:

[0252] The server sends the warning list to the terminal and displays it.

[0253] The server sends the generated reminder list to the terminal, which displays the list. When the user calls a name, the list is referenced and a reminder message is displayed to prevent mistakes.

[0254] Step 8:

[0255] The server acquires data to recognize the user's emotions, which are then analyzed by the emotion engine.

[0256] The server collects the user's voice and facial expression data and passes it to the emotion engine, which analyzes this data and determines the user's emotional state. For example, it recognizes states such as stress, impatience, and excitement.

[0257] Step 9:

[0258] An emotional engine adjusts the interface based on the user's emotional state.

[0259] The emotion engine dynamically adjusts the device's display based on the user's emotional state. For example, if the user is feeling stressed, the device will highlight a warning message by increasing the font size, changing the color to red, or adding an audible warning.

[0260] Step 10:

[0261] The server records emotional data and optimizes future alerts.

[0262] The server records the user's emotional data and optimizes future reminders based on past emotional state data, thereby providing the most effective reminder for the user. For example, it may emphasize reminders during times when the user has experienced a lot of stress in the past.

[0263] Example 2

[0264] 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."

[0265] In hospitals and medical facilities, mispronunciations and misidentifications of patients' names can occur when calling them by name. This can cause confusion and stress for patients and medical staff. Furthermore, there is a lack of means to properly grasp the user's emotions and optimize alerts based on them. To solve these problems, a system is needed that can prevent mispronunciation of specific names and provide optimal alerts according to the user's emotional state.

[0266] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0267] In this invention, the server includes means for reading name usage frequency data, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequencies of the original names and the transposed names, means for identifying names ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for recognizing the user's emotions, means for adjusting the interface based on the user's emotions, and means for recording the user's emotion data and optimizing the warning method based on the data. This makes it possible to prevent mispronunciation of names and to provide optimal warnings according to the user's emotions.

[0268] "Name usage frequency data" refers to information indicating how often a particular name is used.

[0269] "Reading means" refers to the function for acquiring data from outside and importing it into the server.

[0270] The "means for transposing each name in reverse order" refers to a function for rearranging names in reverse order to generate a new name.

[0271] "Means for investigating the frequency of use of transposed names" refers to a function for checking the frequency of use of names transposed in reverse order and obtaining that data.

[0272] "Means for calculating rankings" refers to a function for ranking names and transposed names by prevalence based on frequency of use.

[0273] The "warning list" is information that lists names that are ranked low and is used to warn people.

[0274] "Means of generation" refers to the ability to create new data or lists based on specific conditions.

[0275] The "interface means" refers to a function for displaying the warning list to the user.

[0276] "Means for recognizing the user's emotions" refers to a function for analyzing data such as the user's voice and facial expressions to determine their emotional state.

[0277] "Means for adjusting the interface" refers to a function that changes the way the interface is displayed depending on the user's emotional state.

[0278] The "recording means" refers to a function for saving the user's emotional data.

[0279] The "means for optimizing the attention method" refers to a function for improving the attention method based on the recorded emotion data.

[0280] The present invention is a system for preventing mispronunciation of specific names, and also has the function of recognizing the user's emotions and optimizing alerts. The system of the present invention is intended for use in situations where patients' names are called out in hospitals and medical facilities. This system is realized using the following hardware and software.

[0281] The server first loads the name frequency data. This data is statistical data obtained from CSV files, databases, etc. For example, there are 75,000 occurrences of "Tanaka" and 2,000 occurrences of "Nakata." After loading this data, the server converts it into a Pandas data frame. This allows each name and its frequency of use to be stored in a tabular format for efficient processing.

[0282] Next, the server reverses each name to generate a transposed name. For example, "Tanaka" becomes "Nakada." This is done using string manipulation. The server then checks the frequency of the transposed name and compares the frequency of the original name with the frequency of the transposed name. If the transposed name does not exist, it treats the frequency as zero.

[0283] The server calculates a ranking of names and inversions based on the collected usage frequency data, which evaluates the prevalence of each name. It identifies names with low rankings and adds them to a warning list, which is displayed to users as names requiring caution.

[0284] Furthermore, the system of the present invention is equipped with an emotion engine that recognizes the user's emotions. The server analyzes voice and facial expression data to recognize the user's emotional state. For example, if the user is feeling stressed, the system will recognize this and the terminal will display a warning message in an emphasized manner. Specifically, methods such as increasing the font size or changing the color are used.

[0285] The server also records the user's emotional data and optimizes future alerts based on that data. This data is used to understand the user's preferences and tendencies. Specific software used includes Pandas, a voice recognition library, and OpenCV.

[0286] Specific examples

[0287] Example 1: How to use the name misidentification prevention system

[0288] At a certain hospital, patient A's name is registered in the system as "Tanaka." The server reads the usage frequency data for "Tanaka" and converts it into a Pandas data frame. Then, "Tanaka" is reversed to become "Nakata" and the usage frequency data for the transposed name is investigated. A ranking is calculated and a warning list is generated. This list includes names such as "Tanaka" and is displayed on the terminal to warn the user. If the user is feeling stressed, the terminal will highlight the warning message and display it.

[0289] Example 2: Adaptive interface using emotional data

[0290] When user B is using the system, the server recognizes B's emotional state from voice and facial expression data. If it detects that B is in a stressful state, the device displays a warning message in large letters to emphasize the situation visually.

[0291] Example prompts to input to the generative AI model

[0292] Design a system that issues reminders when patients' names are called in a hospital. Specifically, explain the process of using name frequency data to calculate name transpositions and frequency rankings, and then generating and displaying a reminder list. Also provide an emotion engine function that recognizes the user's emotions and adjusts the interface accordingly. As a concrete example, explain in detail the processing when Tanaka's name is registered.

[0293] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0294] Step 1: Loading name frequency data

[0295] The server retrieves pre-prepared name frequency data from an external CSV file or database. The retrieved data includes names and their frequency of use. Specifically, it reads the CSV file stored on the server and creates a dataset of names and their frequency of use. At this point, the input is the CSV file, and the output is the dataset.

[0296] Step 2: Convert the data into a data frame

[0297] The server converts the name frequency data it retrieves into a Pandas data frame. This keeps each name and its frequency in a tabular format, allowing for efficient processing. The input is the dataset loaded in step 1, and the output is a data frame.

[0298] Step 3: Transpose each name

[0299] The server reverses each name in the data frame to generate a transposed name. For example, "Tanaka" becomes "Nakada." Specifically, it applies an algorithm to reverse the strings of each name in the data frame. The input is a data frame containing the names, and the output is a data frame containing the transposed names.

[0300] Step 4: Frequency of use of transposed names

[0301] The server checks the frequency of use of the transposed name. If the transposed name does not exist, the frequency of use is set to zero. Specifically, the operation checks whether the transposed name exists in the original dataset and obtains the frequency of use. The input is a data frame containing the transposed names, and the output is a data frame with the frequency of use of each transposed name added.

[0302] Step 5: Calculating the rankings

[0303] The server calculates the ranking based on the frequency of use data for the original and transposed names. This evaluates the popularity of each name. Specifically, it applies an algorithm to calculate the ranking of names based on the frequency of use data in the data frame. The input is a data frame with the frequency of use added, and the output is a data frame with the ranking added.

[0304] Step 6: Generate a reminder list

[0305] The server adds names with low rankings (e.g., in the top 75%) to a warning list. Specifically, it filters the ranking data in the data frame and extracts names that require warnings. The input is the data frame with the added rankings, and the output is a warning list.

[0306] Step 7: View the Alert List

[0307] The server sends the generated warning list to the terminal, which then displays the list to the user. Specifically, the warning list is sent to the terminal using a communication means, and the terminal visually displays the list. The input is the warning list, and the output is the displayed warning list.

[0308] Step 8: Recognize the user's emotions

[0309] The server analyzes the voice and facial expression data to recognize the user's emotional state. Specifically, it uses voice and facial expression recognition algorithms to determine the emotional state. The input is the voice and facial expression data, and the output is the recognized emotional state.

[0310] Step 9: Adjusting the Interface

[0311] When a user is feeling stressed, the device displays a highlighted message to alert them. Specific actions include changing the font size and adding a warning sound. The input is the perceived emotional state, and the output is an adjusted user interface.

[0312] Step 10: Record and optimize emotional data

[0313] The server records the user's emotional data and optimizes future reminder methods based on that data. Specifically, it stores the emotional data in a database and analyzes the data to improve the reminder method. The input is the recognized emotional data, and the output is the optimized reminder method.

[0314] (Application example 2)

[0315] 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."

[0316] In workplaces such as factories, mispronouncing the names of parts or materials can lead to reduced work efficiency and quality issues. Furthermore, if appropriate attention is not given in response to the worker's emotional state, there is a risk of increased stress and mistakes. The present invention aims to solve these problems by preventing mispronouncing names and providing optimal attention in response to the worker's emotional state.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0318] In this invention, the server includes means for reading usage frequency data of specific names, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for analyzing the user's emotions and emphasizing warning messages based on the results, and means for recording past emotion data and optimizing future warnings. This prevents mispronunciation of names and enables warnings that match the user's emotions.

[0319] A "specific name" is a name or designation used to identify a specific thing or person.

[0320] "Frequency of use data" is data that indicates how frequently a particular name is used.

[0321] A "server" is a computer system for processing and managing data.

[0322] "Transposing" refers to the operation of rearranging a string of characters in reverse order.

[0323] A "ranking" is an ordering of items based on a particular criterion, or a method of doing so.

[0324] A "warning list" is a list of items that require attention.

[0325] "Interface means" refers to the input and output means by which a user interacts with a system.

[0326] "User" refers to the individual who operates a system or device.

[0327] "Analyzing emotions" refers to analyzing data to recognize the user's emotional state.

[0328] The "warning message" refers to a message intended to alert the user.

[0329] "Past emotion data" is data that indicates the user's previously recorded emotional state.

[0330] "Optimize" refers to adjusting processes and data to their best ability to achieve a specific purpose.

[0331] The present invention relates to a system that prevents mispronunciation of specific names and recognizes the user's emotions to provide optimal attention. This system aims to prevent mispronunciation of parts and materials, particularly in factories, and to provide attention according to the worker's emotional state.

[0332] System configuration

[0333] The system has the following main functions:

[0334] 1. How to read name frequency data

[0335] The server loads pre-prepared specific names and their frequency of use. The data is the names of parts and materials used in the factory and includes their frequency of use.

[0336] 2. Name transposition operation method

[0337] The server reverses each name to generate the transposed name. For example, the part name "PX123" is reversed to become "321XP."

[0338] 3. Frequency of Use Survey Methods

[0339] The server also checks the frequency of use data for the transposed name, and if there is none, treats its frequency of use as zero.

[0340] 4. How the rankings are calculated

[0341] The server calculates a ranking based on the frequency of use of the original and transposed names, thereby assessing the frequency of use of each name.

[0342] 5. How to generate a warning list

[0343] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to the warning list.

[0344] 6. Interface Methods

[0345] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[0346] Emotion engine configuration

[0347] Additionally, the present invention includes an emotion engine that recognizes and responds to user emotions.

[0348] 7. Means of Emotion Analysis

[0349] The server analyzes voice and facial expression data to recognize the user's emotional state. For example, it uses a camera and microphone to capture the user's facial expressions and tone of voice, and analyzes them using an emotion recognition model based on TENSORFLOW (registered trademark).

[0350] 8. A way to reinforce the warning message

[0351] If the user is feeling stressed, the interface means may display a message to alert the user by highlighting it, for example by increasing the font size or adding an audible warning.

[0352] 9. A means of recording past emotional data and optimizing future attention.

[0353] The server records the user's emotional state and optimizes future reminder methods based on past emotional data, thereby providing reminders that best suit the user's emotions.

[0354] Hardware and software used

[0355] Hardware:

[0356] Factory robots (e.g., industrial robots made by company A, company B, etc.)

[0357] display

[0358] Audio / video input devices (microphones, cameras)

[0359] software:

[0360] Python

[0361] Pandas (Data Frame Operations)

[0362] OpenCV (facial expression recognition)

[0363] NLTK (speech analysis)

[0364] TensorFlow (emotion recognition model)

[0365] Specific examples

[0366] For example, if a part is called "PX123" in the factory and is used very frequently, we can reverse the name to "321XP" and calculate a ranking based on the frequency of use of both names. If the ranking is low, we add it to a warning list and display it to the user through the interface.

[0367] The system obtains the user's facial expressions and voice data from the camera and microphone, analyzes them using a TensorFlow model, and if the user is feeling stressed, it increases the text size and displays a message accompanied by a warning sound.

[0368] Prompt Sentence Examples

[0369] Read usage frequency data for a specific name.

[0370] Investigate the frequency of use of transposed names.

[0371] Calculate rankings based on frequency of use.

[0372] Add low ranking names to a warning list.

[0373] Analyze the user's emotional state and emphasize attention-grabbing messages as needed.

[0374] The above is a specific embodiment for carrying out the invention.

[0375] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0376] Step 1:

[0377] The server reads the frequency of use data for a particular name.

[0378] Input: Data file of part and material names and their frequency of use.

[0379] What it does: Reads a data file into a data frame using Python and Pandas.

[0380] Output: A data frame containing the names and their frequency of use.

[0381] Step 2:

[0382] The server transposes each name in reverse order.

[0383] Input: A data frame of loaded names.

[0384] What it does: It runs a process that reverses each name in turn, and adds the transposed names as a new column.

[0385] Output: A data frame containing the original and transposed names.

[0386] Step 3:

[0387] The server investigates the frequency of use of the transposed name.

[0388] Input: A data frame containing the transposed names.

[0389] Operation: Checks whether the transposed name exists in the data frame and gets its frequency of use. If it does not exist, it treats the frequency of use as zero.

[0390] Output: A data frame containing the original names, transposed names, and their frequency of use.

[0391] Step 4:

[0392] The server calculates a ranking based on the frequency of use of the original and transposed names.

[0393] Input: Dataframe with usage frequencies.

[0394] How it works: Calculates the total frequency of use of each name in the data frame and creates a ranking.

[0395] Output: A data frame containing the total frequency and ranking of each name.

[0396] Step 5:

[0397] The server identifies names that are lower in ranking than the original name and generates a warning list.

[0398] Input: Dataframe with rankings.

[0399] How it works: Identifies names that rank in the top 75% or higher and adds them to a warning list.

[0400] Output: A list of warnings.

[0401] Step 6:

[0402] The server transmits the generated reminder list to the terminal, which displays it.

[0403] Input: Reminder list.

[0404] Operation: The warning list is sent to the device and displayed on the device.

[0405] Output: A list of reminders displayed to the user.

[0406] Step 7:

[0407] The server analyzes the user's emotions.

[0408] Input: Voice and facial expression data (obtained from camera and microphone).

[0409] How it works: OpenCV and TensorFlow are used to recognize emotions from acquired data. Audio data is analyzed using NLTK.

[0410] Output: User's emotional state data.

[0411] Step 8:

[0412] The interface means highlights the warning message based on the analysis result.

[0413] Input: User emotional state data.

[0414] How it works: If the user is stressed, it emphasizes the message by making the text larger and adding a warning sound.

[0415] Output: An emphasized warning message.

[0416] Step 9:

[0417] The server records past emotional data and optimizes future alerts.

[0418] Input: User's emotional state data and historical emotional data.

[0419] How it works: Records past emotional data in a database and adjusts future alerts accordingly.

[0420] Output: Optimized reminder system.

[0421] 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.

[0422] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0423] 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.

[0424] [Second embodiment]

[0425] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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).

[0431] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0436] 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."

[0437] This invention is a system for preventing mispronunciation of specific names. This system uses data on the frequency of use of specific names to calculate name transpositions and usage frequency rankings, and generates and displays a warning list. This system is intended for use in situations such as calling out the names of patients in hospitals and medical facilities.

[0438] System Overview

[0439] The system is controlled by a server and has the following main functions:

[0440] 1. Loading name frequency data

[0441] The server reads name frequency data, which indicates how often each name is used.

[0442] 2. Transposition of names

[0443] The server reverses and transposes each name, preparing to identify names that are likely to be mispronounced.

[0444] 3. Frequency of use of transposed names

[0445] The server checks the frequency of the inverted name. If the inverted name exists, it retrieves its frequency data; if it does not exist, it treats the frequency as zero.

[0446] 4. Ranking Calculation

[0447] The server calculates a ranking based on the frequency of use of the names and their inverted names, thereby ranking each name in descending order of popularity.

[0448] 5. Generate a warning list

[0449] The server identifies names that rank lower than the original name and generates a warning list, which lists names that are likely to be mispronounced.

[0450] 6. Display by Interface Means

[0451] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[0452] Specific explanation of program processing

[0453] 1. The server reads the name frequency data

[0454] The server inputs pre-prepared name frequency data into the system, which is in dictionary format and includes information on the names and the number of households where they are used.

[0455] 2. The server performs a transpose operation on each name.

[0456] The server performs string manipulation to reverse each name to generate the inverted name.

[0457] 3. The server checks the frequency of use of the inverted name

[0458] The server checks whether the inverted name exists and obtains the frequency data. If it does not exist, it treats the frequency as zero.

[0459] 4. The server calculates the ranking

[0460] The server calculates a ranking for each name and transposed name based on frequency of use data, with the rankings sorted from highest to lowest frequency of use.

[0461] 5. The server generates a warning list

[0462] The server identifies names that rank lower than the original name and adds them to the warning list.

[0463] 6. The server sends the alert list to the terminal and displays it.

[0464] The server transmits the generated warning list to the terminal, which displays the list, thereby warning the user.

[0465] Specific examples

[0466] For example, if the name data includes "Tanaka," the server reads "Tanaka" and reverse-sorts "Tanaka" to generate "Nakata." It then checks the frequency of use of "Nakata" and calculates the ranking of both names. If "Tanaka" is ranked low, it is added to a warning list. Finally, the server sends this list to the terminal and displays a warning message to the user to avoid accidentally calling "Tanaka" "Nakata."

[0467] The processing flow will be explained below.

[0468] Step 1:

[0469] The server reads name frequency data.

[0470] The server inputs pre-prepared name frequency data into the system. This data contains names and their frequency of use in dictionary format. For example, there are 75,000 households with the name "Tanaka" and 2,000 households with the name "Nakata."

[0471] Step 2:

[0472] The server converts the data into a data frame.

[0473] The server converts the name frequency data it has read into a Pandas data frame, which has each name and its number of households as a row.

[0474] Step 3:

[0475] The server performs the transposition of each name.

[0476] The server reverses each name to generate a transposed name. For example, reverse "Tanaka" to create "Nakatana." This operation is performed for all names.

[0477] Step 4:

[0478] The server checks the frequency of use of the inverted name.

[0479] The server checks the existence of the transposed name and checks its frequency of use. If the transposed name exists, it adds its frequency of use to the data frame; if it does not exist, it treats the frequency of use as zero.

[0480] Step 5:

[0481] The server calculates the ranking.

[0482] The server calculates the ranking of each name, from highest to lowest, based on the frequency of use data for the name and the transposed name. The rankings for the original name and the transposed name are added to a data frame.

[0483] Step 6:

[0484] The server generates a reminder list.

[0485] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to a warning list, which contains names that are prone to mispronunciation based on certain criteria.

[0486] Step 7:

[0487] The server sends the warning list to the terminal and displays it.

[0488] The server sends the generated warning list to the terminal. The terminal receives the list and displays messages and information to warn the user. This allows the user to recognize the risk of mispronouncing names in advance.

[0489] Example 1

[0490] 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."

[0491] When calling patients by name in hospitals and medical facilities, mispronunciations between patients with similar names are common. Such mispronunciations can lead to medical accidents and confusion, and are a major obstacle to providing safe and efficient medical services. The present invention aims to provide a system that calculates name transpositions and rankings based on data on the frequency of use of specific names, and generates and displays a warning list to prevent mispronunciations.

[0492] 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.

[0493] In this invention, the server includes means for reading name usage frequency data, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for acquiring name usage frequency data from a database, means for acquiring the usage frequency of the transposed names from the database, and means for sorting the names in descending order of usage frequency, thereby making it possible to prevent names from being mispronounced.

[0494] "Name usage frequency data" is data that numerically indicates how frequently a particular name is used.

[0495] "Reading means" refers to a function or method by which a server obtains specific data from a database, storage, etc., and makes it available within the system.

[0496] A "transposition means" is a function or method for rearranging a specific string of characters in reverse order. For example, "Tanaka" is converted to "Nakada."

[0497] A "means for investigating frequency of use" is a function or method for obtaining the frequency of use of a specific name from a database or the like.

[0498] The "means for calculating rankings" is a function or method that calculates the ranking of each name based on the collected usage frequency data and rearranges them in descending order of frequency of use.

[0499] The "means for generating a warning list" is a function or method for identifying names that are likely to be mispronounced based on the ranking results and listing them.

[0500] The "interface means" is a function or method for visually displaying the generated reminder list to the user.

[0501] "Means for retrieving from a database" refers to a function or method for searching and retrieving specific data from a database.

[0502] The "means for sorting names in descending order of frequency of use" is a function or method for performing an operation to sort names in descending order of frequency of use based on the data on the frequency of use of the names.

[0503] "Communication means" refers to the method or technology used by the server to transmit data to the terminal, which allows the generated reminder list to be displayed on the terminal.

[0504] The present invention is a system for preventing mispronunciation of specific names. This system has the function of calculating name transpositions and usage frequency rankings based on name usage frequency data, and generating and displaying a warning list. A specific embodiment of this system is described below.

[0505] This system operates among the server, terminals, and users as follows.

[0506] 1. Loading name usage frequency data

[0507] The server retrieves pre-prepared name frequency data from a database. The name frequency data is stored in a MySQL database, and by importing this data, the server can determine how frequently each name is used. For example, this data might record "Tanaka" 30 times and "Nakata" 20 times.

[0508] 2. Name transposition operation

[0509] The server uses string manipulation to reverse the order of each name. For example, "Tanaka" is reversed to become "Nakata." This operation is realized using Python's string manipulation functions.

[0510] 3. Frequency of use of transposed names

[0511] The server retrieves the frequency of use of the transposed name from the database again. For example, it checks whether the transposed name "Nakata" exists and retrieves its frequency of use. If it does not exist, it treats the frequency of use as zero.

[0512] 4. Ranking Calculation

[0513] The server calculates the ranking of each name based on the frequency of use of the original name and the transposed name. The ranking is sorted by frequency of use. The calculation is done using Python's pandas library or similar to sort the data.

[0514] 5. Generate a warning list

[0515] The server then uses the ranking results to identify names that rank lower than the original name and adds them to a warning list, which is used to identify names that are prone to being mispronounced.

[0516] 6. Display of warning list

[0517] The server sends the generated warning list to the terminal, which displays it. The terminal is equipped with a web browser, and data is sent from the server via an HTTP request and displayed in HTML format. This allows the user to visually receive the warning message.

[0518] Specific examples

[0519] For example, if the name data includes "Tanaka," the server reads "Tanaka" and rearranges "Tanaka" in reverse order to generate "Nakata." The server then investigates the frequency of use of "Nakata," and assumes that "Tanaka" is used 30 times and "Nakata" is used 20 times. A ranking is calculated based on this data, and if "Tanaka" is ranked low, it is added to a warning list. Finally, the server sends this list to the device, which displays a warning message to prevent the device from mistakenly calling "Tanaka" "Nakata."

[0520] Examples of prompt statements

[0521] The following are examples of prompts used to test the operation of a system using a generative AI model:

[0522] Enter the name "Tanaka" into the system. Then, obtain the frequency of use data for the transposed name "Nakata" in the same way and calculate the ranking. Finally, if the name "Tanaka" is ranked low, add it to a warning list and display it to the user.

[0523] The present invention provides a system that prevents mispronunciation of names, thereby improving patient safety and quality of service, particularly in hospitals and medical facilities.

[0524] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0525] Step 1:

[0526] The server reads name frequency data. The server retrieves frequency data for specific names from the database. This data contains information on how frequently each name is used. The input is the names stored in the database and their frequency of use, and the output is the frequency data for names loaded into the server's internal memory. As a specific example of how this works, the server uses a SELECT statement from the MySQL database to retrieve the names and their corresponding frequency of use.

[0527] Step 2:

[0528] The server performs a transposition operation on each name. The server rearranges the names in reverse order to generate a new transposed name. The input is the read name, and the output is the transposed version of each name. As a specific example of how it works, the server reverses the names using Python's string manipulation functions.

[0529] Step 3:

[0530] The server checks the frequency of use of the inverted name. The server again retrieves the frequency data of the inverted name from the database. The inverted name is the input, and the frequency data of the inverted name is obtained as the output. If it does not exist, the frequency is treated as zero. As a specific example of operation, the server retrieves the frequency of use of the inverted name from the MySQL database using a SELECT statement, and if it does not exist, it sets it to 0.

[0531] Step 4:

[0532] The server calculates the rankings based on the usage frequency data of the original names and transposed names. The input is the usage frequency data of the original names and transposed names, and the output is the ranking of each name. As a specific example of how it works, the server uses Python's pandas library to sort the usage frequency data and create a ranking.

[0533] Step 5:

[0534] The server generates a warning list. The server identifies the original names that are at the bottom of the rankings and adds them to the warning list. The generated rankings are the input, and the warning list is the output. As a specific example of operation, the server adds names that are at the bottom of the rankings to the list based on a specific threshold.

[0535] Step 6:

[0536] The server sends the warning list to the terminal and displays it. The server sends the generated warning list to the terminal, and the terminal displays it. The input is the generated warning list, and the output is the warning message displayed on the terminal. As a specific example of operation, the server sends the warning list to the terminal using an HTTP request, and the terminal displays the list in HTML format using a web browser.

[0537] (Application example 1)

[0538] 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."

[0539] Mispronouncing certain names can cause confusion and inconvenience to users. In particular, in physical stores, where employees need to efficiently serve many customers in a short amount of time, mispronouncing names can lead to lower customer satisfaction and complaints. Furthermore, with the spread of wearable information devices, there is a demand for dynamic provision of this information.

[0540] 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.

[0541] In this invention, the server includes means for reading usage frequency data of specific names, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, and means for displaying the warning list on a mobile information terminal or wearable information terminal and notifying the user by audio or visual content. This makes it possible to prevent customers from being mispronounced by name and improve the quality of service in physical stores.

[0542] "Data on the frequency of use of a particular name" is statistical data that indicates how frequently a particular name is used.

[0543] The "means for reversing each name" is a process or algorithm for reversing the strings of each name.

[0544] A "means for investigating the frequency of use of a transposed name" is a mechanism for investigating how frequently a transposed name is used.

[0545] A "means for calculating rankings" is an algorithm or system that determines rankings based on frequency of use of the original and transposed names.

[0546] The "means for identifying low-ranking names and generating a warning list" is a process for listing less frequently used names and warning them.

[0547] An "interface means for displaying the reminder list" is a device or software for visually or audibly presenting the reminder list to a user.

[0548] "Means for displaying the warning list on a mobile information terminal or wearable information terminal and notifying the user with audio or visual content" refers to a mechanism for displaying the warning list on a device such as a smartphone or smart glasses and alerting the user with audio or visual messages.

[0549] This invention is a system that prevents mispronouncing specific names. This system is intended for use in brick-and-mortar stores, and generates and displays a list of reminders to prevent employees from mispronouncing customers' names.

[0550] System Configuration

[0551] This system consists of a server, a mobile information terminal (smartphone), and a wearable information terminal (smart glasses or head-mounted display). Each device plays the following role:

[0552] 1. Server

[0553] Loading name frequency data: The server loads the frequency data for a specific name from the database and imports it into the system.

[0554] Transpose each name: The server reverses each name using string manipulation.

[0555] Checking the frequency of use of the transposed name: The server checks the frequency of use of the transposed name from the database and obtains the frequency data if it exists.

[0556] Calculating Ranking: The server calculates a ranking based on the name and inverted name to assess the popularity of the name.

[0557] Generate a warning list: The server identifies names that are ranked lower than the original name and generates a warning list.

[0558] Communication means: The server transmits the generated alert list to the mobile information terminal or wearable information terminal.

[0559] 2. Portable and wearable information terminals

[0560] Interface means: The mobile information terminal or wearable information terminal displays the alert list and notifies the user with audio or visual content.

[0561] Specific explanation of the process

[0562] 1. Loading name frequency data: The server loads name frequency data from the database. This data is stored in a dictionary format, with the key being the name and the value being the frequency of use.

[0563] 2. Generate a transposed version of each name: The server applies an algorithm to reverse the names and generates the transposed version. This is done using a programming language such as Python.

[0564] 3. Frequency check of transposed name: Check whether the transposed name exists in the database and get its frequency of use. If it does not exist, treat the frequency as zero.

[0565] 4. Calculate Ranking: The server calculates the ranking based on the frequency of use of the names and transposed names. This ranking is generated by sorting the frequency of use of each name from most to least frequent.

[0566] 5. Generate Reminder List: The server identifies less frequently used names and adds them to the reminder list.

[0567] 6. Displaying the list on the device and notifying users: The alert list is sent to smartphones or smart glasses, and these devices notify users with voice messages and visual content.

[0568] Specific examples

[0569] For example, suppose the names of customers waiting at a store are "Tanaka" (used 50 times), "Yamada" (used 30 times), "Nakata" (used 20 times), and "Sato" (used 60 times). The server reverses "Tanaka" to generate "Nakata" and adds up the frequency of both (70 times). Ultimately, "Tanaka" is not included in the warning list because it is ranked high.

[0570] Prompt Sentence Examples

[0571] Create a reminder system to prevent mispronunciation of names. Name data is provided in the following format: "Tanaka": 50, "Yamada": 30, "Nakata": 20, "Sato": 60. Sort the names in reverse order, investigate the frequency of their transpositions, and generate a reminder list based on the frequency of each name and its transpositions. The list should contain names that are used 10 times or less.

[0572] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0573] Step 1:

[0574] The server reads name frequency data. This data is retrieved from the database and stored in dictionary format. The input is the database connection information and query, and the output is dictionary data of names and their frequency of use. Specifically, the server connects to the database and retrieves the data by executing an SQL query such as "SELECT name, frequency FROM name_data".

[0575] Step 2:

[0576] The server transposes each name in reverse order. The input is the dictionary of name data obtained in step 1, and the output is the dictionary data of the transposed names. Specifically, each name is reversed using string manipulation and stored as a transposed name in a new dictionary. For example, "Tanaka" is transposed to "Nakata."

[0577] Step 3:

[0578] The server checks the frequency of the inverted name. The input is the dictionary of the inverted names from step 2, and the output is a dictionary with the frequency of the inverted name added. Specifically, it checks whether the inverted name exists in the database, and if so, obtains its frequency; if not, it sets the frequency to zero.

[0579] Step 4:

[0580] The server calculates the ranking based on the frequency of use of the name and transposed name. The input is the frequency data of the name and transposed name obtained in step 3, and the output is a ranking list based on frequency. Specifically, an algorithm is applied to sort the names in descending order of frequency to generate the ranking list.

[0581] Step 5:

[0582] The server identifies the names with low rankings and generates a warning list. The input is the ranking list from step 4, and the output is the warning list. Specifically, it lists names whose frequency of use is below a certain threshold and adds them to the warning list.

[0583] Step 6:

[0584] The server sends the alert list to the mobile or wearable information terminal. The input is the alert list from step 5, and the output is a message to be displayed on the user's device. Specifically, the generated alert list is distributed to smartphones or smart glasses, and these devices notify the user with audio or visual messages.

[0585] Step 7:

[0586] The user checks the warning list through a mobile information terminal or wearable information terminal. The input is the warning list sent to the terminal, and the output is the displayed list and the notification message. Specifically, the user can check the list by operating a smartphone or smart glasses and take measures to prevent mispronunciation of names.

[0587] 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.

[0588] This invention is a system for preventing mispronunciation of specific names, and also includes an emotion engine that recognizes the user's emotions and optimizes alerts. This system uses data on the frequency of use of specific names to calculate name transpositions and usage frequency rankings, and generates and displays an alert list. This system is intended for use in situations where patients are called by name in hospitals, medical facilities, etc.

[0589] System Overview

[0590] The system is controlled by a server and has the following main functions:

[0591] 1. Loading name usage frequency data

[0592] The server reads data on the frequency of name usage. For example, the statistical data shows that "Tanaka" is used in 75,000 households and "Nakata" in 2,000 households.

[0593] 2. Transposition of names

[0594] The server reverses each name to generate the transposed name. For example, "Tanaka" is reversed to become "Nakata."

[0595] 3. Frequency of use of transposed names

[0596] The server checks the frequency of use of the transposed name. If the transposed name exists, it obtains its frequency data; if it does not exist, it treats the frequency as zero.

[0597] 4. Ranking Calculation

[0598] The server calculates the ranking based on the frequency of use data for names and transposed names, thereby ranking each name in descending order of popularity.

[0599] 5. Generate a warning list

[0600] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to the warning list.

[0601] 6. Display by Interface Means

[0602] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[0603] Additional features of the Emotion Engine

[0604] In addition, the present invention is equipped with an emotion engine that analyzes the user's emotions, optimizing the effectiveness of the alert.

[0605] 7. Emotion engine that recognizes user emotions

[0606] The server analyzes voice and facial expression data to recognize the user's emotional state, and the results are used to emphasize alerts.

[0607] 8. Interface adjustment based on emotional state

[0608] If the user is feeling stressed, the device will display a warning message more prominently, by increasing the font size or changing the color.

[0609] 9. Recording emotional data and optimizing future alerts

[0610] The server records the user's emotional state and optimizes future reminders based on past emotional data. This record is used to understand the user's preferences and tendencies.

[0611] Specific explanation of program processing

[0612] 1. The server reads the name frequency data

[0613] The server reads pre-prepared name usage frequency data and inputs it into the system.

[0614] 2. The server converts the data into a data frame

[0615] Convert the read data into a Pandas data frame, with each name and its frequency as a row.

[0616] 3. The server performs a transposition operation on each name.

[0617] Using string manipulation, each name is rearranged in reverse order to generate the transposed name.

[0618] 4. The server checks the frequency of use of the inverted name

[0619] The server checks whether the transposed name exists and obtains its frequency of use data. If it does not exist, it treats the frequency of use as zero.

[0620] 5. The server calculates the ranking

[0621] Based on the frequency of use data, calculate the ranking of each name and add it to the data frame.

[0622] 6. The server generates a warning list

[0623] Identify names with lower rankings and add them to a warning list.

[0624] 7. The server sends the alert list to the device and displays it.

[0625] The server sends the reminder list to the terminal, which displays it.

[0626] Explanation of how the emotion engine works

[0627] 8. The server recognizes the user's emotions

[0628] The server analyzes voice and facial expression data to recognize the user's emotional state.

[0629] For example: If the user is feeling stressed, the system will recognize this.

[0630] 9. Devices will adjust their interfaces based on user emotions

[0631] If the user is feeling stressed, the device will display a message to alert them by highlighting it, for example by making the text larger or adding a warning sound.

[0632] 10. The server records emotional data and optimizes future reminders based on that data.

[0633] The system records past emotional data and adjusts future alert methods based on that data, allowing it to provide alerts that best suit the user's emotions.

[0634] The processing flow will be explained below.

[0635] Step 1:

[0636] The server reads name frequency data.

[0637] The server reads the frequency data for specific names from a pre-prepared data file and inputs it into the system as a large dictionary-style data set, which includes each name and its frequency of use.

[0638] Step 2:

[0639] The server converts the data into a data frame.

[0640] The server converts the data it reads into a Pandas data frame, which stores each name and its frequency as a row. This operation makes it easier to process the data.

[0641] Step 3:

[0642] The server performs the transposition of each name.

[0643] The server generates the inverted name by reversing each name, e.g., changing "Tanaka" to "Nakada." This operation is performed for every name in the data frame, and a new inverted name column is added.

[0644] Step 4:

[0645] The server checks the frequency of use of the inverted name.

[0646] The server checks the frequency of use of the generated inverted name. If the inverted name does not exist, the frequency of use is treated as zero. The frequency of use of the inverted name is added to the data frame.

[0647] Step 5:

[0648] The server calculates the ranking.

[0649] The server calculates the ranking based on the frequency of use data for the original and transposed names. This results in the names being ranked in order of most or least frequently used. Add a ranking column to the data frame.

[0650] Step 6:

[0651] The server generates a reminder list.

[0652] The server identifies names that rank lower than the original name and generates a warning list. Specifically, it lists names that rank in the top 75% or higher of the total. This list includes names that are prone to being mispronounced.

[0653] Step 7:

[0654] The server sends the warning list to the terminal and displays it.

[0655] The server sends the generated reminder list to the terminal, which displays the list. When the user calls a name, the list is referenced and a reminder message is displayed to prevent mistakes.

[0656] Step 8:

[0657] The server acquires data to recognize the user's emotions, which are then analyzed by the emotion engine.

[0658] The server collects the user's voice and facial expression data and passes it to the emotion engine, which analyzes this data and determines the user's emotional state. For example, it recognizes states such as stress, impatience, and excitement.

[0659] Step 9:

[0660] An emotional engine adjusts the interface based on the user's emotional state.

[0661] The emotion engine dynamically adjusts the device's display based on the user's emotional state. For example, if the user is feeling stressed, the device will highlight a warning message by increasing the font size, changing the color to red, or adding an audible warning.

[0662] Step 10:

[0663] The server records emotional data and optimizes future alerts.

[0664] The server records the user's emotional data and optimizes future reminders based on past emotional state data, thereby providing the most effective reminder for the user. For example, it may emphasize reminders during times when the user has experienced a lot of stress in the past.

[0665] Example 2

[0666] 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."

[0667] In hospitals and medical facilities, mispronunciations and misidentifications of patients' names can occur when calling them by name. This can cause confusion and stress for patients and medical staff. Furthermore, there is a lack of means to properly grasp the user's emotions and optimize alerts based on them. To solve these problems, a system is needed that can prevent mispronunciation of specific names and provide optimal alerts according to the user's emotional state.

[0668] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0669] In this invention, the server includes means for reading name usage frequency data, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequencies of the original names and the transposed names, means for identifying names ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for recognizing the user's emotions, means for adjusting the interface based on the user's emotions, and means for recording the user's emotion data and optimizing the warning method based on the data. This makes it possible to prevent mispronunciation of names and to provide optimal warnings according to the user's emotions.

[0670] "Name usage frequency data" refers to information indicating how often a particular name is used.

[0671] "Reading means" refers to the function for acquiring data from outside and importing it into the server.

[0672] The "means for transposing each name in reverse order" refers to a function for rearranging names in reverse order to generate a new name.

[0673] "Means for investigating the frequency of use of transposed names" refers to a function for checking the frequency of use of names transposed in reverse order and obtaining that data.

[0674] "Means for calculating rankings" refers to a function for ranking names and transposed names by prevalence based on frequency of use.

[0675] The "warning list" is information that lists names that are ranked low and is used to warn people.

[0676] "Means of generation" refers to the ability to create new data or lists based on specific conditions.

[0677] The "interface means" refers to a function for displaying the warning list to the user.

[0678] "Means for recognizing the user's emotions" refers to a function for analyzing data such as the user's voice and facial expressions to determine their emotional state.

[0679] "Means for adjusting the interface" refers to a function that changes the way the interface is displayed depending on the user's emotional state.

[0680] The "recording means" refers to a function for saving the user's emotional data.

[0681] The "means for optimizing the attention method" refers to a function for improving the attention method based on the recorded emotion data.

[0682] The present invention is a system for preventing mispronunciation of specific names, and also has the function of recognizing the user's emotions and optimizing alerts. The system of the present invention is intended for use in situations where patients' names are called out in hospitals and medical facilities. This system is realized using the following hardware and software.

[0683] The server first loads the name frequency data. This data is statistical data obtained from CSV files, databases, etc. For example, there are 75,000 occurrences of "Tanaka" and 2,000 occurrences of "Nakata." After loading this data, the server converts it into a Pandas data frame. This allows each name and its frequency of use to be stored in a tabular format for efficient processing.

[0684] Next, the server reverses each name to generate a transposed name. For example, "Tanaka" becomes "Nakada." This is done using string manipulation. The server then checks the frequency of the transposed name and compares the frequency of the original name with the frequency of the transposed name. If the transposed name does not exist, it treats the frequency as zero.

[0685] The server calculates a ranking of names and inversions based on the collected usage frequency data, which evaluates the prevalence of each name. It identifies names with low rankings and adds them to a warning list, which is displayed to users as names requiring caution.

[0686] Furthermore, the system of the present invention is equipped with an emotion engine that recognizes the user's emotions. The server analyzes voice and facial expression data to recognize the user's emotional state. For example, if the user is feeling stressed, the system will recognize this and the terminal will display a warning message in an emphasized manner. Specifically, methods such as increasing the font size or changing the color are used.

[0687] The server also records the user's emotional data and optimizes future alerts based on that data. This data is used to understand the user's preferences and tendencies. Specific software used includes Pandas, a voice recognition library, and OpenCV.

[0688] Specific examples

[0689] Example 1: How to use the name misidentification prevention system

[0690] At a certain hospital, patient A's name is registered in the system as "Tanaka." The server reads the usage frequency data for "Tanaka" and converts it into a Pandas data frame. Then, "Tanaka" is reversed to become "Nakata" and the usage frequency data for the transposed name is investigated. A ranking is calculated and a warning list is generated. This list includes names such as "Tanaka" and is displayed on the terminal to warn the user. If the user is feeling stressed, the terminal will highlight the warning message and display it.

[0691] Example 2: Adaptive interface using emotional data

[0692] When user B is using the system, the server recognizes B's emotional state from voice and facial expression data. If it detects that B is in a stressful state, the device displays a warning message in large letters to emphasize the situation visually.

[0693] Example prompts to input to the generative AI model

[0694] Design a system that issues reminders when patients' names are called in a hospital. Specifically, explain the process of using name frequency data to calculate name transpositions and frequency rankings, and then generating and displaying a reminder list. Also provide an emotion engine function that recognizes the user's emotions and adjusts the interface accordingly. As a concrete example, explain in detail the processing when Tanaka's name is registered.

[0695] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0696] Step 1: Loading name frequency data

[0697] The server retrieves pre-prepared name frequency data from an external CSV file or database. The retrieved data includes names and their frequency of use. Specifically, it reads the CSV file stored on the server and creates a dataset of names and their frequency of use. At this point, the input is the CSV file, and the output is the dataset.

[0698] Step 2: Convert the data into a data frame

[0699] The server converts the name frequency data it retrieves into a Pandas data frame. This keeps each name and its frequency in a tabular format, allowing for efficient processing. The input is the dataset loaded in step 1, and the output is a data frame.

[0700] Step 3: Transpose each name

[0701] The server reverses each name in the data frame to generate a transposed name. For example, "Tanaka" becomes "Nakada." Specifically, it applies an algorithm to reverse the strings of each name in the data frame. The input is a data frame containing the names, and the output is a data frame containing the transposed names.

[0702] Step 4: Frequency of use of transposed names

[0703] The server checks the frequency of use of the transposed name. If the transposed name does not exist, the frequency of use is set to zero. Specifically, the operation checks whether the transposed name exists in the original dataset and obtains the frequency of use. The input is a data frame containing the transposed names, and the output is a data frame with the frequency of use of each transposed name added.

[0704] Step 5: Calculating the rankings

[0705] The server calculates the ranking based on the frequency of use data for the original and transposed names. This evaluates the popularity of each name. Specifically, it applies an algorithm to calculate the ranking of names based on the frequency of use data in the data frame. The input is a data frame with the frequency of use added, and the output is a data frame with the ranking added.

[0706] Step 6: Generate a reminder list

[0707] The server adds names with low rankings (e.g., in the top 75%) to a warning list. Specifically, it filters the ranking data in the data frame and extracts names that require warnings. The input is the data frame with the added rankings, and the output is a warning list.

[0708] Step 7: View the Alert List

[0709] The server sends the generated warning list to the terminal, which then displays the list to the user. Specifically, the warning list is sent to the terminal using a communication means, and the terminal visually displays the list. The input is the warning list, and the output is the displayed warning list.

[0710] Step 8: Recognize the user's emotions

[0711] The server analyzes the voice and facial expression data to recognize the user's emotional state. Specifically, it uses voice and facial expression recognition algorithms to determine the emotional state. The input is the voice and facial expression data, and the output is the recognized emotional state.

[0712] Step 9: Adjusting the Interface

[0713] When a user is feeling stressed, the device displays a highlighted message to alert them. Specific actions include changing the font size and adding a warning sound. The input is the perceived emotional state, and the output is an adjusted user interface.

[0714] Step 10: Record and optimize emotional data

[0715] The server records the user's emotional data and optimizes future reminder methods based on that data. Specifically, it stores the emotional data in a database and analyzes the data to improve the reminder method. The input is the recognized emotional data, and the output is the optimized reminder method.

[0716] (Application example 2)

[0717] 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."

[0718] In workplaces such as factories, mispronouncing the names of parts or materials can lead to reduced work efficiency and quality issues. Furthermore, if appropriate attention is not given in response to the worker's emotional state, there is a risk of increased stress and mistakes. The present invention aims to solve these problems by preventing mispronouncing names and providing optimal attention in response to the worker's emotional state.

[0719] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0720] In this invention, the server includes means for reading usage frequency data of specific names, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for analyzing the user's emotions and emphasizing warning messages based on the results, and means for recording past emotion data and optimizing future warnings. This prevents mispronunciation of names and enables warnings that match the user's emotions.

[0721] A "specific name" is a name or designation used to identify a specific thing or person.

[0722] "Frequency of use data" is data that indicates how frequently a particular name is used.

[0723] A "server" is a computer system for processing and managing data.

[0724] "Transposing" refers to the operation of rearranging a string of characters in reverse order.

[0725] A "ranking" is an ordering of items based on a particular criterion, or a method of doing so.

[0726] A "warning list" is a list of items that require attention.

[0727] "Interface means" refers to the input and output means by which a user interacts with a system.

[0728] "User" refers to the individual who operates a system or device.

[0729] "Analyzing emotions" refers to analyzing data to recognize the user's emotional state.

[0730] The "warning message" refers to a message intended to alert the user.

[0731] "Past emotion data" is data that indicates the user's previously recorded emotional state.

[0732] "Optimize" refers to adjusting processes and data to their best ability to achieve a specific purpose.

[0733] The present invention relates to a system that prevents mispronunciation of specific names and recognizes the user's emotions to provide optimal attention. This system aims to prevent mispronunciation of parts and materials, particularly in factories, and to provide attention according to the worker's emotional state.

[0734] System configuration

[0735] The system has the following main functions:

[0736] 1. How to read name frequency data

[0737] The server loads pre-prepared specific names and their frequency of use. The data is the names of parts and materials used in the factory and includes their frequency of use.

[0738] 2. Name transposition operation method

[0739] The server reverses each name to generate the transposed name. For example, the part name "PX123" is reversed to become "321XP."

[0740] 3. Frequency of Use Survey Methods

[0741] The server also checks the frequency of use data for the transposed name, and if there is none, treats its frequency of use as zero.

[0742] 4. How the rankings are calculated

[0743] The server calculates a ranking based on the frequency of use of the original and transposed names, thereby assessing the frequency of use of each name.

[0744] 5. How to generate a warning list

[0745] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to the warning list.

[0746] 6. Interface Methods

[0747] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[0748] Emotion engine configuration

[0749] Additionally, the present invention includes an emotion engine that recognizes and responds to user emotions.

[0750] 7. Means of Emotion Analysis

[0751] The server analyzes voice and facial expression data to recognize the user's emotional state. For example, it uses a camera and microphone to capture the user's facial expressions and tone of voice, and analyzes them using an emotion recognition model using TensorFlow.

[0752] 8. A way to reinforce the warning message

[0753] If the user is feeling stressed, the interface means may display a message to alert the user by highlighting it, for example by increasing the font size or adding an audible warning.

[0754] 9. A means of recording past emotional data and optimizing future attention.

[0755] The server records the user's emotional state and optimizes future reminder methods based on past emotional data, thereby providing reminders that best suit the user's emotions.

[0756] Hardware and software used

[0757] Hardware:

[0758] Factory robots (e.g., industrial robots made by company A, company B, etc.)

[0759] display

[0760] Audio / video input devices (microphones, cameras)

[0761] software:

[0762] Python

[0763] Pandas (Data Frame Operations)

[0764] OpenCV (facial expression recognition)

[0765] NLTK (speech analysis)

[0766] TensorFlow (emotion recognition model)

[0767] Specific examples

[0768] For example, if a part is called "PX123" in the factory and is used very frequently, we can reverse the name to "321XP" and calculate a ranking based on the frequency of use of both names. If the ranking is low, we add it to a warning list and display it to the user through the interface.

[0769] The system obtains the user's facial expressions and voice data from the camera and microphone, analyzes them using a TensorFlow model, and if the user is feeling stressed, it increases the text size and displays a message accompanied by a warning sound.

[0770] Prompt Sentence Examples

[0771] Read usage frequency data for a specific name.

[0772] Investigate the frequency of use of transposed names.

[0773] Calculate rankings based on frequency of use.

[0774] Add low ranking names to a warning list.

[0775] Analyze the user's emotional state and emphasize attention-grabbing messages as needed.

[0776] The above is a specific embodiment for carrying out the invention.

[0777] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0778] Step 1:

[0779] The server reads the frequency of use data for a particular name.

[0780] Input: Data file of part and material names and their frequency of use.

[0781] What it does: Reads a data file into a data frame using Python and Pandas.

[0782] Output: A data frame containing the names and their frequency of use.

[0783] Step 2:

[0784] The server transposes each name in reverse order.

[0785] Input: A data frame of loaded names.

[0786] What it does: It runs a process that reverses each name in turn, and adds the transposed names as a new column.

[0787] Output: A data frame containing the original and transposed names.

[0788] Step 3:

[0789] The server investigates the frequency of use of the transposed name.

[0790] Input: A data frame containing the transposed names.

[0791] Operation: Checks whether the transposed name exists in the data frame and gets its frequency of use. If it does not exist, it treats the frequency of use as zero.

[0792] Output: A data frame containing the original names, transposed names, and their frequency of use.

[0793] Step 4:

[0794] The server calculates a ranking based on the frequency of use of the original and transposed names.

[0795] Input: Dataframe with usage frequencies.

[0796] How it works: Calculates the total frequency of use of each name in the data frame and creates a ranking.

[0797] Output: A data frame containing the total frequency and ranking of each name.

[0798] Step 5:

[0799] The server identifies names that are lower in ranking than the original name and generates a warning list.

[0800] Input: Dataframe with rankings.

[0801] How it works: Identifies names that rank in the top 75% or higher and adds them to a warning list.

[0802] Output: A list of warnings.

[0803] Step 6:

[0804] The server transmits the generated reminder list to the terminal, which displays it.

[0805] Input: Reminder list.

[0806] Operation: The warning list is sent to the device and displayed on the device.

[0807] Output: A list of reminders displayed to the user.

[0808] Step 7:

[0809] The server analyzes the user's emotions.

[0810] Input: Voice and facial expression data (obtained from camera and microphone).

[0811] How it works: OpenCV and TensorFlow are used to recognize emotions from acquired data. Audio data is analyzed using NLTK.

[0812] Output: User's emotional state data.

[0813] Step 8:

[0814] The interface means highlights the warning message based on the analysis result.

[0815] Input: User emotional state data.

[0816] How it works: If the user is stressed, it emphasizes the message by making the text larger and adding a warning sound.

[0817] Output: An emphasized warning message.

[0818] Step 9:

[0819] The server records past emotional data and optimizes future alerts.

[0820] Input: User's emotional state data and historical emotional data.

[0821] How it works: Records past emotional data in a database and adjusts future alerts accordingly.

[0822] Output: Optimized reminder system.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] [Third embodiment]

[0827] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0828] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0829] 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).

[0830] 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.

[0831] 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.

[0832] 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).

[0833] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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."

[0839] This invention is a system for preventing mispronunciation of specific names. This system uses data on the frequency of use of specific names to calculate name transpositions and usage frequency rankings, and generates and displays a warning list. This system is intended for use in situations such as calling out the names of patients in hospitals and medical facilities.

[0840] System Overview

[0841] The system is controlled by a server and has the following main functions:

[0842] 1. Loading name frequency data

[0843] The server reads name frequency data, which indicates how often each name is used.

[0844] 2. Transposition of names

[0845] The server reverses and transposes each name, preparing to identify names that are likely to be mispronounced.

[0846] 3. Frequency of use of transposed names

[0847] The server checks the frequency of the inverted name. If the inverted name exists, it retrieves its frequency data; if it does not exist, it treats the frequency as zero.

[0848] 4. Ranking Calculation

[0849] The server calculates a ranking based on the frequency of use of the names and their inverted names, thereby ranking each name in descending order of popularity.

[0850] 5. Generate a warning list

[0851] The server identifies names that rank lower than the original name and generates a warning list, which lists names that are likely to be mispronounced.

[0852] 6. Display by Interface Means

[0853] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[0854] Specific explanation of program processing

[0855] 1. The server reads the name frequency data

[0856] The server inputs pre-prepared name frequency data into the system, which is in dictionary format and includes information on the names and the number of households where they are used.

[0857] 2. The server performs a transpose operation on each name.

[0858] The server performs string manipulation to reverse each name to generate the inverted name.

[0859] 3. The server checks the frequency of use of the inverted name

[0860] The server checks whether the inverted name exists and obtains the frequency data. If it does not exist, it treats the frequency as zero.

[0861] 4. The server calculates the ranking

[0862] The server calculates a ranking for each name and transposed name based on frequency of use data, with the rankings sorted from highest to lowest frequency of use.

[0863] 5. The server generates a warning list

[0864] The server identifies names that rank lower than the original name and adds them to the warning list.

[0865] 6. The server sends the alert list to the terminal and displays it.

[0866] The server transmits the generated warning list to the terminal, which displays the list, thereby warning the user.

[0867] Specific examples

[0868] For example, if the name data includes "Tanaka," the server reads "Tanaka" and reverse-sorts "Tanaka" to generate "Nakata." It then checks the frequency of use of "Nakata" and calculates the ranking of both names. If "Tanaka" is ranked low, it is added to a warning list. Finally, the server sends this list to the terminal and displays a warning message to the user to avoid accidentally calling "Tanaka" "Nakata."

[0869] The processing flow will be explained below.

[0870] Step 1:

[0871] The server reads name frequency data.

[0872] The server inputs pre-prepared name frequency data into the system. This data contains names and their frequency of use in dictionary format. For example, there are 75,000 households with the name "Tanaka" and 2,000 households with the name "Nakata."

[0873] Step 2:

[0874] The server converts the data into a data frame.

[0875] The server converts the name frequency data it has read into a Pandas data frame, which has each name and its number of households as a row.

[0876] Step 3:

[0877] The server performs the transposition of each name.

[0878] The server reverses each name to generate a transposed name. For example, reverse "Tanaka" to create "Nakatana." This operation is performed for all names.

[0879] Step 4:

[0880] The server checks the frequency of use of the inverted name.

[0881] The server checks the existence of the transposed name and checks its frequency of use. If the transposed name exists, it adds its frequency of use to the data frame; if it does not exist, it treats the frequency of use as zero.

[0882] Step 5:

[0883] The server calculates the ranking.

[0884] The server calculates the ranking of each name, from highest to lowest, based on the frequency of use data for the name and the transposed name. The rankings for the original name and the transposed name are added to a data frame.

[0885] Step 6:

[0886] The server generates a reminder list.

[0887] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to a warning list, which contains names that are prone to mispronunciation based on certain criteria.

[0888] Step 7:

[0889] The server sends the warning list to the terminal and displays it.

[0890] The server sends the generated warning list to the terminal. The terminal receives the list and displays messages and information to warn the user. This allows the user to recognize the risk of mispronouncing names in advance.

[0891] Example 1

[0892] 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."

[0893] When calling patients by name in hospitals and medical facilities, mispronunciations between patients with similar names are common. Such mispronunciations can lead to medical accidents and confusion, and are a major obstacle to providing safe and efficient medical services. The present invention aims to provide a system that calculates name transpositions and rankings based on data on the frequency of use of specific names, and generates and displays a warning list to prevent mispronunciations.

[0894] 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.

[0895] In this invention, the server includes means for reading name usage frequency data, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for acquiring name usage frequency data from a database, means for acquiring the usage frequency of the transposed names from the database, and means for sorting the names in descending order of usage frequency, thereby making it possible to prevent names from being mispronounced.

[0896] "Name usage frequency data" is data that numerically indicates how frequently a particular name is used.

[0897] "Reading means" refers to a function or method by which a server obtains specific data from a database, storage, etc., and makes it available within the system.

[0898] A "transposition means" is a function or method for rearranging a specific string of characters in reverse order. For example, "Tanaka" is converted to "Nakada."

[0899] A "means for investigating frequency of use" is a function or method for obtaining the frequency of use of a specific name from a database or the like.

[0900] The "means for calculating rankings" is a function or method that calculates the ranking of each name based on the collected usage frequency data and rearranges them in descending order of frequency of use.

[0901] The "means for generating a warning list" is a function or method for identifying names that are likely to be mispronounced based on the ranking results and listing them.

[0902] The "interface means" is a function or method for visually displaying the generated reminder list to the user.

[0903] "Means for retrieving from a database" refers to a function or method for searching and retrieving specific data from a database.

[0904] The "means for sorting names in descending order of frequency of use" is a function or method for performing an operation to sort names in descending order of frequency of use based on the data on the frequency of use of the names.

[0905] "Communication means" refers to the method or technology used by the server to transmit data to the terminal, which allows the generated reminder list to be displayed on the terminal.

[0906] The present invention is a system for preventing mispronunciation of specific names. This system has the function of calculating name transpositions and usage frequency rankings based on name usage frequency data, and generating and displaying a warning list. A specific embodiment of this system is described below.

[0907] This system operates among the server, terminals, and users as follows.

[0908] 1. Loading name usage frequency data

[0909] The server retrieves pre-prepared name frequency data from a database. The name frequency data is stored in a MySQL database, and by importing this data, the server can determine how frequently each name is used. For example, this data might record "Tanaka" 30 times and "Nakata" 20 times.

[0910] 2. Name transposition operation

[0911] The server uses string manipulation to reverse the order of each name. For example, "Tanaka" is reversed to become "Nakata." This operation is realized using Python's string manipulation functions.

[0912] 3. Frequency of use of transposed names

[0913] The server retrieves the frequency of use of the transposed name from the database again. For example, it checks whether the transposed name "Nakata" exists and retrieves its frequency of use. If it does not exist, it treats the frequency of use as zero.

[0914] 4. Ranking Calculation

[0915] The server calculates the ranking of each name based on the frequency of use of the original name and the transposed name. The ranking is sorted by frequency of use. The calculation is done using Python's pandas library or similar to sort the data.

[0916] 5. Generate a warning list

[0917] The server then uses the ranking results to identify names that rank lower than the original name and adds them to a warning list, which is used to identify names that are prone to being mispronounced.

[0918] 6. Display of warning list

[0919] The server sends the generated warning list to the terminal, which displays it. The terminal is equipped with a web browser, and data is sent from the server via an HTTP request and displayed in HTML format. This allows the user to visually receive the warning message.

[0920] Specific examples

[0921] For example, if the name data includes "Tanaka," the server reads "Tanaka" and rearranges "Tanaka" in reverse order to generate "Nakata." The server then investigates the frequency of use of "Nakata," and assumes that "Tanaka" is used 30 times and "Nakata" is used 20 times. A ranking is calculated based on this data, and if "Tanaka" is ranked low, it is added to a warning list. Finally, the server sends this list to the device, which displays a warning message to prevent the device from mistakenly calling "Tanaka" "Nakata."

[0922] Examples of prompt statements

[0923] The following are examples of prompts used to test the operation of a system using a generative AI model:

[0924] Enter the name "Tanaka" into the system. Then, obtain the frequency of use data for the transposed name "Nakata" in the same way and calculate the ranking. Finally, if the name "Tanaka" is ranked low, add it to a warning list and display it to the user.

[0925] The present invention provides a system that prevents mispronunciation of names, thereby improving patient safety and quality of service, particularly in hospitals and medical facilities.

[0926] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0927] Step 1:

[0928] The server reads name frequency data. The server retrieves frequency data for specific names from the database. This data contains information on how frequently each name is used. The input is the names stored in the database and their frequency of use, and the output is the frequency data for names loaded into the server's internal memory. As a specific example of how this works, the server uses a SELECT statement from the MySQL database to retrieve the names and their corresponding frequency of use.

[0929] Step 2:

[0930] The server performs a transposition operation on each name. The server rearranges the names in reverse order to generate a new transposed name. The input is the read name, and the output is the transposed version of each name. As a specific example of how it works, the server reverses the names using Python's string manipulation functions.

[0931] Step 3:

[0932] The server checks the frequency of use of the inverted name. The server again retrieves the frequency data of the inverted name from the database. The inverted name is the input, and the frequency data of the inverted name is obtained as the output. If it does not exist, the frequency is treated as zero. As a specific example of operation, the server retrieves the frequency of use of the inverted name from the MySQL database using a SELECT statement, and if it does not exist, it sets it to 0.

[0933] Step 4:

[0934] The server calculates the rankings based on the usage frequency data of the original names and transposed names. The input is the usage frequency data of the original names and transposed names, and the output is the ranking of each name. As a specific example of how it works, the server uses Python's pandas library to sort the usage frequency data and create a ranking.

[0935] Step 5:

[0936] The server generates a warning list. The server identifies the original names that are at the bottom of the rankings and adds them to the warning list. The generated rankings are the input, and the warning list is the output. As a specific example of operation, the server adds names that are at the bottom of the rankings to the list based on a specific threshold.

[0937] Step 6:

[0938] The server sends the warning list to the terminal and displays it. The server sends the generated warning list to the terminal, and the terminal displays it. The input is the generated warning list, and the output is the warning message displayed on the terminal. As a specific example of operation, the server sends the warning list to the terminal using an HTTP request, and the terminal displays the list in HTML format using a web browser.

[0939] (Application example 1)

[0940] 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."

[0941] Mispronouncing certain names can cause confusion and inconvenience to users. In particular, in physical stores, where employees need to efficiently serve many customers in a short amount of time, mispronouncing names can lead to lower customer satisfaction and complaints. Furthermore, with the spread of wearable information devices, there is a demand for dynamic provision of this information.

[0942] 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.

[0943] In this invention, the server includes means for reading usage frequency data of specific names, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, and means for displaying the warning list on a mobile information terminal or wearable information terminal and notifying the user by audio or visual content. This makes it possible to prevent customers from being mispronounced by name and improve the quality of service in physical stores.

[0944] "Data on the frequency of use of a particular name" is statistical data that indicates how frequently a particular name is used.

[0945] The "means for reversing each name" is a process or algorithm for reversing the strings of each name.

[0946] A "means for investigating the frequency of use of a transposed name" is a mechanism for investigating how frequently a transposed name is used.

[0947] A "means for calculating rankings" is an algorithm or system that determines rankings based on frequency of use of the original and transposed names.

[0948] The "means for identifying low-ranking names and generating a warning list" is a process for listing less frequently used names and warning them.

[0949] An "interface means for displaying the reminder list" is a device or software for visually or audibly presenting the reminder list to a user.

[0950] "Means for displaying the warning list on a mobile information terminal or wearable information terminal and notifying the user with audio or visual content" refers to a mechanism for displaying the warning list on a device such as a smartphone or smart glasses and alerting the user with audio or visual messages.

[0951] This invention is a system that prevents mispronouncing specific names. This system is intended for use in brick-and-mortar stores, and generates and displays a list of reminders to prevent employees from mispronouncing customers' names.

[0952] System Configuration

[0953] This system consists of a server, a mobile information terminal (smartphone), and a wearable information terminal (smart glasses or head-mounted display). Each device plays the following role:

[0954] 1. Server

[0955] Loading name frequency data: The server loads the frequency data for a specific name from the database and imports it into the system.

[0956] Transpose each name: The server reverses each name using string manipulation.

[0957] Checking the frequency of use of the transposed name: The server checks the frequency of use of the transposed name from the database and obtains the frequency data if it exists.

[0958] Calculating Ranking: The server calculates a ranking based on the name and inverted name to assess the popularity of the name.

[0959] Generate a warning list: The server identifies names that are ranked lower than the original name and generates a warning list.

[0960] Communication means: The server transmits the generated alert list to the mobile information terminal or wearable information terminal.

[0961] 2. Portable and wearable information terminals

[0962] Interface means: The mobile information terminal or wearable information terminal displays the alert list and notifies the user with audio or visual content.

[0963] Specific explanation of the process

[0964] 1. Loading name frequency data: The server loads name frequency data from the database. This data is stored in a dictionary format, with the key being the name and the value being the frequency of use.

[0965] 2. Generate a transposed version of each name: The server applies an algorithm to reverse the names and generates the transposed version. This is done using a programming language such as Python.

[0966] 3. Frequency check of transposed name: Check whether the transposed name exists in the database and get its frequency of use. If it does not exist, treat the frequency as zero.

[0967] 4. Calculate Ranking: The server calculates the ranking based on the frequency of use of the names and transposed names. This ranking is generated by sorting the frequency of use of each name from most to least frequent.

[0968] 5. Generate Reminder List: The server identifies less frequently used names and adds them to the reminder list.

[0969] 6. Displaying the list on the device and notifying users: The alert list is sent to smartphones or smart glasses, and these devices notify users with voice messages and visual content.

[0970] Specific examples

[0971] For example, suppose the names of customers waiting at a store are "Tanaka" (used 50 times), "Yamada" (used 30 times), "Nakata" (used 20 times), and "Sato" (used 60 times). The server reverses "Tanaka" to generate "Nakata" and adds up the frequency of both (70 times). Ultimately, "Tanaka" is not included in the warning list because it is ranked high.

[0972] Prompt Sentence Examples

[0973] Create a reminder system to prevent mispronunciation of names. Name data is provided in the following format: "Tanaka": 50, "Yamada": 30, "Nakata": 20, "Sato": 60. Sort the names in reverse order, investigate the frequency of their transpositions, and generate a reminder list based on the frequency of each name and its transpositions. The list should contain names that are used 10 times or less.

[0974] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0975] Step 1:

[0976] The server reads name frequency data. This data is retrieved from the database and stored in dictionary format. The input is the database connection information and query, and the output is dictionary data of names and their frequency of use. Specifically, the server connects to the database and retrieves the data by executing an SQL query such as "SELECT name, frequency FROM name_data".

[0977] Step 2:

[0978] The server transposes each name in reverse order. The input is the dictionary of name data obtained in step 1, and the output is the dictionary data of the transposed names. Specifically, each name is reversed using string manipulation and stored as a transposed name in a new dictionary. For example, "Tanaka" is transposed to "Nakata."

[0979] Step 3:

[0980] The server checks the frequency of the inverted name. The input is the dictionary of the inverted names from step 2, and the output is a dictionary with the frequency of the inverted name added. Specifically, it checks whether the inverted name exists in the database, and if so, obtains its frequency; if not, it sets the frequency to zero.

[0981] Step 4:

[0982] The server calculates the ranking based on the frequency of use of the name and transposed name. The input is the frequency data of the name and transposed name obtained in step 3, and the output is a ranking list based on frequency. Specifically, an algorithm is applied to sort the names in descending order of frequency to generate the ranking list.

[0983] Step 5:

[0984] The server identifies the names with low rankings and generates a warning list. The input is the ranking list from step 4, and the output is the warning list. Specifically, it lists names whose frequency of use is below a certain threshold and adds them to the warning list.

[0985] Step 6:

[0986] The server sends the alert list to the mobile or wearable information terminal. The input is the alert list from step 5, and the output is a message to be displayed on the user's device. Specifically, the generated alert list is distributed to smartphones or smart glasses, and these devices notify the user with audio or visual messages.

[0987] Step 7:

[0988] The user checks the warning list through a mobile information terminal or wearable information terminal. The input is the warning list sent to the terminal, and the output is the displayed list and the notification message. Specifically, the user can check the list by operating a smartphone or smart glasses and take measures to prevent mispronunciation of names.

[0989] 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.

[0990] This invention is a system for preventing mispronunciation of specific names, and also includes an emotion engine that recognizes the user's emotions and optimizes alerts. This system uses data on the frequency of use of specific names to calculate name transpositions and usage frequency rankings, and generates and displays an alert list. This system is intended for use in situations where patients are called by name in hospitals, medical facilities, etc.

[0991] System Overview

[0992] The system is controlled by a server and has the following main functions:

[0993] 1. Loading name usage frequency data

[0994] The server reads data on the frequency of name usage. For example, the statistical data shows that "Tanaka" is used in 75,000 households and "Nakata" in 2,000 households.

[0995] 2. Transposition of names

[0996] The server reverses each name to generate the transposed name. For example, "Tanaka" is reversed to become "Nakata."

[0997] 3. Frequency of use of transposed names

[0998] The server checks the frequency of use of the transposed name. If the transposed name exists, it obtains its frequency data; if it does not exist, it treats the frequency as zero.

[0999] 4. Ranking Calculation

[1000] The server calculates the ranking based on the frequency of use data for names and transposed names, thereby ranking each name in descending order of popularity.

[1001] 5. Generate a warning list

[1002] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to the warning list.

[1003] 6. Display by Interface Means

[1004] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[1005] Additional features of the Emotion Engine

[1006] In addition, the present invention is equipped with an emotion engine that analyzes the user's emotions, optimizing the effectiveness of the alert.

[1007] 7. Emotion engine that recognizes user emotions

[1008] The server analyzes voice and facial expression data to recognize the user's emotional state, and the results are used to emphasize alerts.

[1009] 8. Interface adjustment based on emotional state

[1010] If the user is feeling stressed, the device will display a warning message more prominently, by increasing the font size or changing the color.

[1011] 9. Recording emotional data and optimizing future alerts

[1012] The server records the user's emotional state and optimizes future reminders based on past emotional data. This record is used to understand the user's preferences and tendencies.

[1013] Specific explanation of program processing

[1014] 1. The server reads the name frequency data

[1015] The server reads pre-prepared name usage frequency data and inputs it into the system.

[1016] 2. The server converts the data into a data frame

[1017] Convert the read data into a Pandas data frame, with each name and its frequency as a row.

[1018] 3. The server performs a transposition operation on each name.

[1019] Using string manipulation, each name is rearranged in reverse order to generate the transposed name.

[1020] 4. The server checks the frequency of use of the inverted name

[1021] The server checks whether the transposed name exists and obtains its frequency of use data. If it does not exist, it treats the frequency of use as zero.

[1022] 5. The server calculates the ranking

[1023] Based on the frequency of use data, calculate the ranking of each name and add it to the data frame.

[1024] 6. The server generates a warning list

[1025] Identify names with lower rankings and add them to a warning list.

[1026] 7. The server sends the alert list to the device and displays it.

[1027] The server sends the reminder list to the terminal, which displays it.

[1028] Explanation of how the emotion engine works

[1029] 8. The server recognizes the user's emotions

[1030] The server analyzes voice and facial expression data to recognize the user's emotional state.

[1031] For example: If the user is feeling stressed, the system will recognize this.

[1032] 9. Devices will adjust their interfaces based on user emotions

[1033] If the user is feeling stressed, the device will display a message to alert them by highlighting it, for example by making the text larger or adding a warning sound.

[1034] 10. The server records emotional data and optimizes future reminders based on that data.

[1035] The system records past emotional data and adjusts future alert methods based on that data, allowing it to provide alerts that best suit the user's emotions.

[1036] The processing flow will be explained below.

[1037] Step 1:

[1038] The server reads name frequency data.

[1039] The server reads the frequency data for specific names from a pre-prepared data file and inputs it into the system as a large dictionary-style data set, which includes each name and its frequency of use.

[1040] Step 2:

[1041] The server converts the data into a data frame.

[1042] The server converts the data it reads into a Pandas data frame, which stores each name and its frequency as a row. This operation makes it easier to process the data.

[1043] Step 3:

[1044] The server performs the transposition of each name.

[1045] The server generates the inverted name by reversing each name, e.g., changing "Tanaka" to "Nakada." This operation is performed for every name in the data frame, and a new inverted name column is added.

[1046] Step 4:

[1047] The server checks the frequency of use of the inverted name.

[1048] The server checks the frequency of use of the generated inverted name. If the inverted name does not exist, the frequency of use is treated as zero. The frequency of use of the inverted name is added to the data frame.

[1049] Step 5:

[1050] The server calculates the ranking.

[1051] The server calculates the ranking based on the frequency of use data for the original and transposed names. This results in the names being ranked in order of most or least frequently used. Add a ranking column to the data frame.

[1052] Step 6:

[1053] The server generates a reminder list.

[1054] The server identifies names that rank lower than the original name and generates a warning list. Specifically, it lists names that rank in the top 75% or higher of the total. This list includes names that are prone to being mispronounced.

[1055] Step 7:

[1056] The server sends the warning list to the terminal and displays it.

[1057] The server sends the generated reminder list to the terminal, which displays the list. When the user calls a name, the list is referenced and a reminder message is displayed to prevent mistakes.

[1058] Step 8:

[1059] The server acquires data to recognize the user's emotions, which are then analyzed by the emotion engine.

[1060] The server collects the user's voice and facial expression data and passes it to the emotion engine, which analyzes this data and determines the user's emotional state. For example, it recognizes states such as stress, impatience, and excitement.

[1061] Step 9:

[1062] An emotional engine adjusts the interface based on the user's emotional state.

[1063] The emotion engine dynamically adjusts the device's display based on the user's emotional state. For example, if the user is feeling stressed, the device will highlight a warning message by increasing the font size, changing the color to red, or adding an audible warning.

[1064] Step 10:

[1065] The server records emotional data and optimizes future alerts.

[1066] The server records the user's emotional data and optimizes future reminders based on past emotional state data, thereby providing the most effective reminder for the user. For example, it may emphasize reminders during times when the user has experienced a lot of stress in the past.

[1067] Example 2

[1068] 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."

[1069] In hospitals and medical facilities, mispronunciations and misidentifications of patients' names can occur when calling them by name. This can cause confusion and stress for patients and medical staff. Furthermore, there is a lack of means to properly grasp the user's emotions and optimize alerts based on them. To solve these problems, a system is needed that can prevent mispronunciation of specific names and provide optimal alerts according to the user's emotional state.

[1070] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1071] In this invention, the server includes means for reading name usage frequency data, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequencies of the original names and the transposed names, means for identifying names ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for recognizing the user's emotions, means for adjusting the interface based on the user's emotions, and means for recording the user's emotion data and optimizing the warning method based on the data. This makes it possible to prevent mispronunciation of names and to provide optimal warnings according to the user's emotions.

[1072] "Name usage frequency data" refers to information indicating how often a particular name is used.

[1073] "Reading means" refers to the function for acquiring data from outside and importing it into the server.

[1074] The "means for transposing each name in reverse order" refers to a function for rearranging names in reverse order to generate a new name.

[1075] "Means for investigating the frequency of use of transposed names" refers to a function for checking the frequency of use of names transposed in reverse order and obtaining that data.

[1076] "Means for calculating rankings" refers to a function for ranking names and transposed names by prevalence based on frequency of use.

[1077] The "warning list" is information that lists names that are ranked low and is used to warn people.

[1078] "Means of generation" refers to the ability to create new data or lists based on specific conditions.

[1079] The "interface means" refers to a function for displaying the warning list to the user.

[1080] "Means for recognizing the user's emotions" refers to a function for analyzing data such as the user's voice and facial expressions to determine their emotional state.

[1081] "Means for adjusting the interface" refers to a function that changes the way the interface is displayed depending on the user's emotional state.

[1082] The "recording means" refers to a function for saving the user's emotional data.

[1083] The "means for optimizing the attention method" refers to a function for improving the attention method based on the recorded emotion data.

[1084] The present invention is a system for preventing mispronunciation of specific names, and also has the function of recognizing the user's emotions and optimizing alerts. The system of the present invention is intended for use in situations where patients' names are called out in hospitals and medical facilities. This system is realized using the following hardware and software.

[1085] The server first loads the name frequency data. This data is statistical data obtained from CSV files, databases, etc. For example, there are 75,000 occurrences of "Tanaka" and 2,000 occurrences of "Nakata." After loading this data, the server converts it into a Pandas data frame. This allows each name and its frequency of use to be stored in a tabular format for efficient processing.

[1086] Next, the server reverses each name to generate a transposed name. For example, "Tanaka" becomes "Nakada." This is done using string manipulation. The server then checks the frequency of the transposed name and compares the frequency of the original name with the frequency of the transposed name. If the transposed name does not exist, it treats the frequency as zero.

[1087] The server calculates a ranking of names and inversions based on the collected usage frequency data, which evaluates the prevalence of each name. It identifies names with low rankings and adds them to a warning list, which is displayed to users as names requiring caution.

[1088] Furthermore, the system of the present invention is equipped with an emotion engine that recognizes the user's emotions. The server analyzes voice and facial expression data to recognize the user's emotional state. For example, if the user is feeling stressed, the system will recognize this and the terminal will display a warning message in an emphasized manner. Specifically, methods such as increasing the font size or changing the color are used.

[1089] The server also records the user's emotional data and optimizes future alerts based on that data. This data is used to understand the user's preferences and tendencies. Specific software used includes Pandas, a voice recognition library, and OpenCV.

[1090] Specific examples

[1091] Example 1: How to use the name misidentification prevention system

[1092] At a certain hospital, patient A's name is registered in the system as "Tanaka." The server reads the usage frequency data for "Tanaka" and converts it into a Pandas data frame. Then, "Tanaka" is reversed to become "Nakata" and the usage frequency data for the transposed name is investigated. A ranking is calculated and a warning list is generated. This list includes names such as "Tanaka" and is displayed on the terminal to warn the user. If the user is feeling stressed, the terminal will highlight the warning message and display it.

[1093] Example 2: Adaptive interface using emotional data

[1094] When user B is using the system, the server recognizes B's emotional state from voice and facial expression data. If it detects that B is in a stressful state, the device displays a warning message in large letters to emphasize the situation visually.

[1095] Example prompts to input to the generative AI model

[1096] Design a system that issues reminders when patients' names are called in a hospital. Specifically, explain the process of using name frequency data to calculate name transpositions and frequency rankings, and then generating and displaying a reminder list. Also provide an emotion engine function that recognizes the user's emotions and adjusts the interface accordingly. As a concrete example, explain in detail the processing when Tanaka's name is registered.

[1097] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1098] Step 1: Loading name frequency data

[1099] The server retrieves pre-prepared name frequency data from an external CSV file or database. The retrieved data includes names and their frequency of use. Specifically, it reads the CSV file stored on the server and creates a dataset of names and their frequency of use. At this point, the input is the CSV file, and the output is the dataset.

[1100] Step 2: Convert the data into a data frame

[1101] The server converts the name frequency data it retrieves into a Pandas data frame. This keeps each name and its frequency in a tabular format, allowing for efficient processing. The input is the dataset loaded in step 1, and the output is a data frame.

[1102] Step 3: Transpose each name

[1103] The server reverses each name in the data frame to generate a transposed name. For example, "Tanaka" becomes "Nakada." Specifically, it applies an algorithm to reverse the strings of each name in the data frame. The input is a data frame containing the names, and the output is a data frame containing the transposed names.

[1104] Step 4: Frequency of use of transposed names

[1105] The server checks the frequency of use of the transposed name. If the transposed name does not exist, the frequency of use is set to zero. Specifically, the operation checks whether the transposed name exists in the original dataset and obtains the frequency of use. The input is a data frame containing the transposed names, and the output is a data frame with the frequency of use of each transposed name added.

[1106] Step 5: Calculating the rankings

[1107] The server calculates the ranking based on the frequency of use data for the original and transposed names. This evaluates the popularity of each name. Specifically, it applies an algorithm to calculate the ranking of names based on the frequency of use data in the data frame. The input is a data frame with the frequency of use added, and the output is a data frame with the ranking added.

[1108] Step 6: Generate a reminder list

[1109] The server adds names with low rankings (e.g., in the top 75%) to a warning list. Specifically, it filters the ranking data in the data frame and extracts names that require warnings. The input is the data frame with the added rankings, and the output is a warning list.

[1110] Step 7: View the Alert List

[1111] The server sends the generated warning list to the terminal, which then displays the list to the user. Specifically, the warning list is sent to the terminal using a communication means, and the terminal visually displays the list. The input is the warning list, and the output is the displayed warning list.

[1112] Step 8: Recognize the user's emotions

[1113] The server analyzes the voice and facial expression data to recognize the user's emotional state. Specifically, it uses voice and facial expression recognition algorithms to determine the emotional state. The input is the voice and facial expression data, and the output is the recognized emotional state.

[1114] Step 9: Adjusting the Interface

[1115] When a user is feeling stressed, the device displays a highlighted message to alert them. Specific actions include changing the font size and adding a warning sound. The input is the perceived emotional state, and the output is an adjusted user interface.

[1116] Step 10: Record and optimize emotional data

[1117] The server records the user's emotional data and optimizes future reminder methods based on that data. Specifically, it stores the emotional data in a database and analyzes the data to improve the reminder method. The input is the recognized emotional data, and the output is the optimized reminder method.

[1118] (Application example 2)

[1119] 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."

[1120] In workplaces such as factories, mispronouncing the names of parts or materials can lead to reduced work efficiency and quality issues. Furthermore, if appropriate attention is not given in response to the worker's emotional state, there is a risk of increased stress and mistakes. The present invention aims to solve these problems by preventing mispronouncing names and providing optimal attention in response to the worker's emotional state.

[1121] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1122] In this invention, the server includes means for reading usage frequency data of specific names, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for analyzing the user's emotions and emphasizing warning messages based on the results, and means for recording past emotion data and optimizing future warnings. This prevents mispronunciation of names and enables warnings that match the user's emotions.

[1123] A "specific name" is a name or designation used to identify a specific thing or person.

[1124] "Frequency of use data" is data that indicates how frequently a particular name is used.

[1125] A "server" is a computer system for processing and managing data.

[1126] "Transposing" refers to the operation of rearranging a string of characters in reverse order.

[1127] A "ranking" is an ordering of items based on a particular criterion, or a method of doing so.

[1128] A "warning list" is a list of items that require attention.

[1129] "Interface means" refers to the input and output means by which a user interacts with a system.

[1130] "User" refers to the individual who operates a system or device.

[1131] "Analyzing emotions" refers to analyzing data to recognize the user's emotional state.

[1132] The "warning message" refers to a message intended to alert the user.

[1133] "Past emotion data" is data that indicates the user's previously recorded emotional state.

[1134] "Optimize" refers to adjusting processes and data to their best ability to achieve a specific purpose.

[1135] The present invention relates to a system that prevents mispronunciation of specific names and recognizes the user's emotions to provide optimal attention. This system aims to prevent mispronunciation of parts and materials, particularly in factories, and to provide attention according to the worker's emotional state.

[1136] System configuration

[1137] The system has the following main functions:

[1138] 1. How to read name frequency data

[1139] The server loads pre-prepared specific names and their frequency of use. The data is the names of parts and materials used in the factory and includes their frequency of use.

[1140] 2. Name transposition operation method

[1141] The server reverses each name to generate the transposed name. For example, the part name "PX123" is reversed to become "321XP."

[1142] 3. Frequency of Use Survey Methods

[1143] The server also checks the frequency of use data for the transposed name, and if there is none, treats its frequency of use as zero.

[1144] 4. How the rankings are calculated

[1145] The server calculates a ranking based on the frequency of use of the original and transposed names, thereby assessing the frequency of use of each name.

[1146] 5. How to generate a warning list

[1147] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to the warning list.

[1148] 6. Interface Methods

[1149] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[1150] Emotion engine configuration

[1151] Additionally, the present invention includes an emotion engine that recognizes and responds to user emotions.

[1152] 7. Means of Emotion Analysis

[1153] The server analyzes voice and facial expression data to recognize the user's emotional state. For example, it uses a camera and microphone to capture the user's facial expressions and tone of voice, and analyzes them using an emotion recognition model using TensorFlow.

[1154] 8. A way to reinforce the warning message

[1155] If the user is feeling stressed, the interface means may display a message to alert the user by highlighting it, for example by increasing the font size or adding an audible warning.

[1156] 9. A means of recording past emotional data and optimizing future attention.

[1157] The server records the user's emotional state and optimizes future reminder methods based on past emotional data, thereby providing reminders that best suit the user's emotions.

[1158] Hardware and software used

[1159] Hardware:

[1160] Factory robots (e.g., industrial robots made by company A, company B, etc.)

[1161] display

[1162] Audio / video input devices (microphones, cameras)

[1163] software:

[1164] Python

[1165] Pandas (Data Frame Operations)

[1166] OpenCV (facial expression recognition)

[1167] NLTK (speech analysis)

[1168] TensorFlow (emotion recognition model)

[1169] Specific examples

[1170] For example, if a part is called "PX123" in the factory and is used very frequently, we can reverse the name to "321XP" and calculate a ranking based on the frequency of use of both names. If the ranking is low, we add it to a warning list and display it to the user through the interface.

[1171] The system obtains the user's facial expressions and voice data from the camera and microphone, analyzes them using a TensorFlow model, and if the user is feeling stressed, it increases the text size and displays a message accompanied by a warning sound.

[1172] Prompt Sentence Examples

[1173] Read usage frequency data for a specific name.

[1174] Investigate the frequency of use of transposed names.

[1175] Calculate rankings based on frequency of use.

[1176] Add low ranking names to a warning list.

[1177] Analyze the user's emotional state and emphasize attention-grabbing messages as needed.

[1178] The above is a specific embodiment for carrying out the invention.

[1179] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1180] Step 1:

[1181] The server reads the frequency of use data for a particular name.

[1182] Input: Data file of part and material names and their frequency of use.

[1183] What it does: Reads a data file into a data frame using Python and Pandas.

[1184] Output: A data frame containing the names and their frequency of use.

[1185] Step 2:

[1186] The server transposes each name in reverse order.

[1187] Input: A data frame of loaded names.

[1188] What it does: It runs a process that reverses each name in turn, and adds the transposed names as a new column.

[1189] Output: A data frame containing the original and transposed names.

[1190] Step 3:

[1191] The server investigates the frequency of use of the transposed name.

[1192] Input: A data frame containing the transposed names.

[1193] Operation: Checks whether the transposed name exists in the data frame and gets its frequency of use. If it does not exist, it treats the frequency of use as zero.

[1194] Output: A data frame containing the original names, transposed names, and their frequency of use.

[1195] Step 4:

[1196] The server calculates a ranking based on the frequency of use of the original and transposed names.

[1197] Input: Dataframe with usage frequencies.

[1198] How it works: Calculates the total frequency of use of each name in the data frame and creates a ranking.

[1199] Output: A data frame containing the total frequency and ranking of each name.

[1200] Step 5:

[1201] The server identifies names that are lower in ranking than the original name and generates a warning list.

[1202] Input: Dataframe with rankings.

[1203] How it works: Identifies names that rank in the top 75% or higher and adds them to a warning list.

[1204] Output: A list of warnings.

[1205] Step 6:

[1206] The server transmits the generated reminder list to the terminal, which displays it.

[1207] Input: Reminder list.

[1208] Operation: The warning list is sent to the device and displayed on the device.

[1209] Output: A list of reminders displayed to the user.

[1210] Step 7:

[1211] The server analyzes the user's emotions.

[1212] Input: Voice and facial expression data (obtained from camera and microphone).

[1213] How it works: OpenCV and TensorFlow are used to recognize emotions from acquired data. Audio data is analyzed using NLTK.

[1214] Output: User's emotional state data.

[1215] Step 8:

[1216] The interface means highlights the warning message based on the analysis result.

[1217] Input: User emotional state data.

[1218] How it works: If the user is stressed, it emphasizes the message by making the text larger and adding a warning sound.

[1219] Output: An emphasized warning message.

[1220] Step 9:

[1221] The server records past emotional data and optimizes future alerts.

[1222] Input: User's emotional state data and historical emotional data.

[1223] How it works: Records past emotional data in a database and adjusts future alerts accordingly.

[1224] Output: Optimized reminder system.

[1225] 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.

[1226] 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.

[1227] 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.

[1228] [Fourth embodiment]

[1229] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1230] 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.

[1231] 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).

[1232] 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.

[1233] 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.

[1234] 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).

[1235] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1236] 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.

[1237] 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.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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."

[1242] This invention is a system for preventing mispronunciation of specific names. This system uses data on the frequency of use of specific names to calculate name transpositions and usage frequency rankings, and generates and displays a warning list. This system is intended for use in situations such as calling out the names of patients in hospitals and medical facilities.

[1243] System Overview

[1244] The system is controlled by a server and has the following main functions:

[1245] 1. Loading name frequency data

[1246] The server reads name frequency data, which indicates how often each name is used.

[1247] 2. Transposition of names

[1248] The server reverses and transposes each name, preparing to identify names that are likely to be mispronounced.

[1249] 3. Frequency of use of transposed names

[1250] The server checks the frequency of the inverted name. If the inverted name exists, it retrieves its frequency data; if it does not exist, it treats the frequency as zero.

[1251] 4. Ranking Calculation

[1252] The server calculates a ranking based on the frequency of use of the names and their inverted names, thereby ranking each name in descending order of popularity.

[1253] 5. Generate a warning list

[1254] The server identifies names that rank lower than the original name and generates a warning list, which lists names that are likely to be mispronounced.

[1255] 6. Display by Interface Means

[1256] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[1257] Specific explanation of program processing

[1258] 1. The server reads the name frequency data

[1259] The server inputs pre-prepared name frequency data into the system, which is in dictionary format and includes information on the names and the number of households where they are used.

[1260] 2. The server performs a transpose operation on each name.

[1261] The server performs string manipulation to reverse each name to generate the inverted name.

[1262] 3. The server checks the frequency of use of the inverted name

[1263] The server checks whether the inverted name exists and obtains the frequency data. If it does not exist, it treats the frequency as zero.

[1264] 4. The server calculates the ranking

[1265] The server calculates a ranking for each name and transposed name based on frequency of use data, with the rankings sorted from highest to lowest frequency of use.

[1266] 5. The server generates a warning list

[1267] The server identifies names that rank lower than the original name and adds them to the warning list.

[1268] 6. The server sends the alert list to the terminal and displays it.

[1269] The server transmits the generated warning list to the terminal, which displays the list, thereby warning the user.

[1270] Specific examples

[1271] For example, if the name data includes "Tanaka," the server reads "Tanaka" and reverse-sorts "Tanaka" to generate "Nakata." It then checks the frequency of use of "Nakata" and calculates the ranking of both names. If "Tanaka" is ranked low, it is added to a warning list. Finally, the server sends this list to the terminal and displays a warning message to the user to avoid accidentally calling "Tanaka" "Nakata."

[1272] The processing flow will be explained below.

[1273] Step 1:

[1274] The server reads name frequency data.

[1275] The server inputs pre-prepared name frequency data into the system. This data contains names and their frequency of use in dictionary format. For example, there are 75,000 households with the name "Tanaka" and 2,000 households with the name "Nakata."

[1276] Step 2:

[1277] The server converts the data into a data frame.

[1278] The server converts the name frequency data it has read into a Pandas data frame, which has each name and its number of households as a row.

[1279] Step 3:

[1280] The server performs the transposition of each name.

[1281] The server reverses each name to generate a transposed name. For example, reverse "Tanaka" to create "Nakatana." This operation is performed for all names.

[1282] Step 4:

[1283] The server checks the frequency of use of the inverted name.

[1284] The server checks the existence of the transposed name and checks its frequency of use. If the transposed name exists, it adds its frequency of use to the data frame; if it does not exist, it treats the frequency of use as zero.

[1285] Step 5:

[1286] The server calculates the ranking.

[1287] The server calculates the ranking of each name, from highest to lowest, based on the frequency of use data for the name and the transposed name. The rankings for the original name and the transposed name are added to a data frame.

[1288] Step 6:

[1289] The server generates a reminder list.

[1290] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to a warning list, which contains names that are prone to mispronunciation based on certain criteria.

[1291] Step 7:

[1292] The server sends the warning list to the terminal and displays it.

[1293] The server sends the generated warning list to the terminal. The terminal receives the list and displays messages and information to warn the user. This allows the user to recognize the risk of mispronouncing names in advance.

[1294] Example 1

[1295] 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."

[1296] When calling patients by name in hospitals and medical facilities, mispronunciations between patients with similar names are common. Such mispronunciations can lead to medical accidents and confusion, and are a major obstacle to providing safe and efficient medical services. The present invention aims to provide a system that calculates name transpositions and rankings based on data on the frequency of use of specific names, and generates and displays a warning list to prevent mispronunciations.

[1297] 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.

[1298] In this invention, the server includes means for reading name usage frequency data, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for acquiring name usage frequency data from a database, means for acquiring the usage frequency of the transposed names from the database, and means for sorting the names in descending order of usage frequency, thereby making it possible to prevent names from being mispronounced.

[1299] "Name usage frequency data" is data that numerically indicates how frequently a particular name is used.

[1300] "Reading means" refers to a function or method by which a server obtains specific data from a database, storage, etc., and makes it available within the system.

[1301] A "transposition means" is a function or method for rearranging a specific string of characters in reverse order. For example, "Tanaka" is converted to "Nakada."

[1302] A "means for investigating frequency of use" is a function or method for obtaining the frequency of use of a specific name from a database or the like.

[1303] The "means for calculating rankings" is a function or method that calculates the ranking of each name based on the collected usage frequency data and rearranges them in descending order of frequency of use.

[1304] The "means for generating a warning list" is a function or method for identifying names that are likely to be mispronounced based on the ranking results and listing them.

[1305] The "interface means" is a function or method for visually displaying the generated reminder list to the user.

[1306] "Means for retrieving from a database" refers to a function or method for searching and retrieving specific data from a database.

[1307] The "means for sorting names in descending order of frequency of use" is a function or method for performing an operation to sort names in descending order of frequency of use based on the data on the frequency of use of the names.

[1308] "Communication means" refers to the method or technology used by the server to transmit data to the terminal, which allows the generated reminder list to be displayed on the terminal.

[1309] The present invention is a system for preventing mispronunciation of specific names. This system has the function of calculating name transpositions and usage frequency rankings based on name usage frequency data, and generating and displaying a warning list. A specific embodiment of this system is described below.

[1310] This system operates among the server, terminals, and users as follows.

[1311] 1. Loading name usage frequency data

[1312] The server retrieves pre-prepared name frequency data from a database. The name frequency data is stored in a MySQL database, and by importing this data, the server can determine how frequently each name is used. For example, this data might record "Tanaka" 30 times and "Nakata" 20 times.

[1313] 2. Name transposition operation

[1314] The server uses string manipulation to reverse the order of each name. For example, "Tanaka" is reversed to become "Nakata." This operation is realized using Python's string manipulation functions.

[1315] 3. Frequency of use of transposed names

[1316] The server retrieves the frequency of use of the transposed name from the database again. For example, it checks whether the transposed name "Nakata" exists and retrieves its frequency of use. If it does not exist, it treats the frequency of use as zero.

[1317] 4. Ranking Calculation

[1318] The server calculates the ranking of each name based on the frequency of use of the original name and the transposed name. The ranking is sorted by frequency of use. The calculation is done using Python's pandas library or similar to sort the data.

[1319] 5. Generate a warning list

[1320] The server then uses the ranking results to identify names that rank lower than the original name and adds them to a warning list, which is used to identify names that are prone to being mispronounced.

[1321] 6. Display of warning list

[1322] The server sends the generated warning list to the terminal, which displays it. The terminal is equipped with a web browser, and data is sent from the server via an HTTP request and displayed in HTML format. This allows the user to visually receive the warning message.

[1323] Specific examples

[1324] For example, if the name data includes "Tanaka," the server reads "Tanaka" and rearranges "Tanaka" in reverse order to generate "Nakata." The server then investigates the frequency of use of "Nakata," and assumes that "Tanaka" is used 30 times and "Nakata" is used 20 times. A ranking is calculated based on this data, and if "Tanaka" is ranked low, it is added to a warning list. Finally, the server sends this list to the device, which displays a warning message to prevent the device from mistakenly calling "Tanaka" "Nakata."

[1325] Examples of prompt statements

[1326] The following are examples of prompts used to test the operation of a system using a generative AI model:

[1327] Enter the name "Tanaka" into the system. Then, obtain the frequency of use data for the transposed name "Nakata" in the same way and calculate the ranking. Finally, if the name "Tanaka" is ranked low, add it to a warning list and display it to the user.

[1328] The present invention provides a system that prevents mispronunciation of names, thereby improving patient safety and quality of service, particularly in hospitals and medical facilities.

[1329] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1330] Step 1:

[1331] The server reads name frequency data. The server retrieves frequency data for specific names from the database. This data contains information on how frequently each name is used. The input is the names stored in the database and their frequency of use, and the output is the frequency data for names loaded into the server's internal memory. As a specific example of how this works, the server uses a SELECT statement from the MySQL database to retrieve the names and their corresponding frequency of use.

[1332] Step 2:

[1333] The server performs a transposition operation on each name. The server rearranges the names in reverse order to generate a new transposed name. The input is the read name, and the output is the transposed version of each name. As a specific example of how it works, the server reverses the names using Python's string manipulation functions.

[1334] Step 3:

[1335] The server checks the frequency of use of the inverted name. The server again retrieves the frequency data of the inverted name from the database. The inverted name is the input, and the frequency data of the inverted name is obtained as the output. If it does not exist, the frequency is treated as zero. As a specific example of operation, the server retrieves the frequency of use of the inverted name from the MySQL database using a SELECT statement, and if it does not exist, it sets it to 0.

[1336] Step 4:

[1337] The server calculates the rankings based on the usage frequency data of the original names and transposed names. The input is the usage frequency data of the original names and transposed names, and the output is the ranking of each name. As a specific example of how it works, the server uses Python's pandas library to sort the usage frequency data and create a ranking.

[1338] Step 5:

[1339] The server generates a warning list. The server identifies the original names that are at the bottom of the rankings and adds them to the warning list. The generated rankings are the input, and the warning list is the output. As a specific example of operation, the server adds names that are at the bottom of the rankings to the list based on a specific threshold.

[1340] Step 6:

[1341] The server sends the warning list to the terminal and displays it. The server sends the generated warning list to the terminal, and the terminal displays it. The input is the generated warning list, and the output is the warning message displayed on the terminal. As a specific example of operation, the server sends the warning list to the terminal using an HTTP request, and the terminal displays the list in HTML format using a web browser.

[1342] (Application example 1)

[1343] 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."

[1344] Mispronouncing certain names can cause confusion and inconvenience to users. In particular, in physical stores, where employees need to efficiently serve many customers in a short amount of time, mispronouncing names can lead to lower customer satisfaction and complaints. Furthermore, with the spread of wearable information devices, there is a demand for dynamic provision of this information.

[1345] 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.

[1346] In this invention, the server includes means for reading usage frequency data of specific names, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, and means for displaying the warning list on a mobile information terminal or wearable information terminal and notifying the user by audio or visual content. This makes it possible to prevent customers from being mispronounced by name and improve the quality of service in physical stores.

[1347] "Data on the frequency of use of a particular name" is statistical data that indicates how frequently a particular name is used.

[1348] The "means for reversing each name" is a process or algorithm for reversing the strings of each name.

[1349] A "means for investigating the frequency of use of a transposed name" is a mechanism for investigating how frequently a transposed name is used.

[1350] A "means for calculating rankings" is an algorithm or system that determines rankings based on frequency of use of the original and transposed names.

[1351] The "means for identifying low-ranking names and generating a warning list" is a process for listing less frequently used names and warning them.

[1352] An "interface means for displaying the reminder list" is a device or software for visually or audibly presenting the reminder list to a user.

[1353] "Means for displaying the warning list on a mobile information terminal or wearable information terminal and notifying the user with audio or visual content" refers to a mechanism for displaying the warning list on a device such as a smartphone or smart glasses and alerting the user with audio or visual messages.

[1354] This invention is a system that prevents mispronouncing specific names. This system is intended for use in brick-and-mortar stores, and generates and displays a list of reminders to prevent employees from mispronouncing customers' names.

[1355] System Configuration

[1356] This system consists of a server, a mobile information terminal (smartphone), and a wearable information terminal (smart glasses or head-mounted display). Each device plays the following role:

[1357] 1. Server

[1358] Loading name frequency data: The server loads the frequency data for a specific name from the database and imports it into the system.

[1359] Transpose each name: The server reverses each name using string manipulation.

[1360] Checking the frequency of use of the transposed name: The server checks the frequency of use of the transposed name from the database and obtains the frequency data if it exists.

[1361] Calculating Ranking: The server calculates a ranking based on the name and inverted name to assess the popularity of the name.

[1362] Generate a warning list: The server identifies names that are ranked lower than the original name and generates a warning list.

[1363] Communication means: The server transmits the generated alert list to the mobile information terminal or wearable information terminal.

[1364] 2. Portable and wearable information terminals

[1365] Interface means: The mobile information terminal or wearable information terminal displays the alert list and notifies the user with audio or visual content.

[1366] Specific explanation of the process

[1367] 1. Loading name frequency data: The server loads name frequency data from the database. This data is stored in a dictionary format, with the key being the name and the value being the frequency of use.

[1368] 2. Generate a transposed version of each name: The server applies an algorithm to reverse the names and generates the transposed version. This is done using a programming language such as Python.

[1369] 3. Frequency check of transposed name: Check whether the transposed name exists in the database and get its frequency of use. If it does not exist, treat the frequency as zero.

[1370] 4. Calculate Ranking: The server calculates the ranking based on the frequency of use of the names and transposed names. This ranking is generated by sorting the frequency of use of each name from most to least frequent.

[1371] 5. Generate Reminder List: The server identifies less frequently used names and adds them to the reminder list.

[1372] 6. Displaying the list on the device and notifying users: The alert list is sent to smartphones or smart glasses, and these devices notify users with voice messages and visual content.

[1373] Specific examples

[1374] For example, suppose the names of customers waiting at a store are "Tanaka" (used 50 times), "Yamada" (used 30 times), "Nakata" (used 20 times), and "Sato" (used 60 times). The server reverses "Tanaka" to generate "Nakata" and adds up the frequency of both (70 times). Ultimately, "Tanaka" is not included in the warning list because it is ranked high.

[1375] Prompt Sentence Examples

[1376] Create a reminder system to prevent mispronunciation of names. Name data is provided in the following format: "Tanaka": 50, "Yamada": 30, "Nakata": 20, "Sato": 60. Sort the names in reverse order, investigate the frequency of their transpositions, and generate a reminder list based on the frequency of each name and its transpositions. The list should contain names that are used 10 times or less.

[1377] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1378] Step 1:

[1379] The server reads name frequency data. This data is retrieved from the database and stored in dictionary format. The input is the database connection information and query, and the output is dictionary data of names and their frequency of use. Specifically, the server connects to the database and retrieves the data by executing an SQL query such as "SELECT name, frequency FROM name_data".

[1380] Step 2:

[1381] The server transposes each name in reverse order. The input is the dictionary of name data obtained in step 1, and the output is the dictionary data of the transposed names. Specifically, each name is reversed using string manipulation and stored as a transposed name in a new dictionary. For example, "Tanaka" is transposed to "Nakata."

[1382] Step 3:

[1383] The server checks the frequency of the inverted name. The input is the dictionary of the inverted names from step 2, and the output is a dictionary with the frequency of the inverted name added. Specifically, it checks whether the inverted name exists in the database, and if so, obtains its frequency; if not, it sets the frequency to zero.

[1384] Step 4:

[1385] The server calculates the ranking based on the frequency of use of the name and transposed name. The input is the frequency data of the name and transposed name obtained in step 3, and the output is a ranking list based on frequency. Specifically, an algorithm is applied to sort the names in descending order of frequency to generate the ranking list.

[1386] Step 5:

[1387] The server identifies the names with low rankings and generates a warning list. The input is the ranking list from step 4, and the output is the warning list. Specifically, it lists names whose frequency of use is below a certain threshold and adds them to the warning list.

[1388] Step 6:

[1389] The server sends the alert list to the mobile or wearable information terminal. The input is the alert list from step 5, and the output is a message to be displayed on the user's device. Specifically, the generated alert list is distributed to smartphones or smart glasses, and these devices notify the user with audio or visual messages.

[1390] Step 7:

[1391] The user checks the warning list through a mobile information terminal or wearable information terminal. The input is the warning list sent to the terminal, and the output is the displayed list and the notification message. Specifically, the user can check the list by operating a smartphone or smart glasses and take measures to prevent mispronunciation of names.

[1392] 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.

[1393] This invention is a system for preventing mispronunciation of specific names, and also includes an emotion engine that recognizes the user's emotions and optimizes alerts. This system uses data on the frequency of use of specific names to calculate name transpositions and usage frequency rankings, and generates and displays an alert list. This system is intended for use in situations where patients are called by name in hospitals, medical facilities, etc.

[1394] System Overview

[1395] The system is controlled by a server and has the following main functions:

[1396] 1. Loading name usage frequency data

[1397] The server reads data on the frequency of name usage. For example, the statistical data shows that "Tanaka" is used in 75,000 households and "Nakata" in 2,000 households.

[1398] 2. Transposition of names

[1399] The server reverses each name to generate the transposed name. For example, "Tanaka" is reversed to become "Nakata."

[1400] 3. Frequency of use of transposed names

[1401] The server checks the frequency of use of the transposed name. If the transposed name exists, it obtains its frequency data; if it does not exist, it treats the frequency as zero.

[1402] 4. Ranking Calculation

[1403] The server calculates the ranking based on the frequency of use data for names and transposed names, thereby ranking each name in descending order of popularity.

[1404] 5. Generate a warning list

[1405] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to the warning list.

[1406] 6. Display by Interface Means

[1407] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[1408] Additional features of the Emotion Engine

[1409] In addition, the present invention is equipped with an emotion engine that analyzes the user's emotions, optimizing the effectiveness of the alert.

[1410] 7. Emotion engine that recognizes user emotions

[1411] The server analyzes voice and facial expression data to recognize the user's emotional state, and the results are used to emphasize alerts.

[1412] 8. Interface adjustment based on emotional state

[1413] If the user is feeling stressed, the device will display a warning message more prominently, by increasing the font size or changing the color.

[1414] 9. Recording emotional data and optimizing future alerts

[1415] The server records the user's emotional state and optimizes future reminders based on past emotional data. This record is used to understand the user's preferences and tendencies.

[1416] Specific explanation of program processing

[1417] 1. The server reads the name frequency data

[1418] The server reads pre-prepared name usage frequency data and inputs it into the system.

[1419] 2. The server converts the data into a data frame

[1420] Convert the read data into a Pandas data frame, with each name and its frequency as a row.

[1421] 3. The server performs a transposition operation on each name.

[1422] Using string manipulation, each name is rearranged in reverse order to generate the transposed name.

[1423] 4. The server checks the frequency of use of the inverted name

[1424] The server checks whether the transposed name exists and obtains its frequency of use data. If it does not exist, it treats the frequency of use as zero.

[1425] 5. The server calculates the ranking

[1426] Based on the frequency of use data, calculate the ranking of each name and add it to the data frame.

[1427] 6. The server generates a warning list

[1428] Identify names with lower rankings and add them to a warning list.

[1429] 7. The server sends the alert list to the device and displays it.

[1430] The server sends the reminder list to the terminal, which displays it.

[1431] Explanation of how the emotion engine works

[1432] 8. The server recognizes the user's emotions

[1433] The server analyzes voice and facial expression data to recognize the user's emotional state.

[1434] For example: If the user is feeling stressed, the system will recognize this.

[1435] 9. Devices will adjust their interfaces based on user emotions

[1436] If the user is feeling stressed, the device will display a message to alert them by highlighting it, for example by making the text larger or adding a warning sound.

[1437] 10. The server records emotional data and optimizes future reminders based on that data.

[1438] The system records past emotional data and adjusts future alert methods based on that data, allowing it to provide alerts that best suit the user's emotions.

[1439] The processing flow will be explained below.

[1440] Step 1:

[1441] The server reads name frequency data.

[1442] The server reads the frequency data for specific names from a pre-prepared data file and inputs it into the system as a large dictionary-style data set, which includes each name and its frequency of use.

[1443] Step 2:

[1444] The server converts the data into a data frame.

[1445] The server converts the data it reads into a Pandas data frame, which stores each name and its frequency as a row. This operation makes it easier to process the data.

[1446] Step 3:

[1447] The server performs the transposition of each name.

[1448] The server generates the inverted name by reversing each name, e.g., changing "Tanaka" to "Nakada." This operation is performed for every name in the data frame, and a new inverted name column is added.

[1449] Step 4:

[1450] The server checks the frequency of use of the inverted name.

[1451] The server checks the frequency of use of the generated inverted name. If the inverted name does not exist, the frequency of use is treated as zero. The frequency of use of the inverted name is added to the data frame.

[1452] Step 5:

[1453] The server calculates the ranking.

[1454] The server calculates the ranking based on the frequency of use data for the original and transposed names. This results in the names being ranked in order of most or least frequently used. Add a ranking column to the data frame.

[1455] Step 6:

[1456] The server generates a reminder list.

[1457] The server identifies names that rank lower than the original name and generates a warning list. Specifically, it lists names that rank in the top 75% or higher of the total. This list includes names that are prone to being mispronounced.

[1458] Step 7:

[1459] The server sends the warning list to the terminal and displays it.

[1460] The server sends the generated reminder list to the terminal, which displays the list. When the user calls a name, the list is referenced and a reminder message is displayed to prevent mistakes.

[1461] Step 8:

[1462] The server acquires data to recognize the user's emotions, which are then analyzed by the emotion engine.

[1463] The server collects the user's voice and facial expression data and passes it to the emotion engine, which analyzes this data and determines the user's emotional state. For example, it recognizes states such as stress, impatience, and excitement.

[1464] Step 9:

[1465] An emotional engine adjusts the interface based on the user's emotional state.

[1466] The emotion engine dynamically adjusts the device's display based on the user's emotional state. For example, if the user is feeling stressed, the device will highlight a warning message by increasing the font size, changing the color to red, or adding an audible warning.

[1467] Step 10:

[1468] The server records emotional data and optimizes future alerts.

[1469] The server records the user's emotional data and optimizes future reminders based on past emotional state data, thereby providing the most effective reminder for the user. For example, it may emphasize reminders during times when the user has experienced a lot of stress in the past.

[1470] Example 2

[1471] 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."

[1472] In hospitals and medical facilities, mispronunciations and misidentifications of patients' names can occur when calling them by name. This can cause confusion and stress for patients and medical staff. Furthermore, there is a lack of means to properly grasp the user's emotions and optimize alerts based on them. To solve these problems, a system is needed that can prevent mispronunciation of specific names and provide optimal alerts according to the user's emotional state.

[1473] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1474] In this invention, the server includes means for reading name usage frequency data, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequencies of the original names and the transposed names, means for identifying names ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for recognizing the user's emotions, means for adjusting the interface based on the user's emotions, and means for recording the user's emotion data and optimizing the warning method based on the data. This makes it possible to prevent mispronunciation of names and to provide optimal warnings according to the user's emotions.

[1475] "Name usage frequency data" refers to information indicating how often a particular name is used.

[1476] "Reading means" refers to the function for acquiring data from outside and importing it into the server.

[1477] The "means for transposing each name in reverse order" refers to a function for rearranging names in reverse order to generate a new name.

[1478] "Means for investigating the frequency of use of transposed names" refers to a function for checking the frequency of use of names transposed in reverse order and obtaining that data.

[1479] "Means for calculating rankings" refers to a function for ranking names and transposed names by prevalence based on frequency of use.

[1480] The "warning list" is information that lists names that are ranked low and is used to warn people.

[1481] "Means of generation" refers to the ability to create new data or lists based on specific conditions.

[1482] The "interface means" refers to a function for displaying the warning list to the user.

[1483] "Means for recognizing the user's emotions" refers to a function for analyzing data such as the user's voice and facial expressions to determine their emotional state.

[1484] "Means for adjusting the interface" refers to a function that changes the way the interface is displayed depending on the user's emotional state.

[1485] The "recording means" refers to a function for saving the user's emotional data.

[1486] The "means for optimizing the attention method" refers to a function for improving the attention method based on the recorded emotion data.

[1487] The present invention is a system for preventing mispronunciation of specific names, and also has the function of recognizing the user's emotions and optimizing alerts. The system of the present invention is intended for use in situations where patients' names are called out in hospitals and medical facilities. This system is realized using the following hardware and software.

[1488] The server first loads the name frequency data. This data is statistical data obtained from CSV files, databases, etc. For example, there are 75,000 occurrences of "Tanaka" and 2,000 occurrences of "Nakata." After loading this data, the server converts it into a Pandas data frame. This allows each name and its frequency of use to be stored in a tabular format for efficient processing.

[1489] Next, the server reverses each name to generate a transposed name. For example, "Tanaka" becomes "Nakada." This is done using string manipulation. The server then checks the frequency of the transposed name and compares the frequency of the original name with the frequency of the transposed name. If the transposed name does not exist, it treats the frequency as zero.

[1490] The server calculates a ranking of names and inversions based on the collected usage frequency data, which evaluates the prevalence of each name. It identifies names with low rankings and adds them to a warning list, which is displayed to users as names requiring caution.

[1491] Furthermore, the system of the present invention is equipped with an emotion engine that recognizes the user's emotions. The server analyzes voice and facial expression data to recognize the user's emotional state. For example, if the user is feeling stressed, the system will recognize this and the terminal will display a warning message in an emphasized manner. Specifically, methods such as increasing the font size or changing the color are used.

[1492] The server also records the user's emotional data and optimizes future alerts based on that data. This data is used to understand the user's preferences and tendencies. Specific software used includes Pandas, a voice recognition library, and OpenCV.

[1493] Specific examples

[1494] Example 1: How to use the name misidentification prevention system

[1495] At a certain hospital, patient A's name is registered in the system as "Tanaka." The server reads the usage frequency data for "Tanaka" and converts it into a Pandas data frame. Then, "Tanaka" is reversed to become "Nakata" and the usage frequency data for the transposed name is investigated. A ranking is calculated and a warning list is generated. This list includes names such as "Tanaka" and is displayed on the terminal to warn the user. If the user is feeling stressed, the terminal will highlight the warning message and display it.

[1496] Example 2: Adaptive interface using emotional data

[1497] When user B is using the system, the server recognizes B's emotional state from voice and facial expression data. If it detects that B is in a stressful state, the device displays a warning message in large letters to emphasize the situation visually.

[1498] Example prompts to input to the generative AI model

[1499] Design a system that issues reminders when patients' names are called in a hospital. Specifically, explain the process of using name frequency data to calculate name transpositions and frequency rankings, and then generating and displaying a reminder list. Also provide an emotion engine function that recognizes the user's emotions and adjusts the interface accordingly. As a concrete example, explain in detail the processing when Tanaka's name is registered.

[1500] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1501] Step 1: Loading name frequency data

[1502] The server retrieves pre-prepared name frequency data from an external CSV file or database. The retrieved data includes names and their frequency of use. Specifically, it reads the CSV file stored on the server and creates a dataset of names and their frequency of use. At this point, the input is the CSV file, and the output is the dataset.

[1503] Step 2: Convert the data into a data frame

[1504] The server converts the name frequency data it retrieves into a Pandas data frame. This keeps each name and its frequency in a tabular format, allowing for efficient processing. The input is the dataset loaded in step 1, and the output is a data frame.

[1505] Step 3: Transpose each name

[1506] The server reverses each name in the data frame to generate a transposed name. For example, "Tanaka" becomes "Nakada." Specifically, it applies an algorithm to reverse the strings of each name in the data frame. The input is a data frame containing the names, and the output is a data frame containing the transposed names.

[1507] Step 4: Frequency of use of transposed names

[1508] The server checks the frequency of use of the transposed name. If the transposed name does not exist, the frequency of use is set to zero. Specifically, the operation checks whether the transposed name exists in the original dataset and obtains the frequency of use. The input is a data frame containing the transposed names, and the output is a data frame with the frequency of use of each transposed name added.

[1509] Step 5: Calculating the rankings

[1510] The server calculates the ranking based on the frequency of use data for the original and transposed names. This evaluates the popularity of each name. Specifically, it applies an algorithm to calculate the ranking of names based on the frequency of use data in the data frame. The input is a data frame with the frequency of use added, and the output is a data frame with the ranking added.

[1511] Step 6: Generate a reminder list

[1512] The server adds names with low rankings (e.g., in the top 75%) to a warning list. Specifically, it filters the ranking data in the data frame and extracts names that require warnings. The input is the data frame with the added rankings, and the output is a warning list.

[1513] Step 7: View the Alert List

[1514] The server sends the generated warning list to the terminal, which then displays the list to the user. Specifically, the warning list is sent to the terminal using a communication means, and the terminal visually displays the list. The input is the warning list, and the output is the displayed warning list.

[1515] Step 8: Recognize the user's emotions

[1516] The server analyzes the voice and facial expression data to recognize the user's emotional state. Specifically, it uses voice and facial expression recognition algorithms to determine the emotional state. The input is the voice and facial expression data, and the output is the recognized emotional state.

[1517] Step 9: Adjusting the Interface

[1518] When a user is feeling stressed, the device displays a highlighted message to alert them. Specific actions include changing the font size and adding a warning sound. The input is the perceived emotional state, and the output is an adjusted user interface.

[1519] Step 10: Record and optimize emotional data

[1520] The server records the user's emotional data and optimizes future reminder methods based on that data. Specifically, it stores the emotional data in a database and analyzes the data to improve the reminder method. The input is the recognized emotional data, and the output is the optimized reminder method.

[1521] (Application example 2)

[1522] 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."

[1523] In workplaces such as factories, mispronouncing the names of parts or materials can lead to reduced work efficiency and quality issues. Furthermore, if appropriate attention is not given in response to the worker's emotional state, there is a risk of increased stress and mistakes. The present invention aims to solve these problems by preventing mispronouncing names and providing optimal attention in response to the worker's emotional state.

[1524] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1525] In this invention, the server includes means for reading usage frequency data of specific names, means for transposing each name in reverse order, means for investigating the usage frequency of the transposed names, means for calculating rankings based on the usage frequency of the original names and the transposed names, means for identifying names that are ranked lower than the original names and generating a warning list, interface means for displaying the warning list, means for analyzing the user's emotions and emphasizing warning messages based on the results, and means for recording past emotion data and optimizing future warnings. This prevents mispronunciation of names and enables warnings that match the user's emotions.

[1526] A "specific name" is a name or designation used to identify a specific thing or person.

[1527] "Frequency of use data" is data that indicates how frequently a particular name is used.

[1528] A "server" is a computer system for processing and managing data.

[1529] "Transposing" refers to the operation of rearranging a string of characters in reverse order.

[1530] A "ranking" is an ordering of items based on a particular criterion, or a method of doing so.

[1531] A "warning list" is a list of items that require attention.

[1532] "Interface means" refers to the input and output means by which a user interacts with a system.

[1533] "User" refers to the individual who operates a system or device.

[1534] "Analyzing emotions" refers to analyzing data to recognize the user's emotional state.

[1535] The "warning message" refers to a message intended to alert the user.

[1536] "Past emotion data" is data that indicates the user's previously recorded emotional state.

[1537] "Optimize" refers to adjusting processes and data to their best ability to achieve a specific purpose.

[1538] The present invention relates to a system that prevents mispronunciation of specific names and recognizes the user's emotions to provide optimal attention. This system aims to prevent mispronunciation of parts and materials, particularly in factories, and to provide attention according to the worker's emotional state.

[1539] System configuration

[1540] The system has the following main functions:

[1541] 1. How to read name frequency data

[1542] The server loads pre-prepared specific names and their frequency of use. The data is the names of parts and materials used in the factory and includes their frequency of use.

[1543] 2. Name transposition operation method

[1544] The server reverses each name to generate the transposed name. For example, the part name "PX123" is reversed to become "321XP."

[1545] 3. Frequency of Use Survey Methods

[1546] The server also checks the frequency of use data for the transposed name, and if there is none, treats its frequency of use as zero.

[1547] 4. How the rankings are calculated

[1548] The server calculates a ranking based on the frequency of use of the original and transposed names, thereby assessing the frequency of use of each name.

[1549] 5. How to generate a warning list

[1550] The server identifies names that rank lower than the original name (e.g., in the top 75%) and adds them to the warning list.

[1551] 6. Interface Methods

[1552] The server transmits the generated warning list to the terminal, and the terminal displays the list to warn the user.

[1553] Emotion engine configuration

[1554] Additionally, the present invention includes an emotion engine that recognizes and responds to user emotions.

[1555] 7. Means of Emotion Analysis

[1556] The server analyzes voice and facial expression data to recognize the user's emotional state. For example, it uses a camera and microphone to capture the user's facial expressions and tone of voice, and analyzes them using an emotion recognition model using TensorFlow.

[1557] 8. A way to reinforce the warning message

[1558] If the user is feeling stressed, the interface means may display a message to alert the user by highlighting it, for example by increasing the font size or adding an audible warning.

[1559] 9. A means of recording past emotional data and optimizing future attention.

[1560] The server records the user's emotional state and optimizes future reminder methods based on past emotional data, thereby providing reminders that best suit the user's emotions.

[1561] Hardware and software used

[1562] Hardware:

[1563] Factory robots (e.g., industrial robots made by company A, company B, etc.)

[1564] display

[1565] Audio / video input devices (microphones, cameras)

[1566] software:

[1567] Python

[1568] Pandas (Data Frame Operations)

[1569] OpenCV (facial expression recognition)

[1570] NLTK (speech analysis)

[1571] TensorFlow (emotion recognition model)

[1572] Specific examples

[1573] For example, if a part is called "PX123" in the factory and is used very frequently, we can reverse the name to "321XP" and calculate a ranking based on the frequency of use of both names. If the ranking is low, we add it to a warning list and display it to the user through the interface.

[1574] The system obtains the user's facial expressions and voice data from the camera and microphone, analyzes them using a TensorFlow model, and if the user is feeling stressed, it increases the text size and displays a message accompanied by a warning sound.

[1575] Prompt Sentence Examples

[1576] Read usage frequency data for a specific name.

[1577] Investigate the frequency of use of transposed names.

[1578] Calculate rankings based on frequency of use.

[1579] Add low ranking names to a warning list.

[1580] Analyze the user's emotional state and emphasize attention-grabbing messages as needed.

[1581] The above is a specific embodiment for carrying out the invention.

[1582] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1583] Step 1:

[1584] The server reads the frequency of use data for a particular name.

[1585] Input: Data file of part and material names and their frequency of use.

[1586] What it does: Reads a data file into a data frame using Python and Pandas.

[1587] Output: A data frame containing the names and their frequency of use.

[1588] Step 2:

[1589] The server transposes each name in reverse order.

[1590] Input: A data frame of loaded names.

[1591] What it does: It runs a process that reverses each name in turn, and adds the transposed names as a new column.

[1592] Output: A data frame containing the original and transposed names.

[1593] Step 3:

[1594] The server investigates the frequency of use of the transposed name.

[1595] Input: A data frame containing the transposed names.

[1596] Operation: Checks whether the transposed name exists in the data frame and gets its frequency of use. If it does not exist, it treats the frequency of use as zero.

[1597] Output: A data frame containing the original names, transposed names, and their frequency of use.

[1598] Step 4:

[1599] The server calculates a ranking based on the frequency of use of the original and transposed names.

[1600] Input: Dataframe with usage frequencies.

[1601] How it works: Calculates the total frequency of use of each name in the data frame and creates a ranking.

[1602] Output: A data frame containing the total frequency and ranking of each name.

[1603] Step 5:

[1604] The server identifies names that are lower in ranking than the original name and generates a warning list.

[1605] Input: Dataframe with rankings.

[1606] How it works: Identifies names that rank in the top 75% or higher and adds them to a warning list.

[1607] Output: A list of warnings.

[1608] Step 6:

[1609] The server transmits the generated reminder list to the terminal, which displays it.

[1610] Input: Reminder list.

[1611] Operation: The warning list is sent to the device and displayed on the device.

[1612] Output: A list of reminders displayed to the user.

[1613] Step 7:

[1614] The server analyzes the user's emotions.

[1615] Input: Voice and facial expression data (obtained from camera and microphone).

[1616] How it works: OpenCV and TensorFlow are used to recognize emotions from acquired data. Audio data is analyzed using NLTK.

[1617] Output: User's emotional state data.

[1618] Step 8:

[1619] The interface means highlights the warning message based on the analysis result.

[1620] Input: User emotional state data.

[1621] How it works: If the user is stressed, it emphasizes the message by making the text larger and adding a warning sound.

[1622] Output: An emphasized warning message.

[1623] Step 9:

[1624] The server records past emotional data and optimizes future alerts.

[1625] Input: User's emotional state data and historical emotional data.

[1626] How it works: Records past emotional data in a database and adjusts future alerts accordingly.

[1627] Output: Optimized reminder system.

[1628] 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.

[1629] 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.

[1630] 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.

[1631] 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.

[1632] 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.

[1633] 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.

[1634] 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).

[1635] 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.

[1636] 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."

[1637] 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.

[1638] 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).

[1639] 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.

[1640] 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.

[1641] 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.

[1642] 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.

[1643] 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.

[1644] 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.

[1645] 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.

[1646] 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.

[1647] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1648] 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.

[1649] The following is further disclosed regarding the above embodiment.

[1650] (Claim 1)

[1651] a means for reading frequency data of a particular name;

[1652] a means for transposing each name in reverse order;

[1653] a means of investigating the frequency of use of the transposed names;

[1654] means for calculating a ranking based on the frequency of use of the original name and the transposed name;

[1655] a means for identifying names that are lower in ranking than the original name and generating a warning list;

[1656] an interface means for displaying the alert list;

[1657] A system including:

[1658] (Claim 2)

[1659] 2. The system of claim 1, further comprising means for treating the frequency of use as zero if no transposed name exists.

[1660] (Claim 3)

[1661] 10. The system of claim 1, further comprising a communication means for transmitting the reminder list to the terminal.

[1662] "Example 1"

[1663] (Claim 1)

[1664] means for reading name frequency data;

[1665] a means for transposing each name in reverse order;

[1666] a means of investigating the frequency of use of the transposed names;

[1667] means for calculating a ranking based on the frequency of use of the original name and the transposed name;

[1668] a means for identifying names that are lower in ranking than the original name and generating a warning list;

[1669] an interface means for displaying the alert list;

[1670] a means for obtaining name frequency data from a database;

[1671] A means for obtaining the frequency of use of the inverted name from a database;

[1672] A means to sort names in order of frequency of use,

[1673] A system including:

[1674] (Claim 2)

[1675] 2. The system of claim 1, further comprising means for treating the frequency of use as zero if no transposed name exists.

[1676] (Claim 3)

[1677] 10. The system of claim 1, further comprising a communication means for transmitting the reminder list to the terminal.

[1678] "Application Example 1"

[1679] (Claim 1)

[1680] a means for reading frequency data of a particular name;

[1681] a means for transposing each name in reverse order;

[1682] a means of investigating the frequency of use of the transposed names;

[1683] means for calculating a ranking based on the frequency of use of the original name and the transposed name;

[1684] a means for identifying names that are lower in ranking than the original name and generating a warning list;

[1685] an interface means for displaying the alert list;

[1686] a means for displaying the alert list on a mobile information terminal or a wearable information terminal and notifying the user by audio or visual content;

[1687] A system including:

[1688] (Claim 2)

[1689] 2. The system of claim 1, further comprising means for treating the frequency of use as zero if no transposed name exists.

[1690] (Claim 3)

[1691] 10. The system of claim 1, further comprising a communication means for transmitting the reminder list to the terminal.

[1692] "Example 2: Combining Emotion Engines"

[1693] (Claim 1)

[1694] means for reading name frequency data;

[1695] a means for transposing each name in reverse order;

[1696] a means of investigating the frequency of use of the transposed names;

[1697] means for calculating a ranking based on the frequency of use of the original name and the transposed name;

[1698] a means for identifying names that are lower in ranking than the original name and generating a warning list;

[1699] an interface means for displaying the alert list;

[1700] means for recognizing a user's emotion;

[1701] means for adjusting the interface based on the user's emotions;

[1702] means for recording user emotion data and optimizing a method of alerting the user based on the data;

[1703] A system including:

[1704] (Claim 2)

[1705] 2. The system of claim 1, further comprising means for treating the frequency of use as zero if no transposed name exists.

[1706] (Claim 3)

[1707] 10. The system of claim 1, further comprising a communication means for transmitting the reminder list to the terminal.

[1708] "Application example 2 when combining emotion engines"

[1709] (Claim 1)

[1710] a means for reading frequency data of a particular name;

[1711] a means for transposing each name in reverse order;

[1712] a means of investigating the frequency of use of the transposed names;

[1713] means for calculating a ranking based on the frequency of use of the original name and the transposed name;

[1714] a means for identifying names that are lower in ranking than the original name and generating a warning list;

[1715] an interface means for displaying the alert list;

[1716] means for analyzing the user's emotions and emphasizing a warning message based on the results of the analysis;

[1717] A means of recording past emotional data and optimizing future alerts;

[1718] A system including:

[1719] (Claim 2)

[1720] 2. The system of claim 1, further comprising means for treating the frequency of use as zero if no transposed name exists.

[1721] (Claim 3)

[1722] 10. The system of claim 1, further comprising a communication means for transmitting the reminder list to the terminal. [Explanation of symbols]

[1723] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for reading frequency data of a particular name; a means for transposing each name in reverse order; a means of investigating the frequency of use of the transposed names; means for calculating a ranking based on the frequency of use of the original name and the transposed name; a means for identifying names that are lower in ranking than the original name and generating a warning list; an interface means for displaying the alert list; A system including:

2. 2. The system of claim 1, further comprising means for treating the frequency of use as zero if no inverted name exists.

3. The system of claim 1 further comprising a communication means for transmitting the reminder list to the terminal.

Images