system

Abstract

We provide a system that enables efficient staffing and high customer satisfaction simultaneously, thereby optimizing store operations. [Solution] A system including means for collecting customer information, means for storing the collected customer information in a database, means for inputting the shift information of store employees, means for analyzing the input shift information and storing it in a database, means for calculating the optimal staffing arrangement based on customer information and shift information, means for displaying the optimized schedule to the user and prompting confirmation and correction, means for proposing measures to improve the quality of customer service based on customer satisfaction, means for displaying the proposed improvement measures and prompting their implementation, and means for calculating brand evaluation points and notifying the achievement target.

Description

Technical Field

[0003]

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern store operations, it is an important issue to achieve efficient staffing while enhancing customer satisfaction. However, in conventional store operation systems, it is difficult to predict peak hours and flexibly manage shifts according to customer needs, resulting in insufficient customer service and excessive labor costs. In addition, there is also a lack of systems that can effectively support the improvement of the brand value of stores.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides the following means: means for collecting customer information and storing it in a database, and means for inputting and managing the shift information of store employees. It also includes means for calculating the optimal staffing arrangement based on customer information and shift information, and for displaying and confirming the optimized schedule to the user. Furthermore, it also has means for proposing and displaying measures to improve the quality of customer service based on customer satisfaction, and for calculating brand evaluation points and notifying the user of achievement targets. This system makes it possible to achieve efficient staffing and high customer satisfaction simultaneously, thereby optimizing store management.

[0006] "Customer information" refers to basic data such as the name, contact information, and purchase history of customers who visit the store.

[0007] A "database" refers to a system that systematically stores collected information and allows for efficient access and management as needed.

[0008] "Employee shift information" refers to schedule data such as the working days, arrival and departure times of employees working at the store.

[0009] "Optimal staffing" refers to a plan for the most efficient allocation of personnel based on customer traffic and needs.

[0010] "Users" refer to store managers and frontline staff who operate and manage this system.

[0011] "Measures to improve customer service quality" refers to specific improvement methods and action plans recommended to enhance customer satisfaction.

[0012] "Brand evaluation points" refer to specific indicators used to evaluate the brand value of a store or company.

[0013] "Achievement targets" refer to specific goals and objectives set for purposes such as improving brand value or streamlining operations. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system that collects and manages customer information and employee shift information, and uses this information to achieve optimal staffing. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[0036] 1. Collection and storage of customer information

[0037] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[0038] The server receives the entered customer information and stores it in the database. The server checks the entered information for errors to ensure accurate data collection.

[0039] Specific example: Customer Tanaka comes into the store and registers his name and contact information on a terminal. The terminal sends this information to the server, which stores the information in a database for verification.

[0040] 2. Inputting and managing employee shift information

[0041] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This includes each employee's name, workday, start time, and end time.

[0042] The server analyzes the collected shift information and stores it in a database. The server checks the input data for duplicates and errors and makes corrections as needed.

[0043] Specific example: A frontline manager uses a management terminal to enter the shift information for employees Yamada and Sato for the following day. The server analyzes this information and saves it to the database.

[0044] 3. Calculation and display of optimal staffing levels

[0045] The server predicts the expected number of customers and their needs based on customer information and employee shift schedules. This allows it to calculate the optimal staffing levels for each day and time slot.

[0046] The terminal displays the calculated optimal schedule to the user. The user reviews and modifies the information displayed on the terminal to determine the most efficient staffing arrangement.

[0047] Specific example: The server predicts 100 customers will visit the store the next day and uses that information to optimize the next day's shifts. The frontline manager checks the optimized schedule on their terminal and makes any necessary adjustments.

[0048] 4. Proposal and implementation of measures to improve customer service quality

[0049] The server generates measures to improve customer service quality based on customer feedback and historical data. These include reducing customer waiting times and improving the quality of service.

[0050] The terminal displays customer service quality improvement measures sent from the server to the user and encourages their implementation.

[0051] Specific example: The server detects that customer wait times are long during a particular period and suggests improving service speed. This suggestion is displayed on a terminal, and the frontline manager instructs staff to implement it.

[0052] 5. Notification of brand evaluation and achievement targets

[0053] The server calculates brand evaluation points based on accumulated feedback and performance data. These points are based on evaluation criteria such as prompt response and courteous customer service.

[0054] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[0055] Specific example: The server team recognizes its high rating for "prompt and courteous service" and proposes concrete measures to further enhance this. The frontline manager reviews the proposal and instructs employees to implement it.

[0056] In this way, by having servers, terminals, and users each fulfill their respective roles, a system is realized that improves customer satisfaction and enables efficient store operations. This system allows for optimal staffing and high-quality customer service, thereby enhancing brand value.

[0057] The following describes the processing flow.

[0058] Step 1:

[0059] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[0060] Step 2:

[0061] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[0062] Step 3:

[0063] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0064] Step 4:

[0065] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[0066] Step 5:

[0067] The server predicts the expected number of customers and their needs based on customer information and shift information. Based on this prediction, it calculates the optimal staffing levels for each time slot.

[0068] Step 6:

[0069] The terminal displays the optimal schedule sent from the server to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[0070] Step 7:

[0071] The server notifies that the optimized schedule has resulted in successful staff reductions and increased efficiency. The frontline manager reviews the notification and updates the shift schedule accordingly.

[0072] Step 8:

[0073] The server generates measures to improve customer service quality based on customer feedback and historical data. These include reducing customer waiting times and improving the quality of service.

[0074] Step 9:

[0075] The terminal displays suggestions from the server for improving customer service quality to the user and encourages them to implement specific improvement measures. The user reviews the suggestions and instructs employees to implement them.

[0076] Step 10:

[0077] The server calculates brand evaluation points based on feedback and performance data. It reviews evaluation items such as prompt response and courteous customer service and proposes measures to improve brand value.

[0078] Step 11:

[0079] The device notifies the user of brand evaluation points and achievement targets, and proposes a specific action plan. The user then develops an implementation plan based on the proposal and shares it with employees.

[0080] In this way, a system is built that achieves efficient store operations and high customer satisfaction through the processing flow from step 1 to step 11.

[0081] (Example 1)

[0082] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0083] Traditional store management systems made it difficult to efficiently manage customer information and employee shift schedules, hindering optimal staffing. Furthermore, there was a lack of a system that consistently handled advanced store management tasks such as improving customer satisfaction, calculating brand evaluation points, and notifying achievement targets. As a result, challenges arose, including declining customer satisfaction, reduced staff efficiency, and slower brand value development.

[0084] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0085] In this invention, the server includes means for collecting basic customer information, means for storing the collected basic customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for calculating the optimal staffing arrangement using a machine learning model based on customer information and shift information, means for displaying the optimized schedule to the user and prompting confirmation and correction, means for generating and proposing measures to improve the quality of customer service based on customer feedback, means for displaying the proposed quality improvement measures and prompting their implementation, and means for calculating brand evaluation points based on accumulated feedback and performance data and notifying the achievement target. As a result, customer information and employee shift information can be centrally managed, and by providing optimal staffing and high-quality customer service, it becomes possible to improve customer satisfaction and operate stores efficiently.

[0086] "Customer basic information" refers to basic data about customers who visit the store, such as their name, contact information, and past purchase history.

[0087] A "database" is an information system designed to efficiently store and manage collected information, and is designed to allow for easy searching and updating of data.

[0088] "Employee shift information" refers to data regarding the working days, start times, and end times of employees working at the store.

[0089] A "machine learning model" is an artificial intelligence technology used to analyze large amounts of data and identify patterns and make predictions. In this invention, it is used to calculate the optimal staffing arrangement.

[0090] An "optimized schedule" is a work schedule calculated based on each employee's shift information and the predicted number of customers, resulting in the most efficient staffing arrangement.

[0091] "Feedback" refers to opinions and evaluations provided by customers, and is information that can be used to improve the quality of customer service and enhance the overall service.

[0092] "Proposed quality improvement measures" refer to specific suggestions and measures to improve the quality of customer service and operations, generated based on collected data and feedback.

[0093] "Brand evaluation points" are a numerical indicator of brand value calculated based on customer satisfaction and service quality.

[0094] "Achievement targets" are specific goals set to enhance brand value and represent the standards that employees and the entire store should strive for.

[0095] Modes for carrying out the invention

[0096] This invention is a system that collects and manages basic customer information and employee shift information, and uses this information to achieve optimal staffing. This system aims to improve the efficiency of store operations and enhance customer satisfaction. The following details specific embodiments for implementing this invention.

[0097] System Configuration

[0098] A system primarily consists of three components: servers, terminals, and users.

[0099] The server plays a central role in collecting, analyzing, and storing information. For example, a web application server using the Python Flask framework can be linked to a MySQL® database.

[0100] The terminal functions as an interface for users to input, confirm, and modify information. The terminal utilizes a computer or tablet installed in the store and connects to the server via a web browser.

[0101] Users are store staff and managers who use terminals to input, verify, and modify information.

[0102] Collection and storage of customer information

[0103] 1. The device displays a template screen for the customer to enter their basic information (name, contact information, past purchase history, etc.).

[0104] 2. The user (store staff) enters the customer's basic information. Once the input is complete, press the "Confirm" button on the terminal.

[0105] 3. The terminal sends the input information to the server when the "Confirm" button is pressed.

[0106] 4. The server validates the received information (e.g., checks the email format, checks for required fields) and saves it to the MySQL database.

[0107] Specific example:

[0108] For example, when Mr. Tanaka visits the store, a user (staff member) enters information into a terminal. Once the input is complete, the staff member presses the "Confirm" button. The terminal sends the data to the server, which receives the data, verifies it, and then saves it to the database.

[0109] Entering and managing employee shift information

[0110] 1. The terminal displays a shift information input form on the management screen.

[0111] 2. The user (frontline manager) enters information such as the employee's name, workday, start time, and end time.

[0112] 3. Once you have finished entering the information, press the "Send" button on the device.

[0113] 4. The server processes the received shift information, checks the data integrity, and saves it to the MySQL database.

[0114] Specific example:

[0115] The frontline manager enters Yamada and Sato's shifts for the next day into the terminal and presses the "Send" button. The server receives the data, checks its integrity, and saves it to the database.

[0116] Calculation and display of optimal staffing levels

[0117] 1. The server uses a machine learning model (e.g., the scikit-learn library in Python) to analyze past customer data and shift information and calculate the predicted number of customers for the following day.

[0118] 2. The server calculates the optimal staffing arrangement based on the estimated number of customers it has calculated.

[0119] 3. The server sends the calculated optimal schedule to the terminal.

[0120] 4. The device displays the optimal schedule for the user, and the user makes adjustments as needed.

[0121] Specific example:

[0122] The server predicts 100 customers for the next day and uses that information to calculate the optimal staffing allocation. The server sends the calculation results to a terminal, where the frontline manager reviews the displayed schedule and makes any necessary adjustments.

[0123] Proposal and implementation of measures to improve customer service quality

[0124] 1. The server analyzes customer feedback and historical data to generate measures to improve customer service quality (e.g., reducing waiting times, revising customer service manuals). The Python Pandas library is used for data analysis.

[0125] 2. The server sends the generated quality improvement measures to the terminal.

[0126] 3. The terminal displays quality improvement measures suggested to the user, and the user instructs staff to implement them.

[0127] Specific example:

[0128] The server detects when customer wait times are long during specific periods and uses that information to suggest improvements to service speed. These suggestions are displayed on terminals, and frontline managers instruct staff to implement these improvements.

[0129] Brand evaluation and notification of achievement goals

[0130] 1. The server calculates brand evaluation points based on accumulated feedback and performance data. The Statsmodels library in Python is used for statistical analysis.

[0131] 2. The server sends these evaluation points and achievement targets to the terminal.

[0132] 3. The device notifies the user of evaluation points and achievement goals, and proposes specific actions to improve brand value.

[0133] Specific example:

[0134] The server calculates brand evaluation points and notifies the customer that they have a high rating for "prompt and courteous service." The frontline manager then uses this information to propose specific improvement measures to the staff.

[0135] Example of a prompt

[0136] By inputting prompts like the following into the AI ​​model, you can support the generation of optimal staffing and quality improvement measures:

[0137] "Please calculate the optimal staffing level based on customer information and employee shift schedules."

[0138] "Analyze past data and propose measures to improve customer service quality at our stores."

[0139] In this way, a system is built in which servers, terminals, and users cooperate at each step, aiming for efficient business operations and improved customer satisfaction.

[0140] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0141] Program processing flow

[0142] Step 1: Collecting and storing customer information

[0143] 1. The terminal enters customer information.

[0144] The terminal displays a web form, allowing users (store staff) to input information.

[0145] Input: Customer's name, contact information, and past purchase history.

[0146] Output: Information entered into the terminal.

[0147] Specific action: The user enters customer data and presses the "Confirm" button.

[0148] 2. Sending information from the terminal to the server.

[0149] The terminal sends the entered customer information to the server.

[0150] Input: Customer information entered into the terminal.

[0151] Output: Data sent to the server.

[0152] Specific actions: Establish a connection with the server and send customer data.

[0153] 3. The server receives the information and performs validation.

[0154] The server performs validation on the received information (e.g., checking the email format, verifying required fields).

[0155] Input: Customer information received by the server.

[0156] Output: Validated data or error messages.

[0157] Specific actions: Check the format and verify the presence of required fields.

[0158] 4. The server saves the information to the database.

[0159] The server saves the validated information to a MySQL database.

[0160] Input: Customer information that has passed validation.

[0161] Output: Records stored in the database.

[0162] Specific operation: Execute a MySQL query and insert data into the database.

[0163] Step 2: Enter and manage employee shift information

[0164] 1. The terminal enters the shift information.

[0165] The terminal displays a shift information input form, allowing the user (frontline manager) to input the information.

[0166] Input: Employee's name, workday, start time, end time.

[0167] Output: Shift information entered into the terminal.

[0168] Specific action: The frontline manager enters the shift information and presses the "Submit" button.

[0169] 2. Sending information from the terminal to the server.

[0170] The terminal sends the entered shift information to the server.

[0171] Input: Shift information entered into the terminal.

[0172] Output: Data sent to the server.

[0173] Specific actions: Establish a connection with the server and send shift information.

[0174] 3. The server receives the information and checks its integrity.

[0175] The server analyzes the received shift information and checks for duplicates and inconsistencies.

[0176] Input: Shift information received by the server.

[0177] Output: Data with integrity checked, or error messages.

[0178] Specific operation: Detects duplicate data and inconsistent time zones.

[0179] 4. The server saves the information to the database.

[0180] The server saves the shift information that has passed the integrity check to the MySQL database.

[0181] Input: Shift information that has been checked for consistency.

[0182] Output: Records stored in the database.

[0183] Specific operation: Execute a MySQL query and insert data into the database.

[0184] Step 3: Calculation and display of optimal staffing.

[0185] 1. The server calculates the optimal staffing.

[0186] The server uses a machine learning model (e.g., scikit-learn) to analyze historical data and calculate the predicted number of store visits.

[0187] Input: Saved customer information and shift information.

[0188] Output: Predicted number of customers and optimal staffing.

[0189] Specific operation: Input numerical data into the model and obtain prediction results.

[0190] 2. Send the optimization schedule from the server to the terminal.

[0191] The server sends the calculated optimal schedule to the terminal.

[0192] Input: The calculated optimal schedule.

[0193] Output: Data sent to the terminal.

[0194] Specific action: Send schedule data to the device.

[0195] 3. The device displays the optimization schedule.

[0196] The device displays the optimal schedule to the user and prompts them to review and make corrections.

[0197] Input: Optimization schedule received from the server.

[0198] Output: The schedule displayed on the terminal.

[0199] Specific action: Display the schedule in the user interface.

[0200] Step 4: Propose and implement measures to improve customer service quality.

[0201] 1. The server generates quality improvement measures.

[0202] The server analyzes the accumulated feedback and generates measures to improve customer service quality.

[0203] Input: Past feedback and customer information.

[0204] Output: Proposed quality improvement measures.

[0205] Specific actions: Conduct data analysis and create improvement proposals.

[0206] 2. Send quality improvement measures from the server to the terminal.

[0207] The server sends the generated quality improvement measures to the terminal.

[0208] Input: Created quality improvement measures.

[0209] Output: Data sent to the terminal.

[0210] Specific action: Send the proposal to the terminal.

[0211] 3. The device displays quality improvement measures.

[0212] The device displays quality improvement measures to the user and encourages them to implement them.

[0213] Input: Quality improvement measures received from the server.

[0214] Output: Suggestions displayed on the terminal.

[0215] Specific actions: Display the proposed content and show a message encouraging implementation.

[0216] Step 5: Brand evaluation and notification of achievement goals

[0217] 1. The server calculates the evaluation points.

[0218] The server analyzes accumulated feedback and performance data to calculate brand evaluation points.

[0219] Input: Past feedback and performance data.

[0220] Output: Calculated evaluation points.

[0221] Specific operation: Apply the evaluation algorithm and calculate the evaluation points.

[0222] 2. Send evaluation points and targets from the server to the terminal.

[0223] The server sends the calculated evaluation points and achievement targets to the terminal.

[0224] Input: Calculated evaluation points and achievement targets.

[0225] Output: Data sent to the terminal.

[0226] Specific action: Send evaluation information to the terminal.

[0227] 3. The device displays evaluation points and goals.

[0228] The device notifies the user of their evaluation points and achievement goals, and suggests specific actions.

[0229] Input: Evaluation points and achievement goals received from the server.

[0230] Output: Notifications displayed on the device.

[0231] Specific action: Display a notification message and provide specific suggestions.

[0232] The above describes the specific processing flow of this system's program.

[0233] (Application Example 1)

[0234] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0235] Traditional store operations often failed to effectively utilize customer information and employee shift data, resulting in unoptimized staffing. This led to staff shortages during peak hours, lowering customer satisfaction, and unnecessary labor costs during off-peak hours. Furthermore, the lack of real-time suggestions for improving customer service quality based on customer feedback and the inability to predict staffing levels made rapid responses difficult.

[0236] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0237] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee working hours information, means for analyzing the input working hours information and storing it in a database, means for calculating the optimal staffing based on customer information and working hours information, means for displaying the optimized timetable to the user and prompting confirmation and correction, means for proposing measures to improve the quality of customer service based on customer satisfaction, means for displaying the proposed improvement measures and prompting implementation, means for calculating evaluation points and notifying achievement targets, means for predicting the number of expected customers and calculating the necessary workforce based on that, means for predicting and presenting the optimal staffing in real time, means for analyzing customer feedback using a generative AI model and generating measures to improve the quality of customer service, and means for supporting the efficiency of store operations using prompt messages. This makes it possible to efficiently allocate staff, improve customer satisfaction, and optimize labor costs at the same time.

[0238] "Customer information" refers to data about a customer, such as basic information, contact information, and past purchase history.

[0239] "Means of collection" refers to the function of inputting customer information into a terminal and transmitting it to a server.

[0240] "Means of saving to a database" refers to the function of saving collected data in a digital format and maintaining it in a format that allows for access and editing as needed.

[0241] "Working hours information" refers to data related to shifts, such as employees' working days, start times, and end times.

[0242] "Means of analysis" refers to the function of analyzing collected data and extracting patterns and trends.

[0243] "Optimal staffing" refers to calculating the most suitable staffing configuration for store operations based on factors such as the expected number of customers and employee working hours.

[0244] An "optimized timetable" refers to a shift schedule based on a calculated optimal staffing arrangement.

[0245] "Means to prompt review and correction" refers to a function that presents an optimized schedule to the user, allowing the user to perform final review and make necessary corrections.

[0246] "Means of proposing quality improvement measures" refers to a function that generates improvement measures for customer service methods and service content based on customer satisfaction and feedback.

[0247] "Means for displaying proposed improvement plans and encouraging their implementation" refers to a function that displays generated quality improvement measures to the user and encourages their implementation.

[0248] "Evaluation points" refer to performance indicators for stores and brands that are calculated based on customer feedback and performance data.

[0249] "Means of notifying achievement targets" refers to a function that notifies users of the targets that stores and brands should achieve based on the calculated evaluation points.

[0250] "Methods for predicting the number of customers expected to visit" refers to functions that predict future customer visits based on past data and trends.

[0251] "Means for calculating the required workforce" refers to a function that calculates the number of employees needed for a given time slot based on the expected number of customers.

[0252] "Means of predicting and presenting in real time" refers to a function that calculates the optimal staffing allocation in real time based on current data and presents the results to the user.

[0253] A "generative AI model" refers to an artificial intelligence model that uses machine learning or deep learning to analyze data and automatically perform specific tasks.

[0254] A "prompt message" refers to text used to give specific instructions or data input to an AI model.

[0255] The system for carrying out this invention includes a process for collecting customer information and employee working hours information, storing it in a database, and calculating the optimal staffing arrangement based on that information. Detailed embodiments of this system are described below.

[0256] Collection and storage of customer information

[0257] Customer information is entered on a terminal and sent to the server. The terminal retrieves basic customer information (name, contact information, past purchase history, etc.) and sends this data to the server. The server stores the received data in a database and checks for errors in the input data to ensure accuracy.

[0258] Input and management of employee working hours information

[0259] The user (store manager) uses a management terminal to input employee shift information. Specifically, they input the employee's name, workday, start time, and end time. The server analyzes the received shift information and stores it in a database.

[0260] Calculation and display of optimal staffing levels

[0261] The server uses customer information and working hours data to predict the number of expected customers and their needs, and calculates the optimal staffing allocation. It also calculates the required workforce based on the expected number of customers and generates an optimal shift schedule based on the results. The terminal displays the calculated and optimized timetable to the user, prompting them to review and make any necessary adjustments.

[0262] Proposal and implementation of measures to improve customer service quality

[0263] The server analyzes customer feedback and historical data to generate measures to improve customer service quality. These include reducing customer waiting times and improving the quality of service. The terminal displays the customer service improvement measures generated using the AI ​​model to the user and encourages their implementation.

[0264] Brand evaluation and notification of achievement goals

[0265] The server calculates evaluation points based on accumulated feedback and performance data, and notifies the brand of its evaluation points and achievement targets. The terminal proposes specific actions to the user to improve brand value and encourages their implementation.

[0266] Specific example

[0267] For example, the server predicts the number of customers visiting the store the following day, Monday, and uses that result to calculate the necessary workforce. It predicts 50 customers at 10 AM, requiring 5 staff members. At 1 PM, it predicts 30 customers, requiring 3 staff members. This optimized schedule is displayed on the user's terminal, allowing them to review and modify it.

[0268] Example of a prompt

[0269] "Calculate the optimal shifts for each time slot on Monday. Since the number of customers varies at each time, allocate the appropriate number of employees accordingly. Please write a weekday shift optimization program."

[0270] In this way, this system processes data accurately and efficiently at each step, enabling optimal staffing and thereby increasing customer satisfaction and improving the efficiency of store operations.

[0271] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0272] Step 1: Collecting customer information

[0273] The terminal inputs basic information of customers who visit the store (name, contact information, past purchase history, etc.). This input data is entered by the terminal and sent to the server. The server stores the received customer information in a database. It also checks for errors in the input content to ensure accuracy.

[0274] Step 2: Enter employee working hours information

[0275] The user (store manager) uses a management terminal to input employee work time information (name, workday, start time, and end time, etc.). This input data is entered via the management terminal and sent to the server. The server stores the received work time information in a database, checks for duplicates or errors in the input data, and makes corrections as necessary.

[0276] Step 3: Predicting the number of expected customers

[0277] The server predicts the number of expected customers based on customer information and working hours data. The server generates a customer visit prediction model using accumulated historical data. This generated AI model is used to predict the number of expected customers for a specific date and time. The input here is historical customer data, and the output is the predicted number of customers.

[0278] Step 4: Calculating the optimal staffing levels

[0279] The server calculates the required workforce for each time slot based on the predicted number of customers. The server calculates the number of employees needed based on the expected number of customers and then calculates the optimal staffing. The input here is the expected number of customers, and the output is the required number of employees.

[0280] Step 5: Display the optimized timetable

[0281] The server transmits the result of the optimal personnel allocation calculated by it to the terminal. The terminal displays this optimized schedule to the user and prompts for confirmation and correction. The input here is the optimized shift schedule, and the output is the feedback of confirmation and correction by the user.

[0282] Step 6: Proposal of measures to improve customer service quality

[0283] The server analyzes customer feedback and past data to generate measures to improve customer service quality. The feedback data is analyzed using a generation AI model to generate specific improvement measures. The terminal displays these quality improvement measures to the user and prompts for their implementation. The input here is the feedback data, and the output is the proposed quality improvement measures

[0284] Step 7: Notification of brand evaluation and achievement goals

[0285] The server calculates evaluation points based on the accumulated feedback and performance data and notifies the user. The terminal displays these evaluation points and achievement goals to the user and proposes specific actions for improving brand value. The input here is the feedback and performance data, and the output is the evaluation points and achievement goals.

[0286] Through the above steps, this invention can efficiently perform personnel allocation and achieve customer satisfaction and improved store operation efficiency.

[0287] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion. <00009!0> This invention is a system that collects and manages customer information and employee shift information, and based on this, realizes optimal staffing. Furthermore, by combining this with an emotion engine, it recognizes and analyzes user emotions to improve the quality of customer service and enhance brand value. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[0289] 1. Collection and storage of customer information

[0290] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[0291] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[0292] Specific example: Mr. Tanaka comes into the store and registers his name and contact information on a terminal. The terminal sends this information to the server, which stores the information in a database for verification.

[0293] 2. Inputting and managing employee shift information

[0294] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0295] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[0296] Specific example: A frontline manager uses a management terminal to enter the shift information for employees Yamada and Sato for the following day. The server analyzes this information and saves it to the database.

[0297] 3. Calculation and display of optimal staffing levels

[0298] The server predicts the expected number of customers and their needs based on customer information and employee shift schedules. Based on these predictions, it calculates the optimal staffing levels for each time slot.

[0299] The terminal displays the calculated optimal schedule to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[0300] Specific example: The server predicts 100 customers will visit the store the next day and uses that information to optimize the next day's shifts. The frontline manager checks the optimized shift schedule on a terminal and makes any necessary adjustments.

[0301] 4. Emotion recognition and analysis using an emotion engine

[0302] The device is equipped with an emotion engine that recognizes the emotions of employees and customers in the store in real time. The emotion engine identifies the user's emotional state through facial recognition technology and voice analysis.

[0303] The server receives emotional data recognized by the emotion engine and stores it in a database. Furthermore, it analyzes this data to extract areas for improvement in store operations.

[0304] Specific example: An emotion engine recognizes the frequency of an employee's smiles and sends this information to a server. The server analyzes this information and suggests appropriate countermeasures if it detects certain signs of stress.

[0305] 5. Proposal and implementation of measures to improve customer service quality

[0306] The server generates measures to improve customer service quality based on customer feedback and emotion engine data. This includes reducing customer waiting times and improving the quality of service.

[0307] The terminal displays the customer service improvement measures sent from the server to the user and encourages its implementation.

[0308] Specific example: The server grasps that the waiting time of customers is long in a specific time period and proposes to improve the customer service speed. The proposal is displayed on the terminal, and the front-line manager instructs the staff to take action.

[0309] 6. Notification of Brand Evaluation and Achieved Goals

[0310] The server calculates the brand evaluation points based on the accumulated feedback, sentiment data, and performance data. Based on evaluation items such as prompt response and considerate customer service.

[0311] The terminal notifies the user of the calculated evaluation points and achieved goals, and proposes specific actions for improving brand value.

[0312] Specific example: The server grasps that the evaluation of "prompt and considerate response" is high and proposes specific measures to further strengthen it. The front-line manager confirms the proposal and instructs the employees to implement it.

[0313] In this way, by each of the server, terminal, and user playing their respective roles, a system is constructed that realizes efficient store operation utilizing sentiment recognition and high customer satisfaction. This system can simultaneously achieve optimal staffing, high-quality customer service, and improvement of brand value through utilization of sentiment data.

[0314] The following explains the processing flow.

[0315] Step 1:

[0316] The terminal inputs the basic information (name, contact information, past purchase history, etc.) of the customers who come to the store. This information is input after obtaining the consent of the customers.

[0317] Step 2:

[0318] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[0319] Step 3:

[0320] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0321] Step 4:

[0322] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[0323] Step 5:

[0324] The server predicts the expected number of customers and their needs based on customer information and shift information. Based on this prediction, it calculates the optimal staffing levels for each time slot.

[0325] Step 6:

[0326] The terminal displays the optimal schedule sent from the server to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[0327] Step 7:

[0328] The server notifies that the optimized schedule has resulted in successful staff reductions and increased efficiency. The frontline manager reviews the notification and updates the shift schedule accordingly.

[0329] Step 8:

[0330] The device uses an emotion engine to recognize the emotions of employees and customers in the store in real time. The emotion engine identifies the user's emotional state through facial recognition technology and voice analysis.

[0331] Step 9:

[0332] The server receives emotional data recognized by the emotion engine and stores it in a database. Furthermore, it analyzes this data to extract areas for improvement in store operations.

[0333] Step 10:

[0334] The server generates measures to improve customer service quality based on customer feedback and emotion engine data. This includes reducing customer waiting times and improving the quality of service.

[0335] Step 11:

[0336] The terminal displays suggestions for improving customer service quality, sent from the server, to the user and encourages their implementation. The user reviews the suggestions and issues instructions to employees to implement them.

[0337] Step 12:

[0338] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. It reviews evaluation items such as prompt response and courteous customer service and proposes measures to improve brand value.

[0339] Step 13:

[0340] The device notifies the user of brand evaluation points and achievement targets, and proposes a specific action plan. The user then develops an implementation plan based on the proposal and shares it with employees.

[0341] In this way, through the processing flow from Step 1 to Step 13, a system is built that utilizes emotion recognition to achieve efficient store operations and high customer satisfaction.

[0342] (Example 2)

[0343] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0344] Traditional store management systems often rely on manual processes for managing customer information and employee shifts, making efficient staffing and improved customer service difficult. Furthermore, there's a lack of systems to monitor and respond to employee and customer emotional states in real time. This leads to problems such as decreased customer satisfaction and increased employee stress. Therefore, there's a need to develop systems that support efficient and effective store operations to address these challenges.

[0345] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0346] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for predicting the number of expected customers based on the collected customer information and shift information, means for calculating the optimal staffing based on the predicted number of customers, means for displaying the calculated optimization schedule to the user and proposing measures to improve the quality of customer service based on customer satisfaction, means for displaying the proposed measures to improve the quality of customer service and encouraging their implementation, means for calculating brand evaluation points based on accumulated feedback, emotional data, and performance data and notifying the achievement target, means for recognizing and analyzing the emotions of users and employees through facial recognition and voice analysis, and means for proposing stress management and improvements in customer service quality based on emotional data. This makes it possible to simultaneously achieve efficient staffing, high-quality customer service, and improved brand value through the use of emotional data.

[0347] "Customer information" refers to basic information such as the name, contact information, and past purchase history of customers who use the store.

[0348] A "database" refers to a system that stores and manages customer information, shift information, etc., and has the function of searching and updating data as needed.

[0349] "Shift information" refers to information about an employee's working hours, such as the employee's name, working days, start time, and end time.

[0350] "Optimal staffing" refers to an employee allocation plan that maximizes store operational efficiency and customer satisfaction, based on collected customer and shift information.

[0351] An "emotion engine" refers to a system that uses facial recognition and voice analysis to identify the emotional states of employees and customers, and collects and analyzes this data.

[0352] "Feedback" refers to information based on opinions and evaluations received from customers and employees.

[0353] "Brand evaluation points" refer to indicators used to evaluate the value and quality of a brand, calculated based on accumulated feedback, sentiment data, and performance data.

[0354] "Stress management" refers to the process of monitoring employees' stress levels based on recognized emotional data and proposing appropriate countermeasures.

[0355] "Customer service quality" refers to the quality of service and interaction with customers, and includes prompt responses, courteous service, and appropriate problem-solving.

[0356] "Expected number of visitors" refers to the number of future visitors predicted based on past data and current reservation information.

[0357] Modes for carrying out the invention

[0358] This invention is a system that collects and manages customer information and employee shift information, and based on this, realizes optimal staffing. Furthermore, by combining this with an emotion engine, it recognizes and analyzes user emotions to improve the quality of customer service and enhance brand value. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[0359] 1. Collection and storage of customer information

[0360] The terminal provides a function to input basic information (name, contact information, past purchase history, etc.) of customers who visit the store. The terminal uses a PC or tablet and has a store-specific input application installed.

[0361] The user (store clerk) enters the customer's information into the input form displayed on the screen.

[0362] The terminal validates the entered information and sends it to the server.

[0363] The server uses a database management system (DBMS) to receive customer information sent from the terminal and store it in the database.

[0364] Specific example: For instance, a new customer enters the store, and an employee uses a terminal to input the customer's basic information. The terminal validates the information and sends it to the server. The server saves the information to a database and returns a notification to the terminal that the information has been saved.

[0365] 2. Inputting and managing employee shift information

[0366] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0367] The terminal provides a form for entering shift information. The terminal is a PC or tablet with a dedicated shift management application installed.

[0368] The terminal validates the entered shift information and sends it to the server.

[0369] The server has the functionality to store and verify the collected shift information in a database.

[0370] Specific example: A frontline manager uses a management terminal to input employee shift information. The terminal validates the information and sends it to the server. The server receives the information and stores it in a database.

[0371] 3. Calculation and display of optimal staffing levels

[0372] The server runs an algorithm to predict the expected number of customers based on customer information and employee shift information. This algorithm uses a prediction model written in Python.

[0373] The server calculates the optimal staffing based on the prediction results and sends the result to the terminal. Optimization algorithms such as linear programming are used for optimization.

[0374] The terminal provides a mechanism to display the calculation results to the user.

[0375] Specific example: The server predicts 100 customers will visit the store the next day and optimizes the shift schedule based on that information. The frontline manager checks the schedule on their terminal and makes any necessary adjustments.

[0376] 4. Emotion recognition and analysis using an emotion engine

[0377] The device recognizes the emotions of employees and customers in real time through an emotion engine. The emotion engine is connected to a facial recognition camera and microphone, and analyzes facial expressions and voice tone using OpenCV and TENSORFLOW® software.

[0378] The server receives sentiment data sent from the terminal, stores it in a database, and analyzes it. The analysis uses the Python data analysis libraries Pandas and Matplotlib.

[0379] Specific example: The emotion engine recognizes the frequency of an employee's smiles and sends this information to the server. The server analyzes this information, assesses the employee's stress level, and suggests appropriate countermeasures.

[0380] 5. Proposal and implementation of measures to improve customer service quality

[0381] The server generates strategies for improving customer service quality based on customer feedback and sentiment data. Natural language processing (NLP) algorithms are used to analyze the feedback.

[0382] The device displays the generated suggestions to the user and encourages them to implement them.

[0383] Specific example: The server identifies customer wait times as long during certain periods based on feedback and creates suggestions to improve service speed. A terminal displays these suggestions, and the frontline manager instructs staff to implement them.

[0384] 6. Notification of brand evaluation and achievement targets

[0385] The server calculates brand evaluation points based on feedback, sentiment data, and performance data. Evaluation systems and algorithms are used for the calculation.

[0386] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[0387] Specific example: Feedback data reveals that the server has a high rating for "prompt and courteous response," and measures to improve it are proposed. The frontline manager checks the proposal on their terminal and instructs employees to implement it.

[0388] Example of a prompt:

[0389] "Please explain how the server calculates the optimal staffing based on the number of customers expected the following day and employee shift information, and how the results are displayed on the terminal."

[0390] "Please describe the process of using an emotion engine to recognize employees' emotions in real time and analyzing that data on a server."

[0391] As described above, by having the server, terminal, and user each fulfill their respective roles, we will build a system that utilizes emotion recognition to achieve efficient store operations and high customer satisfaction.

[0392] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0393] Step 1: Collect and store customer information

[0394] Specific actions

[0395] The terminal displays a screen where customers who visit the store can enter their basic information (name, contact information, past purchase history, etc.).

[0396] The user (store clerk) enters customer information into the input form displayed on the screen. This information includes name, contact information, and past purchase history.

[0397] The terminal validates the entered information and sends it to the server. For example, it checks if the name format is correct and if the contact information includes all required fields.

[0398] Input and output

[0399] Input: Your name, contact information, and past purchase history

[0400] Data processing and calculation: Validation (checking the accuracy of the data)

[0401] Output: Send validated customer information to the server

[0402] The server receives customer information sent from the terminal and saves it to the database. Upon successful saving, it sends a save completion notification back to the terminal.

[0403] Step 2: Enter and manage employee shift information

[0404] Specific actions

[0405] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0406] The terminal validates the entered shift information and sends it to the server. For example, it checks whether the work days are entered in the correct format and whether there are any duplicates.

[0407] Input and output

[0408] Input: Employee's name, workday, start time, and end time

[0409] Data processing and calculation: Validation (checking the accuracy of the data)

[0410] Output: Send validated shift information to the server.

[0411] The server saves the received shift information to the database and verifies it. If the saving is successful, it sends a confirmation completion notification to the terminal.

[0412] Step 3: Calculation and display of optimal staffing levels

[0413] Specific actions

[0414] The server runs a predictive model that forecasts the number of customers expected to visit, based on stored customer information and employee shift information. The prediction uses a prediction algorithm written in a Python program.

[0415] The server calculates the optimal staffing based on the prediction results and sends the result to the terminal. Optimization algorithms such as linear programming are used for optimization.

[0416] The terminal provides a screen to display the calculation results.

[0417] Input and output

[0418] Input: Saved customer information, employee shift information

[0419] Data processing and calculation: Predicting the number of customers expected, calculating optimal staffing levels.

[0420] Output: Send optimized staffing schedule to terminal

[0421] As a concrete example, the server predicts that 100 customers will visit the store the next day, and uses that information to optimize the shift schedule. The frontline manager checks the schedule on their terminal and makes any necessary adjustments.

[0422] Step 4: Emotion recognition and analysis using the emotion engine

[0423] Specific actions

[0424] The device recognizes the emotions of employees and customers in real time through an emotion engine. The emotion engine is connected to a facial recognition camera and microphone, and uses OpenCV and TensorFlow software to analyze facial expressions and voice tone.

[0425] The device sends the analyzed emotion data to the server.

[0426] The server receives emotional data, stores it in a database, and analyzes it.

[0427] Input and output

[0428] Input: Face recognition and voice analysis data

[0429] Data processing and calculation: Identification of emotional states, data analysis

[0430] Output: Accumulate analysis results and suggest appropriate countermeasures.

[0431] As a concrete example, the emotion engine recognizes the frequency of an employee's smile and sends this information to the server. The server analyzes this information, assesses signs of employee stress, and suggests appropriate countermeasures.

[0432] Step 5: Propose and implement measures to improve customer service quality.

[0433] Specific actions

[0434] The server generates strategies for improving customer service quality based on feedback and sentiment data. Natural language processing (NLP) algorithms are used to analyze the feedback.

[0435] The device displays the generated suggestions to the user and encourages them to implement them.

[0436] Input and output

[0437] Input: Feedback data, sentiment data

[0438] Data processing and calculation: Feedback analysis, generation of quality improvement measures.

[0439] Output: Display the recommendations on the device.

[0440] As a concrete example, a server identifies customer wait times as long during specific periods based on feedback and creates suggestions to improve service speed. A terminal displays these suggestions, and the frontline manager instructs staff to implement them.

[0441] Step 6: Brand evaluation and notification of achievement goals

[0442] Specific actions

[0443] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. An evaluation system and algorithm are used for the evaluation calculation.

[0444] The device notifies the user of the calculated evaluation points and achievement targets, and suggests actions to improve brand value.

[0445] Input and output

[0446] Input: Feedback data, sentiment data, performance data

[0447] Data processing and calculation: Calculation of brand evaluation points, setting of achievement targets.

[0448] Output: Evaluation points and achievement goals are notified to the device.

[0449] As a concrete example, accumulated data reveals that the server has a high rating for "prompt and courteous response," and a proposal is created to further enhance this. The frontline manager reviews the proposal on their terminal and instructs employees to implement it.

[0450] (Application Example 2)

[0451] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0452] Currently, building a system that optimizes store operations while simultaneously improving customer service quality and brand value is extremely difficult. Furthermore, to enhance customer satisfaction, it's necessary to appropriately recognize employee emotions and implement appropriate responses immediately. However, no technology yet exists that can integrate these elements into a single system. Therefore, there is a need to develop a system that can simultaneously optimize staffing, improve customer service quality, and enhance brand value.

[0453] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0454] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for calculating the optimal staffing arrangement based on customer information and shift information, means for displaying the optimized schedule to the user and prompting confirmation and correction, means for recognizing the emotional state of customers and employees in real time using emotion recognition technology, means for generating and displaying measures to improve customer service quality based on the emotional state, means for prompting the implementation of the proposed measures to improve customer service quality, and means for calculating brand evaluation based on accumulated emotional data and feedback data and notifying the achievement target. This makes it possible to improve customer satisfaction, optimize staffing, and simultaneously improve customer service quality and brand value.

[0455] "Customer information" refers to basic information about a customer, such as their name, contact information, and past purchase history.

[0456] "Collection methods" refer to devices and programs used to acquire customer information and employee shift information.

[0457] "Means of storing data in a database" refers to devices or programs used to store collected data in a database.

[0458] "Employee shift information" refers to information about the employee's name, workday, start time, and end time.

[0459] "Analysis means" refers to devices or programs used to analyze collected information and extract necessary data.

[0460] "Optimal staffing" refers to the best possible staffing arrangement in store operations to maximize customer satisfaction.

[0461] "Schedule display means" refers to a device or program that displays the calculated optimal schedule to the user and prompts them to approve and modify it.

[0462] "Emotion recognition technology" refers to technology that uses facial recognition technology and voice analysis to recognize an individual's emotional state in real time.

[0463] "Quality improvement measure generation means" refers to a device or program that automatically generates customer service quality improvement measures based on collected data.

[0464] "Means for implementing quality improvement measures" refers to devices or programs that present generated quality improvement measures to users and encourage their implementation.

[0465] "Evaluation calculation means" refers to devices or programs used to calculate brand evaluations based on accumulated feedback and sentiment data.

[0466] "Means of notifying achievement targets" refers to devices or programs that notify users of achievement targets based on calculated brand evaluation points.

[0467] The following describes specific embodiments for carrying out the present invention.

[0468] First, let's explain the collection and storage of customer information. In stores, terminals provide a means for customers to enter basic information such as their name, contact information, and past purchase history when they visit the store. This information is entered with the customer's consent, and the server stores this information in a database and checks for any errors.

[0469] Next, we will explain the input and management of employee shift information. The user (store manager) uses a management terminal to input employee shift information. This shift information includes the employee's name, workday, start time, and end time. The server receives this shift information, stores it in the database, and checks for duplicate information and input errors.

[0470] The server predicts the expected number of customers and their needs based on customer information and employee shift information, and calculates the optimal staffing arrangement based on that. The calculated optimal schedule is displayed on the terminal, which the user can review and modify as needed.

[0471] Next, we will explain emotion recognition and analysis using the emotion engine. The terminal is equipped with an emotion engine that recognizes the emotions of employees and customers in the store in real time. This engine uses facial recognition technology and voice analysis to identify the user's emotional state. The server receives the recognized emotion data, stores it in a database, and performs analysis. Based on the results, it extracts areas for improvement in store operations.

[0472] This section describes the proposal and implementation of measures to improve customer service quality. The server generates these improvement measures based on customer feedback and data from the emotion engine. These measures include reducing customer waiting times and improving the quality of service. The terminal displays these suggestions to the user and encourages their implementation.

[0473] Finally, let's discuss brand evaluation and goal notification. The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. This reflects evaluations such as prompt response and courteous customer service. The terminal notifies the user of the calculated evaluation points and goals, and suggests specific actions to improve brand value.

[0474] Specific example:

[0475] A concrete example of collecting and storing customer information: When a customer enters the store, they scan a QR code (registered trademark), and their basic information is instantly entered. The server then stores this information in a database.

[0476] A concrete example of shift information management: An administrator uses a management terminal to enter employee shifts, which are then sent to a server.

[0477] Specific example of optimal staffing: The server calculates the optimal staffing based on the predicted number of customers and notifies the terminal. The administrator reviews this result and makes corrections as needed.

[0478] A concrete example of emotion recognition: An emotion engine identifies the emotions of employees and customers in real time and sends that data to a server.

[0479] Specific example of improving customer service quality: The server generates quality improvement measures based on feedback data and proposes them to employees via a terminal.

[0480] A concrete example of brand value evaluation: The server calculates evaluation points and notifies the terminal of the achievement target.

[0481] Example of a prompt:

[0482] "Please calculate the optimal staffing levels based on the following shift schedule."

[0483] "Based on the following sentiment data, please suggest areas for improvement in customer service quality."

[0484] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0485] Step 1:

[0486] Collection and storage of customer information

[0487] The terminal has a means of inputting basic information such as the customer's name, contact information, and past purchase history. This information is entered with the customer's consent, and the terminal sends it to the server. The server stores the received customer information in a database and checks for any errors in the information.

[0488] Input: Customer name, contact information, purchase history

[0489] Processing: Data integrity check

[0490] Output: Customer information is saved to the database.

[0491] Step 2:

[0492] Entering and managing employee shift information

[0493] The user (store manager) uses a management terminal to enter employee shift information (name, work days, start time, end time). The terminal sends this information to the server. The server stores the received shift information in a database and checks for input errors and duplicates.

[0494] Input: Employee's name, workday, start time, end time

[0495] Processing: Data integrity check

[0496] Output: Shift information is saved to the database.

[0497] Step 3:

[0498] Calculation of optimal staffing

[0499] The server predicts the expected number of customers and their needs based on customer information and employee shift information. Based on this, it calculates the optimal staffing for each time slot and sends the results to the terminal. The terminal displays the optimized schedule to the user and prompts them to review and make adjustments.

[0500] Input: Customer information, shift information

[0501] Processing: Forecasting using demand forecasting algorithms, optimization calculation of personnel allocation.

[0502] Output: The optimized schedule will be displayed on the device.

[0503] Step 4:

[0504] Emotion recognition and data analysis

[0505] The terminal uses its built-in emotion engine to recognize the emotions of employees and customers in the store in real time. This emotion data is sent from the terminal to a server, which stores it in a database. The server then analyzes the emotion data to identify areas for improvement in store operations.

[0506] Input: Facial images and audio data of employees and customers

[0507] Processing: Analysis using an emotion recognition algorithm

[0508] Output: Recognized emotion data is sent to the server and stored in the database.

[0509] Step 5:

[0510] Developing and managing measures to improve customer service quality.

[0511] The server generates suggestions for improving customer service quality based on customer feedback and data from the emotion engine. The terminal displays these suggestions to the user and encourages their implementation.

[0512] Input: Feedback data, sentiment data

[0513] Processing: Generation of suggestions using a customer service improvement algorithm.

[0514] Output: Measures to improve customer service quality are displayed on the terminal.

[0515] Step 6:

[0516] Brand valuation calculation and target notification

[0517] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. The terminal notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[0518] Input: Feedback data, sentiment data, performance data

[0519] Processing: Score calculation using a brand evaluation algorithm.

[0520] Output: Evaluation points and achievement goals are displayed on the device.

[0521] Through the above processing steps, servers, terminals, and users work together to improve customer satisfaction, optimize staffing, and simultaneously enhance customer service quality and brand value.

[0522] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0523] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0524] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0525] [Second Embodiment]

[0526] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0527] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0528] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0529] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0530] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0531] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0532] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0533] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0534] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0535] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0536] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0537] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0538] This invention is a system that collects and manages customer information and employee shift information, and uses this information to achieve optimal staffing. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[0539] 1. Collection and storage of customer information

[0540] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[0541] The server receives the entered customer information and stores it in the database. The server checks the entered information for errors to ensure accurate data collection.

[0542] Specific example: Customer Tanaka comes into the store and registers his name and contact information on a terminal. The terminal sends this information to the server, which stores the information in a database for verification.

[0543] 2. Inputting and managing employee shift information

[0544] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This includes each employee's name, workday, start time, and end time.

[0545] The server analyzes the collected shift information and stores it in a database. The server checks the input data for duplicates and errors and makes corrections as needed.

[0546] Specific example: A frontline manager uses a management terminal to enter the shift information for employees Yamada and Sato for the following day. The server analyzes this information and saves it to the database.

[0547] 3. Calculation and display of optimal staffing levels

[0548] The server predicts the expected number of customers and their needs based on customer information and employee shift schedules. This allows it to calculate the optimal staffing levels for each day and time slot.

[0549] The terminal displays the calculated optimal schedule to the user. The user reviews and modifies the information displayed on the terminal to determine the most efficient staffing arrangement.

[0550] Specific example: The server predicts 100 customers will visit the store the next day and uses that information to optimize the next day's shifts. The frontline manager checks the optimized schedule on their terminal and makes any necessary adjustments.

[0551] 4. Proposal and implementation of measures to improve customer service quality

[0552] The server generates measures to improve customer service quality based on customer feedback and historical data. These include reducing customer waiting times and improving the quality of service.

[0553] The terminal displays customer service quality improvement measures sent from the server to the user and encourages their implementation.

[0554] Specific example: The server detects that customer wait times are long during a particular period and suggests improving service speed. This suggestion is displayed on a terminal, and the frontline manager instructs staff to implement it.

[0555] 5. Notification of brand evaluation and achievement targets

[0556] The server calculates brand evaluation points based on accumulated feedback and performance data. These points are based on evaluation criteria such as prompt response and courteous customer service.

[0557] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[0558] Specific example: The server team recognizes its high rating for "prompt and courteous service" and proposes concrete measures to further enhance this. The frontline manager reviews the proposal and instructs employees to implement it.

[0559] In this way, by having servers, terminals, and users each fulfill their respective roles, a system is realized that improves customer satisfaction and enables efficient store operations. This system allows for optimal staffing and high-quality customer service, thereby enhancing brand value.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[0563] Step 2:

[0564] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[0565] Step 3:

[0566] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0567] Step 4:

[0568] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[0569] Step 5:

[0570] The server predicts the expected number of customers and their needs based on customer information and shift information. Based on this prediction, it calculates the optimal staffing levels for each time slot.

[0571] Step 6:

[0572] The terminal displays the optimal schedule sent from the server to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[0573] Step 7:

[0574] The server notifies that the optimized schedule has resulted in successful staff reductions and increased efficiency. The frontline manager reviews the notification and updates the shift schedule accordingly.

[0575] Step 8:

[0576] The server generates measures to improve customer service quality based on customer feedback and historical data. These include reducing customer waiting times and improving the quality of service.

[0577] Step 9:

[0578] The terminal displays suggestions from the server for improving customer service quality to the user and encourages them to implement specific improvement measures. The user reviews the suggestions and instructs employees to implement them.

[0579] Step 10:

[0580] The server calculates brand evaluation points based on feedback and performance data. It reviews evaluation items such as prompt response and courteous customer service and proposes measures to improve brand value.

[0581] Step 11:

[0582] The device notifies the user of brand evaluation points and achievement targets, and proposes a specific action plan. The user then develops an implementation plan based on the proposal and shares it with employees.

[0583] In this way, a system is built that achieves efficient store operations and high customer satisfaction through the processing flow from step 1 to step 11.

[0584] (Example 1)

[0585] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0586] Traditional store management systems made it difficult to efficiently manage customer information and employee shift schedules, hindering optimal staffing. Furthermore, there was a lack of a system that consistently handled advanced store management tasks such as improving customer satisfaction, calculating brand evaluation points, and notifying achievement targets. As a result, challenges arose, including declining customer satisfaction, reduced staff efficiency, and slower brand value development.

[0587] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0588] In this invention, the server includes means for collecting basic customer information, means for storing the collected basic customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for calculating the optimal staffing arrangement using a machine learning model based on customer information and shift information, means for displaying the optimized schedule to the user and prompting confirmation and correction, means for generating and proposing measures to improve the quality of customer service based on customer feedback, means for displaying the proposed quality improvement measures and prompting their implementation, and means for calculating brand evaluation points based on accumulated feedback and performance data and notifying the achievement target. As a result, customer information and employee shift information can be centrally managed, and by providing optimal staffing and high-quality customer service, it becomes possible to improve customer satisfaction and operate stores efficiently.

[0589] "Customer basic information" refers to basic data about customers who visit the store, such as their name, contact information, and past purchase history.

[0590] A "database" is an information system designed to efficiently store and manage collected information, and is designed to allow for easy searching and updating of data.

[0591] "Employee shift information" refers to data regarding the working days, start times, and end times of employees working at the store.

[0592] A "machine learning model" is an artificial intelligence technology used to analyze large amounts of data and identify patterns and make predictions. In this invention, it is used to calculate the optimal staffing arrangement.

[0593] An "optimized schedule" is a work schedule calculated based on each employee's shift information and the predicted number of customers, resulting in the most efficient staffing arrangement.

[0594] "Feedback" refers to opinions and evaluations provided by customers, and is information that can be used to improve the quality of customer service and enhance the overall service.

[0595] "Proposed quality improvement measures" refer to specific suggestions and measures to improve the quality of customer service and operations, generated based on collected data and feedback.

[0596] "Brand evaluation points" are a numerical indicator of brand value calculated based on customer satisfaction and service quality.

[0597] "Achievement targets" are specific goals set to enhance brand value and represent the standards that employees and the entire store should strive for.

[0598] Modes for carrying out the invention

[0599] This invention is a system that collects and manages basic customer information and employee shift information, and uses this information to achieve optimal staffing. This system aims to improve the efficiency of store operations and enhance customer satisfaction. The following details specific embodiments for implementing this invention.

[0600] System Configuration

[0601] A system primarily consists of three components: servers, terminals, and users.

[0602] The server plays a central role in collecting, analyzing, and storing information. For example, a web application server using the Python Flask framework can be linked to a MySQL database.

[0603] The terminal functions as an interface for users to input, confirm, and modify information. The terminal utilizes a computer or tablet installed in the store and connects to the server via a web browser.

[0604] Users are store staff and managers who use terminals to input, verify, and modify information.

[0605] Collection and storage of customer information

[0606] 1. The device displays a template screen for the customer to enter their basic information (name, contact information, past purchase history, etc.).

[0607] 2. The user (store staff) enters the customer's basic information. Once the input is complete, press the "Confirm" button on the terminal.

[0608] 3. The terminal sends the input information to the server when the "Confirm" button is pressed.

[0609] 4. The server validates the received information (e.g., checks the email format, checks for required fields) and saves it to the MySQL database.

[0610] Specific example:

[0611] For example, when Mr. Tanaka visits the store, a user (staff member) enters information into a terminal. Once the input is complete, the staff member presses the "Confirm" button. The terminal sends the data to the server, which receives the data, verifies it, and then saves it to the database.

[0612] Entering and managing employee shift information

[0613] 1. The terminal displays a shift information input form on the management screen.

[0614] 2. The user (frontline manager) enters information such as the employee's name, workday, start time, and end time.

[0615] 3. Once you have finished entering the information, press the "Send" button on the device.

[0616] 4. The server processes the received shift information, checks the data integrity, and saves it to the MySQL database.

[0617] Specific example:

[0618] The frontline manager enters Yamada and Sato's shifts for the next day into the terminal and presses the "Send" button. The server receives the data, checks its integrity, and saves it to the database.

[0619] Calculation and display of optimal staffing levels

[0620] 1. The server uses a machine learning model (e.g., the scikit-learn library in Python) to analyze past customer data and shift information and calculate the predicted number of customers for the following day.

[0621] 2. The server calculates the optimal staffing arrangement based on the estimated number of customers it has calculated.

[0622] 3. The server sends the calculated optimal schedule to the terminal.

[0623] 4. The device displays the optimal schedule for the user, and the user makes adjustments as needed.

[0624] Specific example:

[0625] The server predicts 100 customers for the next day and uses that information to calculate the optimal staffing allocation. The server sends the calculation results to a terminal, where the frontline manager reviews the displayed schedule and makes any necessary adjustments.

[0626] Proposal and implementation of measures to improve customer service quality

[0627] 1. The server analyzes customer feedback and historical data to generate measures to improve customer service quality (e.g., reducing waiting times, revising customer service manuals). The Python Pandas library is used for data analysis.

[0628] 2. The server sends the generated quality improvement measures to the terminal.

[0629] 3. The terminal displays quality improvement measures suggested to the user, and the user instructs staff to implement them.

[0630] Specific example:

[0631] The server detects when customer wait times are long during specific periods and uses that information to suggest improvements to service speed. These suggestions are displayed on terminals, and frontline managers instruct staff to implement these improvements.

[0632] Brand evaluation and notification of achievement goals

[0633] 1. The server calculates brand evaluation points based on accumulated feedback and performance data. The Statsmodels library in Python is used for statistical analysis.

[0634] 2. The server sends these evaluation points and achievement targets to the terminal.

[0635] 3. The device notifies the user of evaluation points and achievement goals, and proposes specific actions to improve brand value.

[0636] Specific example:

[0637] The server calculates brand evaluation points and notifies the customer that they have a high rating for "prompt and courteous service." The frontline manager then uses this information to propose specific improvement measures to the staff.

[0638] Example of a prompt

[0639] By inputting prompts like the following into the AI ​​model, you can support the generation of optimal staffing and quality improvement measures:

[0640] "Please calculate the optimal staffing level based on customer information and employee shift schedules."

[0641] "Analyze past data and propose measures to improve customer service quality at our stores."

[0642] In this way, a system is built in which servers, terminals, and users cooperate at each step, aiming for efficient business operations and improved customer satisfaction.

[0643] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0644] Program processing flow

[0645] Step 1: Collecting and storing customer information

[0646] 1. The terminal enters customer information.

[0647] The terminal displays a web form, allowing users (store staff) to input information.

[0648] Input: Customer's name, contact information, and past purchase history.

[0649] Output: Information entered into the terminal.

[0650] Specific action: The user enters customer data and presses the "Confirm" button.

[0651] 2. Sending information from the terminal to the server.

[0652] The terminal sends the entered customer information to the server.

[0653] Input: Customer information entered into the terminal.

[0654] Output: Data sent to the server.

[0655] Specific actions: Establish a connection with the server and send customer data.

[0656] 3. The server receives the information and performs validation.

[0657] The server performs validation on the received information (e.g., checking the email format, verifying required fields).

[0658] Input: Customer information received by the server.

[0659] Output: Validated data or error messages.

[0660] Specific actions: Check the format and verify the presence of required fields.

[0661] 4. The server saves the information to the database.

[0662] The server saves the validated information to a MySQL database.

[0663] Input: Customer information that has passed validation.

[0664] Output: Records stored in the database.

[0665] Specific operation: Execute a MySQL query and insert data into the database.

[0666] Step 2: Enter and manage employee shift information

[0667] 1. The terminal enters the shift information.

[0668] The terminal displays a shift information input form, allowing the user (frontline manager) to input the information.

[0669] Input: Employee's name, workday, start time, end time.

[0670] Output: Shift information entered into the terminal.

[0671] Specific action: The frontline manager enters the shift information and presses the "Submit" button.

[0672] 2. Sending information from the terminal to the server.

[0673] The terminal sends the entered shift information to the server.

[0674] Input: Shift information entered into the terminal.

[0675] Output: Data sent to the server.

[0676] Specific actions: Establish a connection with the server and send shift information.

[0677] 3. The server receives the information and checks its integrity.

[0678] The server analyzes the received shift information and checks for duplicates and inconsistencies.

[0679] Input: Shift information received by the server.

[0680] Output: Data with integrity checked, or error messages.

[0681] Specific operation: Detects duplicate data and inconsistent time zones.

[0682] 4. The server saves the information to the database.

[0683] The server saves the shift information that has passed the integrity check to the MySQL database.

[0684] Input: Shift information that has been checked for consistency.

[0685] Output: Records stored in the database.

[0686] Specific operation: Execute a MySQL query and insert data into the database.

[0687] Step 3: Calculation and display of optimal staffing.

[0688] 1. The server calculates the optimal staffing.

[0689] The server uses a machine learning model (e.g., scikit-learn) to analyze historical data and calculate the predicted number of store visits.

[0690] Input: Saved customer information and shift information.

[0691] Output: Predicted number of customers and optimal staffing.

[0692] Specific operation: Input numerical data into the model and obtain prediction results.

[0693] 2. Send the optimization schedule from the server to the terminal.

[0694] The server sends the calculated optimal schedule to the terminal.

[0695] Input: The calculated optimal schedule.

[0696] Output: Data sent to the terminal.

[0697] Specific action: Send schedule data to the device.

[0698] 3. The device displays the optimization schedule.

[0699] The device displays the optimal schedule to the user and prompts them to review and make corrections.

[0700] Input: Optimization schedule received from the server.

[0701] Output: The schedule displayed on the terminal.

[0702] Specific action: Display the schedule in the user interface.

[0703] Step 4: Propose and implement measures to improve customer service quality.

[0704] 1. The server generates quality improvement measures.

[0705] The server analyzes the accumulated feedback and generates measures to improve customer service quality.

[0706] Input: Past feedback and customer information.

[0707] Output: Proposed quality improvement measures.

[0708] Specific actions: Conduct data analysis and create improvement proposals.

[0709] 2. Send quality improvement measures from the server to the terminal.

[0710] The server sends the generated quality improvement measures to the terminal.

[0711] Input: Created quality improvement measures.

[0712] Output: Data sent to the terminal.

[0713] Specific action: Send the proposal to the terminal.

[0714] 3. The device displays quality improvement measures.

[0715] The device displays quality improvement measures to the user and encourages them to implement them.

[0716] Input: Quality improvement measures received from the server.

[0717] Output: Suggestions displayed on the terminal.

[0718] Specific actions: Display the proposed content and show a message encouraging implementation.

[0719] Step 5: Brand evaluation and notification of achievement goals

[0720] 1. The server calculates the evaluation points.

[0721] The server analyzes accumulated feedback and performance data to calculate brand evaluation points.

[0722] Input: Past feedback and performance data.

[0723] Output: Calculated evaluation points.

[0724] Specific operation: Apply the evaluation algorithm and calculate the evaluation points.

[0725] 2. Send evaluation points and targets from the server to the terminal.

[0726] The server sends the calculated evaluation points and achievement targets to the terminal.

[0727] Input: Calculated evaluation points and achievement targets.

[0728] Output: Data sent to the terminal.

[0729] Specific action: Send evaluation information to the terminal.

[0730] 3. The device displays evaluation points and goals.

[0731] The device notifies the user of their evaluation points and achievement goals, and suggests specific actions.

[0732] Input: Evaluation points and achievement goals received from the server.

[0733] Output: Notifications displayed on the device.

[0734] Specific action: Display a notification message and provide specific suggestions.

[0735] The above describes the specific processing flow of this system's program.

[0736] (Application Example 1)

[0737] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0738] Traditional store operations often failed to effectively utilize customer information and employee shift data, resulting in unoptimized staffing. This led to staff shortages during peak hours, lowering customer satisfaction, and unnecessary labor costs during off-peak hours. Furthermore, the lack of real-time suggestions for improving customer service quality based on customer feedback and the inability to predict staffing levels made rapid responses difficult.

[0739] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0740] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee working hours information, means for analyzing the input working hours information and storing it in a database, means for calculating the optimal staffing based on customer information and working hours information, means for displaying the optimized timetable to the user and prompting confirmation and correction, means for proposing measures to improve the quality of customer service based on customer satisfaction, means for displaying the proposed improvement measures and prompting implementation, means for calculating evaluation points and notifying achievement targets, means for predicting the number of expected customers and calculating the necessary workforce based on that, means for predicting and presenting the optimal staffing in real time, means for analyzing customer feedback using a generative AI model and generating measures to improve the quality of customer service, and means for supporting the efficiency of store operations using prompt messages. This makes it possible to efficiently allocate staff, improve customer satisfaction, and optimize labor costs at the same time.

[0741] "Customer information" refers to data about a customer, such as basic information, contact information, and past purchase history.

[0742] "Means of collection" refers to the function of inputting customer information into a terminal and transmitting it to a server.

[0743] "Means of saving to a database" refers to the function of saving collected data in a digital format and maintaining it in a format that allows for access and editing as needed.

[0744] "Working hours information" refers to data related to shifts, such as employees' working days, start times, and end times.

[0745] "Means of analysis" refers to the function of analyzing collected data and extracting patterns and trends.

[0746] "Optimal staffing" refers to calculating the most suitable staffing configuration for store operations based on factors such as the expected number of customers and employee working hours.

[0747] An "optimized timetable" refers to a shift schedule based on a calculated optimal staffing arrangement.

[0748] "Means to prompt review and correction" refers to a function that presents an optimized schedule to the user, allowing the user to perform final review and make necessary corrections.

[0749] "Means of proposing quality improvement measures" refers to a function that generates improvement measures for customer service methods and service content based on customer satisfaction and feedback.

[0750] "Means for displaying proposed improvement plans and encouraging their implementation" refers to a function that displays generated quality improvement measures to the user and encourages their implementation.

[0751] "Evaluation points" refer to performance indicators for stores and brands that are calculated based on customer feedback and performance data.

[0752] "Means of notifying achievement targets" refers to a function that notifies users of the targets that stores and brands should achieve based on the calculated evaluation points.

[0753] "Methods for predicting the number of customers expected to visit" refers to functions that predict future customer visits based on past data and trends.

[0754] "Means for calculating the required workforce" refers to a function that calculates the number of employees needed for a given time slot based on the expected number of customers.

[0755] "Means of predicting and presenting in real time" refers to a function that calculates the optimal staffing allocation in real time based on current data and presents the results to the user.

[0756] A "generative AI model" refers to an artificial intelligence model that uses machine learning or deep learning to analyze data and automatically perform specific tasks.

[0757] A "prompt message" refers to text used to give specific instructions or data input to an AI model.

[0758] The system for carrying out this invention includes a process for collecting customer information and employee working hours information, storing it in a database, and calculating the optimal staffing arrangement based on that information. Detailed embodiments of this system are described below.

[0759] Collection and storage of customer information

[0760] Customer information is entered on a terminal and sent to the server. The terminal retrieves basic customer information (name, contact information, past purchase history, etc.) and sends this data to the server. The server stores the received data in a database and checks for errors in the input data to ensure accuracy.

[0761] Input and management of employee working hours information

[0762] The user (store manager) uses a management terminal to input employee shift information. Specifically, they input the employee's name, workday, start time, and end time. The server analyzes the received shift information and stores it in a database.

[0763] Calculation and display of optimal staffing levels

[0764] The server uses customer information and working hours data to predict the number of expected customers and their needs, and calculates the optimal staffing allocation. It also calculates the required workforce based on the expected number of customers and generates an optimal shift schedule based on the results. The terminal displays the calculated and optimized timetable to the user, prompting them to review and make any necessary adjustments.

[0765] Proposal and implementation of measures to improve customer service quality

[0766] The server analyzes customer feedback and historical data to generate measures to improve customer service quality. These include reducing customer waiting times and improving the quality of service. The terminal displays the customer service improvement measures generated using the AI ​​model to the user and encourages their implementation.

[0767] Brand evaluation and notification of achievement goals

[0768] The server calculates evaluation points based on accumulated feedback and performance data, and notifies the brand of its evaluation points and achievement targets. The terminal proposes specific actions to the user to improve brand value and encourages their implementation.

[0769] Specific example

[0770] For example, the server predicts the number of customers visiting the store the following day, Monday, and uses that result to calculate the necessary workforce. It predicts 50 customers at 10 AM, requiring 5 staff members. At 1 PM, it predicts 30 customers, requiring 3 staff members. This optimized schedule is displayed on the user's terminal, allowing them to review and modify it.

[0771] Example of a prompt

[0772] "Calculate the optimal shifts for each time slot on Monday. Since the number of customers varies at each time, allocate the appropriate number of employees accordingly. Please write a weekday shift optimization program."

[0773] In this way, this system processes data accurately and efficiently at each step, enabling optimal staffing and thereby increasing customer satisfaction and improving the efficiency of store operations.

[0774] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0775] Step 1: Collecting customer information

[0776] The terminal inputs basic information of customers who visit the store (name, contact information, past purchase history, etc.). This input data is entered by the terminal and sent to the server. The server stores the received customer information in a database. It also checks for errors in the input content to ensure accuracy.

[0777] Step 2: Enter employee working hours information

[0778] The user (store manager) uses a management terminal to input employee work time information (name, workday, start time, and end time, etc.). This input data is entered via the management terminal and sent to the server. The server stores the received work time information in a database, checks for duplicates or errors in the input data, and makes corrections as necessary.

[0779] Step 3: Predicting the number of expected customers

[0780] The server predicts the number of expected customers based on customer information and working hours data. The server generates a customer visit prediction model using accumulated historical data. This generated AI model is used to predict the number of expected customers for a specific date and time. The input here is historical customer data, and the output is the predicted number of customers.

[0781] Step 4: Calculating the optimal staffing levels

[0782] The server calculates the required workforce for each time slot based on the predicted number of customers. The server calculates the number of employees needed based on the expected number of customers and then calculates the optimal staffing. The input here is the expected number of customers, and the output is the required number of employees.

[0783] Step 5: Display the optimized timetable

[0784] The server sends the result of its calculated optimal staffing allocation to the terminal. The terminal displays this optimized schedule to the user, prompting them to review and make corrections. The input here is the optimized shift schedule, and the output is the user's feedback for review and correction.

[0785] Step 6: Propose measures to improve customer service quality

[0786] The server analyzes customer feedback and historical data to generate measures for improving customer service quality. It uses a generation AI model to analyze feedback data and generate specific improvement measures. The terminal displays these quality improvement measures to the user and encourages their implementation. Here, the input is feedback data, and the output is the proposed quality improvement measures.

[0787] Step 7: Brand evaluation and notification of achievement goals

[0788] The server calculates evaluation points based on accumulated feedback and performance data and notifies the user. The terminal displays these evaluation points and achievement targets to the user and suggests specific actions to improve brand value. The inputs here are feedback and performance data, and the outputs are evaluation points and achievement targets.

[0789] Through the steps described above, this invention makes it possible to efficiently allocate personnel and achieve customer satisfaction and efficient store operations.

[0790] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0791] This invention is a system that collects and manages customer information and employee shift information, and based on this, realizes optimal staffing. Furthermore, by combining this with an emotion engine, it recognizes and analyzes user emotions to improve the quality of customer service and enhance brand value. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[0792] 1. Collection and storage of customer information

[0793] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[0794] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[0795] Specific example: Mr. Tanaka comes into the store and registers his name and contact information on a terminal. The terminal sends this information to the server, which stores the information in a database for verification.

[0796] 2. Inputting and managing employee shift information

[0797] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0798] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[0799] Specific example: A frontline manager uses a management terminal to enter the shift information for employees Yamada and Sato for the following day. The server analyzes this information and saves it to the database.

[0800] 3. Calculation and display of optimal staffing levels

[0801] The server predicts the expected number of customers and their needs based on customer information and employee shift schedules. Based on these predictions, it calculates the optimal staffing levels for each time slot.

[0802] The terminal displays the calculated optimal schedule to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[0803] Specific example: The server predicts 100 customers will visit the store the next day and uses that information to optimize the next day's shifts. The frontline manager checks the optimized shift schedule on a terminal and makes any necessary adjustments.

[0804] 4. Emotion recognition and analysis using an emotion engine

[0805] The device is equipped with an emotion engine that recognizes the emotions of employees and customers in the store in real time. The emotion engine identifies the user's emotional state through facial recognition technology and voice analysis.

[0806] The server receives emotional data recognized by the emotion engine and stores it in a database. Furthermore, it analyzes this data to extract areas for improvement in store operations.

[0807] Specific example: An emotion engine recognizes the frequency of an employee's smiles and sends this information to a server. The server analyzes this information and suggests appropriate countermeasures if it detects certain signs of stress.

[0808] 5. Proposal and implementation of measures to improve customer service quality

[0809] The server generates measures to improve customer service quality based on customer feedback and emotion engine data. This includes reducing customer waiting times and improving the quality of service.

[0810] The terminal displays customer service quality improvement measures sent from the server to the user and encourages their implementation.

[0811] Specific example: The server detects that customer wait times are long during a particular period and suggests improving service speed. This suggestion is displayed on a terminal, and the frontline manager instructs staff to implement it.

[0812] 6. Notification of brand evaluation and achievement targets

[0813] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. These points are based on evaluation criteria such as prompt response and courteous customer service.

[0814] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[0815] Specific example: The server team recognizes its high rating for "prompt and courteous service" and proposes concrete measures to further enhance this. The frontline manager reviews the proposal and instructs employees to implement it.

[0816] In this way, by having the server, terminals, and users each fulfill their respective roles, a system is built that enables efficient store operations and high customer satisfaction through the use of emotion recognition. This system can simultaneously achieve optimal staffing, high-quality customer service, and enhanced brand value through the use of emotional data.

[0817] The following describes the processing flow.

[0818] Step 1:

[0819] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[0820] Step 2:

[0821] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[0822] Step 3:

[0823] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0824] Step 4:

[0825] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[0826] Step 5:

[0827] The server predicts the expected number of customers and their needs based on customer information and shift information. Based on this prediction, it calculates the optimal staffing levels for each time slot.

[0828] Step 6:

[0829] The terminal displays the optimal schedule sent from the server to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[0830] Step 7:

[0831] The server notifies that the optimized schedule has resulted in successful staff reductions and increased efficiency. The frontline manager reviews the notification and updates the shift schedule accordingly.

[0832] Step 8:

[0833] The device uses an emotion engine to recognize the emotions of employees and customers in the store in real time. The emotion engine identifies the user's emotional state through facial recognition technology and voice analysis.

[0834] Step 9:

[0835] The server receives emotional data recognized by the emotion engine and stores it in a database. Furthermore, it analyzes this data to extract areas for improvement in store operations.

[0836] Step 10:

[0837] The server generates measures to improve customer service quality based on customer feedback and emotion engine data. This includes reducing customer waiting times and improving the quality of service.

[0838] Step 11:

[0839] The terminal displays suggestions for improving customer service quality, sent from the server, to the user and encourages their implementation. The user reviews the suggestions and issues instructions to employees to implement them.

[0840] Step 12:

[0841] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. It reviews evaluation items such as prompt response and courteous customer service and proposes measures to improve brand value.

[0842] Step 13:

[0843] The device notifies the user of brand evaluation points and achievement targets, and proposes a specific action plan. The user then develops an implementation plan based on the proposal and shares it with employees.

[0844] In this way, through the processing flow from Step 1 to Step 13, a system is built that utilizes emotion recognition to achieve efficient store operations and high customer satisfaction.

[0845] (Example 2)

[0846] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0847] Traditional store management systems often rely on manual processes for managing customer information and employee shifts, making efficient staffing and improved customer service difficult. Furthermore, there's a lack of systems to monitor and respond to employee and customer emotional states in real time. This leads to problems such as decreased customer satisfaction and increased employee stress. Therefore, there's a need to develop systems that support efficient and effective store operations to address these challenges.

[0848] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0849] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for predicting the number of expected customers based on the collected customer information and shift information, means for calculating the optimal staffing based on the predicted number of customers, means for displaying the calculated optimization schedule to the user and proposing measures to improve the quality of customer service based on customer satisfaction, means for displaying the proposed measures to improve the quality of customer service and encouraging their implementation, means for calculating brand evaluation points based on accumulated feedback, emotional data, and performance data and notifying the achievement target, means for recognizing and analyzing the emotions of users and employees through facial recognition and voice analysis, and means for proposing stress management and improvements in customer service quality based on emotional data. This makes it possible to simultaneously achieve efficient staffing, high-quality customer service, and improved brand value through the use of emotional data.

[0850] "Customer information" refers to basic information such as the name, contact information, and past purchase history of customers who use the store.

[0851] A "database" refers to a system that stores and manages customer information, shift information, etc., and has the function of searching and updating data as needed.

[0852] "Shift information" refers to information about an employee's working hours, such as the employee's name, working days, start time, and end time.

[0853] "Optimal staffing" refers to an employee allocation plan that maximizes store operational efficiency and customer satisfaction, based on collected customer and shift information.

[0854] An "emotion engine" refers to a system that uses facial recognition and voice analysis to identify the emotional states of employees and customers, and collects and analyzes this data.

[0855] "Feedback" refers to information based on opinions and evaluations received from customers and employees.

[0856] "Brand evaluation points" refer to indicators used to evaluate the value and quality of a brand, calculated based on accumulated feedback, sentiment data, and performance data.

[0857] "Stress management" refers to the process of monitoring employees' stress levels based on recognized emotional data and proposing appropriate countermeasures.

[0858] "Customer service quality" refers to the quality of service and interaction with customers, and includes prompt responses, courteous service, and appropriate problem-solving.

[0859] "Expected number of visitors" refers to the number of future visitors predicted based on past data and current reservation information.

[0860] Modes for carrying out the invention

[0861] This invention is a system that collects and manages customer information and employee shift information, and based on this, realizes optimal staffing. Furthermore, by combining this with an emotion engine, it recognizes and analyzes user emotions to improve the quality of customer service and enhance brand value. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[0862] 1. Collection and storage of customer information

[0863] The terminal provides a function to input basic information (name, contact information, past purchase history, etc.) of customers who visit the store. The terminal uses a PC or tablet and has a store-specific input application installed.

[0864] The user (store clerk) enters the customer's information into the input form displayed on the screen.

[0865] The terminal validates the entered information and sends it to the server.

[0866] The server uses a database management system (DBMS) to receive customer information sent from the terminal and store it in the database.

[0867] Specific example: For instance, a new customer enters the store, and an employee uses a terminal to input the customer's basic information. The terminal validates the information and sends it to the server. The server saves the information to a database and returns a notification to the terminal that the information has been saved.

[0868] 2. Inputting and managing employee shift information

[0869] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0870] The terminal provides a form for entering shift information. The terminal is a PC or tablet with a dedicated shift management application installed.

[0871] The terminal validates the entered shift information and sends it to the server.

[0872] The server has the functionality to store and verify the collected shift information in a database.

[0873] Specific example: A frontline manager uses a management terminal to input employee shift information. The terminal validates the information and sends it to the server. The server receives the information and stores it in a database.

[0874] 3. Calculation and display of optimal staffing levels

[0875] The server runs an algorithm to predict the expected number of customers based on customer information and employee shift information. This algorithm uses a prediction model written in Python.

[0876] The server calculates the optimal staffing based on the prediction results and sends the result to the terminal. Optimization algorithms such as linear programming are used for optimization.

[0877] The terminal provides a mechanism to display the calculation results to the user.

[0878] Specific example: The server predicts 100 customers will visit the store the next day and optimizes the shift schedule based on that information. The frontline manager checks the schedule on their terminal and makes any necessary adjustments.

[0879] 4. Emotion recognition and analysis using an emotion engine

[0880] The device recognizes the emotions of employees and customers in real time through an emotion engine. The emotion engine is connected to a facial recognition camera and microphone, and uses OpenCV and TensorFlow software to analyze facial expressions and voice tone.

[0881] The server receives sentiment data sent from the terminal, stores it in a database, and analyzes it. The analysis uses the Python data analysis libraries Pandas and Matplotlib.

[0882] Specific example: The emotion engine recognizes the frequency of an employee's smiles and sends this information to the server. The server analyzes this information, assesses the employee's stress level, and suggests appropriate countermeasures.

[0883] 5. Proposal and implementation of measures to improve customer service quality

[0884] The server generates strategies for improving customer service quality based on customer feedback and sentiment data. Natural language processing (NLP) algorithms are used to analyze the feedback.

[0885] The device displays the generated suggestions to the user and encourages them to implement them.

[0886] Specific example: The server identifies customer wait times as long during certain periods based on feedback and creates suggestions to improve service speed. A terminal displays these suggestions, and the frontline manager instructs staff to implement them.

[0887] 6. Notification of brand evaluation and achievement targets

[0888] The server calculates brand evaluation points based on feedback, sentiment data, and performance data. Evaluation systems and algorithms are used for the calculation.

[0889] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[0890] Specific example: Feedback data reveals that the server has a high rating for "prompt and courteous response," and measures to improve it are proposed. The frontline manager checks the proposal on their terminal and instructs employees to implement it.

[0891] Example of a prompt:

[0892] "Please explain how the server calculates the optimal staffing based on the number of customers expected the following day and employee shift information, and how the results are displayed on the terminal."

[0893] "Please describe the process of using an emotion engine to recognize employees' emotions in real time and analyzing that data on a server."

[0894] As described above, by having the server, terminal, and user each fulfill their respective roles, we will build a system that utilizes emotion recognition to achieve efficient store operations and high customer satisfaction.

[0895] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0896] Step 1: Collect and store customer information

[0897] Specific actions

[0898] The terminal displays a screen where customers who visit the store can enter their basic information (name, contact information, past purchase history, etc.).

[0899] The user (store clerk) enters customer information into the input form displayed on the screen. This information includes name, contact information, and past purchase history.

[0900] The terminal validates the entered information and sends it to the server. For example, it checks if the name format is correct and if the contact information includes all required fields.

[0901] Input and output

[0902] Input: Your name, contact information, and past purchase history

[0903] Data processing and calculation: Validation (checking the accuracy of the data)

[0904] Output: Send validated customer information to the server

[0905] The server receives customer information sent from the terminal and saves it to the database. Upon successful saving, it sends a save completion notification back to the terminal.

[0906] Step 2: Enter and manage employee shift information

[0907] Specific actions

[0908] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[0909] The terminal validates the entered shift information and sends it to the server. For example, it checks whether the work days are entered in the correct format and whether there are any duplicates.

[0910] Input and output

[0911] Input: Employee's name, workday, start time, and end time

[0912] Data processing and calculation: Validation (checking the accuracy of the data)

[0913] Output: Send validated shift information to the server.

[0914] The server saves the received shift information to the database and verifies it. If the saving is successful, it sends a confirmation completion notification to the terminal.

[0915] Step 3: Calculation and display of optimal staffing levels

[0916] Specific actions

[0917] The server runs a predictive model that forecasts the number of customers expected to visit, based on stored customer information and employee shift information. The prediction uses a prediction algorithm written in a Python program.

[0918] The server calculates the optimal staffing based on the prediction results and sends the result to the terminal. Optimization algorithms such as linear programming are used for optimization.

[0919] The terminal provides a screen to display the calculation results.

[0920] Input and output

[0921] Input: Saved customer information, employee shift information

[0922] Data processing and calculation: Predicting the number of customers expected, calculating optimal staffing levels.

[0923] Output: Send optimized staffing schedule to terminal

[0924] As a concrete example, the server predicts that 100 customers will visit the store the next day, and uses that information to optimize the shift schedule. The frontline manager checks the schedule on their terminal and makes any necessary adjustments.

[0925] Step 4: Emotion recognition and analysis using the emotion engine

[0926] Specific actions

[0927] The device recognizes the emotions of employees and customers in real time through an emotion engine. The emotion engine is connected to a facial recognition camera and microphone, and uses OpenCV and TensorFlow software to analyze facial expressions and voice tone.

[0928] The device sends the analyzed emotion data to the server.

[0929] The server receives emotional data, stores it in a database, and analyzes it.

[0930] Input and output

[0931] Input: Face recognition and voice analysis data

[0932] Data processing and calculation: Identification of emotional states, data analysis

[0933] Output: Accumulate analysis results and suggest appropriate countermeasures.

[0934] As a concrete example, the emotion engine recognizes the frequency of an employee's smile and sends this information to the server. The server analyzes this information, assesses signs of employee stress, and suggests appropriate countermeasures.

[0935] Step 5: Propose and implement measures to improve customer service quality.

[0936] Specific actions

[0937] The server generates strategies for improving customer service quality based on feedback and sentiment data. Natural language processing (NLP) algorithms are used to analyze the feedback.

[0938] The device displays the generated suggestions to the user and encourages them to implement them.

[0939] Input and output

[0940] Input: Feedback data, sentiment data

[0941] Data processing and calculation: Feedback analysis, generation of quality improvement measures.

[0942] Output: Display the recommendations on the device.

[0943] As a concrete example, a server identifies customer wait times as long during specific periods based on feedback and creates suggestions to improve service speed. A terminal displays these suggestions, and the frontline manager instructs staff to implement them.

[0944] Step 6: Brand evaluation and notification of achievement goals

[0945] Specific actions

[0946] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. An evaluation system and algorithm are used for the evaluation calculation.

[0947] The device notifies the user of the calculated evaluation points and achievement targets, and suggests actions to improve brand value.

[0948] Input and output

[0949] Input: Feedback data, sentiment data, performance data

[0950] Data processing and calculation: Calculation of brand evaluation points, setting of achievement targets.

[0951] Output: Evaluation points and achievement goals are notified to the device.

[0952] As a concrete example, accumulated data reveals that the server has a high rating for "prompt and courteous response," and a proposal is created to further enhance this. The frontline manager reviews the proposal on their terminal and instructs employees to implement it.

[0953] (Application Example 2)

[0954] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0955] Currently, building a system that optimizes store operations while simultaneously improving customer service quality and brand value is extremely difficult. Furthermore, to enhance customer satisfaction, it's necessary to appropriately recognize employee emotions and implement appropriate responses immediately. However, no technology yet exists that can integrate these elements into a single system. Therefore, there is a need to develop a system that can simultaneously optimize staffing, improve customer service quality, and enhance brand value.

[0956] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0957] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for calculating the optimal staffing arrangement based on customer information and shift information, means for displaying the optimized schedule to the user and prompting confirmation and correction, means for recognizing the emotional state of customers and employees in real time using emotion recognition technology, means for generating and displaying measures to improve customer service quality based on the emotional state, means for prompting the implementation of the proposed measures to improve customer service quality, and means for calculating brand evaluation based on accumulated emotional data and feedback data and notifying the achievement target. This makes it possible to improve customer satisfaction, optimize staffing, and simultaneously improve customer service quality and brand value.

[0958] "Customer information" refers to basic information about a customer, such as their name, contact information, and past purchase history.

[0959] "Collection methods" refer to devices and programs used to acquire customer information and employee shift information.

[0960] "Means of storing data in a database" refers to devices or programs used to store collected data in a database.

[0961] "Employee shift information" refers to information about the employee's name, workday, start time, and end time.

[0962] "Analysis means" refers to devices or programs used to analyze collected information and extract necessary data.

[0963] "Optimal staffing" refers to the best possible staffing arrangement in store operations to maximize customer satisfaction.

[0964] "Schedule display means" refers to a device or program that displays the calculated optimal schedule to the user and prompts them to approve and modify it.

[0965] "Emotion recognition technology" refers to technology that uses facial recognition technology and voice analysis to recognize an individual's emotional state in real time.

[0966] "Quality improvement measure generation means" refers to a device or program that automatically generates customer service quality improvement measures based on collected data.

[0967] "Means for implementing quality improvement measures" refers to devices or programs that present generated quality improvement measures to users and encourage their implementation.

[0968] "Evaluation calculation means" refers to devices or programs used to calculate brand evaluations based on accumulated feedback and sentiment data.

[0969] "Means of notifying achievement targets" refers to devices or programs that notify users of achievement targets based on calculated brand evaluation points.

[0970] The following describes specific embodiments for carrying out the present invention.

[0971] First, let's explain the collection and storage of customer information. In stores, terminals provide a means for customers to enter basic information such as their name, contact information, and past purchase history when they visit the store. This information is entered with the customer's consent, and the server stores this information in a database and checks for any errors.

[0972] Next, we will explain the input and management of employee shift information. The user (store manager) uses a management terminal to input employee shift information. This shift information includes the employee's name, workday, start time, and end time. The server receives this shift information, stores it in the database, and checks for duplicate information and input errors.

[0973] The server predicts the expected number of customers and their needs based on customer information and employee shift information, and calculates the optimal staffing arrangement based on that. The calculated optimal schedule is displayed on the terminal, which the user can review and modify as needed.

[0974] Next, we will explain emotion recognition and analysis using the emotion engine. The terminal is equipped with an emotion engine that recognizes the emotions of employees and customers in the store in real time. This engine uses facial recognition technology and voice analysis to identify the user's emotional state. The server receives the recognized emotion data, stores it in a database, and performs analysis. Based on the results, it extracts areas for improvement in store operations.

[0975] This section describes the proposal and implementation of measures to improve customer service quality. The server generates these improvement measures based on customer feedback and data from the emotion engine. These measures include reducing customer waiting times and improving the quality of service. The terminal displays these suggestions to the user and encourages their implementation.

[0976] Finally, let's discuss brand evaluation and goal notification. The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. This reflects evaluations such as prompt response and courteous customer service. The terminal notifies the user of the calculated evaluation points and goals, and suggests specific actions to improve brand value.

[0977] Specific example:

[0978] A concrete example of collecting and storing customer information: When a customer enters the store, they scan a QR code, and their basic information is instantly entered. The server then stores this information in a database.

[0979] A concrete example of shift information management: An administrator uses a management terminal to enter employee shifts, which are then sent to a server.

[0980] Specific example of optimal staffing: The server calculates the optimal staffing based on the predicted number of customers and notifies the terminal. The administrator reviews this result and makes corrections as needed.

[0981] A concrete example of emotion recognition: An emotion engine identifies the emotions of employees and customers in real time and sends that data to a server.

[0982] Specific example of improving customer service quality: The server generates quality improvement measures based on feedback data and proposes them to employees via a terminal.

[0983] A concrete example of brand value evaluation: The server calculates evaluation points and notifies the terminal of the achievement target.

[0984] Example of a prompt:

[0985] "Please calculate the optimal staffing levels based on the following shift schedule."

[0986] "Based on the following sentiment data, please suggest areas for improvement in customer service quality."

[0987] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0988] Step 1:

[0989] Collection and storage of customer information

[0990] The terminal has a means of inputting basic information such as the customer's name, contact information, and past purchase history. This information is entered with the customer's consent, and the terminal sends it to the server. The server stores the received customer information in a database and checks for any errors in the information.

[0991] Input: Customer name, contact information, purchase history

[0992] Processing: Data integrity check

[0993] Output: Customer information is saved to the database.

[0994] Step 2:

[0995] Entering and managing employee shift information

[0996] The user (store manager) uses a management terminal to enter employee shift information (name, work days, start time, end time). The terminal sends this information to the server. The server stores the received shift information in a database and checks for input errors and duplicates.

[0997] Input: Employee's name, workday, start time, end time

[0998] Processing: Data integrity check

[0999] Output: Shift information is saved to the database.

[1000] Step 3:

[1001] Calculation of optimal staffing

[1002] The server predicts the expected number of customers and their needs based on customer information and employee shift information. Based on this, it calculates the optimal staffing for each time slot and sends the results to the terminal. The terminal displays the optimized schedule to the user and prompts them to review and make adjustments.

[1003] Input: Customer information, shift information

[1004] Processing: Forecasting using demand forecasting algorithms, optimization calculation of personnel allocation.

[1005] Output: The optimized schedule will be displayed on the device.

[1006] Step 4:

[1007] Emotion recognition and data analysis

[1008] The terminal uses its built-in emotion engine to recognize the emotions of employees and customers in the store in real time. This emotion data is sent from the terminal to a server, which stores it in a database. The server then analyzes the emotion data to identify areas for improvement in store operations.

[1009] Input: Facial images and audio data of employees and customers

[1010] Processing: Analysis using an emotion recognition algorithm

[1011] Output: Recognized emotion data is sent to the server and stored in the database.

[1012] Step 5:

[1013] Developing and managing measures to improve customer service quality.

[1014] The server generates suggestions for improving customer service quality based on customer feedback and data from the emotion engine. The terminal displays these suggestions to the user and encourages their implementation.

[1015] Input: Feedback data, sentiment data

[1016] Processing: Generation of suggestions using a customer service improvement algorithm.

[1017] Output: Measures to improve customer service quality are displayed on the terminal.

[1018] Step 6:

[1019] Brand valuation calculation and target notification

[1020] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. The terminal notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[1021] Input: Feedback data, sentiment data, performance data

[1022] Processing: Score calculation using a brand evaluation algorithm.

[1023] Output: Evaluation points and achievement goals are displayed on the device.

[1024] Through the above processing steps, servers, terminals, and users work together to improve customer satisfaction, optimize staffing, and simultaneously enhance customer service quality and brand value.

[1025] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1026] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1027] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1028] [Third Embodiment]

[1029] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1030] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1032] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1033] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1034] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1036] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1037] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1039] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1041] This invention is a system that collects and manages customer information and employee shift information, and uses this information to achieve optimal staffing. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[1042] 1. Collection and storage of customer information

[1043] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[1044] The server receives the entered customer information and stores it in the database. The server checks the entered information for errors to ensure accurate data collection.

[1045] Specific example: Customer Tanaka comes into the store and registers his name and contact information on a terminal. The terminal sends this information to the server, which stores the information in a database for verification.

[1046] 2. Inputting and managing employee shift information

[1047] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This includes each employee's name, workday, start time, and end time.

[1048] The server analyzes the collected shift information and stores it in a database. The server checks the input data for duplicates and errors and makes corrections as needed.

[1049] Specific example: A frontline manager uses a management terminal to enter the shift information for employees Yamada and Sato for the following day. The server analyzes this information and saves it to the database.

[1050] 3. Calculation and display of optimal staffing levels

[1051] The server predicts the expected number of customers and their needs based on customer information and employee shift schedules. This allows it to calculate the optimal staffing levels for each day and time slot.

[1052] The terminal displays the calculated optimal schedule to the user. The user reviews and modifies the information displayed on the terminal to determine the most efficient staffing arrangement.

[1053] Specific example: The server predicts 100 customers will visit the store the next day and uses that information to optimize the next day's shifts. The frontline manager checks the optimized schedule on their terminal and makes any necessary adjustments.

[1054] 4. Proposal and implementation of measures to improve customer service quality

[1055] The server generates measures to improve customer service quality based on customer feedback and historical data. These include reducing customer waiting times and improving the quality of service.

[1056] The terminal displays customer service quality improvement measures sent from the server to the user and encourages their implementation.

[1057] Specific example: The server detects that customer wait times are long during a particular period and suggests improving service speed. This suggestion is displayed on a terminal, and the frontline manager instructs staff to implement it.

[1058] 5. Notification of brand evaluation and achievement targets

[1059] The server calculates brand evaluation points based on accumulated feedback and performance data. These points are based on evaluation criteria such as prompt response and courteous customer service.

[1060] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[1061] Specific example: The server team recognizes its high rating for "prompt and courteous service" and proposes concrete measures to further enhance this. The frontline manager reviews the proposal and instructs employees to implement it.

[1062] In this way, by having servers, terminals, and users each fulfill their respective roles, a system is realized that improves customer satisfaction and enables efficient store operations. This system allows for optimal staffing and high-quality customer service, thereby enhancing brand value.

[1063] The following describes the processing flow.

[1064] Step 1:

[1065] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[1066] Step 2:

[1067] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[1068] Step 3:

[1069] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[1070] Step 4:

[1071] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[1072] Step 5:

[1073] The server predicts the expected number of customers and their needs based on customer information and shift information. Based on this prediction, it calculates the optimal staffing levels for each time slot.

[1074] Step 6:

[1075] The terminal displays the optimal schedule sent from the server to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[1076] Step 7:

[1077] The server notifies that the optimized schedule has resulted in successful staff reductions and increased efficiency. The frontline manager reviews the notification and updates the shift schedule accordingly.

[1078] Step 8:

[1079] The server generates measures to improve customer service quality based on customer feedback and historical data. These include reducing customer waiting times and improving the quality of service.

[1080] Step 9:

[1081] The terminal displays suggestions from the server for improving customer service quality to the user and encourages them to implement specific improvement measures. The user reviews the suggestions and instructs employees to implement them.

[1082] Step 10:

[1083] The server calculates brand evaluation points based on feedback and performance data. It reviews evaluation items such as prompt response and courteous customer service and proposes measures to improve brand value.

[1084] Step 11:

[1085] The device notifies the user of brand evaluation points and achievement targets, and proposes a specific action plan. The user then develops an implementation plan based on the proposal and shares it with employees.

[1086] In this way, a system is built that achieves efficient store operations and high customer satisfaction through the processing flow from step 1 to step 11.

[1087] (Example 1)

[1088] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1089] Traditional store management systems made it difficult to efficiently manage customer information and employee shift schedules, hindering optimal staffing. Furthermore, there was a lack of a system that consistently handled advanced store management tasks such as improving customer satisfaction, calculating brand evaluation points, and notifying achievement targets. As a result, challenges arose, including declining customer satisfaction, reduced staff efficiency, and slower brand value development.

[1090] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1091] In this invention, the server includes means for collecting basic customer information, means for storing the collected basic customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for calculating the optimal staffing arrangement using a machine learning model based on customer information and shift information, means for displaying the optimized schedule to the user and prompting confirmation and correction, means for generating and proposing measures to improve the quality of customer service based on customer feedback, means for displaying the proposed quality improvement measures and prompting their implementation, and means for calculating brand evaluation points based on accumulated feedback and performance data and notifying the achievement target. As a result, customer information and employee shift information can be centrally managed, and by providing optimal staffing and high-quality customer service, it becomes possible to improve customer satisfaction and operate stores efficiently.

[1092] "Customer basic information" refers to basic data about customers who visit the store, such as their name, contact information, and past purchase history.

[1093] A "database" is an information system designed to efficiently store and manage collected information, and is designed to allow for easy searching and updating of data.

[1094] "Employee shift information" refers to data regarding the working days, start times, and end times of employees working at the store.

[1095] A "machine learning model" is an artificial intelligence technology used to analyze large amounts of data and identify patterns and make predictions. In this invention, it is used to calculate the optimal staffing arrangement.

[1096] An "optimized schedule" is a work schedule calculated based on each employee's shift information and the predicted number of customers, resulting in the most efficient staffing arrangement.

[1097] "Feedback" refers to opinions and evaluations provided by customers, and is information that can be used to improve the quality of customer service and enhance the overall service.

[1098] "Proposed quality improvement measures" refer to specific suggestions and measures to improve the quality of customer service and operations, generated based on collected data and feedback.

[1099] "Brand evaluation points" are a numerical indicator of brand value calculated based on customer satisfaction and service quality.

[1100] "Achievement targets" are specific goals set to enhance brand value and represent the standards that employees and the entire store should strive for.

[1101] Modes for carrying out the invention

[1102] This invention is a system that collects and manages basic customer information and employee shift information, and uses this information to achieve optimal staffing. This system aims to improve the efficiency of store operations and enhance customer satisfaction. The following details specific embodiments for implementing this invention.

[1103] System Configuration

[1104] A system primarily consists of three components: servers, terminals, and users.

[1105] The server plays a central role in collecting, analyzing, and storing information. For example, a web application server using the Python Flask framework can be linked to a MySQL database.

[1106] The terminal functions as an interface for users to input, confirm, and modify information. The terminal utilizes a computer or tablet installed in the store and connects to the server via a web browser.

[1107] Users are store staff and managers who use terminals to input, verify, and modify information.

[1108] Collection and storage of customer information

[1109] 1. The device displays a template screen for the customer to enter their basic information (name, contact information, past purchase history, etc.).

[1110] 2. The user (store staff) enters the customer's basic information. Once the input is complete, press the "Confirm" button on the terminal.

[1111] 3. The terminal sends the input information to the server when the "Confirm" button is pressed.

[1112] 4. The server validates the received information (e.g., checks the email format, checks for required fields) and saves it to the MySQL database.

[1113] Specific example:

[1114] For example, when Mr. Tanaka visits the store, a user (staff member) enters information into a terminal. Once the input is complete, the staff member presses the "Confirm" button. The terminal sends the data to the server, which receives the data, verifies it, and then saves it to the database.

[1115] Entering and managing employee shift information

[1116] 1. The terminal displays a shift information input form on the management screen.

[1117] 2. The user (frontline manager) enters information such as the employee's name, workday, start time, and end time.

[1118] 3. Once you have finished entering the information, press the "Send" button on the device.

[1119] 4. The server processes the received shift information, checks the data integrity, and saves it to the MySQL database.

[1120] Specific example:

[1121] The frontline manager enters Yamada and Sato's shifts for the next day into the terminal and presses the "Send" button. The server receives the data, checks its integrity, and saves it to the database.

[1122] Calculation and display of optimal staffing levels

[1123] 1. The server uses a machine learning model (e.g., the scikit-learn library in Python) to analyze past customer data and shift information and calculate the predicted number of customers for the following day.

[1124] 2. The server calculates the optimal staffing arrangement based on the estimated number of customers it has calculated.

[1125] 3. The server sends the calculated optimal schedule to the terminal.

[1126] 4. The device displays the optimal schedule for the user, and the user makes adjustments as needed.

[1127] Specific example:

[1128] The server predicts 100 customers for the next day and uses that information to calculate the optimal staffing allocation. The server sends the calculation results to a terminal, where the frontline manager reviews the displayed schedule and makes any necessary adjustments.

[1129] Proposal and implementation of measures to improve customer service quality

[1130] 1. The server analyzes customer feedback and historical data to generate measures to improve customer service quality (e.g., reducing waiting times, revising customer service manuals). The Python Pandas library is used for data analysis.

[1131] 2. The server sends the generated quality improvement measures to the terminal.

[1132] 3. The terminal displays quality improvement measures suggested to the user, and the user instructs staff to implement them.

[1133] Specific example:

[1134] The server detects when customer wait times are long during specific periods and uses that information to suggest improvements to service speed. These suggestions are displayed on terminals, and frontline managers instruct staff to implement these improvements.

[1135] Brand evaluation and notification of achievement goals

[1136] 1. The server calculates brand evaluation points based on accumulated feedback and performance data. The Statsmodels library in Python is used for statistical analysis.

[1137] 2. The server sends these evaluation points and achievement targets to the terminal.

[1138] 3. The device notifies the user of evaluation points and achievement goals, and proposes specific actions to improve brand value.

[1139] Specific example:

[1140] The server calculates brand evaluation points and notifies the customer that they have a high rating for "prompt and courteous service." The frontline manager then uses this information to propose specific improvement measures to the staff.

[1141] Example of a prompt

[1142] By inputting prompts like the following into the AI ​​model, you can support the generation of optimal staffing and quality improvement measures:

[1143] "Please calculate the optimal staffing level based on customer information and employee shift schedules."

[1144] "Analyze past data and propose measures to improve customer service quality at our stores."

[1145] In this way, a system is built in which servers, terminals, and users cooperate at each step, aiming for efficient business operations and improved customer satisfaction.

[1146] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1147] Program processing flow

[1148] Step 1: Collecting and storing customer information

[1149] 1. The terminal enters customer information.

[1150] The terminal displays a web form, allowing users (store staff) to input information.

[1151] Input: Customer's name, contact information, and past purchase history.

[1152] Output: Information entered into the terminal.

[1153] Specific action: The user enters customer data and presses the "Confirm" button.

[1154] 2. Sending information from the terminal to the server.

[1155] The terminal sends the entered customer information to the server.

[1156] Input: Customer information entered into the terminal.

[1157] Output: Data sent to the server.

[1158] Specific actions: Establish a connection with the server and send customer data.

[1159] 3. The server receives the information and performs validation.

[1160] The server performs validation on the received information (e.g., checking the email format, verifying required fields).

[1161] Input: Customer information received by the server.

[1162] Output: Validated data or error messages.

[1163] Specific actions: Check the format and verify the presence of required fields.

[1164] 4. The server saves the information to the database.

[1165] The server saves the validated information to a MySQL database.

[1166] Input: Customer information that has passed validation.

[1167] Output: Records stored in the database.

[1168] Specific operation: Execute a MySQL query and insert data into the database.

[1169] Step 2: Enter and manage employee shift information

[1170] 1. The terminal enters the shift information.

[1171] The terminal displays a shift information input form, allowing the user (frontline manager) to input the information.

[1172] Input: Employee's name, workday, start time, end time.

[1173] Output: Shift information entered into the terminal.

[1174] Specific action: The frontline manager enters the shift information and presses the "Submit" button.

[1175] 2. Sending information from the terminal to the server.

[1176] The terminal sends the entered shift information to the server.

[1177] Input: Shift information entered into the terminal.

[1178] Output: Data sent to the server.

[1179] Specific actions: Establish a connection with the server and send shift information.

[1180] 3. The server receives the information and checks its integrity.

[1181] The server analyzes the received shift information and checks for duplicates and inconsistencies.

[1182] Input: Shift information received by the server.

[1183] Output: Data with integrity checked, or error messages.

[1184] Specific operation: Detects duplicate data and inconsistent time zones.

[1185] 4. The server saves the information to the database.

[1186] The server saves the shift information that has passed the integrity check to the MySQL database.

[1187] Input: Shift information that has been checked for consistency.

[1188] Output: Records stored in the database.

[1189] Specific operation: Execute a MySQL query and insert data into the database.

[1190] Step 3: Calculation and display of optimal staffing.

[1191] 1. The server calculates the optimal staffing.

[1192] The server uses a machine learning model (e.g., scikit-learn) to analyze historical data and calculate the predicted number of store visits.

[1193] Input: Saved customer information and shift information.

[1194] Output: Predicted number of customers and optimal staffing.

[1195] Specific operation: Input numerical data into the model and obtain prediction results.

[1196] 2. Send the optimization schedule from the server to the terminal.

[1197] The server sends the calculated optimal schedule to the terminal.

[1198] Input: The calculated optimal schedule.

[1199] Output: Data sent to the terminal.

[1200] Specific action: Send schedule data to the device.

[1201] 3. The device displays the optimization schedule.

[1202] The device displays the optimal schedule to the user and prompts them to review and make corrections.

[1203] Input: Optimization schedule received from the server.

[1204] Output: The schedule displayed on the terminal.

[1205] Specific action: Display the schedule in the user interface.

[1206] Step 4: Propose and implement measures to improve customer service quality.

[1207] 1. The server generates quality improvement measures.

[1208] The server analyzes the accumulated feedback and generates measures to improve customer service quality.

[1209] Input: Past feedback and customer information.

[1210] Output: Proposed quality improvement measures.

[1211] Specific actions: Conduct data analysis and create improvement proposals.

[1212] 2. Send quality improvement measures from the server to the terminal.

[1213] The server sends the generated quality improvement measures to the terminal.

[1214] Input: Created quality improvement measures.

[1215] Output: Data sent to the terminal.

[1216] Specific action: Send the proposal to the terminal.

[1217] 3. The device displays quality improvement measures.

[1218] The device displays quality improvement measures to the user and encourages them to implement them.

[1219] Input: Quality improvement measures received from the server.

[1220] Output: Suggestions displayed on the terminal.

[1221] Specific actions: Display the proposed content and show a message encouraging implementation.

[1222] Step 5: Brand evaluation and notification of achievement goals

[1223] 1. The server calculates the evaluation points.

[1224] The server analyzes accumulated feedback and performance data to calculate brand evaluation points.

[1225] Input: Past feedback and performance data.

[1226] Output: Calculated evaluation points.

[1227] Specific operation: Apply the evaluation algorithm and calculate the evaluation points.

[1228] 2. Send evaluation points and targets from the server to the terminal.

[1229] The server sends the calculated evaluation points and achievement targets to the terminal.

[1230] Input: Calculated evaluation points and achievement targets.

[1231] Output: Data sent to the terminal.

[1232] Specific action: Send evaluation information to the terminal.

[1233] 3. The device displays evaluation points and goals.

[1234] The device notifies the user of their evaluation points and achievement goals, and suggests specific actions.

[1235] Input: Evaluation points and achievement goals received from the server.

[1236] Output: Notifications displayed on the device.

[1237] Specific action: Display a notification message and provide specific suggestions.

[1238] The above describes the specific processing flow of this system's program.

[1239] (Application Example 1)

[1240] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1241] Traditional store operations often failed to effectively utilize customer information and employee shift data, resulting in unoptimized staffing. This led to staff shortages during peak hours, lowering customer satisfaction, and unnecessary labor costs during off-peak hours. Furthermore, the lack of real-time suggestions for improving customer service quality based on customer feedback and the inability to predict staffing levels made rapid responses difficult.

[1242] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1243] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee working hours information, means for analyzing the input working hours information and storing it in a database, means for calculating the optimal staffing based on customer information and working hours information, means for displaying the optimized timetable to the user and prompting confirmation and correction, means for proposing measures to improve the quality of customer service based on customer satisfaction, means for displaying the proposed improvement measures and prompting implementation, means for calculating evaluation points and notifying achievement targets, means for predicting the number of expected customers and calculating the necessary workforce based on that, means for predicting and presenting the optimal staffing in real time, means for analyzing customer feedback using a generative AI model and generating measures to improve the quality of customer service, and means for supporting the efficiency of store operations using prompt messages. This makes it possible to efficiently allocate staff, improve customer satisfaction, and optimize labor costs at the same time.

[1244] "Customer information" refers to data about a customer, such as basic information, contact information, and past purchase history.

[1245] "Means of collection" refers to the function of inputting customer information into a terminal and transmitting it to a server.

[1246] "Means of saving to a database" refers to the function of saving collected data in a digital format and maintaining it in a format that allows for access and editing as needed.

[1247] "Working hours information" refers to data related to shifts, such as employees' working days, start times, and end times.

[1248] "Means of analysis" refers to the function of analyzing collected data and extracting patterns and trends.

[1249] "Optimal staffing" refers to calculating the most suitable staffing configuration for store operations based on factors such as the expected number of customers and employee working hours.

[1250] An "optimized timetable" refers to a shift schedule based on a calculated optimal staffing arrangement.

[1251] "Means to prompt review and correction" refers to a function that presents an optimized schedule to the user, allowing the user to perform final review and make necessary corrections.

[1252] "Means of proposing quality improvement measures" refers to a function that generates improvement measures for customer service methods and service content based on customer satisfaction and feedback.

[1253] "Means for displaying proposed improvement plans and encouraging their implementation" refers to a function that displays generated quality improvement measures to the user and encourages their implementation.

[1254] "Evaluation points" refer to performance indicators for stores and brands that are calculated based on customer feedback and performance data.

[1255] "Means of notifying achievement targets" refers to a function that notifies users of the targets that stores and brands should achieve based on the calculated evaluation points.

[1256] "Methods for predicting the number of customers expected to visit" refers to functions that predict future customer visits based on past data and trends.

[1257] "Means for calculating the required workforce" refers to a function that calculates the number of employees needed for a given time slot based on the expected number of customers.

[1258] "Means of predicting and presenting in real time" refers to a function that calculates the optimal staffing allocation in real time based on current data and presents the results to the user.

[1259] A "generative AI model" refers to an artificial intelligence model that uses machine learning or deep learning to analyze data and automatically perform specific tasks.

[1260] A "prompt message" refers to text used to give specific instructions or data input to an AI model.

[1261] The system for carrying out this invention includes a process for collecting customer information and employee working hours information, storing it in a database, and calculating the optimal staffing arrangement based on that information. Detailed embodiments of this system are described below.

[1262] Collection and storage of customer information

[1263] Customer information is entered on a terminal and sent to the server. The terminal retrieves basic customer information (name, contact information, past purchase history, etc.) and sends this data to the server. The server stores the received data in a database and checks for errors in the input data to ensure accuracy.

[1264] Input and management of employee working hours information

[1265] The user (store manager) uses a management terminal to input employee shift information. Specifically, they input the employee's name, workday, start time, and end time. The server analyzes the received shift information and stores it in a database.

[1266] Calculation and display of optimal staffing levels

[1267] The server uses customer information and working hours data to predict the number of expected customers and their needs, and calculates the optimal staffing allocation. It also calculates the required workforce based on the expected number of customers and generates an optimal shift schedule based on the results. The terminal displays the calculated and optimized timetable to the user, prompting them to review and make any necessary adjustments.

[1268] Proposal and implementation of measures to improve customer service quality

[1269] The server analyzes customer feedback and historical data to generate measures to improve customer service quality. These include reducing customer waiting times and improving the quality of service. The terminal displays the customer service improvement measures generated using the AI ​​model to the user and encourages their implementation.

[1270] Brand evaluation and notification of achievement goals

[1271] The server calculates evaluation points based on accumulated feedback and performance data, and notifies the brand of its evaluation points and achievement targets. The terminal proposes specific actions to the user to improve brand value and encourages their implementation.

[1272] Specific example

[1273] For example, the server predicts the number of customers visiting the store the following day, Monday, and uses that result to calculate the necessary workforce. It predicts 50 customers at 10 AM, requiring 5 staff members. At 1 PM, it predicts 30 customers, requiring 3 staff members. This optimized schedule is displayed on the user's terminal, allowing them to review and modify it.

[1274] Example of a prompt

[1275] "Calculate the optimal shifts for each time slot on Monday. Since the number of customers varies at each time, allocate the appropriate number of employees accordingly. Please write a weekday shift optimization program."

[1276] In this way, this system processes data accurately and efficiently at each step, enabling optimal staffing and thereby increasing customer satisfaction and improving the efficiency of store operations.

[1277] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1278] Step 1: Collecting customer information

[1279] The terminal inputs basic information of customers who visit the store (name, contact information, past purchase history, etc.). This input data is entered by the terminal and sent to the server. The server stores the received customer information in a database. It also checks for errors in the input content to ensure accuracy.

[1280] Step 2: Enter employee working hours information

[1281] The user (store manager) uses a management terminal to input employee work time information (name, workday, start time, and end time, etc.). This input data is entered via the management terminal and sent to the server. The server stores the received work time information in a database, checks for duplicates or errors in the input data, and makes corrections as necessary.

[1282] Step 3: Predicting the number of expected customers

[1283] The server predicts the number of expected customers based on customer information and working hours data. The server generates a customer visit prediction model using accumulated historical data. This generated AI model is used to predict the number of expected customers for a specific date and time. The input here is historical customer data, and the output is the predicted number of customers.

[1284] Step 4: Calculating the optimal staffing levels

[1285] The server calculates the required workforce for each time slot based on the predicted number of customers. The server calculates the number of employees needed based on the expected number of customers and then calculates the optimal staffing. The input here is the expected number of customers, and the output is the required number of employees.

[1286] Step 5: Display the optimized timetable

[1287] The server sends the result of its calculated optimal staffing allocation to the terminal. The terminal displays this optimized schedule to the user, prompting them to review and make corrections. The input here is the optimized shift schedule, and the output is the user's feedback for review and correction.

[1288] Step 6: Propose measures to improve customer service quality

[1289] The server analyzes customer feedback and historical data to generate measures for improving customer service quality. It uses a generation AI model to analyze feedback data and generate specific improvement measures. The terminal displays these quality improvement measures to the user and encourages their implementation. Here, the input is feedback data, and the output is the proposed quality improvement measures.

[1290] Step 7: Brand evaluation and notification of achievement goals

[1291] The server calculates evaluation points based on accumulated feedback and performance data and notifies the user. The terminal displays these evaluation points and achievement targets to the user and suggests specific actions to improve brand value. The inputs here are feedback and performance data, and the outputs are evaluation points and achievement targets.

[1292] Through the steps described above, this invention makes it possible to efficiently allocate personnel and achieve customer satisfaction and efficient store operations.

[1293] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1294] This invention is a system that collects and manages customer information and employee shift information, and based on this, realizes optimal staffing. Furthermore, by combining this with an emotion engine, it recognizes and analyzes user emotions to improve the quality of customer service and enhance brand value. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[1295] 1. Collection and storage of customer information

[1296] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[1297] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[1298] Specific example: Mr. Tanaka comes into the store and registers his name and contact information on a terminal. The terminal sends this information to the server, which stores the information in a database for verification.

[1299] 2. Inputting and managing employee shift information

[1300] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[1301] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[1302] Specific example: A frontline manager uses a management terminal to enter the shift information for employees Yamada and Sato for the following day. The server analyzes this information and saves it to the database.

[1303] 3. Calculation and display of optimal staffing levels

[1304] The server predicts the expected number of customers and their needs based on customer information and employee shift schedules. Based on these predictions, it calculates the optimal staffing levels for each time slot.

[1305] The terminal displays the calculated optimal schedule to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[1306] Specific example: The server predicts 100 customers will visit the store the next day and uses that information to optimize the next day's shifts. The frontline manager checks the optimized shift schedule on a terminal and makes any necessary adjustments.

[1307] 4. Emotion recognition and analysis using an emotion engine

[1308] The device is equipped with an emotion engine that recognizes the emotions of employees and customers in the store in real time. The emotion engine identifies the user's emotional state through facial recognition technology and voice analysis.

[1309] The server receives emotional data recognized by the emotion engine and stores it in a database. Furthermore, it analyzes this data to extract areas for improvement in store operations.

[1310] Specific example: An emotion engine recognizes the frequency of an employee's smiles and sends this information to a server. The server analyzes this information and suggests appropriate countermeasures if it detects certain signs of stress.

[1311] 5. Proposal and implementation of measures to improve customer service quality

[1312] The server generates measures to improve customer service quality based on customer feedback and emotion engine data. This includes reducing customer waiting times and improving the quality of service.

[1313] The terminal displays customer service quality improvement measures sent from the server to the user and encourages their implementation.

[1314] Specific example: The server detects that customer wait times are long during a particular period and suggests improving service speed. This suggestion is displayed on a terminal, and the frontline manager instructs staff to implement it.

[1315] 6. Notification of brand evaluation and achievement targets

[1316] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. These points are based on evaluation criteria such as prompt response and courteous customer service.

[1317] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[1318] Specific example: The server team recognizes its high rating for "prompt and courteous service" and proposes concrete measures to further enhance this. The frontline manager reviews the proposal and instructs employees to implement it.

[1319] In this way, by having the server, terminals, and users each fulfill their respective roles, a system is built that enables efficient store operations and high customer satisfaction through the use of emotion recognition. This system can simultaneously achieve optimal staffing, high-quality customer service, and enhanced brand value through the use of emotional data.

[1320] The following describes the processing flow.

[1321] Step 1:

[1322] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[1323] Step 2:

[1324] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[1325] Step 3:

[1326] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[1327] Step 4:

[1328] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[1329] Step 5:

[1330] The server predicts the expected number of customers and their needs based on customer information and shift information. Based on this prediction, it calculates the optimal staffing levels for each time slot.

[1331] Step 6:

[1332] The terminal displays the optimal schedule sent from the server to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[1333] Step 7:

[1334] The server notifies that the optimized schedule has resulted in successful staff reductions and increased efficiency. The frontline manager reviews the notification and updates the shift schedule accordingly.

[1335] Step 8:

[1336] The device uses an emotion engine to recognize the emotions of employees and customers in the store in real time. The emotion engine identifies the user's emotional state through facial recognition technology and voice analysis.

[1337] Step 9:

[1338] The server receives emotional data recognized by the emotion engine and stores it in a database. Furthermore, it analyzes this data to extract areas for improvement in store operations.

[1339] Step 10:

[1340] The server generates measures to improve customer service quality based on customer feedback and emotion engine data. This includes reducing customer waiting times and improving the quality of service.

[1341] Step 11:

[1342] The terminal displays suggestions for improving customer service quality, sent from the server, to the user and encourages their implementation. The user reviews the suggestions and issues instructions to employees to implement them.

[1343] Step 12:

[1344] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. It reviews evaluation items such as prompt response and courteous customer service and proposes measures to improve brand value.

[1345] Step 13:

[1346] The device notifies the user of brand evaluation points and achievement targets, and proposes a specific action plan. The user then develops an implementation plan based on the proposal and shares it with employees.

[1347] In this way, through the processing flow from Step 1 to Step 13, a system is built that utilizes emotion recognition to achieve efficient store operations and high customer satisfaction.

[1348] (Example 2)

[1349] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1350] Traditional store management systems often rely on manual processes for managing customer information and employee shifts, making efficient staffing and improved customer service difficult. Furthermore, there's a lack of systems to monitor and respond to employee and customer emotional states in real time. This leads to problems such as decreased customer satisfaction and increased employee stress. Therefore, there's a need to develop systems that support efficient and effective store operations to address these challenges.

[1351] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1352] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for predicting the number of expected customers based on the collected customer information and shift information, means for calculating the optimal staffing based on the predicted number of customers, means for displaying the calculated optimization schedule to the user and proposing measures to improve the quality of customer service based on customer satisfaction, means for displaying the proposed measures to improve the quality of customer service and encouraging their implementation, means for calculating brand evaluation points based on accumulated feedback, emotional data, and performance data and notifying the achievement target, means for recognizing and analyzing the emotions of users and employees through facial recognition and voice analysis, and means for proposing stress management and improvements in customer service quality based on emotional data. This makes it possible to simultaneously achieve efficient staffing, high-quality customer service, and improved brand value through the use of emotional data.

[1353] "Customer information" refers to basic information such as the name, contact information, and past purchase history of customers who use the store.

[1354] A "database" refers to a system that stores and manages customer information, shift information, etc., and has the function of searching and updating data as needed.

[1355] "Shift information" refers to information about an employee's working hours, such as the employee's name, working days, start time, and end time.

[1356] "Optimal staffing" refers to an employee allocation plan that maximizes store operational efficiency and customer satisfaction, based on collected customer and shift information.

[1357] An "emotion engine" refers to a system that uses facial recognition and voice analysis to identify the emotional states of employees and customers, and collects and analyzes this data.

[1358] "Feedback" refers to information based on opinions and evaluations received from customers and employees.

[1359] "Brand evaluation points" refer to indicators used to evaluate the value and quality of a brand, calculated based on accumulated feedback, sentiment data, and performance data.

[1360] "Stress management" refers to the process of monitoring employees' stress levels based on recognized emotional data and proposing appropriate countermeasures.

[1361] "Customer service quality" refers to the quality of service and interaction with customers, and includes prompt responses, courteous service, and appropriate problem-solving.

[1362] "Expected number of visitors" refers to the number of future visitors predicted based on past data and current reservation information.

[1363] Modes for carrying out the invention

[1364] This invention is a system that collects and manages customer information and employee shift information, and based on this, realizes optimal staffing. Furthermore, by combining this with an emotion engine, it recognizes and analyzes user emotions to improve the quality of customer service and enhance brand value. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[1365] 1. Collection and storage of customer information

[1366] The terminal provides a function to input basic information (name, contact information, past purchase history, etc.) of customers who visit the store. The terminal uses a PC or tablet and has a store-specific input application installed.

[1367] The user (store clerk) enters the customer's information into the input form displayed on the screen.

[1368] The terminal validates the entered information and sends it to the server.

[1369] The server uses a database management system (DBMS) to receive customer information sent from the terminal and store it in the database.

[1370] Specific example: For instance, a new customer enters the store, and an employee uses a terminal to input the customer's basic information. The terminal validates the information and sends it to the server. The server saves the information to a database and returns a notification to the terminal that the information has been saved.

[1371] 2. Inputting and managing employee shift information

[1372] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[1373] The terminal provides a form for entering shift information. The terminal is a PC or tablet with a dedicated shift management application installed.

[1374] The terminal validates the entered shift information and sends it to the server.

[1375] The server has the functionality to store and verify the collected shift information in a database.

[1376] Specific example: A frontline manager uses a management terminal to input employee shift information. The terminal validates the information and sends it to the server. The server receives the information and stores it in a database.

[1377] 3. Calculation and display of optimal staffing levels

[1378] The server runs an algorithm to predict the expected number of customers based on customer information and employee shift information. This algorithm uses a prediction model written in Python.

[1379] The server calculates the optimal staffing based on the prediction results and sends the result to the terminal. Optimization algorithms such as linear programming are used for optimization.

[1380] The terminal provides a mechanism to display the calculation results to the user.

[1381] Specific example: The server predicts 100 customers will visit the store the next day and optimizes the shift schedule based on that information. The frontline manager checks the schedule on their terminal and makes any necessary adjustments.

[1382] 4. Emotion recognition and analysis using an emotion engine

[1383] The device recognizes the emotions of employees and customers in real time through an emotion engine. The emotion engine is connected to a facial recognition camera and microphone, and uses OpenCV and TensorFlow software to analyze facial expressions and voice tone.

[1384] The server receives sentiment data sent from the terminal, stores it in a database, and analyzes it. The analysis uses the Python data analysis libraries Pandas and Matplotlib.

[1385] Specific example: The emotion engine recognizes the frequency of an employee's smiles and sends this information to the server. The server analyzes this information, assesses the employee's stress level, and suggests appropriate countermeasures.

[1386] 5. Proposal and implementation of measures to improve customer service quality

[1387] The server generates strategies for improving customer service quality based on customer feedback and sentiment data. Natural language processing (NLP) algorithms are used to analyze the feedback.

[1388] The device displays the generated suggestions to the user and encourages them to implement them.

[1389] Specific example: The server identifies customer wait times as long during certain periods based on feedback and creates suggestions to improve service speed. A terminal displays these suggestions, and the frontline manager instructs staff to implement them.

[1390] 6. Notification of brand evaluation and achievement targets

[1391] The server calculates brand evaluation points based on feedback, sentiment data, and performance data. Evaluation systems and algorithms are used for the calculation.

[1392] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[1393] Specific example: Feedback data reveals that the server has a high rating for "prompt and courteous response," and measures to improve it are proposed. The frontline manager checks the proposal on their terminal and instructs employees to implement it.

[1394] Example of a prompt:

[1395] "Please explain how the server calculates the optimal staffing based on the number of customers expected the following day and employee shift information, and how the results are displayed on the terminal."

[1396] "Please describe the process of using an emotion engine to recognize employees' emotions in real time and analyzing that data on a server."

[1397] As described above, by having the server, terminal, and user each fulfill their respective roles, we will build a system that utilizes emotion recognition to achieve efficient store operations and high customer satisfaction.

[1398] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1399] Step 1: Collect and store customer information

[1400] Specific actions

[1401] The terminal displays a screen where customers who visit the store can enter their basic information (name, contact information, past purchase history, etc.).

[1402] The user (store clerk) enters customer information into the input form displayed on the screen. This information includes name, contact information, and past purchase history.

[1403] The terminal validates the entered information and sends it to the server. For example, it checks if the name format is correct and if the contact information includes all required fields.

[1404] Input and output

[1405] Input: Your name, contact information, and past purchase history

[1406] Data processing and calculation: Validation (checking the accuracy of the data)

[1407] Output: Send validated customer information to the server

[1408] The server receives customer information sent from the terminal and saves it to the database. Upon successful saving, it sends a save completion notification back to the terminal.

[1409] Step 2: Enter and manage employee shift information

[1410] Specific actions

[1411] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[1412] The terminal validates the entered shift information and sends it to the server. For example, it checks whether the work days are entered in the correct format and whether there are any duplicates.

[1413] Input and output

[1414] Input: Employee's name, workday, start time, and end time

[1415] Data processing and calculation: Validation (checking the accuracy of the data)

[1416] Output: Send validated shift information to the server.

[1417] The server saves the received shift information to the database and verifies it. If the saving is successful, it sends a confirmation completion notification to the terminal.

[1418] Step 3: Calculation and display of optimal staffing levels

[1419] Specific actions

[1420] The server runs a predictive model that forecasts the number of customers expected to visit, based on stored customer information and employee shift information. The prediction uses a prediction algorithm written in a Python program.

[1421] The server calculates the optimal staffing based on the prediction results and sends the result to the terminal. Optimization algorithms such as linear programming are used for optimization.

[1422] The terminal provides a screen to display the calculation results.

[1423] Input and output

[1424] Input: Saved customer information, employee shift information

[1425] Data processing and calculation: Predicting the number of customers expected, calculating optimal staffing levels.

[1426] Output: Send optimized staffing schedule to terminal

[1427] As a concrete example, the server predicts that 100 customers will visit the store the next day, and uses that information to optimize the shift schedule. The frontline manager checks the schedule on their terminal and makes any necessary adjustments.

[1428] Step 4: Emotion recognition and analysis using the emotion engine

[1429] Specific actions

[1430] The device recognizes the emotions of employees and customers in real time through an emotion engine. The emotion engine is connected to a facial recognition camera and microphone, and uses OpenCV and TensorFlow software to analyze facial expressions and voice tone.

[1431] The device sends the analyzed emotion data to the server.

[1432] The server receives emotional data, stores it in a database, and analyzes it.

[1433] Input and output

[1434] Input: Face recognition and voice analysis data

[1435] Data processing and calculation: Identification of emotional states, data analysis

[1436] Output: Accumulate analysis results and suggest appropriate countermeasures.

[1437] As a concrete example, the emotion engine recognizes the frequency of an employee's smile and sends this information to the server. The server analyzes this information, assesses signs of employee stress, and suggests appropriate countermeasures.

[1438] Step 5: Propose and implement measures to improve customer service quality.

[1439] Specific actions

[1440] The server generates strategies for improving customer service quality based on feedback and sentiment data. Natural language processing (NLP) algorithms are used to analyze the feedback.

[1441] The device displays the generated suggestions to the user and encourages them to implement them.

[1442] Input and output

[1443] Input: Feedback data, sentiment data

[1444] Data processing and calculation: Feedback analysis, generation of quality improvement measures.

[1445] Output: Display the recommendations on the device.

[1446] As a concrete example, a server identifies customer wait times as long during specific periods based on feedback and creates suggestions to improve service speed. A terminal displays these suggestions, and the frontline manager instructs staff to implement them.

[1447] Step 6: Brand evaluation and notification of achievement goals

[1448] Specific actions

[1449] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. An evaluation system and algorithm are used for the evaluation calculation.

[1450] The device notifies the user of the calculated evaluation points and achievement targets, and suggests actions to improve brand value.

[1451] Input and output

[1452] Input: Feedback data, sentiment data, performance data

[1453] Data processing and calculation: Calculation of brand evaluation points, setting of achievement targets.

[1454] Output: Evaluation points and achievement goals are notified to the device.

[1455] As a concrete example, accumulated data reveals that the server has a high rating for "prompt and courteous response," and a proposal is created to further enhance this. The frontline manager reviews the proposal on their terminal and instructs employees to implement it.

[1456] (Application Example 2)

[1457] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1458] Currently, building a system that optimizes store operations while simultaneously improving customer service quality and brand value is extremely difficult. Furthermore, to enhance customer satisfaction, it's necessary to appropriately recognize employee emotions and implement appropriate responses immediately. However, no technology yet exists that can integrate these elements into a single system. Therefore, there is a need to develop a system that can simultaneously optimize staffing, improve customer service quality, and enhance brand value.

[1459] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1460] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for calculating the optimal staffing arrangement based on customer information and shift information, means for displaying the optimized schedule to the user and prompting confirmation and correction, means for recognizing the emotional state of customers and employees in real time using emotion recognition technology, means for generating and displaying measures to improve customer service quality based on the emotional state, means for prompting the implementation of the proposed measures to improve customer service quality, and means for calculating brand evaluation based on accumulated emotional data and feedback data and notifying the achievement target. This makes it possible to improve customer satisfaction, optimize staffing, and simultaneously improve customer service quality and brand value.

[1461] "Customer information" refers to basic information about a customer, such as their name, contact information, and past purchase history.

[1462] "Collection methods" refer to devices and programs used to acquire customer information and employee shift information.

[1463] "Means of storing data in a database" refers to devices or programs used to store collected data in a database.

[1464] "Employee shift information" refers to information about the employee's name, workday, start time, and end time.

[1465] "Analysis means" refers to devices or programs used to analyze collected information and extract necessary data.

[1466] "Optimal staffing" refers to the best possible staffing arrangement in store operations to maximize customer satisfaction.

[1467] "Schedule display means" refers to a device or program that displays the calculated optimal schedule to the user and prompts them to approve and modify it.

[1468] "Emotion recognition technology" refers to technology that uses facial recognition technology and voice analysis to recognize an individual's emotional state in real time.

[1469] "Quality improvement measure generation means" refers to a device or program that automatically generates customer service quality improvement measures based on collected data.

[1470] "Means for implementing quality improvement measures" refers to devices or programs that present generated quality improvement measures to users and encourage their implementation.

[1471] "Evaluation calculation means" refers to devices or programs used to calculate brand evaluations based on accumulated feedback and sentiment data.

[1472] "Means of notifying achievement targets" refers to devices or programs that notify users of achievement targets based on calculated brand evaluation points.

[1473] The following describes specific embodiments for carrying out the present invention.

[1474] First, let's explain the collection and storage of customer information. In stores, terminals provide a means for customers to enter basic information such as their name, contact information, and past purchase history when they visit the store. This information is entered with the customer's consent, and the server stores this information in a database and checks for any errors.

[1475] Next, we will explain the input and management of employee shift information. The user (store manager) uses a management terminal to input employee shift information. This shift information includes the employee's name, workday, start time, and end time. The server receives this shift information, stores it in the database, and checks for duplicate information and input errors.

[1476] The server predicts the expected number of customers and their needs based on customer information and employee shift information, and calculates the optimal staffing arrangement based on that. The calculated optimal schedule is displayed on the terminal, which the user can review and modify as needed.

[1477] Next, we will explain emotion recognition and analysis using the emotion engine. The terminal is equipped with an emotion engine that recognizes the emotions of employees and customers in the store in real time. This engine uses facial recognition technology and voice analysis to identify the user's emotional state. The server receives the recognized emotion data, stores it in a database, and performs analysis. Based on the results, it extracts areas for improvement in store operations.

[1478] This section describes the proposal and implementation of measures to improve customer service quality. The server generates these improvement measures based on customer feedback and data from the emotion engine. These measures include reducing customer waiting times and improving the quality of service. The terminal displays these suggestions to the user and encourages their implementation.

[1479] Finally, let's discuss brand evaluation and goal notification. The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. This reflects evaluations such as prompt response and courteous customer service. The terminal notifies the user of the calculated evaluation points and goals, and suggests specific actions to improve brand value.

[1480] Specific example:

[1481] A concrete example of collecting and storing customer information: When a customer enters the store, they scan a QR code, and their basic information is instantly entered. The server then stores this information in a database.

[1482] A concrete example of shift information management: An administrator uses a management terminal to enter employee shifts, which are then sent to a server.

[1483] Specific example of optimal staffing: The server calculates the optimal staffing based on the predicted number of customers and notifies the terminal. The administrator reviews this result and makes corrections as needed.

[1484] A concrete example of emotion recognition: An emotion engine identifies the emotions of employees and customers in real time and sends that data to a server.

[1485] Specific example of improving customer service quality: The server generates quality improvement measures based on feedback data and proposes them to employees via a terminal.

[1486] A concrete example of brand value evaluation: The server calculates evaluation points and notifies the terminal of the achievement target.

[1487] Example of a prompt:

[1488] "Please calculate the optimal staffing levels based on the following shift schedule."

[1489] "Based on the following sentiment data, please suggest areas for improvement in customer service quality."

[1490] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1491] Step 1:

[1492] Collection and storage of customer information

[1493] The terminal has a means of inputting basic information such as the customer's name, contact information, and past purchase history. This information is entered with the customer's consent, and the terminal sends it to the server. The server stores the received customer information in a database and checks for any errors in the information.

[1494] Input: Customer name, contact information, purchase history

[1495] Processing: Data integrity check

[1496] Output: Customer information is saved to the database.

[1497] Step 2:

[1498] Entering and managing employee shift information

[1499] The user (store manager) uses a management terminal to enter employee shift information (name, work days, start time, end time). The terminal sends this information to the server. The server stores the received shift information in a database and checks for input errors and duplicates.

[1500] Input: Employee's name, workday, start time, end time

[1501] Processing: Data integrity check

[1502] Output: Shift information is saved to the database.

[1503] Step 3:

[1504] Calculation of optimal staffing

[1505] The server predicts the expected number of customers and their needs based on customer information and employee shift information. Based on this, it calculates the optimal staffing for each time slot and sends the results to the terminal. The terminal displays the optimized schedule to the user and prompts them to review and make adjustments.

[1506] Input: Customer information, shift information

[1507] Processing: Forecasting using demand forecasting algorithms, optimization calculation of personnel allocation.

[1508] Output: The optimized schedule will be displayed on the device.

[1509] Step 4:

[1510] Emotion recognition and data analysis

[1511] The terminal uses its built-in emotion engine to recognize the emotions of employees and customers in the store in real time. This emotion data is sent from the terminal to a server, which stores it in a database. The server then analyzes the emotion data to identify areas for improvement in store operations.

[1512] Input: Facial images and audio data of employees and customers

[1513] Processing: Analysis using an emotion recognition algorithm

[1514] Output: Recognized emotion data is sent to the server and stored in the database.

[1515] Step 5:

[1516] Developing and managing measures to improve customer service quality.

[1517] The server generates suggestions for improving customer service quality based on customer feedback and data from the emotion engine. The terminal displays these suggestions to the user and encourages their implementation.

[1518] Input: Feedback data, sentiment data

[1519] Processing: Generation of suggestions using a customer service improvement algorithm.

[1520] Output: Measures to improve customer service quality are displayed on the terminal.

[1521] Step 6:

[1522] Brand valuation calculation and target notification

[1523] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. The terminal notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[1524] Input: Feedback data, sentiment data, performance data

[1525] Processing: Score calculation using a brand evaluation algorithm.

[1526] Output: Evaluation points and achievement goals are displayed on the device.

[1527] Through the above processing steps, servers, terminals, and users work together to improve customer satisfaction, optimize staffing, and simultaneously enhance customer service quality and brand value.

[1528] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1529] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1530] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1531] [Fourth Embodiment]

[1532] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1533] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1534] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1535] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1536] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1537] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1538] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1539] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1540] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1541] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1542] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1543] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1544] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1545] This invention is a system that collects and manages customer information and employee shift information, and uses this information to achieve optimal staffing. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[1546] 1. Collection and storage of customer information

[1547] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[1548] The server receives the entered customer information and stores it in the database. The server checks the entered information for errors to ensure accurate data collection.

[1549] Specific example: Customer Tanaka comes into the store and registers his name and contact information on a terminal. The terminal sends this information to the server, which stores the information in a database for verification.

[1550] 2. Inputting and managing employee shift information

[1551] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This includes each employee's name, workday, start time, and end time.

[1552] The server analyzes the collected shift information and stores it in a database. The server checks the input data for duplicates and errors and makes corrections as needed.

[1553] Specific example: A frontline manager uses a management terminal to enter the shift information for employees Yamada and Sato for the following day. The server analyzes this information and saves it to the database.

[1554] 3. Calculation and display of optimal staffing levels

[1555] The server predicts the expected number of customers and their needs based on customer information and employee shift schedules. This allows it to calculate the optimal staffing levels for each day and time slot.

[1556] The terminal displays the calculated optimal schedule to the user. The user reviews and modifies the information displayed on the terminal to determine the most efficient staffing arrangement.

[1557] Specific example: The server predicts 100 customers will visit the store the next day and uses that information to optimize the next day's shifts. The frontline manager checks the optimized schedule on their terminal and makes any necessary adjustments.

[1558] 4. Proposal and implementation of measures to improve customer service quality

[1559] The server generates measures to improve customer service quality based on customer feedback and historical data. These include reducing customer waiting times and improving the quality of service.

[1560] The terminal displays customer service quality improvement measures sent from the server to the user and encourages their implementation.

[1561] Specific example: The server detects that customer wait times are long during a particular period and suggests improving service speed. This suggestion is displayed on a terminal, and the frontline manager instructs staff to implement it.

[1562] 5. Notification of brand evaluation and achievement targets

[1563] The server calculates brand evaluation points based on accumulated feedback and performance data. These points are based on evaluation criteria such as prompt response and courteous customer service.

[1564] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[1565] Specific example: The server team recognizes its high rating for "prompt and courteous service" and proposes concrete measures to further enhance this. The frontline manager reviews the proposal and instructs employees to implement it.

[1566] In this way, by having servers, terminals, and users each fulfill their respective roles, a system is realized that improves customer satisfaction and enables efficient store operations. This system allows for optimal staffing and high-quality customer service, thereby enhancing brand value.

[1567] The following describes the processing flow.

[1568] Step 1:

[1569] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[1570] Step 2:

[1571] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[1572] Step 3:

[1573] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[1574] Step 4:

[1575] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[1576] Step 5:

[1577] The server predicts the expected number of customers and their needs based on customer information and shift information. Based on this prediction, it calculates the optimal staffing levels for each time slot.

[1578] Step 6:

[1579] The terminal displays the optimal schedule sent from the server to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[1580] Step 7:

[1581] The server notifies that the optimized schedule has resulted in successful staff reductions and increased efficiency. The frontline manager reviews the notification and updates the shift schedule accordingly.

[1582] Step 8:

[1583] The server generates measures to improve customer service quality based on customer feedback and historical data. These include reducing customer waiting times and improving the quality of service.

[1584] Step 9:

[1585] The terminal displays suggestions from the server for improving customer service quality to the user and encourages them to implement specific improvement measures. The user reviews the suggestions and instructs employees to implement them.

[1586] Step 10:

[1587] The server calculates brand evaluation points based on feedback and performance data. It reviews evaluation items such as prompt response and courteous customer service and proposes measures to improve brand value.

[1588] Step 11:

[1589] The device notifies the user of brand evaluation points and achievement targets, and proposes a specific action plan. The user then develops an implementation plan based on the proposal and shares it with employees.

[1590] In this way, a system is built that achieves efficient store operations and high customer satisfaction through the processing flow from step 1 to step 11.

[1591] (Example 1)

[1592] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1593] Traditional store management systems made it difficult to efficiently manage customer information and employee shift schedules, hindering optimal staffing. Furthermore, there was a lack of a system that consistently handled advanced store management tasks such as improving customer satisfaction, calculating brand evaluation points, and notifying achievement targets. As a result, challenges arose, including declining customer satisfaction, reduced staff efficiency, and slower brand value development.

[1594] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1595] In this invention, the server includes means for collecting basic customer information, means for storing the collected basic customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for calculating the optimal staffing arrangement using a machine learning model based on customer information and shift information, means for displaying the optimized schedule to the user and prompting confirmation and correction, means for generating and proposing measures to improve the quality of customer service based on customer feedback, means for displaying the proposed quality improvement measures and prompting their implementation, and means for calculating brand evaluation points based on accumulated feedback and performance data and notifying the achievement target. As a result, customer information and employee shift information can be centrally managed, and by providing optimal staffing and high-quality customer service, it becomes possible to improve customer satisfaction and operate stores efficiently.

[1596] "Customer basic information" refers to basic data about customers who visit the store, such as their name, contact information, and past purchase history.

[1597] A "database" is an information system designed to efficiently store and manage collected information, and is designed to allow for easy searching and updating of data.

[1598] "Employee shift information" refers to data regarding the working days, start times, and end times of employees working at the store.

[1599] A "machine learning model" is an artificial intelligence technology used to analyze large amounts of data and identify patterns and make predictions. In this invention, it is used to calculate the optimal staffing arrangement.

[1600] An "optimized schedule" is a work schedule calculated based on each employee's shift information and the predicted number of customers, resulting in the most efficient staffing arrangement.

[1601] "Feedback" refers to opinions and evaluations provided by customers, and is information that can be used to improve the quality of customer service and enhance the overall service.

[1602] "Proposed quality improvement measures" refer to specific suggestions and measures to improve the quality of customer service and operations, generated based on collected data and feedback.

[1603] "Brand evaluation points" are a numerical indicator of brand value calculated based on customer satisfaction and service quality.

[1604] "Achievement targets" are specific goals set to enhance brand value and represent the standards that employees and the entire store should strive for.

[1605] Modes for carrying out the invention

[1606] This invention is a system that collects and manages basic customer information and employee shift information, and uses this information to achieve optimal staffing. This system aims to improve the efficiency of store operations and enhance customer satisfaction. The following details specific embodiments for implementing this invention.

[1607] System Configuration

[1608] A system primarily consists of three components: servers, terminals, and users.

[1609] The server plays a central role in collecting, analyzing, and storing information. For example, a web application server using the Python Flask framework can be linked to a MySQL database.

[1610] The terminal functions as an interface for users to input, confirm, and modify information. The terminal utilizes a computer or tablet installed in the store and connects to the server via a web browser.

[1611] Users are store staff and managers who use terminals to input, verify, and modify information.

[1612] Collection and storage of customer information

[1613] 1. The device displays a template screen for the customer to enter their basic information (name, contact information, past purchase history, etc.).

[1614] 2. The user (store staff) enters the customer's basic information. Once the input is complete, press the "Confirm" button on the terminal.

[1615] 3. The terminal sends the input information to the server when the "Confirm" button is pressed.

[1616] 4. The server validates the received information (e.g., checks the email format, checks for required fields) and saves it to the MySQL database.

[1617] Specific example:

[1618] For example, when Mr. Tanaka visits the store, a user (staff member) enters information into a terminal. Once the input is complete, the staff member presses the "Confirm" button. The terminal sends the data to the server, which receives the data, verifies it, and then saves it to the database.

[1619] Entering and managing employee shift information

[1620] 1. The terminal displays a shift information input form on the management screen.

[1621] 2. The user (frontline manager) enters information such as the employee's name, workday, start time, and end time.

[1622] 3. Once you have finished entering the information, press the "Send" button on the device.

[1623] 4. The server processes the received shift information, checks the data integrity, and saves it to the MySQL database.

[1624] Specific example:

[1625] The frontline manager enters Yamada and Sato's shifts for the next day into the terminal and presses the "Send" button. The server receives the data, checks its integrity, and saves it to the database.

[1626] Calculation and display of optimal staffing levels

[1627] 1. The server uses a machine learning model (e.g., the scikit-learn library in Python) to analyze past customer data and shift information and calculate the predicted number of customers for the following day.

[1628] 2. The server calculates the optimal staffing arrangement based on the estimated number of customers it has calculated.

[1629] 3. The server sends the calculated optimal schedule to the terminal.

[1630] 4. The device displays the optimal schedule for the user, and the user makes adjustments as needed.

[1631] Specific example:

[1632] The server predicts 100 customers for the next day and uses that information to calculate the optimal staffing allocation. The server sends the calculation results to a terminal, where the frontline manager reviews the displayed schedule and makes any necessary adjustments.

[1633] Proposal and implementation of measures to improve customer service quality

[1634] 1. The server analyzes customer feedback and historical data to generate measures to improve customer service quality (e.g., reducing waiting times, revising customer service manuals). The Python Pandas library is used for data analysis.

[1635] 2. The server sends the generated quality improvement measures to the terminal.

[1636] 3. The terminal displays quality improvement measures suggested to the user, and the user instructs staff to implement them.

[1637] Specific example:

[1638] The server detects when customer wait times are long during specific periods and uses that information to suggest improvements to service speed. These suggestions are displayed on terminals, and frontline managers instruct staff to implement these improvements.

[1639] Brand evaluation and notification of achievement goals

[1640] 1. The server calculates brand evaluation points based on accumulated feedback and performance data. The Statsmodels library in Python is used for statistical analysis.

[1641] 2. The server sends these evaluation points and achievement targets to the terminal.

[1642] 3. The device notifies the user of evaluation points and achievement goals, and proposes specific actions to improve brand value.

[1643] Specific example:

[1644] The server calculates brand evaluation points and notifies the customer that they have a high rating for "prompt and courteous service." The frontline manager then uses this information to propose specific improvement measures to the staff.

[1645] Example of a prompt

[1646] By inputting prompts like the following into the AI ​​model, you can support the generation of optimal staffing and quality improvement measures:

[1647] "Please calculate the optimal staffing level based on customer information and employee shift schedules."

[1648] "Analyze past data and propose measures to improve customer service quality at our stores."

[1649] In this way, a system is built in which servers, terminals, and users cooperate at each step, aiming for efficient business operations and improved customer satisfaction.

[1650] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1651] Program processing flow

[1652] Step 1: Collecting and storing customer information

[1653] 1. The terminal enters customer information.

[1654] The terminal displays a web form, allowing users (store staff) to input information.

[1655] Input: Customer's name, contact information, and past purchase history.

[1656] Output: Information entered into the terminal.

[1657] Specific action: The user enters customer data and presses the "Confirm" button.

[1658] 2. Sending information from the terminal to the server.

[1659] The terminal sends the entered customer information to the server.

[1660] Input: Customer information entered into the terminal.

[1661] Output: Data sent to the server.

[1662] Specific actions: Establish a connection with the server and send customer data.

[1663] 3. The server receives the information and performs validation.

[1664] The server performs validation on the received information (e.g., checking the email format, verifying required fields).

[1665] Input: Customer information received by the server.

[1666] Output: Validated data or error messages.

[1667] Specific actions: Check the format and verify the presence of required fields.

[1668] 4. The server saves the information to the database.

[1669] The server saves the validated information to a MySQL database.

[1670] Input: Customer information that has passed validation.

[1671] Output: Records stored in the database.

[1672] Specific operation: Execute a MySQL query and insert data into the database.

[1673] Step 2: Enter and manage employee shift information

[1674] 1. The terminal enters the shift information.

[1675] The terminal displays a shift information input form, allowing the user (frontline manager) to input the information.

[1676] Input: Employee's name, workday, start time, end time.

[1677] Output: Shift information entered into the terminal.

[1678] Specific action: The frontline manager enters the shift information and presses the "Submit" button.

[1679] 2. Sending information from the terminal to the server.

[1680] The terminal sends the entered shift information to the server.

[1681] Input: Shift information entered into the terminal.

[1682] Output: Data sent to the server.

[1683] Specific actions: Establish a connection with the server and send shift information.

[1684] 3. The server receives the information and checks its integrity.

[1685] The server analyzes the received shift information and checks for duplicates and inconsistencies.

[1686] Input: Shift information received by the server.

[1687] Output: Data with integrity checked, or error messages.

[1688] Specific operation: Detects duplicate data and inconsistent time zones.

[1689] 4. The server saves the information to the database.

[1690] The server saves the shift information that has passed the integrity check to the MySQL database.

[1691] Input: Shift information that has been checked for consistency.

[1692] Output: Records stored in the database.

[1693] Specific operation: Execute a MySQL query and insert data into the database.

[1694] Step 3: Calculation and display of optimal staffing.

[1695] 1. The server calculates the optimal staffing.

[1696] The server uses a machine learning model (e.g., scikit-learn) to analyze historical data and calculate the predicted number of store visits.

[1697] Input: Saved customer information and shift information.

[1698] Output: Predicted number of customers and optimal staffing.

[1699] Specific operation: Input numerical data into the model and obtain prediction results.

[1700] 2. Send the optimization schedule from the server to the terminal.

[1701] The server sends the calculated optimal schedule to the terminal.

[1702] Input: The calculated optimal schedule.

[1703] Output: Data sent to the terminal.

[1704] Specific action: Send schedule data to the device.

[1705] 3. The device displays the optimization schedule.

[1706] The device displays the optimal schedule to the user and prompts them to review and make corrections.

[1707] Input: Optimization schedule received from the server.

[1708] Output: The schedule displayed on the terminal.

[1709] Specific action: Display the schedule in the user interface.

[1710] Step 4: Propose and implement measures to improve customer service quality.

[1711] 1. The server generates quality improvement measures.

[1712] The server analyzes the accumulated feedback and generates measures to improve customer service quality.

[1713] Input: Past feedback and customer information.

[1714] Output: Proposed quality improvement measures.

[1715] Specific actions: Conduct data analysis and create improvement proposals.

[1716] 2. Send quality improvement measures from the server to the terminal.

[1717] The server sends the generated quality improvement measures to the terminal.

[1718] Input: Created quality improvement measures.

[1719] Output: Data sent to the terminal.

[1720] Specific action: Send the proposal to the terminal.

[1721] 3. The device displays quality improvement measures.

[1722] The device displays quality improvement measures to the user and encourages them to implement them.

[1723] Input: Quality improvement measures received from the server.

[1724] Output: Suggestions displayed on the terminal.

[1725] Specific actions: Display the proposed content and show a message encouraging implementation.

[1726] Step 5: Brand evaluation and notification of achievement goals

[1727] 1. The server calculates the evaluation points.

[1728] The server analyzes accumulated feedback and performance data to calculate brand evaluation points.

[1729] Input: Past feedback and performance data.

[1730] Output: Calculated evaluation points.

[1731] Specific operation: Apply the evaluation algorithm and calculate the evaluation points.

[1732] 2. Send evaluation points and targets from the server to the terminal.

[1733] The server sends the calculated evaluation points and achievement targets to the terminal.

[1734] Input: Calculated evaluation points and achievement targets.

[1735] Output: Data sent to the terminal.

[1736] Specific action: Send evaluation information to the terminal.

[1737] 3. The device displays evaluation points and goals.

[1738] The device notifies the user of their evaluation points and achievement goals, and suggests specific actions.

[1739] Input: Evaluation points and achievement goals received from the server.

[1740] Output: Notifications displayed on the device.

[1741] Specific action: Display a notification message and provide specific suggestions.

[1742] The above describes the specific processing flow of this system's program.

[1743] (Application Example 1)

[1744] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1745] Traditional store operations often failed to effectively utilize customer information and employee shift data, resulting in unoptimized staffing. This led to staff shortages during peak hours, lowering customer satisfaction, and unnecessary labor costs during off-peak hours. Furthermore, the lack of real-time suggestions for improving customer service quality based on customer feedback and the inability to predict staffing levels made rapid responses difficult.

[1746] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1747] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee working hours information, means for analyzing the input working hours information and storing it in a database, means for calculating the optimal staffing based on customer information and working hours information, means for displaying the optimized timetable to the user and prompting confirmation and correction, means for proposing measures to improve the quality of customer service based on customer satisfaction, means for displaying the proposed improvement measures and prompting implementation, means for calculating evaluation points and notifying achievement targets, means for predicting the number of expected customers and calculating the necessary workforce based on that, means for predicting and presenting the optimal staffing in real time, means for analyzing customer feedback using a generative AI model and generating measures to improve the quality of customer service, and means for supporting the efficiency of store operations using prompt messages. This makes it possible to efficiently allocate staff, improve customer satisfaction, and optimize labor costs at the same time.

[1748] "Customer information" refers to data about a customer, such as basic information, contact information, and past purchase history.

[1749] "Means of collection" refers to the function of inputting customer information into a terminal and transmitting it to a server.

[1750] "Means of saving to a database" refers to the function of saving collected data in a digital format and maintaining it in a format that allows for access and editing as needed.

[1751] "Working hours information" refers to data related to shifts, such as employees' working days, start times, and end times.

[1752] "Means of analysis" refers to the function of analyzing collected data and extracting patterns and trends.

[1753] "Optimal staffing" refers to calculating the most suitable staffing configuration for store operations based on factors such as the expected number of customers and employee working hours.

[1754] An "optimized timetable" refers to a shift schedule based on a calculated optimal staffing arrangement.

[1755] "Means to prompt review and correction" refers to a function that presents an optimized schedule to the user, allowing the user to perform final review and make necessary corrections.

[1756] "Means of proposing quality improvement measures" refers to a function that generates improvement measures for customer service methods and service content based on customer satisfaction and feedback.

[1757] "Means for displaying proposed improvement plans and encouraging their implementation" refers to a function that displays generated quality improvement measures to the user and encourages their implementation.

[1758] "Evaluation points" refer to performance indicators for stores and brands that are calculated based on customer feedback and performance data.

[1759] "Means of notifying achievement targets" refers to a function that notifies users of the targets that stores and brands should achieve based on the calculated evaluation points.

[1760] "Methods for predicting the number of customers expected to visit" refers to functions that predict future customer visits based on past data and trends.

[1761] "Means for calculating the required workforce" refers to a function that calculates the number of employees needed for a given time slot based on the expected number of customers.

[1762] "Means of predicting and presenting in real time" refers to a function that calculates the optimal staffing allocation in real time based on current data and presents the results to the user.

[1763] A "generative AI model" refers to an artificial intelligence model that uses machine learning or deep learning to analyze data and automatically perform specific tasks.

[1764] A "prompt message" refers to text used to give specific instructions or data input to an AI model.

[1765] The system for carrying out this invention includes a process for collecting customer information and employee working hours information, storing it in a database, and calculating the optimal staffing arrangement based on that information. Detailed embodiments of this system are described below.

[1766] Collection and storage of customer information

[1767] Customer information is entered on a terminal and sent to the server. The terminal retrieves basic customer information (name, contact information, past purchase history, etc.) and sends this data to the server. The server stores the received data in a database and checks for errors in the input data to ensure accuracy.

[1768] Input and management of employee working hours information

[1769] The user (store manager) uses a management terminal to input employee shift information. Specifically, they input the employee's name, workday, start time, and end time. The server analyzes the received shift information and stores it in a database.

[1770] Calculation and display of optimal staffing levels

[1771] The server uses customer information and working hours data to predict the number of expected customers and their needs, and calculates the optimal staffing allocation. It also calculates the required workforce based on the expected number of customers and generates an optimal shift schedule based on the results. The terminal displays the calculated and optimized timetable to the user, prompting them to review and make any necessary adjustments.

[1772] Proposal and implementation of measures to improve customer service quality

[1773] The server analyzes customer feedback and historical data to generate measures to improve customer service quality. These include reducing customer waiting times and improving the quality of service. The terminal displays the customer service improvement measures generated using the AI ​​model to the user and encourages their implementation.

[1774] Brand evaluation and notification of achievement goals

[1775] The server calculates evaluation points based on accumulated feedback and performance data, and notifies the brand of its evaluation points and achievement targets. The terminal proposes specific actions to the user to improve brand value and encourages their implementation.

[1776] Specific example

[1777] For example, the server predicts the number of customers visiting the store the following day, Monday, and uses that result to calculate the necessary workforce. It predicts 50 customers at 10 AM, requiring 5 staff members. At 1 PM, it predicts 30 customers, requiring 3 staff members. This optimized schedule is displayed on the user's terminal, allowing them to review and modify it.

[1778] Example of a prompt

[1779] "Calculate the optimal shifts for each time slot on Monday. Since the number of customers varies at each time, allocate the appropriate number of employees accordingly. Please write a weekday shift optimization program."

[1780] In this way, this system processes data accurately and efficiently at each step, enabling optimal staffing and thereby increasing customer satisfaction and improving the efficiency of store operations.

[1781] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1782] Step 1: Collecting customer information

[1783] The terminal inputs basic information of customers who visit the store (name, contact information, past purchase history, etc.). This input data is entered by the terminal and sent to the server. The server stores the received customer information in a database. It also checks for errors in the input content to ensure accuracy.

[1784] Step 2: Enter employee working hours information

[1785] The user (store manager) uses a management terminal to input employee work time information (name, workday, start time, and end time, etc.). This input data is entered via the management terminal and sent to the server. The server stores the received work time information in a database, checks for duplicates or errors in the input data, and makes corrections as necessary.

[1786] Step 3: Predicting the number of expected customers

[1787] The server predicts the number of expected customers based on customer information and working hours data. The server generates a customer visit prediction model using accumulated historical data. This generated AI model is used to predict the number of expected customers for a specific date and time. The input here is historical customer data, and the output is the predicted number of customers.

[1788] Step 4: Calculating the optimal staffing levels

[1789] The server calculates the required workforce for each time slot based on the predicted number of customers. The server calculates the number of employees needed based on the expected number of customers and then calculates the optimal staffing. The input here is the expected number of customers, and the output is the required number of employees.

[1790] Step 5: Display the optimized timetable

[1791] The server sends the result of its calculated optimal staffing allocation to the terminal. The terminal displays this optimized schedule to the user, prompting them to review and make corrections. The input here is the optimized shift schedule, and the output is the user's feedback for review and correction.

[1792] Step 6: Propose measures to improve customer service quality

[1793] The server analyzes customer feedback and historical data to generate measures for improving customer service quality. It uses a generation AI model to analyze feedback data and generate specific improvement measures. The terminal displays these quality improvement measures to the user and encourages their implementation. Here, the input is feedback data, and the output is the proposed quality improvement measures.

[1794] Step 7: Brand evaluation and notification of achievement goals

[1795] The server calculates evaluation points based on accumulated feedback and performance data and notifies the user. The terminal displays these evaluation points and achievement targets to the user and suggests specific actions to improve brand value. The inputs here are feedback and performance data, and the outputs are evaluation points and achievement targets.

[1796] Through the steps described above, this invention makes it possible to efficiently allocate personnel and achieve customer satisfaction and efficient store operations.

[1797] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1798] This invention is a system that collects and manages customer information and employee shift information, and based on this, realizes optimal staffing. Furthermore, by combining this with an emotion engine, it recognizes and analyzes user emotions to improve the quality of customer service and enhance brand value. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[1799] 1. Collection and storage of customer information

[1800] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[1801] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[1802] Specific example: Mr. Tanaka comes into the store and registers his name and contact information on a terminal. The terminal sends this information to the server, which stores the information in a database for verification.

[1803] 2. Inputting and managing employee shift information

[1804] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[1805] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[1806] Specific example: A frontline manager uses a management terminal to enter the shift information for employees Yamada and Sato for the following day. The server analyzes this information and saves it to the database.

[1807] 3. Calculation and display of optimal staffing levels

[1808] The server predicts the expected number of customers and their needs based on customer information and employee shift schedules. Based on these predictions, it calculates the optimal staffing levels for each time slot.

[1809] The terminal displays the calculated optimal schedule to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[1810] Specific example: The server predicts 100 customers will visit the store the next day and uses that information to optimize the next day's shifts. The frontline manager checks the optimized shift schedule on a terminal and makes any necessary adjustments.

[1811] 4. Emotion recognition and analysis using an emotion engine

[1812] The device is equipped with an emotion engine that recognizes the emotions of employees and customers in the store in real time. The emotion engine identifies the user's emotional state through facial recognition technology and voice analysis.

[1813] The server receives emotional data recognized by the emotion engine and stores it in a database. Furthermore, it analyzes this data to extract areas for improvement in store operations.

[1814] Specific example: An emotion engine recognizes the frequency of an employee's smiles and sends this information to a server. The server analyzes this information and suggests appropriate countermeasures if it detects certain signs of stress.

[1815] 5. Proposal and implementation of measures to improve customer service quality

[1816] The server generates measures to improve customer service quality based on customer feedback and emotion engine data. This includes reducing customer waiting times and improving the quality of service.

[1817] The terminal displays customer service quality improvement measures sent from the server to the user and encourages their implementation.

[1818] Specific example: The server detects that customer wait times are long during a particular period and suggests improving service speed. This suggestion is displayed on a terminal, and the frontline manager instructs staff to implement it.

[1819] 6. Notification of brand evaluation and achievement targets

[1820] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. These points are based on evaluation criteria such as prompt response and courteous customer service.

[1821] The device notifies the user of the calculated evaluation points and achievement targets, and proposes specific actions to improve brand value.

[1822] Specific example: The server team recognizes its high rating for "prompt and courteous service" and proposes concrete measures to further enhance this. The frontline manager reviews the proposal and instructs employees to implement it.

[1823] In this way, by having the server, terminals, and users each fulfill their respective roles, a system is built that enables efficient store operations and high customer satisfaction through the use of emotion recognition. This system can simultaneously achieve optimal staffing, high-quality customer service, and enhanced brand value through the use of emotional data.

[1824] The following describes the processing flow.

[1825] Step 1:

[1826] The terminal enters basic information about customers who visit the store (name, contact information, past purchase history, etc.). This information is entered only with the customer's consent.

[1827] Step 2:

[1828] The server receives customer information sent from the terminal and stores it in the database. The server checks the information for errors and stores the data accurately.

[1829] Step 3:

[1830] The user (the store's frontline manager) uses a management terminal to enter employee shift information. This information includes the employee's name, workday, start time, and end time.

[1831] Step 4:

[1832] The server receives the collected shift information and stores it in the database. The server checks for duplicates and input errors and makes corrections as needed.

[1833] Step 5:

[1834] The server predicts the expected number of customers and their needs based on customer information and shift information. Based on this prediction, it calculates the optimal staffing levels for each time slot.

[1835] Step 6:

[1836] The terminal displays the optimal schedule sent from the server to the user. The frontline manager reviews the displayed schedule and makes adjustments as needed.

[1837] Step 7:

[1838] The server notifies that the optimized schedule has resulted in successful staff reductions and increased efficiency. The frontline manager reviews the notification and updates the shift schedule accordingly.

[1839] Step 8:

[1840] The device uses an emotion engine to recognize the emotions of employees and customers in the store in real time. The emotion engine identifies the user's emotional state through facial recognition technology and voice analysis.

[1841] Step 9:

[1842] The server receives emotional data recognized by the emotion engine and stores it in a database. Furthermore, it analyzes this data to extract areas for improvement in store operations.

[1843] Step 10:

[1844] The server generates measures to improve customer service quality based on customer feedback and emotion engine data. This includes reducing customer waiting times and improving the quality of service.

[1845] Step 11:

[1846] The terminal displays suggestions for improving customer service quality, sent from the server, to the user and encourages their implementation. The user reviews the suggestions and issues instructions to employees to implement them.

[1847] Step 12:

[1848] The server calculates brand evaluation points based on accumulated feedback, sentiment data, and performance data. It reviews evaluation items such as prompt response and courteous customer service and proposes measures to improve brand value.

[1849] Step 13:

[1850] The device notifies the user of brand evaluation points and achievement targets, and proposes a specific action plan. The user then develops an implementation plan based on the proposal and shares it with employees.

[1851] In this way, through the processing flow from Step 1 to Step 13, a system is built that utilizes emotion recognition to achieve efficient store operations and high customer satisfaction.

[1852] (Example 2)

[1853] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1854] Traditional store management systems often rely on manual processes for managing customer information and employee shifts, making efficient staffing and improved customer service difficult. Furthermore, there's a lack of systems to monitor and respond to employee and customer emotional states in real time. This leads to problems such as decreased customer satisfaction and increased employee stress. Therefore, there's a need to develop systems that support efficient and effective store operations to address these challenges.

[1855] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1856] In this invention, the server includes means for collecting customer information, means for storing the collected customer information in a database, means for inputting employee shift information, means for analyzing the input shift information and storing it in a database, means for predicting the number of expected customers based on the collected customer information and shift information, means for calculating the optimal staffing based on the predicted number of customers, means for displaying the calculated optimization schedule to the user and proposing measures to improve the quality of customer service based on customer satisfaction, means for displaying the proposed measures to improve the quality of customer service and encouraging their implementation, means for calculating brand evaluation points based on accumulated feedback, emotional data, and performance data and notifying the achievement target, means for recognizing and analyzing the emotions of users and employees through facial recognition and voice analysis, and means for proposing stress management and improvements in customer service quality based on emotional data. This makes it possible to simultaneously achieve efficient staffing, high-quality customer service, and improved brand value through the use of emotional data.

[1857] "Customer information" refers to basic information such as the name, contact information, and past purchase history of customers who use the store.

[1858] A "database" refers to a system that stores and manages customer information, shift information, etc., and has the function of searching and updating data as needed.

[1859] "Shift information" refers to information about an employee's working hours, such as the employee's name, working days, start time, and end time.

[1860] "Optimal staffing" refers to an employee allocation plan that maximizes store operational efficiency and customer satisfaction, based on collected customer and shift information.

[1861] An "emotion engine" refers to a system that uses facial recognition and voice analysis to identify the emotional states of employees and customers, and collects and analyzes this data.

[1862] "Feedback" refers to information based on opinions and evaluations received from customers and employees.

[1863] "Brand evaluation points" refer to indicators used to evaluate the value and quality of a brand, calculated based on accumulated feedback, sentiment data, and performance data.

[1864] "Stress management" refers to the process of monitoring employees' stress levels based on recognized emotional data and proposing appropriate countermeasures.

[1865] "Customer service quality" refers to the quality of service and interaction with customers, and includes prompt responses, courteous service, and appropriate problem-solving.

[1866] "Expected number of visitors" refers to the number of future visitors predicted based on past data and current reservation information.

[1867] Modes for carrying out the invention

[1868] This invention is a system that collects and manages customer information and employee shift information, and based on this, realizes optimal staffing. Furthermore, by combining this with an emotion engine, it recognizes and analyzes user emotions to improve the quality of customer service and enhance brand value. This system has various functions to support improved customer satisfaction and efficient store operations. Specific embodiments for implementing this invention are described below.

[1869] 1. Collection and storag...

Claims

1. Means of collecting customer information, A means of storing collected customer information in a database, A means of entering the shift information of store employees, A means of analyzing the entered shift information and saving it to a database, A method for calculating the optimal staffing arrangement based on customer information and shift information, A means to display an optimized schedule to the user and prompt them to review and correct it, A means of proposing measures to improve the quality of customer service based on customer satisfaction, A means of displaying proposed improvements and encouraging their implementation, A means of calculating brand evaluation points and notifying achievement targets. A system that includes this.

2. In the system described in claim 1, A system that includes means for notifying employees of personnel reductions due to optimized scheduling.

3. In the system described in claim 1, A system that includes means to propose specific actions for improving brand value based on accumulated feedback and performance data.

Images