System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting operational status data of a store; means for collecting productivity data of a crew; means for pre-processing the collected data; means for designing a shift by identifying a busy period and an off-peak period of the store using the pre-processed data; means for notifying the crew of the designed shift; means for readjusting the shift by receiving a shift adjustment request from the crew; and means for feeding back an actual operation result and reflecting the actual operation result in a next shift design.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The purpose of this invention is to solve the problem of store shift allocation. Conventionally, the appropriate allocation of crew members according to the store's busy and slow seasons has relied on experience and intuition, making efficient management difficult. In addition, there have been issues with crew vacation and new employee training plans being delayed, preventing progress in improving work styles. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: Collect store operation status data and crew productivity data and preprocess this data. Use the preprocessed data to train an AI model and identify busy and slow periods for the store. Then, design shifts based on the learning results and notify the crew. Receive shift adjustment requests from crew members and make readjustments. Then, reflect feedback obtained from actual operation results in the next shift design, achieving efficient and flexible shift allocation. The system also includes means for allocating appropriate crew members during busy periods based on their skill level and years of experience, and for training new crew members and encouraging crew members to take vacations during slow periods.

[0006] "Store operation status data" refers to data related to all performance indicators related to store operations, such as store sales, customer numbers, and product sales trends.

[0007] "Crew productivity data" refers to data for evaluating the productivity of each crew member, such as the number of sales, the time spent responding to customers, and the number of transactions processed.

[0008] "Data preprocessing" is the process of complementing and removing missing and outliers from collected data and preparing it in a format suitable for analysis.

[0009] An "AI model" is a mathematical and statistical model that uses machine learning algorithms to learn patterns from data and make predictions and classifications.

[0010] "Shift design" is the process of planning and deciding crew working hours and deployment based on factors such as store operating conditions and crew productivity.

[0011] A "shift adjustment request" is an action in which a crew member requests a change to an existing shift schedule based on their own plans or circumstances.

[0012] "Feedback" refers to the act of returning actual shift operation results and opinions and areas for improvement regarding work performance to the system.

[0013] "Skill level" is an indicator that evaluates each crew member's ability to perform their duties and their level of knowledge proficiency.

[0014] "Years of experience" is a number that indicates the length of time a crew member has been working in a particular job or industry.

[0015] A "busy season" is a period when a store experiences a particularly high number of customer visits and sales.

[0016] The "off season" refers to a period when the number of customers visiting a store and sales are particularly low. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] System Overview

[0039] This invention is a system for optimizing store shift allocation, collecting and analyzing store operating status data and crew productivity data to design effective shifts. The system is composed of server, terminal, and user elements, and achieves shift optimization through multiple processing procedures. The specific form is shown below.

[0040] Program processing

[0041] Data collection and preprocessing

[0042] Server: First, it collects data on the store's operational status. This data includes past sales, the number of customers visiting the store, and trends in product sales. At the same time, it also collects crew productivity data. This data includes each crew member's sales volume, customer service time, and number of transactions processed.

[0043] These data are then formatted for analysis by imputing missing values, removing outliers, and so on, for example, standardizing numerical data and identifying anomalous data points and treating them appropriately.

[0044] Training an AI model

[0045] Server: The preprocessed data is used to prepare the AI ​​model for training. Feature values ​​include sales data for each time period and day of the week, and crew productivity indicators. Machine learning algorithms (such as random forests and neural networks) are used to create a model that predicts peak and off-peak seasons.

[0046] Shift planning and notifications

[0047] Server: Designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or taking time off on slow days. The designed shift schedule is appropriately divided for each crew member and notified to the crew via their device (smartphone or PC).

[0048] Terminal (Crew): Each crew member uses their own terminal to check their upcoming shift schedule. The shift schedule includes details of busy and slow periods, as well as specific work instructions for each crew member.

[0049] Feedback and Adjustments

[0050] User (Crew): If a crew member is dissatisfied with a shift, they can use their terminal to request a shift adjustment. For example, they can send an adjustment request to the system saying, "I have a family appointment on this day, so I would like to take the day off."

[0051] Server: Receives adjustment requests and regenerates the shift schedule. This includes rescheduling other crew members' arrival times and unscheduled shift changes. The updated shift schedule is then notified to the crew members again.

[0052] Production Feedback

[0053] Terminal (Crew): Crew members work according to their shifts and provide feedback on their actual work performance to the server via their terminals. For example, they provide specific feedback such as, "Friday afternoon was busier than expected."

[0054] Servers: Reflect the collected feedback in the generation of the next shift, improving shift effectiveness and flexibility and optimizing the overall operational efficiency of the store.

[0055] Specific examples

[0056] Consider the following scenario: Data shows that Monday mornings are always the busiest time at a particular store. Using this information, the server assigns more of its most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a slower time, the server can use them as training days for new crew members and recommend paid vacation for veteran crew members.

[0057] In this way, the system of the present invention realizes data-driven shift optimization, contributing to improved store productivity and improved work styles for crew members.

[0058] The processing flow will be explained below.

[0059] Step 1: Data collection

[0060] Server: Collects store operation status data (past sales performance, number of customers, sales data by product, etc.) from the database. Also collects crew productivity data (number of customers served, sales volume, working hours, etc.). Additionally, crew schedules and attribute information (years of experience, skill level, etc.) are also collected.

[0061] Step 2: Data Preprocessing

[0062] Server: Preprocesses the collected data. Missing values ​​are filled with the mean or median, and outliers are removed as appropriate. The data format is standardized and sorted as time-series data. The data is organized by crew ID and date and time to make it easier to analyze.

[0063] Step 3: Feature selection

[0064] Server: Selects important features from the preprocessed data, such as sales, number of customers, and productivity indicators for each crew member. Based on these features, prepares training data for the AI ​​model.

[0065] Step 4: Model training

[0066] Server: Trains the AI ​​model using machine learning algorithms (e.g., random forests and neural networks). Using the training data, it builds a model that predicts peak and slow periods for the store. It evaluates the accuracy of the model using validation data and retrains it as needed.

[0067] Step 5: Shift Generation

[0068] Server: Based on the learning results, the next shift schedule is automatically generated. On busy days, more highly productive crew members are assigned, and on slow days, new crew members are trained and existing crew members are encouraged to take paid leave. The system also takes into account the attribute information of each crew member to plan the optimal crew assignment.

[0069] Step 6: Shift Notification

[0070] Server: Divides the generated shift schedule into individual crew members' groups and prepares for notification. The shift schedule is distributed to crew members' devices via email or a dedicated shift management application.

[0071] Terminal (Crew): Crew members use their terminals to check their upcoming shift schedule, including details such as work days, work hours, and duties.

[0072] Step 7: Request a shift adjustment

[0073] User (Crew): If adjustments to the shift are necessary, submit a request for adjustments via the shift management app or email. For example, a request such as "I would like to take time off on a specific day because I have family plans."

[0074] Server: Receives the adjustment request and regenerates the shift schedule. Review the work shifts of other crew members and make changes according to the request. Notify the crew of the re-adjusted shift schedule again.

[0075] Step 8: Production and feedback

[0076] Terminal (Crew): Crew members work based on the notified shift. They record their work performance during the shift and send any special notes or areas for improvement as feedback to the server.

[0077] Server: Receives feedback and reflects it in the next shift generation. Analyzes the obtained information and incorporates suggestions for improving shift allocation to optimize store operational efficiency. Repeating this loop improves the accuracy and flexibility of shifts.

[0078] Through the above process, the present invention optimizes store shift allocation, improving productivity and improving the way crews work.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] Conventional store shift management has the problem of making it difficult to accurately predict busy and slow periods and allocate crews efficiently. In particular, the lack of detailed data-based analysis has led to unnecessary staffing and excessive workloads, resulting in reduced work efficiency and lower crew satisfaction.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server includes a means for collecting hourly operating status data of the store, a means for collecting crew work efficiency data, and a means for pre-processing the collected data to extract necessary information and remove outliers, thereby enabling appropriate shift planning based on the data.

[0084] "Store operating status data by hour" is data that indicates the store's operating status, such as the store's sales performance, the number of customers visiting the store, and product sales during each time period.

[0085] "Crew work efficiency data" is data that indicates the productivity of the work that each crew member is responsible for, and includes, for example, sales volume, customer response time, number of transactions, etc.

[0086] "Preprocessing" refers to the process of preparing collected data in a format suitable for analysis or learning, and specifically includes filling in missing values ​​and removing outliers.

[0087] An "AI model" is a model that uses machine learning algorithms to analyze data and learn patterns, such as random forests and neural networks.

[0088] "Shift design" is the process of determining crew working hours and deployment based on store operating status and crew work efficiency data.

[0089] "Displaying to the crew" means visually displaying the designed shift schedule on the terminal used by the crew, so that the crew can check the next shift schedule.

[0090] A "shift adjustment request" is a request by a crew member to request a change to their shift. For example, this includes requests for vacation time or a shift change.

[0091] "Feedback" is the action of crew members providing comments and evaluations about their actual work situation and returning that information to the system.

[0092] This invention is a system for optimizing store shift allocation, and it collects and analyzes store operating status data and crew work efficiency data to design effective shifts. A specific embodiment of the system is shown below.

[0093] System Configuration

[0094] The system consists of the following elements: server, terminal, and user.

[0095] Data collection

[0096] Server: Collects hourly store operation status data and crew work efficiency data. Store operation status data includes past sales performance data obtained from the POS system, the number of customer visits obtained from the count sensor, and product sales data. Crew work efficiency data includes sales figures, customer response time, and number of transactions per crew obtained from the attendance management system.

[0097] Data Preprocessing

[0098] Server: The collected data is filled with missing values ​​and outliers are removed. This process uses Python libraries (Pandas, NumPy, etc.). For example, the server performs standardization of numerical data and detects and corrects anomalous data points.

[0099] Training an AI model

[0100] Server: A generative AI model based on preprocessed data predicts the store's busy and slow seasons. The machine learning algorithm used is a random forest using the Scikit-learn library or a neural network using TENSORFLOW (registered trademark). Sales data for each time period and day of the week and crew work efficiency data are used as features to train the model, and the AI ​​model makes predictions for shift planning.

[0101] Shift planning and notifications

[0102] Server: Designs optimal shifts based on the prediction results. On busy days, it concentrates crew members with high work efficiency, and on slow days, it trains new crew members or recommends crew vacations. The designed shift schedule is displayed to crew members via their devices (smartphones or PCs) using a push notification API. For example, notifications can be sent using Firebase Cloud Messaging (FCM).

[0103] Terminal (Crew): Each crew member checks their next shift schedule via a dedicated app. The shift schedule includes details of peak and off-peak periods, as well as specific work instructions for each crew member.

[0104] Feedback and Shift Adjustment

[0105] User (crew): Provides feedback on shifts and requests for adjustments via the device. For example, a request such as "I would like to take a day off because I have family plans" can be sent via a dedicated app or web portal.

[0106] Server: Receives adjustment requests and readjusts the shift schedule. Rearranges the attendance times of other crew members and notifies them of the new shift schedule.

[0107] Production Feedback

[0108] Terminal (Crew): After their shift, crew members report their specific work performance as feedback. For example, they send feedback such as "Friday afternoon was busier than expected" to the server via their terminal.

[0109] Servers: By incorporating collected feedback into the next shift generation, they improve shift effectiveness and flexibility, optimizing the overall operational efficiency of the store.

[0110] Specific examples

[0111] Consider the following scenario for a certain store. Data shows that Monday mornings are always the busiest period. Based on this information, the server assigns more of the most efficient crew members to Monday mornings. If Tuesday afternoons are predicted to be a slow period, the server can make them training days for new crew members and recommend paid vacation for veteran crew members. This will contribute to improving store productivity and crew working practices.

[0112] Example prompts for generative AI models

[0113] "Using the following data, please analyze the store's operating status and crew productivity and generate the optimal shift schedule. The data includes past sales performance, the number of customers visiting the store, product sales trends, the number of sales made by each crew member, the time spent serving customers, and the number of transactions. Based on this information, please predict busy and slow seasons and propose the optimal shift arrangement."

[0114] The above is an embodiment of the present invention, which realizes data-driven shift optimization and improves store operation efficiency and crew satisfaction.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Program processing flow

[0117] Step 1: Data collection

[0118] Server: Collects store operation status data and crew work efficiency data. Specifically, it obtains sales performance data from the POS system, customer visit data from the count sensor, and crew work efficiency data from the attendance management system via API and database connections. This data is integrated and stored on the server for later processing.

[0119] Input: Data from POS systems, count sensors, and attendance management systems

[0120] Output: Integrated store operation status data and crew work efficiency data

[0121] Step 2: Data Preprocessing

[0122] Server: The collected data is filled with missing values ​​and outliers are removed. For example, using Python's Pandas and NumPy libraries, missing values ​​are filled with the mean or median, and outliers are detected and removed by calculating Z-scores. This prepares the data in a format suitable for analysis and model training.

[0123] Input: Raw data collected

[0124] Output: Preprocessed and clean data

[0125] Step 3: Feature Engineering

[0126] Server: Extract features using preprocessed data. Add features such as sales data by day of the week and time of day, and crew productivity data to the data frame. Perform feature engineering using the Scikit-learn library.

[0127] Input: Preprocessed data

[0128] Output: Data frame with added features

[0129] Step 4: Training the AI ​​model

[0130] Server: Train a generative AI model using the preprocessed data and features. The algorithms used are random forests and neural networks, and the model is built and trained using the Scikit-learn or TensorFlow library. For example, create a model with RandomForestRegressor() and train it with model.fit(X_train, y_train).

[0131] Input: Data frame with added features

[0132] Output: Trained AI model

[0133] Step 5: Shift design

[0134] Server: Using a trained AI model, it predicts future peak and off-peak periods and designs optimal shifts. Based on the prediction results, it assigns more crew members with high operational efficiency to peak days, and recommends training new crew members and giving veteran crew members time off on off-peak days.

[0135] Input: trained AI model, new data to predict

[0136] Output: Designed shift table

[0137] Step 6: Notification of shift schedule

[0138] Server: Notifies the crew of the designed shift schedule. Using a push notification API (e.g., Firebase Cloud Messaging), the shift schedule is sent to the crew's smartphones or PCs.

[0139] Input: Designed shift schedule

[0140] Output: Shift schedule notification to crew terminal

[0141] Step 7: Accepting feedback

[0142] User (Crew): Crew members submit feedback on shifts and requests for adjustments through a dedicated app or web portal. For example, they input a request such as, "I have a family appointment on this day, so I would like to take the day off."

[0143] Input: Shift adjustment requests and feedback from crew members

[0144] Output: Adjustment request data to the server

[0145] Step 8: Realign your shifts

[0146] Server: Regenerates the shift schedule based on the received adjustment request. Rearranges the attendance times of other crew members and notifies them of the updated shift schedule.

[0147] Input: Crew adjustment request data, current shift schedule

[0148] Output: Reworked shift schedule, new notifications

[0149] Step 9: Production Feedback

[0150] Terminal (Crew): Crew members provide feedback on their performance after their actual work. For example, they can enter comments such as, "Friday afternoon was busier than expected" through a dedicated app.

[0151] Input: Crew post-job feedback

[0152] Output: Feedback data to the server

[0153] Step 10: Incorporating feedback

[0154] Server: Reflects the collected feedback in the next shift design. Analyzes the feedback data, adds it as a feature when generating the next shift, and retrains the AI ​​model.

[0155] Input: Crew feedback data

[0156] Output: Improved AI model, more accurate design for next shift

[0157] Through these steps, the system optimizes store shift allocation, enabling efficient and effective operations.

[0158] (Application example 1)

[0159] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0160] Store shift allocation depends on the store's operating status and worker productivity, and if not managed properly, it can lead to reduced work efficiency and increased worker burden. However, traditional manual shift planning is time-consuming and difficult to predict busy and slow periods, making it difficult to achieve optimal shift allocation. It is also difficult to reflect worker feedback in real time and flexibly readjust shifts.

[0161] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0162] In this invention, the server includes means for collecting store operation status data, means for collecting worker productivity data, means for preprocessing the collected data, means for identifying busy and slow seasons for the store and designing shifts using the preprocessed data, means for notifying workers of the designed shifts, means for receiving shift adjustment requests from workers and readjusting the shifts, means for feeding back actual operation results and reflecting them in the next shift design, and means for readjusting the shifts based on feedback data collected from an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. This enables optimal shift design based on real-time data, thereby improving store operation efficiency and worker working styles.

[0163] "Store operation status data" refers to data related to store operations, such as sales performance at the store, the number of customers visiting the store, and trends in product sales.

[0164] "Worker productivity data" is data that indicates the performance of each worker, such as the number of tasks processed, the number of sales, and the time spent responding to customers.

[0165] "Preprocessed data" refers to data that has been processed into a format suitable for analysis, such as by filling in missing values, removing outliers, and standardizing numerical data.

[0166] The "busy season" refers to the period when a store is most active and when the number of customers visiting the store and sales increase.

[0167] A "slow season" is a period when store operations are slow and customer traffic and sales decline.

[0168] A "shift" refers to the time period during which store workers work and their placement.

[0169] "Means of notification" refers to the method of conveying information to workers via smartphones, computers, or other devices.

[0170] The "means for receiving adjustment requests" refers to the method for receiving requests for shift changes and vacation from workers.

[0171] "Actual operational results" refers to feedback data regarding store operations and worker performance.

[0172] "Feedback data" refers to data that records in real time what workers feel and accomplishments while working.

[0173] A "generative AI model" is a model that uses machine learning algorithms to analyze data and predict future states.

[0174] A "prompt" refers to a sentence of instructions or questions that is input to a generative AI model.

[0175] The present invention is a system for optimizing store shift allocation using an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. Specific embodiments of the present invention are described below.

[0176] System Configuration

[0177] The present invention is composed of the following elements: a server, a terminal (such as a worker's smartphone), and a user (worker). The system achieves shift optimization through the following steps:

[0178] Data collection and preprocessing

[0179] server:

[0180] Store operation status data and worker productivity data are collected. Store operation status data includes past sales performance, number of customer visits, and product sales trends. Worker productivity data includes each worker's number of tasks processed, number of sales, and customer response time. The collected data is preprocessed, including missing value completion and standardization, and then formatted into a format suitable for analysis.

[0181] Training an AI model

[0182] server:

[0183] The preprocessed data is used to train a generative AI model. For training, a machine learning algorithm (such as Scikit-Learn or TensorFlow) is used to create a model that predicts peak and off-peak seasons. Specifically, a classification model using random forests or a neural network can be used.

[0184] Shift planning and notifications

[0185] server:

[0186] Shifts are designed based on the learning results of the AI ​​model. During busy periods, many highly productive workers are assigned, and during slow periods, training of new workers is encouraged and workers are encouraged to take vacations. The designed shifts are saved in a database and notifications are sent to workers' devices (smartphones and PCs).

[0187] Terminal (Worker):

[0188] Each worker uses their own device to check their next shift schedule, which includes details of busy and slow periods as well as specific work instructions for each worker.

[0189] Feedback and Adjustments

[0190] User (operator):

[0191] If a worker is dissatisfied with their shift, they can use their terminal to request a shift adjustment. For example, they can send a request to the system saying, "I have a family appointment on this day, so I would like to take the day off."

[0192] server:

[0193] Upon receiving the adjustment request, the shift schedule is regenerated. This process includes readjusting the arrival times of other workers and making unplanned shift changes. The updated shift schedule is then notified to the workers again.

[0194] Production Feedback

[0195] Terminal (Worker):

[0196] Workers work according to their shifts and provide feedback on their actual work performance to the server via their terminals, such as "Friday afternoon was busier than expected."

[0197] server:

[0198] The collected feedback is reflected in the next shift generation, improving the effectiveness and flexibility of shift allocation and optimizing the overall operational efficiency of the store.

[0199] Specific examples

[0200] For example, data shows that Monday mornings are always the busiest period at a certain store. Based on this information, the server assigns many of the most productive workers to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet period, the server can set them as training days for new employees and recommend paid vacation for experienced workers. In this way, the system of the present invention enables optimal shift planning based on real-time data, improving store operational efficiency and employee working styles.

[0201] Prompt Sentence Examples

[0202] Monday mornings are always busy and we deploy the most productive crews. Tuesday afternoons are slower and are used as training days for new crew members and to encourage paid time off for veteran crew members.

[0203] The above is a specific embodiment of the present invention.

[0204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0205] Step 1: Data collection and preprocessing

[0206] server:

[0207] Input: Store operation status data (past sales performance, number of customers visiting the store, product sales trends, etc.) and worker productivity data (number of transactions, number of sales, customer response time, etc.).

[0208] The server collects this data and performs preprocessing such as filling in missing values, removing outliers, and standardizing numerical data, preparing it in a format suitable for analysis.

[0209] Output: Preprocessed store utilization data and worker productivity data.

[0210] Step 2: Training the AI ​​model

[0211] server:

[0212] Input: Preprocessed data.

[0213] The server uses machine learning algorithms such as Scikit-Learn and TensorFlow to train a generative AI model, specifically using random forests and neural networks to create a model that predicts peak and off-peak seasons.

[0214] Output: The trained AI model.

[0215] Step 3: Design the shift

[0216] server:

[0217] Inputs: Trained AI model, latest operating status and productivity data.

[0218] Based on the predictions of the AI ​​model, the server designs shifts that assign many highly productive workers during busy periods and encourage training of new workers and taking vacations during slow periods.

[0219] Output: The created shift schedule.

[0220] Step 4: Shift Notification

[0221] server:

[0222] Input: The created shift schedule.

[0223] The server uses a notification service such as Firebase Cloud Messaging to notify workers of the planned shifts on their devices (smartphones or PCs).

[0224] Output: Shift notification sent to worker's device.

[0225] Step 5: Accepting a shift adjustment request

[0226] User (operator):

[0227] Input: Shift adjustment request sent by the user from the terminal.

[0228] If a user is dissatisfied with a shift, the user uses the terminal to send a request to the server for a shift adjustment, such as "I have family plans on this day, so I would like to take the day off."

[0229] Output: Shift adjustment request received by the server.

[0230] Step 6: Realign your shifts

[0231] server:

[0232] Inputs: Received shift adjustment requests, latest utilization and productivity data.

[0233] Based on the shift adjustment request, the server readjusts the arrival times of other workers and makes unscheduled shift changes, and regenerates the shift schedule.

[0234] Output: Rescaled shift table.

[0235] Step 7: Notification of rearranged shifts

[0236] server:

[0237] Input: Rebalanced shift table.

[0238] The server notifies the worker's terminal of the regenerated shift schedule again.

[0239] Output: Rearranged shift notification sent to worker's device.

[0240] Step 8: Gather production feedback

[0241] User (operator):

[0242] Input: Work performance feedback sent by the user from the device.

[0243] Users work according to their shifts and provide feedback to the server via their devices about their impressions and performance during work, such as "Friday afternoon was busier than expected."

[0244] Output: The feedback data received by the server.

[0245] Step 9: Incorporating feedback

[0246] server:

[0247] Input: Received feedback data.

[0248] The server reflects the feedback data in the next shift generation, improving the effectiveness and flexibility of shift allocation.

[0249] Output: Data for designing the next shift that reflects the feedback.

[0250] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0251] System Overview

[0252] This invention is a system for optimizing store shift allocation. It collects and analyzes store operating status data, crew productivity data, and crew emotion data to design effective shifts. The system is composed of a server, terminals, and user elements, and achieves shift optimization through multiple processing procedures. In addition, by utilizing an emotion engine, it is possible to adjust shifts taking into account the emotional state of crew members.

[0253] Program processing

[0254] Data collection and preprocessing

[0255] Server: First, it collects data on the store's operational status. This data includes past sales performance, the number of customers visiting the store, and trends in product sales. At the same time, it also collects crew productivity data, such as the number of sales made by each crew member, the time spent serving customers, and the number of tasks processed. Furthermore, it periodically collects crew emotional data using an emotion engine. This emotional data records the crew member's daily stress level and emotional fluctuations.

[0256] These data are then formatted for analysis by imputing missing values, removing outliers, and so on, for example, standardizing numerical data and identifying anomalous data points and treating them appropriately.

[0257] Training an AI model

[0258] Server: The preprocessed data is used to prepare the AI ​​model for training. Features include sales data for each time period and day of the week, crew productivity indicators, and sentiment data. Machine learning algorithms (e.g., random forests and neural networks) are used to build a model that predicts peak and off-peak seasons.

[0259] Shift planning and notifications

[0260] Server: Designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or giving them time off on slow days. It also takes into account emotional data and provides appropriate rest for stressed crew members. The designed shift schedule is appropriately divided for each crew member and notified to their device (smartphone or PC).

[0261] Terminal (Crew): Each crew member uses their own terminal to check their upcoming shift schedule. The shift schedule includes details of busy and slow periods, as well as specific work instructions for each crew member.

[0262] Shift adjustment based on emotion data

[0263] User (Crew): If the crew is dissatisfied with their shift or if their emotional state is different from usual, they can use their device to request a shift adjustment. The emotion engine analyzes the crew's emotional state in real time, and if improvements are needed, the system automatically proposes adjustments.

[0264] Server: Receives the adjustment request and regenerates the shift schedule. Based on the emotional data, it assigns lighter tasks to stressed crew members or provides them with rest days. The re-adjusted shift schedule is then notified to the crew members again.

[0265] Production Feedback

[0266] Terminal (Crew): Crew members work their shifts and provide feedback to the server on their actual work performance and emotional state via their terminals. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[0267] Server: Receives feedback and reflects it in the next shift generation. Analyzes the information obtained and incorporates suggestions for improving shift allocation and emotional management to optimize store operational efficiency and crew comfort.

[0268] Specific examples

[0269] Consider the following scenario: Data reveals that Monday mornings are always the busiest time at a certain store. Using this information, the server allocates more of its most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet time, the server can use them as training days for new crew members and recommend paid time off for veteran crew members. Using the emotion engine, if the server detects that a particular crew member is feeling stressed, the server can adjust their shifts to allow them a rest day.

[0270] In this way, the system of the present invention realizes data-driven shift optimization and contributes to improving store productivity and work styles, including crew emotional management.

[0271] The processing flow will be explained below.

[0272] Step 1: Data collection

[0273] Server: Collects store operation status data (e.g., past sales performance, number of customers, sales data by product, etc.) from a database. In addition, it also collects crew productivity data (e.g., number of customers served, number of sales, working hours, etc.). Furthermore, it periodically collects crew emotion data through an emotion engine. This emotion data includes the crew's daily stress level and emotional fluctuations.

[0274] Step 2: Data Preprocessing

[0275] Server: Preprocesses the collected data. Specifically, missing values ​​are filled with the mean or median, and outliers are removed as appropriate. The data format is standardized and sorted as time-series data. The data is organized by crew ID and date and time to make it easier to analyze.

[0276] Step 3: Feature selection

[0277] Server: Selects effective features from the preprocessed data. Specifically, the server selects sales figures, number of customers, productivity indicators for each crew member, and emotional data. Based on these features, it prepares training data for the AI ​​model.

[0278] Step 4: Model training

[0279] Server: Trains an AI model using machine learning algorithms (e.g., random forests or neural networks). Using the training data, it builds a model that predicts peak and slow periods for the store. It evaluates the accuracy of the model using validation data and retrains it as needed.

[0280] Step 5: Shift Generation

[0281] Server: Based on the learning results, the next shift schedule is automatically generated. On busy days, more highly productive crew members are assigned, and on slow days, new crew members are trained and existing crew members are encouraged to take paid vacation. Emotional data is also taken into consideration, and appropriate rest periods are provided for stressed crew members.

[0282] Step 6: Shift Notification

[0283] Server: Divides the generated shift schedule into individual crew members' groups and prepares for notification. The shift schedule is distributed to crew members' devices via email or a dedicated shift management application.

[0284] Terminal (Crew): Crew members use their terminals to view their upcoming shift schedule, which includes work days, work hours, tasks, and considerations based on emotional state.

[0285] Step 7: Request a shift adjustment

[0286] User (Crew): If adjustments to the shift are necessary, the user requests them via a terminal. The emotion engine analyzes the crew's emotional state in real time and automatically proposes adjustments if necessary. For example, a request might be, "I have family plans on this day, so I would like to take time off," or "I've been stressed lately, so I would like to have lighter work."

[0287] Server: Receives the adjustment request and regenerates the shift schedule based on the emotion data and existing shift data. It readjusts the arrival times and work contents of other crew members and notifies the crew of the adjusted shift schedule.

[0288] Step 8: Production and feedback

[0289] Terminal (Crew): Crew members work based on the notified shift. They use their terminals to provide feedback to the server on their actual work performance and emotional state. For example, they may provide feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[0290] Server: Collects feedback and reflects it in the next shift generation. Analyzes the feedback and incorporates improvements in shift allocation and emotional management to optimize store operational efficiency and crew comfort.

[0291] Specific examples

[0292] For example, if data shows that Monday mornings are always the busiest at a particular store, the server will use that information to assign the most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet period, the server will use that as a training day for new crew members and recommend paid vacation for veteran crew members. Furthermore, if the emotion engine detects that a particular crew member is feeling stressed, the server will adjust that crew member's shift and provide them with an appropriate rest day.

[0293] This enables the system to realize data-driven shift optimization, contributing to increased store productivity and improved working styles, including the emotional state of crew members.

[0294] Example 2

[0295] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0296] Store shift management requires optimal crew allocation according to busy and slow seasons, but conventional systems are limited to simple predictions based on operating status data and productivity data, making it difficult to flexibly adjust shifts that take into account the actual operational results of cloud services and the emotional state of crew members. Furthermore, it was not possible to utilize crew emotional data or real-time feedback, resulting in a lack of shift design that would improve crew work efficiency. This resulted in problems such as reduced store operational efficiency and reduced crew satisfaction.

[0297] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting store operation status data, means for collecting crew productivity data, means for collecting crew emotion data, means for pre-processing the collected data, means for identifying busy and slow seasons of the store using the pre-processed data and designing shifts, means for notifying crews of the designed shifts, means for receiving shift adjustment requests from crews and readjusting the shifts, and means for feeding back actual operation results and reflecting them in the next shift design. This enables advanced shift management that integrates multiple data sources and combines crew productivity and emotional states.

[0298] "Store operation status data" refers to data related to store operations, including past sales performance, the number of customers visiting the store, and trends in product sales.

[0299] "Crew productivity data" refers to data on the work performance of crew members, such as the number of sales made by each crew member, the time spent responding to customers, and the number of transactions processed.

[0300] "Crew emotional data" is data that records the crew's daily stress levels and emotional fluctuations.

[0301] "Preprocessing" is the process of converting collected data into a format suitable for analysis, such as filling in missing values, removing outliers, and standardizing data.

[0302] An "AI model" is a predictive model that uses machine learning algorithms and is used to predict peak and off-peak seasons.

[0303] "Shift design" is the process of optimizing crew working hours and roles based on store operating status, crew productivity, and emotional data.

[0304] "Shift notification" is the process of distributing the designed shift schedule to the crew, and is mainly done via terminals.

[0305] A "shift adjustment request" is a request made by a crew member for a change or adjustment to a shift.

[0306] "Performance feedback" refers to crew members providing feedback on their actual work performance and emotional state, which is reflected in the design of the next shift.

[0307] System Overview

[0308] This invention is a system for optimizing store shift allocation, collecting and analyzing store operating status data, crew productivity data, and crew emotion data to design effective shifts. The system is composed of a server, terminals, and user elements, and centrally manages shift design, notifications, and adjustments.

[0309] Hardware / Software used

[0310] The server collects and preprocesses data, trains the AI ​​model, designs shifts, and processes feedback. It uses software such as Python scripts, machine learning frameworks (TensorFlow, Scikit-Learn), and Emotion AI. A database (e.g., PostgreSQL) is used to store the data.

[0311] Crew members use the devices to check their shift schedules and provide feedback. The devices can be smartphones or PCs, and use the Google (registered trademark) Calendar app or a dedicated application.

[0312] Users (crew members) provide feedback on their work performance and emotional state, and also request shift adjustments.

[0313] Data collection details

[0314] The server collects the following data:

[0315] Store operation data: past sales performance, customer visits, product sales trends, etc.

[0316] Crew productivity data: sales volume, customer service time, transaction volume, etc. for each crew member.

[0317] Crew Emotion Data: Emotion AI is used to record crew members' daily stress levels and emotional fluctuations.

[0318] Data preprocessing details

[0319] The server performs the following data preprocessing:

[0320] Imputing missing values: for example, imputing with the mean or estimated value.

[0321] Outlier removal: Remove statistically abnormal data using box plots and Z scores.

[0322] Data standardization: Converting numerical data to a consistent scale.

[0323] Training an AI model

[0324] The server uses machine learning algorithms to train the AI ​​model. Algorithms used include random forests and neural networks, and the features used include sales data for each time period and day of the week, crew productivity indicators, and emotional data. This allows the creation of a model that predicts peak and off-peak seasons.

[0325] Shift Design

[0326] The server designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members during busy periods, and recommends training new crew members and taking vacations during slow periods. It also takes emotional data into account and provides appropriate rest for stressed crew members.

[0327] Shift notifications

[0328] The server converts the designed shift schedule into Google Calendar format and notifies each crew member via email or a dedicated application, allowing them to check their shift schedule on their own devices.

[0329] Shift adjustment based on emotion data

[0330] If a user (crew member) is dissatisfied with their shift or feels unwell, they can request a shift adjustment using their device. The emotion engine then analyzes the crew member's emotional state in real time, and the system automatically proposes adjustments.

[0331] The server receives the adjustment request and regenerates the shift schedule based on the emotion data. The re-adjusted shift schedule is also notified to the crew.

[0332] Production Feedback

[0333] Users (crew members) work according to their shifts and provide feedback to the server on their actual work performance and emotional state via their devices. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[0334] The server receives this feedback and reflects it in the next shift generation. The feedback information is analyzed and suggestions for improving shift allocation and emotion management are incorporated to optimize store operational efficiency and crew work comfort.

[0335] Specific examples

[0336] For example, data might reveal that Monday mornings are a busy time for a particular store. The server can then use this information to allocate more of its most productive crew members to that time. Alternatively, if Tuesday afternoons are predicted to be a slower time, the server can use them as training days for new crew members and recommend paid time off for veteran crew members. If the emotion engine detects that a particular crew member is stressed, the server can adjust their shifts to accommodate a rest day.

[0337] Example prompts to input to the generative AI model

[0338] "Use past store operation data, crew productivity data, and sentiment data to design the next shift schedule. Monday morning is the busiest time, so assign many highly productive crew members to that time. Also, Tuesday afternoon is predicted to be a slow period, so use it as a training day for new crew members and recommend paid vacation for veteran crew members."

[0339] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0340] The flow of this system's program processing

[0341] Step 1: Data collection

[0342] The server retrieves store operation status data from the database and saves it in JSON format. This data includes past sales performance, customer visits, and product sales trends. It also aggregates each crew member's productivity data, such as sales volume, customer service time, and number of transactions, from daily reports and stores the data in Excel files. Furthermore, an emotion engine is used to collect crew member emotional data (stress levels, emotional fluctuations) via sensors and apps.

[0343] Input: Store operation status data, crew productivity data, crew emotion data

[0344] Output: Raw data for preprocessing

[0345] Step 2: Data Preprocessing

[0346] The server uses Python scripts to impute and standardize the collected data, imputing missing values ​​with means or estimated values, statistically identifying and removing outliers using box plots and Z-scores, and converting and standardizing numerical data to a consistent scale.

[0347] Input: Raw data collected

[0348] Output: Preprocessed data

[0349] Step 3: Training the AI ​​model

[0350] The server uses machine learning algorithms (such as random forests and neural networks) to train an AI model based on the preprocessed data. The features used in this process include sales data for each time period and day of the week, crew productivity indicators, and emotional data. This allows the creation of a model that predicts peak and off-peak seasons.

[0351] Input: Preprocessed data

[0352] Output: Trained AI model

[0353] Step 4: Design the shift

[0354] The server uses the results of the trained AI model to design shifts. Specifically, it assigns more highly productive crew members during busy periods and recommends training new crew members or giving crew members time off during slow periods. It also takes emotional data into account and applies algorithms (e.g., linear programming) to ensure that stressed crew members receive adequate rest time.

[0355] Input: Trained AI model, latest store operation status data, crew productivity data, crew emotion data

[0356] Output: Designed shift table

[0357] Step 5: Shift Notification

[0358] The server converts the designed shift schedule into Google Calendar format and notifies each crew member via email or a dedicated application. Crew members can then check their shift schedules on their own devices using the Google Calendar app or a dedicated application.

[0359] Input: Designed shift schedule

[0360] Output: Shift schedule notified to crew

[0361] Step 6: Accepting and rescheduling shift adjustment requests

[0362] If a user (crew member) is dissatisfied with their shift or feels unwell, they can request a shift adjustment from their device. The server receives this adjustment request and recalculates the shift schedule based on the emotion data and crew member feedback. The recalculated shift schedule is also notified to the crew member.

[0363] Input: Shift adjustment request, crew emotion data, feedback data

[0364] Output: Reworked shift schedule, crew notification

[0365] Step 7: Production Feedback

[0366] Users (crew members) work according to their shifts and provide feedback to the server via their devices about their actual work performance and emotional state. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[0367] Input: Actual work data, crew feedback

[0368] Output: Feedback data

[0369] Step 8: Improve shift generation

[0370] The server analyzes the collected feedback data and reflects it in the next shift generation. New algorithms and methods are introduced to continuously optimize the shifts.

[0371] Input: Feedback data

[0372] Output: Improved shift generation model

[0373] (Application example 2)

[0374] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0375] Conventional store shift management systems design shifts taking into account store operating conditions and crew productivity, but it is difficult to ensure that these shifts reflect the emotional state of crew members and adjust shifts in real time. Furthermore, there is a lack of efficient means for notifying on-site crew members of shifts and accepting crew requests. This has led to problems such as lower labor productivity and reduced crew satisfaction.

[0376] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting store operation status data, means for collecting crew productivity data, means for collecting crew emotional states, means for pre-processing the collected data, means for identifying busy and slow seasons for the store using the pre-processed data and designing shifts, means for notifying crew members of the designed shifts, means for receiving shift adjustment requests from crew members and readjusting the shifts, means for feeding back actual operation results and reflecting them in the next shift design, and means for notifying shift schedules as an application installed on a smartphone. This enables shift design and real-time shift adjustment that takes crew emotional states into consideration, and effective shift notification to each crew member.

[0377] "Store operating status data" refers to data relating to the store's operating status, such as sales, number of customers, and product sales trends while the store is open.

[0378] "Crew productivity data" is data that indicates the work efficiency of each crew member, such as the number of sales made by each crew member, the time spent responding to customers, and the number of transactions processed.

[0379] "Crew emotional state" refers to data on the crew's daily stress levels and emotional fluctuations.

[0380] "Preprocessing" refers to the process of preparing collected data in a format suitable for analysis by completing missing values, removing outliers, standardizing, and so on.

[0381] An "AI model" is a model built using machine learning algorithms to predict busy and slow seasons for a store.

[0382] "Shift design" is the act of creating a schedule to optimize crew working hours and deployment based on collected and analyzed data.

[0383] "Notification means" refers to the method of communicating the designed shift schedule to crew members, using smartphones or other devices.

[0384] "Shift Adjustment Request" means a request by a crew member for a change to their shift schedule.

[0385] "Feedback" is an information gathering and analysis process that collects information about actual operational results and the emotional state of the crew and reflects it in the design of the next shift.

[0386] The "application installed on a smartphone" is software that notifies employees of shift schedules and accepts adjustment requests.

[0387]

[0388] System Overview

[0389] The system of this invention collects and analyzes store operation status data, crew productivity data, and crew emotional states to design optimal shifts. The system is composed of a server, terminals, and user elements.

[0390] Data collection and preprocessing

[0391] The server first collects data on the store's operational status. This data includes past sales performance, the number of customers visiting the store, and trends in product sales. At the same time, crew productivity data is collected, including each crew member's sales volume, customer service time, and number of transactions. Furthermore, crew members' emotional states are periodically collected. This emotional data records the crew member's daily stress level and emotional fluctuations. This data is then formatted for analysis by completing missing values ​​and removing outliers. StandardScaler is used to standardize the data.

[0392] AI model training and prediction

[0393] The server uses the preprocessed data to train an AI model. Feature values ​​include sales data for each time period and day of the week, crew productivity indicators, and emotional data. Machine learning algorithms such as random forests and neural networks are used. The server then uses this model to predict peak and off-peak periods.

[0394] Shift planning and notifications

[0395] The server designs shifts based on the learning results. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or giving them time off on slow days. It also takes into account emotional data and provides appropriate rest for stressed crew members. The designed shift schedule is divided into sections for each crew member and notified to their device (smartphone or PC).

[0396] Crew members who are users use their devices to check their next shift schedule. The shift schedule they receive includes details of busy and slow periods, as well as specific work instructions for each crew member.

[0397] Shift Adjustment and Feedback

[0398] If a crew member is dissatisfied with their shift or if their emotional state is different from usual, they can use their device to request a shift adjustment. The server receives this request and regenerates the shift schedule. Based on the emotional data, stressed crew members can be assigned lighter tasks or given rest days. The re-adjusted shift schedule is then notified to the crew again.

[0399] Using the terminals, crew members provide feedback to the server about their actual work performance and emotional state. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support." The server receives the feedback and reflects it in the generation of the next shift.

[0400] Specific examples and examples of AI prompts

[0401] For example, if data shows that Monday mornings are always busy, the server will use that information to allocate more of the most productive crew members to those times. If a slower period is predicted, the server will recommend training days for new crew members and paid vacation days for veteran crew members. If the emotion engine detects that a particular crew member is stressed, the server will adjust their shifts to allow them a rest day.

[0402] Example prompt for a generative AI model:

[0403] "Design the most efficient shift schedule using store sales data, crew productivity data, and emotional data for Monday morning and Tuesday afternoon. In particular, take into consideration the emotional data of crew members and include shift adjustments that reduce stress levels."

[0404] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0405] Step 1: Data collection and preprocessing

[0406] The server collects store operation status data, crew productivity data, and crew emotional state data. The collected data input includes past sales performance, customer visits, product sales trends, sales volume for each crew member, customer service time, number of transactions, crew member daily stress levels and emotional fluctuations, etc. The server imputes missing values ​​and removes outliers, and converts the data into a standardized format (specifically, using StandardScaler). This results in clean, standardized data being output.

[0407] Step 2: Training the AI ​​model

[0408] The server uses the preprocessed data to train an AI model. The input data is store operation status data, crew productivity data, and emotion data. The server uses machine learning algorithms such as random forests and neural networks. The output is a trained model for predicting the store's peak and slack periods.

[0409] Step 3: Shift design

[0410] The server designs shifts based on the prediction results of the trained model. The inputs are the trained model, current store operating status data, and crew productivity and emotion data. Based on the prediction results, the server assigns more highly productive crew members to busy days and recommends training new crew members or taking time off on slow days. This outputs a specific shift schedule for each crew member.

[0411] Step 4: Shift Notification

[0412] The server notifies the terminal of the designed shift schedule. The input is the shift schedule, and the output is the shift information notified to the crew's terminal (smartphone, etc.). This allows each crew member to check the next shift schedule through their own terminal.

[0413] Step 5: Receive a shift adjustment request

[0414] The user (crew member) uses a terminal to request a shift adjustment. The input is the crew member's request, and an adjustment request based on the crew member's emotional data and physical condition is sent to the server. The output is the shift adjustment request information.

[0415] Step 6: Shifting

[0416] The server readjusts the shift schedule based on the received shift adjustment request. The input is the shift adjustment request information and real-time emotion data. The server assigns lighter tasks to stressed crew members and provides rest days as necessary. The output is the adjusted shift schedule, which is notified to the crew again.

[0417] Step 7: Production Feedback

[0418] Using terminals, crew members provide feedback on their actual work performance and emotional state to the server. The input is specific feedback information from the crew, such as "Friday afternoon was busier than expected, but with appropriate support, it was less stressful." The server receives this feedback. The output is feedback information that will be reflected in the next shift plan.

[0419] Step 8: Reflection in next shift generation

[0420] The server reflects the feedback information in the generation of the next shift schedule. The input is the feedback information and all the data mentioned above. This generates a new shift schedule that takes into account improvements to shift allocation and emotion management. The output is the next shift schedule.

[0421] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0422] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0423] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0424] [Second embodiment]

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

[0426] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0427] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0428] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0429] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0430] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[0432] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0433] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0434] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

[0436] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0437] System Overview

[0438] This invention is a system for optimizing store shift allocation, collecting and analyzing store operating status data and crew productivity data to design effective shifts. The system is composed of server, terminal, and user elements, and achieves shift optimization through multiple processing procedures. The specific form is shown below.

[0439] Program processing

[0440] Data collection and preprocessing

[0441] Server: First, it collects data on the store's operational status. This data includes past sales, the number of customers visiting the store, and trends in product sales. At the same time, it also collects crew productivity data. This data includes each crew member's sales volume, customer service time, and number of transactions processed.

[0442] These data are then formatted for analysis by imputing missing values, removing outliers, and so on, for example, standardizing numerical data and identifying anomalous data points and treating them appropriately.

[0443] Training an AI model

[0444] Server: The preprocessed data is used to prepare the AI ​​model for training. Feature values ​​include sales data for each time period and day of the week, and crew productivity indicators. Machine learning algorithms (such as random forests and neural networks) are used to create a model that predicts peak and off-peak seasons.

[0445] Shift planning and notifications

[0446] Server: Designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or taking time off on slow days. The designed shift schedule is appropriately divided for each crew member and notified to the crew via their device (smartphone or PC).

[0447] Terminal (Crew): Each crew member uses their own terminal to check their upcoming shift schedule. The shift schedule includes details of busy and slow periods, as well as specific work instructions for each crew member.

[0448] Feedback and Adjustments

[0449] User (Crew): If a crew member is dissatisfied with a shift, they can use their terminal to request a shift adjustment. For example, they can send an adjustment request to the system saying, "I have a family appointment on this day, so I would like to take the day off."

[0450] Server: Receives adjustment requests and regenerates the shift schedule. This includes rescheduling other crew members' arrival times and unscheduled shift changes. The updated shift schedule is then notified to the crew members again.

[0451] Production Feedback

[0452] Terminal (Crew): Crew members work according to their shifts and provide feedback on their actual work performance to the server via their terminals. For example, they provide specific feedback such as, "Friday afternoon was busier than expected."

[0453] Servers: Reflect the collected feedback in the generation of the next shift, improving shift effectiveness and flexibility and optimizing the overall operational efficiency of the store.

[0454] Specific examples

[0455] Consider the following scenario: Data shows that Monday mornings are always the busiest time at a particular store. Using this information, the server assigns more of its most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a slower time, the server can use them as training days for new crew members and recommend paid vacation for veteran crew members.

[0456] In this way, the system of the present invention realizes data-driven shift optimization, contributing to improved store productivity and improved work styles for crew members.

[0457] The processing flow will be explained below.

[0458] Step 1: Data collection

[0459] Server: Collects store operation status data (past sales performance, number of customers, sales data by product, etc.) from the database. Also collects crew productivity data (number of customers served, sales volume, working hours, etc.). Additionally, crew schedules and attribute information (years of experience, skill level, etc.) are also collected.

[0460] Step 2: Data Preprocessing

[0461] Server: Preprocesses the collected data. Missing values ​​are filled with the mean or median, and outliers are removed as appropriate. The data format is standardized and sorted as time-series data. The data is organized by crew ID and date and time to make it easier to analyze.

[0462] Step 3: Feature selection

[0463] Server: Selects important features from the preprocessed data, such as sales, number of customers, and productivity indicators for each crew member. Based on these features, prepares training data for the AI ​​model.

[0464] Step 4: Model training

[0465] Server: Trains the AI ​​model using machine learning algorithms (e.g., random forests and neural networks). Using the training data, it builds a model that predicts peak and slow periods for the store. It evaluates the accuracy of the model using validation data and retrains it as needed.

[0466] Step 5: Shift Generation

[0467] Server: Based on the learning results, the next shift schedule is automatically generated. On busy days, more highly productive crew members are assigned, and on slow days, new crew members are trained and existing crew members are encouraged to take paid leave. The system also takes into account the attribute information of each crew member to plan the optimal crew assignment.

[0468] Step 6: Shift Notification

[0469] Server: Divides the generated shift schedule into individual crew members' groups and prepares for notification. The shift schedule is distributed to crew members' devices via email or a dedicated shift management application.

[0470] Terminal (Crew): Crew members use their terminals to check their upcoming shift schedule, including details such as work days, work hours, and duties.

[0471] Step 7: Request a shift adjustment

[0472] User (Crew): If adjustments to the shift are necessary, submit a request for adjustments via the shift management app or email. For example, a request such as "I would like to take time off on a specific day because I have family plans."

[0473] Server: Receives the adjustment request and regenerates the shift schedule. Review the work shifts of other crew members and make changes according to the request. Notify the crew of the re-adjusted shift schedule again.

[0474] Step 8: Production and feedback

[0475] Terminal (Crew): Crew members work based on the notified shift. They record their work performance during the shift and send any special notes or areas for improvement as feedback to the server.

[0476] Server: Receives feedback and reflects it in the next shift generation. Analyzes the obtained information and incorporates suggestions for improving shift allocation to optimize store operational efficiency. Repeating this loop improves the accuracy and flexibility of shifts.

[0477] Through the above process, the present invention optimizes store shift allocation, improving productivity and improving the way crews work.

[0478] Example 1

[0479] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0480] Conventional store shift management has the problem of making it difficult to accurately predict busy and slow periods and allocate crews efficiently. In particular, the lack of detailed data-based analysis has led to unnecessary staffing and excessive workloads, resulting in reduced work efficiency and lower crew satisfaction.

[0481] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0482] In this invention, the server includes a means for collecting hourly operating status data of the store, a means for collecting crew work efficiency data, and a means for pre-processing the collected data to extract necessary information and remove outliers, thereby enabling appropriate shift planning based on the data.

[0483] "Store operating status data by hour" is data that indicates the store's operating status, such as the store's sales performance, the number of customers visiting the store, and product sales during each time period.

[0484] "Crew work efficiency data" is data that indicates the productivity of the work that each crew member is responsible for, and includes, for example, sales volume, customer response time, number of transactions, etc.

[0485] "Preprocessing" refers to the process of preparing collected data in a format suitable for analysis or learning, and specifically includes filling in missing values ​​and removing outliers.

[0486] An "AI model" is a model that uses machine learning algorithms to analyze data and learn patterns, such as random forests and neural networks.

[0487] "Shift design" is the process of determining crew working hours and deployment based on store operating status and crew work efficiency data.

[0488] "Displaying to the crew" means visually displaying the designed shift schedule on the terminal used by the crew, so that the crew can check the next shift schedule.

[0489] A "shift adjustment request" is a request by a crew member to request a change to their shift. For example, this includes requests for vacation time or a shift change.

[0490] "Feedback" is the action of crew members providing comments and evaluations about their actual work situation and returning that information to the system.

[0491] This invention is a system for optimizing store shift allocation, and it collects and analyzes store operating status data and crew work efficiency data to design effective shifts. A specific embodiment of the system is shown below.

[0492] System Configuration

[0493] The system consists of the following elements: server, terminal, and user.

[0494] Data collection

[0495] Server: Collects hourly store operation status data and crew work efficiency data. Store operation status data includes past sales performance data obtained from the POS system, the number of customer visits obtained from the count sensor, and product sales data. Crew work efficiency data includes sales figures, customer response time, and number of transactions per crew obtained from the attendance management system.

[0496] Data Preprocessing

[0497] Server: The collected data is filled with missing values ​​and outliers are removed. This process uses Python libraries (Pandas, NumPy, etc.). For example, the server performs standardization of numerical data and detects and corrects anomalous data points.

[0498] Training an AI model

[0499] Server: A generative AI model based on preprocessed data predicts the store's busy and slow seasons. The machine learning algorithm used is a random forest using the Scikit-learn library or a neural network using TensorFlow. Sales data for each time period and day of the week and crew efficiency data are used as features to train the model, and the AI ​​model makes predictions for shift planning.

[0500] Shift planning and notifications

[0501] Server: Designs optimal shifts based on the prediction results. On busy days, it concentrates crew members with high work efficiency, and on slow days, it trains new crew members or recommends crew vacations. The designed shift schedule is displayed to crew members via their devices (smartphones or PCs) using a push notification API. For example, notifications can be sent using Firebase Cloud Messaging (FCM).

[0502] Terminal (Crew): Each crew member checks their next shift schedule via a dedicated app. The shift schedule includes details of peak and off-peak periods, as well as specific work instructions for each crew member.

[0503] Feedback and Shift Adjustment

[0504] User (crew): Provides feedback on shifts and requests for adjustments via the device. For example, a request such as "I would like to take a day off because I have family plans" can be sent via a dedicated app or web portal.

[0505] Server: Receives adjustment requests and readjusts the shift schedule. Rearranges the attendance times of other crew members and notifies them of the new shift schedule.

[0506] Production Feedback

[0507] Terminal (Crew): After their shift, crew members report their specific work performance as feedback. For example, they send feedback such as "Friday afternoon was busier than expected" to the server via their terminal.

[0508] Servers: By incorporating collected feedback into the next shift generation, they improve shift effectiveness and flexibility, optimizing the overall operational efficiency of the store.

[0509] Specific examples

[0510] Consider the following scenario for a certain store. Data shows that Monday mornings are always the busiest period. Based on this information, the server assigns more of the most efficient crew members to Monday mornings. If Tuesday afternoons are predicted to be a slow period, the server can make them training days for new crew members and recommend paid vacation for veteran crew members. This will contribute to improving store productivity and crew working practices.

[0511] Example prompts for generative AI models

[0512] "Using the following data, please analyze the store's operating status and crew productivity and generate the optimal shift schedule. The data includes past sales performance, the number of customers visiting the store, product sales trends, the number of sales made by each crew member, the time spent serving customers, and the number of transactions. Based on this information, please predict busy and slow seasons and propose the optimal shift arrangement."

[0513] The above is an embodiment of the present invention, which realizes data-driven shift optimization and improves store operation efficiency and crew satisfaction.

[0514] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0515] Program processing flow

[0516] Step 1: Data collection

[0517] Server: Collects store operation status data and crew work efficiency data. Specifically, it obtains sales performance data from the POS system, customer visit data from the count sensor, and crew work efficiency data from the attendance management system via API and database connections. This data is integrated and stored on the server for later processing.

[0518] Input: Data from POS systems, count sensors, and attendance management systems

[0519] Output: Integrated store operation status data and crew work efficiency data

[0520] Step 2: Data Preprocessing

[0521] Server: The collected data is filled with missing values ​​and outliers are removed. For example, using Python's Pandas and NumPy libraries, missing values ​​are filled with the mean or median, and outliers are detected and removed by calculating Z-scores. This prepares the data in a format suitable for analysis and model training.

[0522] Input: Raw data collected

[0523] Output: Preprocessed and clean data

[0524] Step 3: Feature Engineering

[0525] Server: Extract features using preprocessed data. Add features such as sales data by day of the week and time of day, and crew productivity data to the data frame. Perform feature engineering using the Scikit-learn library.

[0526] Input: Preprocessed data

[0527] Output: Data frame with added features

[0528] Step 4: Training the AI ​​model

[0529] Server: Train a generative AI model using the preprocessed data and features. The algorithms used are random forests and neural networks, and the model is built and trained using the Scikit-learn or TensorFlow library. For example, create a model with RandomForestRegressor() and train it with model.fit(X_train, y_train).

[0530] Input: Data frame with added features

[0531] Output: Trained AI model

[0532] Step 5: Shift design

[0533] Server: Using a trained AI model, it predicts future peak and off-peak periods and designs optimal shifts. Based on the prediction results, it assigns more crew members with high operational efficiency to peak days, and recommends training new crew members and giving veteran crew members time off on off-peak days.

[0534] Input: trained AI model, new data to predict

[0535] Output: Designed shift table

[0536] Step 6: Notification of shift schedule

[0537] Server: Notifies the crew of the designed shift schedule. Using a push notification API (e.g., Firebase Cloud Messaging), the shift schedule is sent to the crew's smartphones or PCs.

[0538] Input: Designed shift schedule

[0539] Output: Shift schedule notification to crew terminal

[0540] Step 7: Accepting feedback

[0541] User (Crew): Crew members submit feedback on shifts and requests for adjustments through a dedicated app or web portal. For example, they input a request such as, "I have a family appointment on this day, so I would like to take the day off."

[0542] Input: Shift adjustment requests and feedback from crew members

[0543] Output: Adjustment request data to the server

[0544] Step 8: Realign your shifts

[0545] Server: Regenerates the shift schedule based on the received adjustment request. Rearranges the attendance times of other crew members and notifies them of the updated shift schedule.

[0546] Input: Crew adjustment request data, current shift schedule

[0547] Output: Reworked shift schedule, new notifications

[0548] Step 9: Production Feedback

[0549] Terminal (Crew): Crew members provide feedback on their performance after their actual work. For example, they can enter comments such as, "Friday afternoon was busier than expected" through a dedicated app.

[0550] Input: Crew post-job feedback

[0551] Output: Feedback data to the server

[0552] Step 10: Incorporating feedback

[0553] Server: Reflects the collected feedback in the next shift design. Analyzes the feedback data, adds it as a feature when generating the next shift, and retrains the AI ​​model.

[0554] Input: Crew feedback data

[0555] Output: Improved AI model, more accurate design for next shift

[0556] Through these steps, the system optimizes store shift allocation, enabling efficient and effective operations.

[0557] (Application example 1)

[0558] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0559] Store shift allocation depends on the store's operating status and worker productivity, and if not managed properly, it can lead to reduced work efficiency and increased worker burden. However, traditional manual shift planning is time-consuming and difficult to predict busy and slow periods, making it difficult to achieve optimal shift allocation. It is also difficult to reflect worker feedback in real time and flexibly readjust shifts.

[0560] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0561] In this invention, the server includes means for collecting store operation status data, means for collecting worker productivity data, means for preprocessing the collected data, means for identifying busy and slow seasons for the store and designing shifts using the preprocessed data, means for notifying workers of the designed shifts, means for receiving shift adjustment requests from workers and readjusting the shifts, means for feeding back actual operation results and reflecting them in the next shift design, and means for readjusting the shifts based on feedback data collected from an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. This enables optimal shift design based on real-time data, thereby improving store operation efficiency and worker working styles.

[0562] "Store operation status data" refers to data related to store operations, such as sales performance at the store, the number of customers visiting the store, and trends in product sales.

[0563] "Worker productivity data" is data that indicates the performance of each worker, such as the number of tasks processed, the number of sales, and the time spent responding to customers.

[0564] "Preprocessed data" refers to data that has been processed into a format suitable for analysis, such as by filling in missing values, removing outliers, and standardizing numerical data.

[0565] The "busy season" refers to the period when a store is most active and when the number of customers visiting the store and sales increase.

[0566] A "slow season" is a period when store operations are slow and customer traffic and sales decline.

[0567] A "shift" refers to the time period during which store workers work and their placement.

[0568] "Means of notification" refers to the method of conveying information to workers via smartphones, computers, or other devices.

[0569] The "means for receiving adjustment requests" refers to the method for receiving requests for shift changes and vacation from workers.

[0570] "Actual operational results" refers to feedback data regarding store operations and worker performance.

[0571] "Feedback data" refers to data that records in real time what workers feel and accomplishments while working.

[0572] A "generative AI model" is a model that uses machine learning algorithms to analyze data and predict future states.

[0573] A "prompt" refers to a sentence of instructions or questions that is input to a generative AI model.

[0574] The present invention is a system for optimizing store shift allocation using an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. Specific embodiments of the present invention are described below.

[0575] System Configuration

[0576] The present invention is composed of the following elements: a server, a terminal (such as a worker's smartphone), and a user (worker). The system achieves shift optimization through the following steps:

[0577] Data collection and preprocessing

[0578] server:

[0579] Store operation status data and worker productivity data are collected. Store operation status data includes past sales performance, number of customer visits, and product sales trends. Worker productivity data includes each worker's number of tasks processed, number of sales, and customer response time. The collected data is preprocessed, including missing value completion and standardization, and then formatted into a format suitable for analysis.

[0580] Training an AI model

[0581] server:

[0582] The preprocessed data is used to train a generative AI model. For training, a machine learning algorithm (such as Scikit-Learn or TensorFlow) is used to create a model that predicts peak and off-peak seasons. Specifically, a classification model using random forests or a neural network can be used.

[0583] Shift planning and notifications

[0584] server:

[0585] Shifts are designed based on the learning results of the AI ​​model. During busy periods, many highly productive workers are assigned, and during slow periods, training of new workers is encouraged and workers are encouraged to take vacations. The designed shifts are saved in a database and notifications are sent to workers' devices (smartphones and PCs).

[0586] Terminal (Worker):

[0587] Each worker uses their own device to check their next shift schedule, which includes details of busy and slow periods as well as specific work instructions for each worker.

[0588] Feedback and Adjustments

[0589] User (operator):

[0590] If a worker is dissatisfied with their shift, they can use their terminal to request a shift adjustment. For example, they can send a request to the system saying, "I have a family appointment on this day, so I would like to take the day off."

[0591] server:

[0592] Upon receiving the adjustment request, the shift schedule is regenerated. This process includes readjusting the arrival times of other workers and making unplanned shift changes. The updated shift schedule is then notified to the workers again.

[0593] Production Feedback

[0594] Terminal (Worker):

[0595] Workers work according to their shifts and provide feedback on their actual work performance to the server via their terminals, such as "Friday afternoon was busier than expected."

[0596] server:

[0597] The collected feedback is reflected in the next shift generation, improving the effectiveness and flexibility of shift allocation and optimizing the overall operational efficiency of the store.

[0598] Specific examples

[0599] For example, data shows that Monday mornings are always the busiest period at a certain store. Based on this information, the server assigns many of the most productive workers to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet period, the server can set them as training days for new employees and recommend paid vacation for experienced workers. In this way, the system of the present invention enables optimal shift planning based on real-time data, improving store operational efficiency and employee working styles.

[0600] Prompt Sentence Examples

[0601] Monday mornings are always busy and we deploy the most productive crews. Tuesday afternoons are slower and are used as training days for new crew members and to encourage paid time off for veteran crew members.

[0602] The above is a specific embodiment of the present invention.

[0603] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0604] Step 1: Data collection and preprocessing

[0605] server:

[0606] Input: Store operation status data (past sales performance, number of customers visiting the store, product sales trends, etc.) and worker productivity data (number of transactions, number of sales, customer response time, etc.).

[0607] The server collects this data and performs preprocessing such as filling in missing values, removing outliers, and standardizing numerical data, preparing it in a format suitable for analysis.

[0608] Output: Preprocessed store utilization data and worker productivity data.

[0609] Step 2: Training the AI ​​model

[0610] server:

[0611] Input: Preprocessed data.

[0612] The server uses machine learning algorithms such as Scikit-Learn and TensorFlow to train a generative AI model, specifically using random forests and neural networks to create a model that predicts peak and off-peak seasons.

[0613] Output: The trained AI model.

[0614] Step 3: Design the shift

[0615] server:

[0616] Inputs: Trained AI model, latest operating status and productivity data.

[0617] Based on the predictions of the AI ​​model, the server designs shifts that assign many highly productive workers during busy periods and encourage training of new workers and taking vacations during slow periods.

[0618] Output: The created shift schedule.

[0619] Step 4: Shift Notification

[0620] server:

[0621] Input: The created shift schedule.

[0622] The server uses a notification service such as Firebase Cloud Messaging to notify workers of the planned shifts on their devices (smartphones or PCs).

[0623] Output: Shift notification sent to worker's device.

[0624] Step 5: Accepting a shift adjustment request

[0625] User (operator):

[0626] Input: Shift adjustment request sent by the user from the terminal.

[0627] If a user is dissatisfied with a shift, the user uses the terminal to send a request to the server for a shift adjustment, such as "I have family plans on this day, so I would like to take the day off."

[0628] Output: Shift adjustment request received by the server.

[0629] Step 6: Realign your shifts

[0630] server:

[0631] Inputs: Received shift adjustment requests, latest utilization and productivity data.

[0632] Based on the shift adjustment request, the server readjusts the arrival times of other workers and makes unscheduled shift changes, and regenerates the shift schedule.

[0633] Output: Rescaled shift table.

[0634] Step 7: Notification of rearranged shifts

[0635] server:

[0636] Input: Rebalanced shift table.

[0637] The server notifies the worker's terminal of the regenerated shift schedule again.

[0638] Output: Rearranged shift notification sent to worker's device.

[0639] Step 8: Gather production feedback

[0640] User (operator):

[0641] Input: Work performance feedback sent by the user from the device.

[0642] Users work according to their shifts and provide feedback to the server via their devices about their impressions and performance during work, such as "Friday afternoon was busier than expected."

[0643] Output: The feedback data received by the server.

[0644] Step 9: Incorporating feedback

[0645] server:

[0646] Input: Received feedback data.

[0647] The server reflects the feedback data in the next shift generation, improving the effectiveness and flexibility of shift allocation.

[0648] Output: Data for designing the next shift that reflects the feedback.

[0649] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0650] System Overview

[0651] This invention is a system for optimizing store shift allocation. It collects and analyzes store operating status data, crew productivity data, and crew emotion data to design effective shifts. The system is composed of a server, terminals, and user elements, and achieves shift optimization through multiple processing procedures. In addition, by utilizing an emotion engine, it is possible to adjust shifts taking into account the emotional state of crew members.

[0652] Program processing

[0653] Data collection and preprocessing

[0654] Server: First, it collects data on the store's operational status. This data includes past sales performance, the number of customers visiting the store, and trends in product sales. At the same time, it also collects crew productivity data, such as the number of sales made by each crew member, the time spent serving customers, and the number of tasks processed. Furthermore, it periodically collects crew emotional data using an emotion engine. This emotional data records the crew member's daily stress level and emotional fluctuations.

[0655] These data are then formatted for analysis by imputing missing values, removing outliers, and so on, for example, standardizing numerical data and identifying anomalous data points and treating them appropriately.

[0656] Training an AI model

[0657] Server: The preprocessed data is used to prepare the AI ​​model for training. Features include sales data for each time period and day of the week, crew productivity indicators, and sentiment data. Machine learning algorithms (e.g., random forests and neural networks) are used to build a model that predicts peak and off-peak seasons.

[0658] Shift planning and notifications

[0659] Server: Designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or giving them time off on slow days. It also takes into account emotional data and provides appropriate rest for stressed crew members. The designed shift schedule is appropriately divided for each crew member and notified to their device (smartphone or PC).

[0660] Terminal (Crew): Each crew member uses their own terminal to check their upcoming shift schedule. The shift schedule includes details of busy and slow periods, as well as specific work instructions for each crew member.

[0661] Shift adjustment based on emotion data

[0662] User (Crew): If the crew is dissatisfied with their shift or if their emotional state is different from usual, they can use their device to request a shift adjustment. The emotion engine analyzes the crew's emotional state in real time, and if improvements are needed, the system automatically proposes adjustments.

[0663] Server: Receives the adjustment request and regenerates the shift schedule. Based on the emotional data, it assigns lighter tasks to stressed crew members or provides them with rest days. The re-adjusted shift schedule is then notified to the crew members again.

[0664] Production Feedback

[0665] Terminal (Crew): Crew members work their shifts and provide feedback to the server on their actual work performance and emotional state via their terminals. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[0666] Server: Receives feedback and reflects it in the next shift generation. Analyzes the information obtained and incorporates suggestions for improving shift allocation and emotional management to optimize store operational efficiency and crew comfort.

[0667] Specific examples

[0668] Consider the following scenario: Data reveals that Monday mornings are always the busiest time at a certain store. Using this information, the server allocates more of its most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet time, the server can use them as training days for new crew members and recommend paid time off for veteran crew members. Using the emotion engine, if the server detects that a particular crew member is feeling stressed, the server can adjust their shifts to allow them a rest day.

[0669] In this way, the system of the present invention realizes data-driven shift optimization and contributes to improving store productivity and work styles, including crew emotional management.

[0670] The processing flow will be explained below.

[0671] Step 1: Data collection

[0672] Server: Collects store operation status data (e.g., past sales performance, number of customers, sales data by product, etc.) from a database. In addition, it also collects crew productivity data (e.g., number of customers served, number of sales, working hours, etc.). Furthermore, it periodically collects crew emotion data through an emotion engine. This emotion data includes the crew's daily stress level and emotional fluctuations.

[0673] Step 2: Data Preprocessing

[0674] Server: Preprocesses the collected data. Specifically, missing values ​​are filled with the mean or median, and outliers are removed as appropriate. The data format is standardized and sorted as time-series data. The data is organized by crew ID and date and time to make it easier to analyze.

[0675] Step 3: Feature selection

[0676] Server: Selects effective features from the preprocessed data. Specifically, the server selects sales figures, number of customers, productivity indicators for each crew member, and emotional data. Based on these features, it prepares training data for the AI ​​model.

[0677] Step 4: Model training

[0678] Server: Trains an AI model using machine learning algorithms (e.g., random forests or neural networks). Using the training data, it builds a model that predicts peak and slow periods for the store. It evaluates the accuracy of the model using validation data and retrains it as needed.

[0679] Step 5: Shift Generation

[0680] Server: Based on the learning results, the next shift schedule is automatically generated. On busy days, more highly productive crew members are assigned, and on slow days, new crew members are trained and existing crew members are encouraged to take paid vacation. Emotional data is also taken into consideration, and appropriate rest periods are provided for stressed crew members.

[0681] Step 6: Shift Notification

[0682] Server: Divides the generated shift schedule into individual crew members' groups and prepares for notification. The shift schedule is distributed to crew members' devices via email or a dedicated shift management application.

[0683] Terminal (Crew): Crew members use their terminals to view their upcoming shift schedule, which includes work days, work hours, tasks, and considerations based on emotional state.

[0684] Step 7: Request a shift adjustment

[0685] User (Crew): If adjustments to the shift are necessary, the user requests them via a terminal. The emotion engine analyzes the crew's emotional state in real time and automatically proposes adjustments if necessary. For example, a request might be, "I have family plans on this day, so I would like to take time off," or "I've been stressed lately, so I would like to have lighter work."

[0686] Server: Receives the adjustment request and regenerates the shift schedule based on the emotion data and existing shift data. It readjusts the arrival times and work contents of other crew members and notifies the crew of the adjusted shift schedule.

[0687] Step 8: Production and feedback

[0688] Terminal (Crew): Crew members work based on the notified shift. They use their terminals to provide feedback to the server on their actual work performance and emotional state. For example, they may provide feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[0689] Server: Collects feedback and reflects it in the next shift generation. Analyzes the feedback and incorporates improvements in shift allocation and emotional management to optimize store operational efficiency and crew comfort.

[0690] Specific examples

[0691] For example, if data shows that Monday mornings are always the busiest at a particular store, the server will use that information to assign the most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet period, the server will use that as a training day for new crew members and recommend paid vacation for veteran crew members. Furthermore, if the emotion engine detects that a particular crew member is feeling stressed, the server will adjust that crew member's shift and provide them with an appropriate rest day.

[0692] This enables the system to realize data-driven shift optimization, contributing to increased store productivity and improved working styles, including the emotional state of crew members.

[0693] Example 2

[0694] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0695] Store shift management requires optimal crew allocation according to busy and slow seasons, but conventional systems are limited to simple predictions based on operating status data and productivity data, making it difficult to flexibly adjust shifts that take into account the actual operational results of cloud services and the emotional state of crew members. Furthermore, it was not possible to utilize crew emotional data or real-time feedback, resulting in a lack of shift design that would improve crew work efficiency. This resulted in problems such as reduced store operational efficiency and reduced crew satisfaction.

[0696] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting store operation status data, means for collecting crew productivity data, means for collecting crew emotion data, means for pre-processing the collected data, means for identifying busy and slow seasons of the store using the pre-processed data and designing shifts, means for notifying crews of the designed shifts, means for receiving shift adjustment requests from crews and readjusting the shifts, and means for feeding back actual operation results and reflecting them in the next shift design. This enables advanced shift management that integrates multiple data sources and combines crew productivity and emotional states.

[0697] "Store operation status data" refers to data related to store operations, including past sales performance, the number of customers visiting the store, and trends in product sales.

[0698] "Crew productivity data" refers to data on the work performance of crew members, such as the number of sales made by each crew member, the time spent responding to customers, and the number of transactions processed.

[0699] "Crew emotional data" is data that records the crew's daily stress levels and emotional fluctuations.

[0700] "Preprocessing" is the process of converting collected data into a format suitable for analysis, such as filling in missing values, removing outliers, and standardizing data.

[0701] An "AI model" is a predictive model that uses machine learning algorithms and is used to predict peak and off-peak seasons.

[0702] "Shift design" is the process of optimizing crew working hours and roles based on store operating status, crew productivity, and emotional data.

[0703] "Shift notification" is the process of distributing the designed shift schedule to the crew, and is mainly done via terminals.

[0704] A "shift adjustment request" is a request made by a crew member for a change or adjustment to a shift.

[0705] "Performance feedback" refers to crew members providing feedback on their actual work performance and emotional state, which is reflected in the design of the next shift.

[0706] System Overview

[0707] This invention is a system for optimizing store shift allocation, collecting and analyzing store operating status data, crew productivity data, and crew emotion data to design effective shifts. The system is composed of a server, terminals, and user elements, and centrally manages shift design, notifications, and adjustments.

[0708] Hardware / Software used

[0709] The server collects and preprocesses data, trains the AI ​​model, designs shifts, and processes feedback. It uses software such as Python scripts, machine learning frameworks (TensorFlow, Scikit-Learn), and Emotion AI. A database (e.g., PostgreSQL) is used to store the data.

[0710] Crew members use the devices to check their shift schedules and provide feedback. The devices can be smartphones or PCs, and use the Google Calendar app or a dedicated application.

[0711] Users (crew members) provide feedback on their work performance and emotional state, and also request shift adjustments.

[0712] Data collection details

[0713] The server collects the following data:

[0714] Store operation data: past sales performance, customer visits, product sales trends, etc.

[0715] Crew productivity data: sales volume, customer service time, transaction volume, etc. for each crew member.

[0716] Crew Emotion Data: Emotion AI is used to record crew members' daily stress levels and emotional fluctuations.

[0717] Data preprocessing details

[0718] The server performs the following data preprocessing:

[0719] Imputing missing values: for example, imputing with the mean or estimated value.

[0720] Outlier removal: Remove statistically abnormal data using box plots and Z scores.

[0721] Data standardization: Converting numerical data to a consistent scale.

[0722] Training an AI model

[0723] The server uses machine learning algorithms to train the AI ​​model. Algorithms used include random forests and neural networks, and the features used include sales data for each time period and day of the week, crew productivity indicators, and emotional data. This allows the creation of a model that predicts peak and off-peak seasons.

[0724] Shift Design

[0725] The server designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members during busy periods, and recommends training new crew members and taking vacations during slow periods. It also takes emotional data into account and provides appropriate rest for stressed crew members.

[0726] Shift notifications

[0727] The server converts the designed shift schedule into Google Calendar format and notifies each crew member via email or a dedicated application, allowing them to check their shift schedule on their own devices.

[0728] Shift adjustment based on emotion data

[0729] If a user (crew member) is dissatisfied with their shift or feels unwell, they can request a shift adjustment using their device. The emotion engine then analyzes the crew member's emotional state in real time, and the system automatically proposes adjustments.

[0730] The server receives the adjustment request and regenerates the shift schedule based on the emotion data. The re-adjusted shift schedule is also notified to the crew.

[0731] Production Feedback

[0732] Users (crew members) work according to their shifts and provide feedback to the server on their actual work performance and emotional state via their devices. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[0733] The server receives this feedback and reflects it in the next shift generation. The feedback information is analyzed and suggestions for improving shift allocation and emotion management are incorporated to optimize store operational efficiency and crew work comfort.

[0734] Specific examples

[0735] For example, data might reveal that Monday mornings are a busy time for a particular store. The server can then use this information to allocate more of its most productive crew members to that time. Alternatively, if Tuesday afternoons are predicted to be a slower time, the server can use them as training days for new crew members and recommend paid time off for veteran crew members. If the emotion engine detects that a particular crew member is stressed, the server can adjust their shifts to accommodate a rest day.

[0736] Example prompts to input to the generative AI model

[0737] "Use past store operation data, crew productivity data, and sentiment data to design the next shift schedule. Monday morning is the busiest time, so assign many highly productive crew members to that time. Also, Tuesday afternoon is predicted to be a slow period, so use it as a training day for new crew members and recommend paid vacation for veteran crew members."

[0738] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0739] The flow of this system's program processing

[0740] Step 1: Data collection

[0741] The server retrieves store operation status data from the database and saves it in JSON format. This data includes past sales performance, customer visits, and product sales trends. It also aggregates each crew member's productivity data, such as sales volume, customer service time, and number of transactions, from daily reports and stores the data in Excel files. Furthermore, an emotion engine is used to collect crew member emotional data (stress levels, emotional fluctuations) via sensors and apps.

[0742] Input: Store operation status data, crew productivity data, crew emotion data

[0743] Output: Raw data for preprocessing

[0744] Step 2: Data Preprocessing

[0745] The server uses Python scripts to impute and standardize the collected data, imputing missing values ​​with means or estimated values, statistically identifying and removing outliers using box plots and Z-scores, and converting and standardizing numerical data to a consistent scale.

[0746] Input: Raw data collected

[0747] Output: Preprocessed data

[0748] Step 3: Training the AI ​​model

[0749] The server uses machine learning algorithms (such as random forests and neural networks) to train an AI model based on the preprocessed data. The features used in this process include sales data for each time period and day of the week, crew productivity indicators, and emotional data. This allows the creation of a model that predicts peak and off-peak seasons.

[0750] Input: Preprocessed data

[0751] Output: Trained AI model

[0752] Step 4: Design the shift

[0753] The server uses the results of the trained AI model to design shifts. Specifically, it assigns more highly productive crew members during busy periods and recommends training new crew members or giving crew members time off during slow periods. It also takes emotional data into account and applies algorithms (e.g., linear programming) to ensure that stressed crew members receive adequate rest time.

[0754] Input: Trained AI model, latest store operation status data, crew productivity data, crew emotion data

[0755] Output: Designed shift table

[0756] Step 5: Shift Notification

[0757] The server converts the designed shift schedule into Google Calendar format and notifies each crew member via email or a dedicated application. Crew members can then check their shift schedules on their own devices using the Google Calendar app or a dedicated application.

[0758] Input: Designed shift schedule

[0759] Output: Shift schedule notified to crew

[0760] Step 6: Accepting and rescheduling shift adjustment requests

[0761] If a user (crew member) is dissatisfied with their shift or feels unwell, they can request a shift adjustment from their device. The server receives this adjustment request and recalculates the shift schedule based on the emotion data and crew member feedback. The recalculated shift schedule is also notified to the crew member.

[0762] Input: Shift adjustment request, crew emotion data, feedback data

[0763] Output: Reworked shift schedule, crew notification

[0764] Step 7: Production Feedback

[0765] Users (crew members) work according to their shifts and provide feedback to the server via their devices about their actual work performance and emotional state. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[0766] Input: Actual work data, crew feedback

[0767] Output: Feedback data

[0768] Step 8: Improve shift generation

[0769] The server analyzes the collected feedback data and reflects it in the next shift generation. New algorithms and methods are introduced to continuously optimize the shifts.

[0770] Input: Feedback data

[0771] Output: Improved shift generation model

[0772] (Application example 2)

[0773] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0774] Conventional store shift management systems design shifts taking into account store operating conditions and crew productivity, but it is difficult to ensure that these shifts reflect the emotional state of crew members and adjust shifts in real time. Furthermore, there is a lack of efficient means for notifying on-site crew members of shifts and accepting crew requests. This has led to problems such as lower labor productivity and reduced crew satisfaction.

[0775] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting store operation status data, means for collecting crew productivity data, means for collecting crew emotional states, means for pre-processing the collected data, means for identifying busy and slow seasons for the store using the pre-processed data and designing shifts, means for notifying crew members of the designed shifts, means for receiving shift adjustment requests from crew members and readjusting the shifts, means for feeding back actual operation results and reflecting them in the next shift design, and means for notifying shift schedules as an application installed on a smartphone. This enables shift design and real-time shift adjustment that takes crew emotional states into consideration, and effective shift notification to each crew member.

[0776] "Store operating status data" refers to data relating to the store's operating status, such as sales, number of customers, and product sales trends while the store is open.

[0777] "Crew productivity data" is data that indicates the work efficiency of each crew member, such as the number of sales made by each crew member, the time spent responding to customers, and the number of transactions processed.

[0778] "Crew emotional state" refers to data on the crew's daily stress levels and emotional fluctuations.

[0779] "Preprocessing" refers to the process of preparing collected data in a format suitable for analysis by completing missing values, removing outliers, standardizing, and so on.

[0780] An "AI model" is a model built using machine learning algorithms to predict busy and slow seasons for a store.

[0781] "Shift design" is the act of creating a schedule to optimize crew working hours and deployment based on collected and analyzed data.

[0782] "Notification means" refers to the method of communicating the designed shift schedule to crew members, using smartphones or other devices.

[0783] "Shift Adjustment Request" means a request by a crew member for a change to their shift schedule.

[0784] "Feedback" is an information gathering and analysis process that collects information about actual operational results and the emotional state of the crew and reflects it in the design of the next shift.

[0785] The "application installed on a smartphone" is software that notifies employees of shift schedules and accepts adjustment requests.

[0786]

[0787] System Overview

[0788] The system of this invention collects and analyzes store operation status data, crew productivity data, and crew emotional states to design optimal shifts. The system is composed of a server, terminals, and user elements.

[0789] Data collection and preprocessing

[0790] The server first collects data on the store's operational status. This data includes past sales performance, the number of customers visiting the store, and trends in product sales. At the same time, crew productivity data is collected, including each crew member's sales volume, customer service time, and number of transactions. Furthermore, crew members' emotional states are periodically collected. This emotional data records the crew member's daily stress level and emotional fluctuations. This data is then formatted for analysis by completing missing values ​​and removing outliers. StandardScaler is used to standardize the data.

[0791] AI model training and prediction

[0792] The server uses the preprocessed data to train an AI model. Feature values ​​include sales data for each time period and day of the week, crew productivity indicators, and emotional data. Machine learning algorithms such as random forests and neural networks are used. The server then uses this model to predict peak and off-peak periods.

[0793] Shift planning and notifications

[0794] The server designs shifts based on the learning results. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or giving them time off on slow days. It also takes into account emotional data and provides appropriate rest for stressed crew members. The designed shift schedule is divided into sections for each crew member and notified to their device (smartphone or PC).

[0795] Crew members who are users use their devices to check their next shift schedule. The shift schedule they receive includes details of busy and slow periods, as well as specific work instructions for each crew member.

[0796] Shift Adjustment and Feedback

[0797] If a crew member is dissatisfied with their shift or if their emotional state is different from usual, they can use their device to request a shift adjustment. The server receives this request and regenerates the shift schedule. Based on the emotional data, stressed crew members can be assigned lighter tasks or given rest days. The re-adjusted shift schedule is then notified to the crew again.

[0798] Using the terminals, crew members provide feedback to the server about their actual work performance and emotional state. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support." The server receives the feedback and reflects it in the generation of the next shift.

[0799] Specific examples and examples of AI prompts

[0800] For example, if data shows that Monday mornings are always busy, the server will use that information to allocate more of the most productive crew members to those times. If a slower period is predicted, the server will recommend training days for new crew members and paid vacation days for veteran crew members. If the emotion engine detects that a particular crew member is stressed, the server will adjust their shifts to allow them a rest day.

[0801] Example prompt for a generative AI model:

[0802] "Design the most efficient shift schedule using store sales data, crew productivity data, and emotional data for Monday morning and Tuesday afternoon. In particular, take into consideration the emotional data of crew members and include shift adjustments that reduce stress levels."

[0803] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0804] Step 1: Data collection and preprocessing

[0805] The server collects store operation status data, crew productivity data, and crew emotional state data. The collected data input includes past sales performance, customer visits, product sales trends, sales volume for each crew member, customer service time, number of transactions, crew member daily stress levels and emotional fluctuations, etc. The server imputes missing values ​​and removes outliers, and converts the data into a standardized format (specifically, using StandardScaler). This results in clean, standardized data being output.

[0806] Step 2: Training the AI ​​model

[0807] The server uses the preprocessed data to train an AI model. The input data is store operation status data, crew productivity data, and emotion data. The server uses machine learning algorithms such as random forests and neural networks. The output is a trained model for predicting the store's peak and slack periods.

[0808] Step 3: Shift design

[0809] The server designs shifts based on the prediction results of the trained model. The inputs are the trained model, current store operating status data, and crew productivity and emotion data. Based on the prediction results, the server assigns more highly productive crew members to busy days and recommends training new crew members or taking time off on slow days. This outputs a specific shift schedule for each crew member.

[0810] Step 4: Shift Notification

[0811] The server notifies the terminal of the designed shift schedule. The input is the shift schedule, and the output is the shift information notified to the crew's terminal (smartphone, etc.). This allows each crew member to check the next shift schedule through their own terminal.

[0812] Step 5: Receive a shift adjustment request

[0813] The user (crew member) uses a terminal to request a shift adjustment. The input is the crew member's request, and an adjustment request based on the crew member's emotional data and physical condition is sent to the server. The output is the shift adjustment request information.

[0814] Step 6: Shifting

[0815] The server readjusts the shift schedule based on the received shift adjustment request. The input is the shift adjustment request information and real-time emotion data. The server assigns lighter tasks to stressed crew members and provides rest days as necessary. The output is the adjusted shift schedule, which is notified to the crew again.

[0816] Step 7: Production Feedback

[0817] Using terminals, crew members provide feedback on their actual work performance and emotional state to the server. The input is specific feedback information from the crew, such as "Friday afternoon was busier than expected, but with appropriate support, it was less stressful." The server receives this feedback. The output is feedback information that will be reflected in the next shift plan.

[0818] Step 8: Reflection in next shift generation

[0819] The server reflects the feedback information in the generation of the next shift schedule. The input is the feedback information and all the data mentioned above. This generates a new shift schedule that takes into account improvements to shift allocation and emotion management. The output is the next shift schedule.

[0820] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0821] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0822] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0823] [Third embodiment]

[0824] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0825] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0826] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0827] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0828] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0829] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0830] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0831] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0832] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0833] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0834] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0835] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0836] System Overview

[0837] This invention is a system for optimizing store shift allocation, collecting and analyzing store operating status data and crew productivity data to design effective shifts. The system is composed of server, terminal, and user elements, and achieves shift optimization through multiple processing procedures. The specific form is shown below.

[0838] Program processing

[0839] Data collection and preprocessing

[0840] Server: First, it collects data on the store's operational status. This data includes past sales, the number of customers visiting the store, and trends in product sales. At the same time, it also collects crew productivity data. This data includes each crew member's sales volume, customer service time, and number of transactions processed.

[0841] These data are then formatted for analysis by imputing missing values, removing outliers, and so on, for example, standardizing numerical data and identifying anomalous data points and treating them appropriately.

[0842] Training an AI model

[0843] Server: The preprocessed data is used to prepare the AI ​​model for training. Feature values ​​include sales data for each time period and day of the week, and crew productivity indicators. Machine learning algorithms (such as random forests and neural networks) are used to create a model that predicts peak and off-peak seasons.

[0844] Shift planning and notifications

[0845] Server: Designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or taking time off on slow days. The designed shift schedule is appropriately divided for each crew member and notified to the crew via their device (smartphone or PC).

[0846] Terminal (Crew): Each crew member uses their own terminal to check their upcoming shift schedule. The shift schedule includes details of busy and slow periods, as well as specific work instructions for each crew member.

[0847] Feedback and Adjustments

[0848] User (Crew): If a crew member is dissatisfied with a shift, they can use their terminal to request a shift adjustment. For example, they can send an adjustment request to the system saying, "I have a family appointment on this day, so I would like to take the day off."

[0849] Server: Receives adjustment requests and regenerates the shift schedule. This includes rescheduling other crew members' arrival times and unscheduled shift changes. The updated shift schedule is then notified to the crew members again.

[0850] Production Feedback

[0851] Terminal (Crew): Crew members work according to their shifts and provide feedback on their actual work performance to the server via their terminals. For example, they provide specific feedback such as, "Friday afternoon was busier than expected."

[0852] Servers: Reflect the collected feedback in the generation of the next shift, improving shift effectiveness and flexibility and optimizing the overall operational efficiency of the store.

[0853] Specific examples

[0854] Consider the following scenario: Data shows that Monday mornings are always the busiest time at a particular store. Using this information, the server assigns more of its most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a slower time, the server can use them as training days for new crew members and recommend paid vacation for veteran crew members.

[0855] In this way, the system of the present invention realizes data-driven shift optimization, contributing to improved store productivity and improved work styles for crew members.

[0856] The processing flow will be explained below.

[0857] Step 1: Data collection

[0858] Server: Collects store operation status data (past sales performance, number of customers, sales data by product, etc.) from the database. Also collects crew productivity data (number of customers served, sales volume, working hours, etc.). Additionally, crew schedules and attribute information (years of experience, skill level, etc.) are also collected.

[0859] Step 2: Data Preprocessing

[0860] Server: Preprocesses the collected data. Missing values ​​are filled with the mean or median, and outliers are removed as appropriate. The data format is standardized and sorted as time-series data. The data is organized by crew ID and date and time to make it easier to analyze.

[0861] Step 3: Feature selection

[0862] Server: Selects important features from the preprocessed data, such as sales, number of customers, and productivity indicators for each crew member. Based on these features, prepares training data for the AI ​​model.

[0863] Step 4: Model training

[0864] Server: Trains the AI ​​model using machine learning algorithms (e.g., random forests and neural networks). Using the training data, it builds a model that predicts peak and slow periods for the store. It evaluates the accuracy of the model using validation data and retrains it as needed.

[0865] Step 5: Shift Generation

[0866] Server: Based on the learning results, the next shift schedule is automatically generated. On busy days, more highly productive crew members are assigned, and on slow days, new crew members are trained and existing crew members are encouraged to take paid leave. The system also takes into account the attribute information of each crew member to plan the optimal crew assignment.

[0867] Step 6: Shift Notification

[0868] Server: Divides the generated shift schedule into individual crew members' groups and prepares for notification. The shift schedule is distributed to crew members' devices via email or a dedicated shift management application.

[0869] Terminal (Crew): Crew members use their terminals to check their upcoming shift schedule, including details such as work days, work hours, and duties.

[0870] Step 7: Request a shift adjustment

[0871] User (Crew): If adjustments to the shift are necessary, submit a request for adjustments via the shift management app or email. For example, a request such as "I would like to take time off on a specific day because I have family plans."

[0872] Server: Receives the adjustment request and regenerates the shift schedule. Review the work shifts of other crew members and make changes according to the request. Notify the crew of the re-adjusted shift schedule again.

[0873] Step 8: Production and feedback

[0874] Terminal (Crew): Crew members work based on the notified shift. They record their work performance during the shift and send any special notes or areas for improvement as feedback to the server.

[0875] Server: Receives feedback and reflects it in the next shift generation. Analyzes the obtained information and incorporates suggestions for improving shift allocation to optimize store operational efficiency. Repeating this loop improves the accuracy and flexibility of shifts.

[0876] Through the above process, the present invention optimizes store shift allocation, improving productivity and improving the way crews work.

[0877] Example 1

[0878] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0879] Conventional store shift management has the problem of making it difficult to accurately predict busy and slow periods and allocate crews efficiently. In particular, the lack of detailed data-based analysis has led to unnecessary staffing and excessive workloads, resulting in reduced work efficiency and lower crew satisfaction.

[0880] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0881] In this invention, the server includes a means for collecting hourly operating status data of the store, a means for collecting crew work efficiency data, and a means for pre-processing the collected data to extract necessary information and remove outliers, thereby enabling appropriate shift planning based on the data.

[0882] "Store operating status data by hour" is data that indicates the store's operating status, such as the store's sales performance, the number of customers visiting the store, and product sales during each time period.

[0883] "Crew work efficiency data" is data that indicates the productivity of the work that each crew member is responsible for, and includes, for example, sales volume, customer response time, number of transactions, etc.

[0884] "Preprocessing" refers to the process of preparing collected data in a format suitable for analysis or learning, and specifically includes filling in missing values ​​and removing outliers.

[0885] An "AI model" is a model that uses machine learning algorithms to analyze data and learn patterns, such as random forests and neural networks.

[0886] "Shift design" is the process of determining crew working hours and deployment based on store operating status and crew work efficiency data.

[0887] "Displaying to the crew" means visually displaying the designed shift schedule on the terminal used by the crew, so that the crew can check the next shift schedule.

[0888] A "shift adjustment request" is a request by a crew member to request a change to their shift. For example, this includes requests for vacation time or a shift change.

[0889] "Feedback" is the action of crew members providing comments and evaluations about their actual work situation and returning that information to the system.

[0890] This invention is a system for optimizing store shift allocation, and it collects and analyzes store operating status data and crew work efficiency data to design effective shifts. A specific embodiment of the system is shown below.

[0891] System Configuration

[0892] The system consists of the following elements: server, terminal, and user.

[0893] Data collection

[0894] Server: Collects hourly store operation status data and crew work efficiency data. Store operation status data includes past sales performance data obtained from the POS system, the number of customer visits obtained from the count sensor, and product sales data. Crew work efficiency data includes sales figures, customer response time, and number of transactions per crew obtained from the attendance management system.

[0895] Data Preprocessing

[0896] Server: The collected data is filled with missing values ​​and outliers are removed. This process uses Python libraries (Pandas, NumPy, etc.). For example, the server performs standardization of numerical data and detects and corrects anomalous data points.

[0897] Training an AI model

[0898] Server: A generative AI model based on preprocessed data predicts the store's busy and slow seasons. The machine learning algorithm used is a random forest using the Scikit-learn library or a neural network using TensorFlow. Sales data for each time period and day of the week and crew efficiency data are used as features to train the model, and the AI ​​model makes predictions for shift planning.

[0899] Shift planning and notifications

[0900] Server: Designs optimal shifts based on the prediction results. On busy days, it concentrates crew members with high work efficiency, and on slow days, it trains new crew members or recommends crew vacations. The designed shift schedule is displayed to crew members via their devices (smartphones or PCs) using a push notification API. For example, notifications can be sent using Firebase Cloud Messaging (FCM).

[0901] Terminal (Crew): Each crew member checks their next shift schedule via a dedicated app. The shift schedule includes details of peak and off-peak periods, as well as specific work instructions for each crew member.

[0902] Feedback and Shift Adjustment

[0903] User (crew): Provides feedback on shifts and requests for adjustments via the device. For example, a request such as "I would like to take a day off because I have family plans" can be sent via a dedicated app or web portal.

[0904] Server: Receives adjustment requests and readjusts the shift schedule. Rearranges the attendance times of other crew members and notifies them of the new shift schedule.

[0905] Production Feedback

[0906] Terminal (Crew): After their shift, crew members report their specific work performance as feedback. For example, they send feedback such as "Friday afternoon was busier than expected" to the server via their terminal.

[0907] Servers: By incorporating collected feedback into the next shift generation, they improve shift effectiveness and flexibility, optimizing the overall operational efficiency of the store.

[0908] Specific examples

[0909] Consider the following scenario for a certain store. Data shows that Monday mornings are always the busiest period. Based on this information, the server assigns more of the most efficient crew members to Monday mornings. If Tuesday afternoons are predicted to be a slow period, the server can make them training days for new crew members and recommend paid vacation for veteran crew members. This will contribute to improving store productivity and crew working practices.

[0910] Example prompts for generative AI models

[0911] "Using the following data, please analyze the store's operating status and crew productivity and generate the optimal shift schedule. The data includes past sales performance, the number of customers visiting the store, product sales trends, the number of sales made by each crew member, the time spent serving customers, and the number of transactions. Based on this information, please predict busy and slow seasons and propose the optimal shift arrangement."

[0912] The above is an embodiment of the present invention, which realizes data-driven shift optimization and improves store operation efficiency and crew satisfaction.

[0913] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0914] Program processing flow

[0915] Step 1: Data collection

[0916] Server: Collects store operation status data and crew work efficiency data. Specifically, it obtains sales performance data from the POS system, customer visit data from the count sensor, and crew work efficiency data from the attendance management system via API and database connections. This data is integrated and stored on the server for later processing.

[0917] Input: Data from POS systems, count sensors, and attendance management systems

[0918] Output: Integrated store operation status data and crew work efficiency data

[0919] Step 2: Data Preprocessing

[0920] Server: The collected data is filled with missing values ​​and outliers are removed. For example, using Python's Pandas and NumPy libraries, missing values ​​are filled with the mean or median, and outliers are detected and removed by calculating Z-scores. This prepares the data in a format suitable for analysis and model training.

[0921] Input: Raw data collected

[0922] Output: Preprocessed and clean data

[0923] Step 3: Feature Engineering

[0924] Server: Extract features using preprocessed data. Add features such as sales data by day of the week and time of day, and crew productivity data to the data frame. Perform feature engineering using the Scikit-learn library.

[0925] Input: Preprocessed data

[0926] Output: Data frame with added features

[0927] Step 4: Training the AI ​​model

[0928] Server: Train a generative AI model using the preprocessed data and features. The algorithms used are random forests and neural networks, and the model is built and trained using the Scikit-learn or TensorFlow library. For example, create a model with RandomForestRegressor() and train it with model.fit(X_train, y_train).

[0929] Input: Data frame with added features

[0930] Output: Trained AI model

[0931] Step 5: Shift design

[0932] Server: Using a trained AI model, it predicts future peak and off-peak periods and designs optimal shifts. Based on the prediction results, it assigns more crew members with high operational efficiency to peak days, and recommends training new crew members and giving veteran crew members time off on off-peak days.

[0933] Input: trained AI model, new data to predict

[0934] Output: Designed shift table

[0935] Step 6: Notification of shift schedule

[0936] Server: Notifies the crew of the designed shift schedule. Using a push notification API (e.g., Firebase Cloud Messaging), the shift schedule is sent to the crew's smartphones or PCs.

[0937] Input: Designed shift schedule

[0938] Output: Shift schedule notification to crew terminal

[0939] Step 7: Accepting feedback

[0940] User (Crew): Crew members submit feedback on shifts and requests for adjustments through a dedicated app or web portal. For example, they input a request such as, "I have a family appointment on this day, so I would like to take the day off."

[0941] Input: Shift adjustment requests and feedback from crew members

[0942] Output: Adjustment request data to the server

[0943] Step 8: Realign your shifts

[0944] Server: Regenerates the shift schedule based on the received adjustment request. Rearranges the attendance times of other crew members and notifies them of the updated shift schedule.

[0945] Input: Crew adjustment request data, current shift schedule

[0946] Output: Reworked shift schedule, new notifications

[0947] Step 9: Production Feedback

[0948] Terminal (Crew): Crew members provide feedback on their performance after their actual work. For example, they can enter comments such as, "Friday afternoon was busier than expected" through a dedicated app.

[0949] Input: Crew post-job feedback

[0950] Output: Feedback data to the server

[0951] Step 10: Incorporating feedback

[0952] Server: Reflects the collected feedback in the next shift design. Analyzes the feedback data, adds it as a feature when generating the next shift, and retrains the AI ​​model.

[0953] Input: Crew feedback data

[0954] Output: Improved AI model, more accurate design for next shift

[0955] Through these steps, the system optimizes store shift allocation, enabling efficient and effective operations.

[0956] (Application example 1)

[0957] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0958] Store shift allocation depends on the store's operating status and worker productivity, and if not managed properly, it can lead to reduced work efficiency and increased worker burden. However, traditional manual shift planning is time-consuming and difficult to predict busy and slow periods, making it difficult to achieve optimal shift allocation. It is also difficult to reflect worker feedback in real time and flexibly readjust shifts.

[0959] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0960] In this invention, the server includes means for collecting store operation status data, means for collecting worker productivity data, means for preprocessing the collected data, means for identifying busy and slow seasons for the store and designing shifts using the preprocessed data, means for notifying workers of the designed shifts, means for receiving shift adjustment requests from workers and readjusting the shifts, means for feeding back actual operation results and reflecting them in the next shift design, and means for readjusting the shifts based on feedback data collected from an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. This enables optimal shift design based on real-time data, thereby improving store operation efficiency and worker working styles.

[0961] "Store operation status data" refers to data related to store operations, such as sales performance at the store, the number of customers visiting the store, and trends in product sales.

[0962] "Worker productivity data" is data that indicates the performance of each worker, such as the number of tasks processed, the number of sales, and the time spent responding to customers.

[0963] "Preprocessed data" refers to data that has been processed into a format suitable for analysis, such as by filling in missing values, removing outliers, and standardizing numerical data.

[0964] The "busy season" refers to the period when a store is most active and when the number of customers visiting the store and sales increase.

[0965] A "slow season" is a period when store operations are slow and customer traffic and sales decline.

[0966] A "shift" refers to the time period during which store workers work and their placement.

[0967] "Means of notification" refers to the method of conveying information to workers via smartphones, computers, or other devices.

[0968] The "means for receiving adjustment requests" refers to the method for receiving requests for shift changes and vacation from workers.

[0969] "Actual operational results" refers to feedback data regarding store operations and worker performance.

[0970] "Feedback data" refers to data that records in real time what workers feel and accomplishments while working.

[0971] A "generative AI model" is a model that uses machine learning algorithms to analyze data and predict future states.

[0972] A "prompt" refers to a sentence of instructions or questions that is input to a generative AI model.

[0973] The present invention is a system for optimizing store shift allocation using an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. Specific embodiments of the present invention are described below.

[0974] System Configuration

[0975] The present invention is composed of the following elements: a server, a terminal (such as a worker's smartphone), and a user (worker). The system achieves shift optimization through the following steps:

[0976] Data collection and preprocessing

[0977] server:

[0978] Store operation status data and worker productivity data are collected. Store operation status data includes past sales performance, number of customer visits, and product sales trends. Worker productivity data includes each worker's number of tasks processed, number of sales, and customer response time. The collected data is preprocessed, including missing value completion and standardization, and then formatted into a format suitable for analysis.

[0979] Training an AI model

[0980] server:

[0981] The preprocessed data is used to train a generative AI model. For training, a machine learning algorithm (such as Scikit-Learn or TensorFlow) is used to create a model that predicts peak and off-peak seasons. Specifically, a classification model using random forests or a neural network can be used.

[0982] Shift planning and notifications

[0983] server:

[0984] Shifts are designed based on the learning results of the AI ​​model. During busy periods, many highly productive workers are assigned, and during slow periods, training of new workers is encouraged and workers are encouraged to take vacations. The designed shifts are saved in a database and notifications are sent to workers' devices (smartphones and PCs).

[0985] Terminal (Worker):

[0986] Each worker uses their own device to check their next shift schedule, which includes details of busy and slow periods as well as specific work instructions for each worker.

[0987] Feedback and Adjustments

[0988] User (operator):

[0989] If a worker is dissatisfied with their shift, they can use their terminal to request a shift adjustment. For example, they can send a request to the system saying, "I have a family appointment on this day, so I would like to take the day off."

[0990] server:

[0991] Upon receiving the adjustment request, the shift schedule is regenerated. This process includes readjusting the arrival times of other workers and making unplanned shift changes. The updated shift schedule is then notified to the workers again.

[0992] Production Feedback

[0993] Terminal (Worker):

[0994] Workers work according to their shifts and provide feedback on their actual work performance to the server via their terminals, such as "Friday afternoon was busier than expected."

[0995] server:

[0996] The collected feedback is reflected in the next shift generation, improving the effectiveness and flexibility of shift allocation and optimizing the overall operational efficiency of the store.

[0997] Specific examples

[0998] For example, data shows that Monday mornings are always the busiest period at a certain store. Based on this information, the server assigns many of the most productive workers to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet period, the server can set them as training days for new employees and recommend paid vacation for experienced workers. In this way, the system of the present invention enables optimal shift planning based on real-time data, improving store operational efficiency and employee working styles.

[0999] Prompt Sentence Examples

[1000] Monday mornings are always busy and we deploy the most productive crews. Tuesday afternoons are slower and are used as training days for new crew members and to encourage paid time off for veteran crew members.

[1001] The above is a specific embodiment of the present invention.

[1002] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1003] Step 1: Data collection and preprocessing

[1004] server:

[1005] Input: Store operation status data (past sales performance, number of customers visiting the store, product sales trends, etc.) and worker productivity data (number of transactions, number of sales, customer response time, etc.).

[1006] The server collects this data and performs preprocessing such as filling in missing values, removing outliers, and standardizing numerical data, preparing it in a format suitable for analysis.

[1007] Output: Preprocessed store utilization data and worker productivity data.

[1008] Step 2: Training the AI ​​model

[1009] server:

[1010] Input: Preprocessed data.

[1011] The server uses machine learning algorithms such as Scikit-Learn and TensorFlow to train a generative AI model, specifically using random forests and neural networks to create a model that predicts peak and off-peak seasons.

[1012] Output: The trained AI model.

[1013] Step 3: Design the shift

[1014] server:

[1015] Inputs: Trained AI model, latest operating status and productivity data.

[1016] Based on the predictions of the AI ​​model, the server designs shifts that assign many highly productive workers during busy periods and encourage training of new workers and taking vacations during slow periods.

[1017] Output: The created shift schedule.

[1018] Step 4: Shift Notification

[1019] server:

[1020] Input: The created shift schedule.

[1021] The server uses a notification service such as Firebase Cloud Messaging to notify workers of the planned shifts on their devices (smartphones or PCs).

[1022] Output: Shift notification sent to worker's device.

[1023] Step 5: Accepting a shift adjustment request

[1024] User (operator):

[1025] Input: Shift adjustment request sent by the user from the terminal.

[1026] If a user is dissatisfied with a shift, the user uses the terminal to send a request to the server for a shift adjustment, such as "I have family plans on this day, so I would like to take the day off."

[1027] Output: Shift adjustment request received by the server.

[1028] Step 6: Realign your shifts

[1029] server:

[1030] Inputs: Received shift adjustment requests, latest utilization and productivity data.

[1031] Based on the shift adjustment request, the server readjusts the arrival times of other workers and makes unscheduled shift changes, and regenerates the shift schedule.

[1032] Output: Rescaled shift table.

[1033] Step 7: Notification of rearranged shifts

[1034] server:

[1035] Input: Rebalanced shift table.

[1036] The server notifies the worker's terminal of the regenerated shift schedule again.

[1037] Output: Rearranged shift notification sent to worker's device.

[1038] Step 8: Gather production feedback

[1039] User (operator):

[1040] Input: Work performance feedback sent by the user from the device.

[1041] Users work according to their shifts and provide feedback to the server via their devices about their impressions and performance during work, such as "Friday afternoon was busier than expected."

[1042] Output: The feedback data received by the server.

[1043] Step 9: Incorporating feedback

[1044] server:

[1045] Input: Received feedback data.

[1046] The server reflects the feedback data in the next shift generation, improving the effectiveness and flexibility of shift allocation.

[1047] Output: Data for designing the next shift that reflects the feedback.

[1048] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1049] System Overview

[1050] This invention is a system for optimizing store shift allocation. It collects and analyzes store operating status data, crew productivity data, and crew emotion data to design effective shifts. The system is composed of a server, terminals, and user elements, and achieves shift optimization through multiple processing procedures. In addition, by utilizing an emotion engine, it is possible to adjust shifts taking into account the emotional state of crew members.

[1051] Program processing

[1052] Data collection and preprocessing

[1053] Server: First, it collects data on the store's operational status. This data includes past sales performance, the number of customers visiting the store, and trends in product sales. At the same time, it also collects crew productivity data, such as the number of sales made by each crew member, the time spent serving customers, and the number of tasks processed. Furthermore, it periodically collects crew emotional data using an emotion engine. This emotional data records the crew member's daily stress level and emotional fluctuations.

[1054] These data are then formatted for analysis by imputing missing values, removing outliers, and so on, for example, standardizing numerical data and identifying anomalous data points and treating them appropriately.

[1055] Training an AI model

[1056] Server: The preprocessed data is used to prepare the AI ​​model for training. Features include sales data for each time period and day of the week, crew productivity indicators, and sentiment data. Machine learning algorithms (e.g., random forests and neural networks) are used to build a model that predicts peak and off-peak seasons.

[1057] Shift planning and notifications

[1058] Server: Designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or giving them time off on slow days. It also takes into account emotional data and provides appropriate rest for stressed crew members. The designed shift schedule is appropriately divided for each crew member and notified to their device (smartphone or PC).

[1059] Terminal (Crew): Each crew member uses their own terminal to check their upcoming shift schedule. The shift schedule includes details of busy and slow periods, as well as specific work instructions for each crew member.

[1060] Shift adjustment based on emotion data

[1061] User (Crew): If the crew is dissatisfied with their shift or if their emotional state is different from usual, they can use their device to request a shift adjustment. The emotion engine analyzes the crew's emotional state in real time, and if improvements are needed, the system automatically proposes adjustments.

[1062] Server: Receives the adjustment request and regenerates the shift schedule. Based on the emotional data, it assigns lighter tasks to stressed crew members or provides them with rest days. The re-adjusted shift schedule is then notified to the crew members again.

[1063] Production Feedback

[1064] Terminal (Crew): Crew members work their shifts and provide feedback to the server on their actual work performance and emotional state via their terminals. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[1065] Server: Receives feedback and reflects it in the next shift generation. Analyzes the information obtained and incorporates suggestions for improving shift allocation and emotional management to optimize store operational efficiency and crew comfort.

[1066] Specific examples

[1067] Consider the following scenario: Data reveals that Monday mornings are always the busiest time at a certain store. Using this information, the server allocates more of its most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet time, the server can use them as training days for new crew members and recommend paid time off for veteran crew members. Using the emotion engine, if the server detects that a particular crew member is feeling stressed, the server can adjust their shifts to allow them a rest day.

[1068] In this way, the system of the present invention realizes data-driven shift optimization and contributes to improving store productivity and work styles, including crew emotional management.

[1069] The processing flow will be explained below.

[1070] Step 1: Data collection

[1071] Server: Collects store operation status data (e.g., past sales performance, number of customers, sales data by product, etc.) from a database. In addition, it also collects crew productivity data (e.g., number of customers served, number of sales, working hours, etc.). Furthermore, it periodically collects crew emotion data through an emotion engine. This emotion data includes the crew's daily stress level and emotional fluctuations.

[1072] Step 2: Data Preprocessing

[1073] Server: Preprocesses the collected data. Specifically, missing values ​​are filled with the mean or median, and outliers are removed as appropriate. The data format is standardized and sorted as time-series data. The data is organized by crew ID and date and time to make it easier to analyze.

[1074] Step 3: Feature selection

[1075] Server: Selects effective features from the preprocessed data. Specifically, the server selects sales figures, number of customers, productivity indicators for each crew member, and emotional data. Based on these features, it prepares training data for the AI ​​model.

[1076] Step 4: Model training

[1077] Server: Trains an AI model using machine learning algorithms (e.g., random forests or neural networks). Using the training data, it builds a model that predicts peak and slow periods for the store. It evaluates the accuracy of the model using validation data and retrains it as needed.

[1078] Step 5: Shift Generation

[1079] Server: Based on the learning results, the next shift schedule is automatically generated. On busy days, more highly productive crew members are assigned, and on slow days, new crew members are trained and existing crew members are encouraged to take paid vacation. Emotional data is also taken into consideration, and appropriate rest periods are provided for stressed crew members.

[1080] Step 6: Shift Notification

[1081] Server: Divides the generated shift schedule into individual crew members' groups and prepares for notification. The shift schedule is distributed to crew members' devices via email or a dedicated shift management application.

[1082] Terminal (Crew): Crew members use their terminals to view their upcoming shift schedule, which includes work days, work hours, tasks, and considerations based on emotional state.

[1083] Step 7: Request a shift adjustment

[1084] User (Crew): If adjustments to the shift are necessary, the user requests them via a terminal. The emotion engine analyzes the crew's emotional state in real time and automatically proposes adjustments if necessary. For example, a request might be, "I have family plans on this day, so I would like to take time off," or "I've been stressed lately, so I would like to have lighter work."

[1085] Server: Receives the adjustment request and regenerates the shift schedule based on the emotion data and existing shift data. It readjusts the arrival times and work contents of other crew members and notifies the crew of the adjusted shift schedule.

[1086] Step 8: Production and feedback

[1087] Terminal (Crew): Crew members work based on the notified shift. They use their terminals to provide feedback to the server on their actual work performance and emotional state. For example, they may provide feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[1088] Server: Collects feedback and reflects it in the next shift generation. Analyzes the feedback and incorporates improvements in shift allocation and emotional management to optimize store operational efficiency and crew comfort.

[1089] Specific examples

[1090] For example, if data shows that Monday mornings are always the busiest at a particular store, the server will use that information to assign the most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet period, the server will use that as a training day for new crew members and recommend paid vacation for veteran crew members. Furthermore, if the emotion engine detects that a particular crew member is feeling stressed, the server will adjust that crew member's shift and provide them with an appropriate rest day.

[1091] This enables the system to realize data-driven shift optimization, contributing to increased store productivity and improved working styles, including the emotional state of crew members.

[1092] Example 2

[1093] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1094] Store shift management requires optimal crew allocation according to busy and slow seasons, but conventional systems are limited to simple predictions based on operating status data and productivity data, making it difficult to flexibly adjust shifts that take into account the actual operational results of cloud services and the emotional state of crew members. Furthermore, it was not possible to utilize crew emotional data or real-time feedback, resulting in a lack of shift design that would improve crew work efficiency. This resulted in problems such as reduced store operational efficiency and reduced crew satisfaction.

[1095] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting store operation status data, means for collecting crew productivity data, means for collecting crew emotion data, means for pre-processing the collected data, means for identifying busy and slow seasons of the store using the pre-processed data and designing shifts, means for notifying crews of the designed shifts, means for receiving shift adjustment requests from crews and readjusting the shifts, and means for feeding back actual operation results and reflecting them in the next shift design. This enables advanced shift management that integrates multiple data sources and combines crew productivity and emotional states.

[1096] "Store operation status data" refers to data related to store operations, including past sales performance, the number of customers visiting the store, and trends in product sales.

[1097] "Crew productivity data" refers to data on the work performance of crew members, such as the number of sales made by each crew member, the time spent responding to customers, and the number of transactions processed.

[1098] "Crew emotional data" is data that records the crew's daily stress levels and emotional fluctuations.

[1099] "Preprocessing" is the process of converting collected data into a format suitable for analysis, such as filling in missing values, removing outliers, and standardizing data.

[1100] An "AI model" is a predictive model that uses machine learning algorithms and is used to predict peak and off-peak seasons.

[1101] "Shift design" is the process of optimizing crew working hours and roles based on store operating status, crew productivity, and emotional data.

[1102] "Shift notification" is the process of distributing the designed shift schedule to the crew, and is mainly done via terminals.

[1103] A "shift adjustment request" is a request made by a crew member for a change or adjustment to a shift.

[1104] "Performance feedback" refers to crew members providing feedback on their actual work performance and emotional state, which is reflected in the design of the next shift.

[1105] System Overview

[1106] This invention is a system for optimizing store shift allocation, collecting and analyzing store operating status data, crew productivity data, and crew emotion data to design effective shifts. The system is composed of a server, terminals, and user elements, and centrally manages shift design, notifications, and adjustments.

[1107] Hardware / Software used

[1108] The server collects and preprocesses data, trains the AI ​​model, designs shifts, and processes feedback. It uses software such as Python scripts, machine learning frameworks (TensorFlow, Scikit-Learn), and Emotion AI. A database (e.g., PostgreSQL) is used to store the data.

[1109] Crew members use the devices to check their shift schedules and provide feedback. The devices can be smartphones or PCs, and use the Google Calendar app or a dedicated application.

[1110] Users (crew members) provide feedback on their work performance and emotional state, and also request shift adjustments.

[1111] Data collection details

[1112] The server collects the following data:

[1113] Store operation data: past sales performance, customer visits, product sales trends, etc.

[1114] Crew productivity data: sales volume, customer service time, transaction volume, etc. for each crew member.

[1115] Crew Emotion Data: Emotion AI is used to record crew members' daily stress levels and emotional fluctuations.

[1116] Data preprocessing details

[1117] The server performs the following data preprocessing:

[1118] Imputing missing values: for example, imputing with the mean or estimated value.

[1119] Outlier removal: Remove statistically abnormal data using box plots and Z scores.

[1120] Data standardization: Converting numerical data to a consistent scale.

[1121] Training an AI model

[1122] The server uses machine learning algorithms to train the AI ​​model. Algorithms used include random forests and neural networks, and the features used include sales data for each time period and day of the week, crew productivity indicators, and emotional data. This allows the creation of a model that predicts peak and off-peak seasons.

[1123] Shift Design

[1124] The server designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members during busy periods, and recommends training new crew members and taking vacations during slow periods. It also takes emotional data into account and provides appropriate rest for stressed crew members.

[1125] Shift notifications

[1126] The server converts the designed shift schedule into Google Calendar format and notifies each crew member via email or a dedicated application, allowing them to check their shift schedule on their own devices.

[1127] Shift adjustment based on emotion data

[1128] If a user (crew member) is dissatisfied with their shift or feels unwell, they can request a shift adjustment using their device. The emotion engine then analyzes the crew member's emotional state in real time, and the system automatically proposes adjustments.

[1129] The server receives the adjustment request and regenerates the shift schedule based on the emotion data. The re-adjusted shift schedule is also notified to the crew.

[1130] Production Feedback

[1131] Users (crew members) work according to their shifts and provide feedback to the server on their actual work performance and emotional state via their devices. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[1132] The server receives this feedback and reflects it in the next shift generation. The feedback information is analyzed and suggestions for improving shift allocation and emotion management are incorporated to optimize store operational efficiency and crew work comfort.

[1133] Specific examples

[1134] For example, data might reveal that Monday mornings are a busy time for a particular store. The server can then use this information to allocate more of its most productive crew members to that time. Alternatively, if Tuesday afternoons are predicted to be a slower time, the server can use them as training days for new crew members and recommend paid time off for veteran crew members. If the emotion engine detects that a particular crew member is stressed, the server can adjust their shifts to accommodate a rest day.

[1135] Example prompts to input to the generative AI model

[1136] "Use past store operation data, crew productivity data, and sentiment data to design the next shift schedule. Monday morning is the busiest time, so assign many highly productive crew members to that time. Also, Tuesday afternoon is predicted to be a slow period, so use it as a training day for new crew members and recommend paid vacation for veteran crew members."

[1137] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1138] The flow of this system's program processing

[1139] Step 1: Data collection

[1140] The server retrieves store operation status data from the database and saves it in JSON format. This data includes past sales performance, customer visits, and product sales trends. It also aggregates each crew member's productivity data, such as sales volume, customer service time, and number of transactions, from daily reports and stores the data in Excel files. Furthermore, an emotion engine is used to collect crew member emotional data (stress levels, emotional fluctuations) via sensors and apps.

[1141] Input: Store operation status data, crew productivity data, crew emotion data

[1142] Output: Raw data for preprocessing

[1143] Step 2: Data Preprocessing

[1144] The server uses Python scripts to impute and standardize the collected data, imputing missing values ​​with means or estimated values, statistically identifying and removing outliers using box plots and Z-scores, and converting and standardizing numerical data to a consistent scale.

[1145] Input: Raw data collected

[1146] Output: Preprocessed data

[1147] Step 3: Training the AI ​​model

[1148] The server uses machine learning algorithms (such as random forests and neural networks) to train an AI model based on the preprocessed data. The features used in this process include sales data for each time period and day of the week, crew productivity indicators, and emotional data. This allows the creation of a model that predicts peak and off-peak seasons.

[1149] Input: Preprocessed data

[1150] Output: Trained AI model

[1151] Step 4: Design the shift

[1152] The server uses the results of the trained AI model to design shifts. Specifically, it assigns more highly productive crew members during busy periods and recommends training new crew members or giving crew members time off during slow periods. It also takes emotional data into account and applies algorithms (e.g., linear programming) to ensure that stressed crew members receive adequate rest time.

[1153] Input: Trained AI model, latest store operation status data, crew productivity data, crew emotion data

[1154] Output: Designed shift table

[1155] Step 5: Shift Notification

[1156] The server converts the designed shift schedule into Google Calendar format and notifies each crew member via email or a dedicated application. Crew members can then check their shift schedules on their own devices using the Google Calendar app or a dedicated application.

[1157] Input: Designed shift schedule

[1158] Output: Shift schedule notified to crew

[1159] Step 6: Accepting and rescheduling shift adjustment requests

[1160] If a user (crew member) is dissatisfied with their shift or feels unwell, they can request a shift adjustment from their device. The server receives this adjustment request and recalculates the shift schedule based on the emotion data and crew member feedback. The recalculated shift schedule is also notified to the crew member.

[1161] Input: Shift adjustment request, crew emotion data, feedback data

[1162] Output: Reworked shift schedule, crew notification

[1163] Step 7: Production Feedback

[1164] Users (crew members) work according to their shifts and provide feedback to the server via their devices about their actual work performance and emotional state. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[1165] Input: Actual work data, crew feedback

[1166] Output: Feedback data

[1167] Step 8: Improve shift generation

[1168] The server analyzes the collected feedback data and reflects it in the next shift generation. New algorithms and methods are introduced to continuously optimize the shifts.

[1169] Input: Feedback data

[1170] Output: Improved shift generation model

[1171] (Application example 2)

[1172] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1173] Conventional store shift management systems design shifts taking into account store operating conditions and crew productivity, but it is difficult to ensure that these shifts reflect the emotional state of crew members and adjust shifts in real time. Furthermore, there is a lack of efficient means for notifying on-site crew members of shifts and accepting crew requests. This has led to problems such as lower labor productivity and reduced crew satisfaction.

[1174] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting store operation status data, means for collecting crew productivity data, means for collecting crew emotional states, means for pre-processing the collected data, means for identifying busy and slow seasons for the store using the pre-processed data and designing shifts, means for notifying crew members of the designed shifts, means for receiving shift adjustment requests from crew members and readjusting the shifts, means for feeding back actual operation results and reflecting them in the next shift design, and means for notifying shift schedules as an application installed on a smartphone. This enables shift design and real-time shift adjustment that takes crew emotional states into consideration, and effective shift notification to each crew member.

[1175] "Store operating status data" refers to data relating to the store's operating status, such as sales, number of customers, and product sales trends while the store is open.

[1176] "Crew productivity data" is data that indicates the work efficiency of each crew member, such as the number of sales made by each crew member, the time spent responding to customers, and the number of transactions processed.

[1177] "Crew emotional state" refers to data on the crew's daily stress levels and emotional fluctuations.

[1178] "Preprocessing" refers to the process of preparing collected data in a format suitable for analysis by completing missing values, removing outliers, standardizing, and so on.

[1179] An "AI model" is a model built using machine learning algorithms to predict busy and slow seasons for a store.

[1180] "Shift design" is the act of creating a schedule to optimize crew working hours and deployment based on collected and analyzed data.

[1181] "Notification means" refers to the method of communicating the designed shift schedule to crew members, using smartphones or other devices.

[1182] "Shift Adjustment Request" means a request by a crew member for a change to their shift schedule.

[1183] "Feedback" is an information gathering and analysis process that collects information about actual operational results and the emotional state of the crew and reflects it in the design of the next shift.

[1184] The "application installed on a smartphone" is software that notifies employees of shift schedules and accepts adjustment requests.

[1185]

[1186] System Overview

[1187] The system of this invention collects and analyzes store operation status data, crew productivity data, and crew emotional states to design optimal shifts. The system is composed of a server, terminals, and user elements.

[1188] Data collection and preprocessing

[1189] The server first collects data on the store's operational status. This data includes past sales performance, the number of customers visiting the store, and trends in product sales. At the same time, crew productivity data is collected, including each crew member's sales volume, customer service time, and number of transactions. Furthermore, crew members' emotional states are periodically collected. This emotional data records the crew member's daily stress level and emotional fluctuations. This data is then formatted for analysis by completing missing values ​​and removing outliers. StandardScaler is used to standardize the data.

[1190] AI model training and prediction

[1191] The server uses the preprocessed data to train an AI model. Feature values ​​include sales data for each time period and day of the week, crew productivity indicators, and emotional data. Machine learning algorithms such as random forests and neural networks are used. The server then uses this model to predict peak and off-peak periods.

[1192] Shift planning and notifications

[1193] The server designs shifts based on the learning results. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or giving them time off on slow days. It also takes into account emotional data and provides appropriate rest for stressed crew members. The designed shift schedule is divided into sections for each crew member and notified to their device (smartphone or PC).

[1194] Crew members who are users use their devices to check their next shift schedule. The shift schedule they receive includes details of busy and slow periods, as well as specific work instructions for each crew member.

[1195] Shift Adjustment and Feedback

[1196] If a crew member is dissatisfied with their shift or if their emotional state is different from usual, they can use their device to request a shift adjustment. The server receives this request and regenerates the shift schedule. Based on the emotional data, stressed crew members can be assigned lighter tasks or given rest days. The re-adjusted shift schedule is then notified to the crew again.

[1197] Using the terminals, crew members provide feedback to the server about their actual work performance and emotional state. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support." The server receives the feedback and reflects it in the generation of the next shift.

[1198] Specific examples and examples of AI prompts

[1199] For example, if data shows that Monday mornings are always busy, the server will use that information to allocate more of the most productive crew members to those times. If a slower period is predicted, the server will recommend training days for new crew members and paid vacation days for veteran crew members. If the emotion engine detects that a particular crew member is stressed, the server will adjust their shifts to allow them a rest day.

[1200] Example prompt for a generative AI model:

[1201] "Design the most efficient shift schedule using store sales data, crew productivity data, and emotional data for Monday morning and Tuesday afternoon. In particular, take into consideration the emotional data of crew members and include shift adjustments that reduce stress levels."

[1202] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1203] Step 1: Data collection and preprocessing

[1204] The server collects store operation status data, crew productivity data, and crew emotional state data. The collected data input includes past sales performance, customer visits, product sales trends, sales volume for each crew member, customer service time, number of transactions, crew member daily stress levels and emotional fluctuations, etc. The server imputes missing values ​​and removes outliers, and converts the data into a standardized format (specifically, using StandardScaler). This results in clean, standardized data being output.

[1205] Step 2: Training the AI ​​model

[1206] The server uses the preprocessed data to train an AI model. The input data is store operation status data, crew productivity data, and emotion data. The server uses machine learning algorithms such as random forests and neural networks. The output is a trained model for predicting the store's peak and slack periods.

[1207] Step 3: Shift design

[1208] The server designs shifts based on the prediction results of the trained model. The inputs are the trained model, current store operating status data, and crew productivity and emotion data. Based on the prediction results, the server assigns more highly productive crew members to busy days and recommends training new crew members or taking time off on slow days. This outputs a specific shift schedule for each crew member.

[1209] Step 4: Shift Notification

[1210] The server notifies the terminal of the designed shift schedule. The input is the shift schedule, and the output is the shift information notified to the crew's terminal (smartphone, etc.). This allows each crew member to check the next shift schedule through their own terminal.

[1211] Step 5: Receive a shift adjustment request

[1212] The user (crew member) uses a terminal to request a shift adjustment. The input is the crew member's request, and an adjustment request based on the crew member's emotional data and physical condition is sent to the server. The output is the shift adjustment request information.

[1213] Step 6: Shifting

[1214] The server readjusts the shift schedule based on the received shift adjustment request. The input is the shift adjustment request information and real-time emotion data. The server assigns lighter tasks to stressed crew members and provides rest days as necessary. The output is the adjusted shift schedule, which is notified to the crew again.

[1215] Step 7: Production Feedback

[1216] Using terminals, crew members provide feedback on their actual work performance and emotional state to the server. The input is specific feedback information from the crew, such as "Friday afternoon was busier than expected, but with appropriate support, it was less stressful." The server receives this feedback. The output is feedback information that will be reflected in the next shift plan.

[1217] Step 8: Reflection in next shift generation

[1218] The server reflects the feedback information in the generation of the next shift schedule. The input is the feedback information and all the data mentioned above. This generates a new shift schedule that takes into account improvements to shift allocation and emotion management. The output is the next shift schedule.

[1219] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1220] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1221] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1222] [Fourth embodiment]

[1223] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1224] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1225] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1226] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1227] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1228] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1229] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1230] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1231] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1232] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1233] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1234] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1235] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1236] System Overview

[1237] This invention is a system for optimizing store shift allocation, collecting and analyzing store operating status data and crew productivity data to design effective shifts. The system is composed of server, terminal, and user elements, and achieves shift optimization through multiple processing procedures. The specific form is shown below.

[1238] Program processing

[1239] Data collection and preprocessing

[1240] Server: First, it collects data on the store's operational status. This data includes past sales, the number of customers visiting the store, and trends in product sales. At the same time, it also collects crew productivity data. This data includes each crew member's sales volume, customer service time, and number of transactions processed.

[1241] These data are then formatted for analysis by imputing missing values, removing outliers, and so on, for example, standardizing numerical data and identifying anomalous data points and treating them appropriately.

[1242] Training an AI model

[1243] Server: The preprocessed data is used to prepare the AI ​​model for training. Feature values ​​include sales data for each time period and day of the week, and crew productivity indicators. Machine learning algorithms (such as random forests and neural networks) are used to create a model that predicts peak and off-peak seasons.

[1244] Shift planning and notifications

[1245] Server: Designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or taking time off on slow days. The designed shift schedule is appropriately divided for each crew member and notified to the crew via their device (smartphone or PC).

[1246] Terminal (Crew): Each crew member uses their own terminal to check their upcoming shift schedule. The shift schedule includes details of busy and slow periods, as well as specific work instructions for each crew member.

[1247] Feedback and Adjustments

[1248] User (Crew): If a crew member is dissatisfied with a shift, they can use their terminal to request a shift adjustment. For example, they can send an adjustment request to the system saying, "I have a family appointment on this day, so I would like to take the day off."

[1249] Server: Receives adjustment requests and regenerates the shift schedule. This includes rescheduling other crew members' arrival times and unscheduled shift changes. The updated shift schedule is then notified to the crew members again.

[1250] Production Feedback

[1251] Terminal (Crew): Crew members work according to their shifts and provide feedback on their actual work performance to the server via their terminals. For example, they provide specific feedback such as, "Friday afternoon was busier than expected."

[1252] Servers: Reflect the collected feedback in the generation of the next shift, improving shift effectiveness and flexibility and optimizing the overall operational efficiency of the store.

[1253] Specific examples

[1254] Consider the following scenario: Data shows that Monday mornings are always the busiest time at a particular store. Using this information, the server assigns more of its most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a slower time, the server can use them as training days for new crew members and recommend paid vacation for veteran crew members.

[1255] In this way, the system of the present invention realizes data-driven shift optimization, contributing to improved store productivity and improved work styles for crew members.

[1256] The processing flow will be explained below.

[1257] Step 1: Data collection

[1258] Server: Collects store operation status data (past sales performance, number of customers, sales data by product, etc.) from the database. Also collects crew productivity data (number of customers served, sales volume, working hours, etc.). Additionally, crew schedules and attribute information (years of experience, skill level, etc.) are also collected.

[1259] Step 2: Data Preprocessing

[1260] Server: Preprocesses the collected data. Missing values ​​are filled with the mean or median, and outliers are removed as appropriate. The data format is standardized and sorted as time-series data. The data is organized by crew ID and date and time to make it easier to analyze.

[1261] Step 3: Feature selection

[1262] Server: Selects important features from the preprocessed data, such as sales, number of customers, and productivity indicators for each crew member. Based on these features, prepares training data for the AI ​​model.

[1263] Step 4: Model training

[1264] Server: Trains the AI ​​model using machine learning algorithms (e.g., random forests and neural networks). Using the training data, it builds a model that predicts peak and slow periods for the store. It evaluates the accuracy of the model using validation data and retrains it as needed.

[1265] Step 5: Shift Generation

[1266] Server: Based on the learning results, the next shift schedule is automatically generated. On busy days, more highly productive crew members are assigned, and on slow days, new crew members are trained and existing crew members are encouraged to take paid leave. The system also takes into account the attribute information of each crew member to plan the optimal crew assignment.

[1267] Step 6: Shift Notification

[1268] Server: Divides the generated shift schedule into individual crew members' groups and prepares for notification. The shift schedule is distributed to crew members' devices via email or a dedicated shift management application.

[1269] Terminal (Crew): Crew members use their terminals to check their upcoming shift schedule, including details such as work days, work hours, and duties.

[1270] Step 7: Request a shift adjustment

[1271] User (Crew): If adjustments to the shift are necessary, submit a request for adjustments via the shift management app or email. For example, a request such as "I would like to take time off on a specific day because I have family plans."

[1272] Server: Receives the adjustment request and regenerates the shift schedule. Review the work shifts of other crew members and make changes according to the request. Notify the crew of the re-adjusted shift schedule again.

[1273] Step 8: Production and feedback

[1274] Terminal (Crew): Crew members work based on the notified shift. They record their work performance during the shift and send any special notes or areas for improvement as feedback to the server.

[1275] Server: Receives feedback and reflects it in the next shift generation. Analyzes the obtained information and incorporates suggestions for improving shift allocation to optimize store operational efficiency. Repeating this loop improves the accuracy and flexibility of shifts.

[1276] Through the above process, the present invention optimizes store shift allocation, improving productivity and improving the way crews work.

[1277] Example 1

[1278] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1279] Conventional store shift management has the problem of making it difficult to accurately predict busy and slow periods and allocate crews efficiently. In particular, the lack of detailed data-based analysis has led to unnecessary staffing and excessive workloads, resulting in reduced work efficiency and lower crew satisfaction.

[1280] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1281] In this invention, the server includes a means for collecting hourly operating status data of the store, a means for collecting crew work efficiency data, and a means for pre-processing the collected data to extract necessary information and remove outliers, thereby enabling appropriate shift planning based on the data.

[1282] "Store operating status data by hour" is data that indicates the store's operating status, such as the store's sales performance, the number of customers visiting the store, and product sales during each time period.

[1283] "Crew work efficiency data" is data that indicates the productivity of the work that each crew member is responsible for, and includes, for example, sales volume, customer response time, number of transactions, etc.

[1284] "Preprocessing" refers to the process of preparing collected data in a format suitable for analysis or learning, and specifically includes filling in missing values ​​and removing outliers.

[1285] An "AI model" is a model that uses machine learning algorithms to analyze data and learn patterns, such as random forests and neural networks.

[1286] "Shift design" is the process of determining crew working hours and deployment based on store operating status and crew work efficiency data.

[1287] "Displaying to the crew" means visually displaying the designed shift schedule on the terminal used by the crew, so that the crew can check the next shift schedule.

[1288] A "shift adjustment request" is a request by a crew member to request a change to their shift. For example, this includes requests for vacation time or a shift change.

[1289] "Feedback" is the action of crew members providing comments and evaluations about their actual work situation and returning that information to the system.

[1290] This invention is a system for optimizing store shift allocation, and it collects and analyzes store operating status data and crew work efficiency data to design effective shifts. A specific embodiment of the system is shown below.

[1291] System Configuration

[1292] The system consists of the following elements: server, terminal, and user.

[1293] Data collection

[1294] Server: Collects hourly store operation status data and crew work efficiency data. Store operation status data includes past sales performance data obtained from the POS system, the number of customer visits obtained from the count sensor, and product sales data. Crew work efficiency data includes sales figures, customer response time, and number of transactions per crew obtained from the attendance management system.

[1295] Data Preprocessing

[1296] Server: The collected data is filled with missing values ​​and outliers are removed. This process uses Python libraries (Pandas, NumPy, etc.). For example, the server performs standardization of numerical data and detects and corrects anomalous data points.

[1297] Training an AI model

[1298] Server: A generative AI model based on preprocessed data predicts the store's busy and slow seasons. The machine learning algorithm used is a random forest using the Scikit-learn library or a neural network using TensorFlow. Sales data for each time period and day of the week and crew efficiency data are used as features to train the model, and the AI ​​model makes predictions for shift planning.

[1299] Shift planning and notifications

[1300] Server: Designs optimal shifts based on the prediction results. On busy days, it concentrates crew members with high work efficiency, and on slow days, it trains new crew members or recommends crew vacations. The designed shift schedule is displayed to crew members via their devices (smartphones or PCs) using a push notification API. For example, notifications can be sent using Firebase Cloud Messaging (FCM).

[1301] Terminal (Crew): Each crew member checks their next shift schedule via a dedicated app. The shift schedule includes details of peak and off-peak periods, as well as specific work instructions for each crew member.

[1302] Feedback and Shift Adjustment

[1303] User (crew): Provides feedback on shifts and requests for adjustments via the device. For example, a request such as "I would like to take a day off because I have family plans" can be sent via a dedicated app or web portal.

[1304] Server: Receives adjustment requests and readjusts the shift schedule. Rearranges the attendance times of other crew members and notifies them of the new shift schedule.

[1305] Production Feedback

[1306] Terminal (Crew): After their shift, crew members report their specific work performance as feedback. For example, they send feedback such as "Friday afternoon was busier than expected" to the server via their terminal.

[1307] Servers: By incorporating collected feedback into the next shift generation, they improve shift effectiveness and flexibility, optimizing the overall operational efficiency of the store.

[1308] Specific examples

[1309] Consider the following scenario for a certain store. Data shows that Monday mornings are always the busiest period. Based on this information, the server assigns more of the most efficient crew members to Monday mornings. If Tuesday afternoons are predicted to be a slow period, the server can make them training days for new crew members and recommend paid vacation for veteran crew members. This will contribute to improving store productivity and crew working practices.

[1310] Example prompts for generative AI models

[1311] "Using the following data, please analyze the store's operating status and crew productivity and generate the optimal shift schedule. The data includes past sales performance, the number of customers visiting the store, product sales trends, the number of sales made by each crew member, the time spent serving customers, and the number of transactions. Based on this information, please predict busy and slow seasons and propose the optimal shift arrangement."

[1312] The above is an embodiment of the present invention, which realizes data-driven shift optimization and improves store operation efficiency and crew satisfaction.

[1313] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1314] Program processing flow

[1315] Step 1: Data collection

[1316] Server: Collects store operation status data and crew work efficiency data. Specifically, it obtains sales performance data from the POS system, customer visit data from the count sensor, and crew work efficiency data from the attendance management system via API and database connections. This data is integrated and stored on the server for later processing.

[1317] Input: Data from POS systems, count sensors, and attendance management systems

[1318] Output: Integrated store operation status data and crew work efficiency data

[1319] Step 2: Data Preprocessing

[1320] Server: The collected data is filled with missing values ​​and outliers are removed. For example, using Python's Pandas and NumPy libraries, missing values ​​are filled with the mean or median, and outliers are detected and removed by calculating Z-scores. This prepares the data in a format suitable for analysis and model training.

[1321] Input: Raw data collected

[1322] Output: Preprocessed and clean data

[1323] Step 3: Feature Engineering

[1324] Server: Extract features using preprocessed data. Add features such as sales data by day of the week and time of day, and crew productivity data to the data frame. Perform feature engineering using the Scikit-learn library.

[1325] Input: Preprocessed data

[1326] Output: Data frame with added features

[1327] Step 4: Training the AI ​​model

[1328] Server: Train a generative AI model using the preprocessed data and features. The algorithms used are random forests and neural networks, and the model is built and trained using the Scikit-learn or TensorFlow library. For example, create a model with RandomForestRegressor() and train it with model.fit(X_train, y_train).

[1329] Input: Data frame with added features

[1330] Output: Trained AI model

[1331] Step 5: Shift design

[1332] Server: Using a trained AI model, it predicts future peak and off-peak periods and designs optimal shifts. Based on the prediction results, it assigns more crew members with high operational efficiency to peak days, and recommends training new crew members and giving veteran crew members time off on off-peak days.

[1333] Input: trained AI model, new data to predict

[1334] Output: Designed shift table

[1335] Step 6: Notification of shift schedule

[1336] Server: Notifies the crew of the designed shift schedule. Using a push notification API (e.g., Firebase Cloud Messaging), the shift schedule is sent to the crew's smartphones or PCs.

[1337] Input: Designed shift schedule

[1338] Output: Shift schedule notification to crew terminal

[1339] Step 7: Accepting feedback

[1340] User (Crew): Crew members submit feedback on shifts and requests for adjustments through a dedicated app or web portal. For example, they input a request such as, "I have a family appointment on this day, so I would like to take the day off."

[1341] Input: Shift adjustment requests and feedback from crew members

[1342] Output: Adjustment request data to the server

[1343] Step 8: Realign your shifts

[1344] Server: Regenerates the shift schedule based on the received adjustment request. Rearranges the attendance times of other crew members and notifies them of the updated shift schedule.

[1345] Input: Crew adjustment request data, current shift schedule

[1346] Output: Reworked shift schedule, new notifications

[1347] Step 9: Production Feedback

[1348] Terminal (Crew): Crew members provide feedback on their performance after their actual work. For example, they can enter comments such as, "Friday afternoon was busier than expected" through a dedicated app.

[1349] Input: Crew post-job feedback

[1350] Output: Feedback data to the server

[1351] Step 10: Incorporating feedback

[1352] Server: Reflects the collected feedback in the next shift design. Analyzes the feedback data, adds it as a feature when generating the next shift, and retrains the AI ​​model.

[1353] Input: Crew feedback data

[1354] Output: Improved AI model, more accurate design for next shift

[1355] Through these steps, the system optimizes store shift allocation, enabling efficient and effective operations.

[1356] (Application example 1)

[1357] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1358] Store shift allocation depends on the store's operating status and worker productivity, and if not managed properly, it can lead to reduced work efficiency and increased worker burden. However, traditional manual shift planning is time-consuming and difficult to predict busy and slow periods, making it difficult to achieve optimal shift allocation. It is also difficult to reflect worker feedback in real time and flexibly readjust shifts.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1360] In this invention, the server includes means for collecting store operation status data, means for collecting worker productivity data, means for preprocessing the collected data, means for identifying busy and slow seasons for the store and designing shifts using the preprocessed data, means for notifying workers of the designed shifts, means for receiving shift adjustment requests from workers and readjusting the shifts, means for feeding back actual operation results and reflecting them in the next shift design, and means for readjusting the shifts based on feedback data collected from an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. This enables optimal shift design based on real-time data, thereby improving store operation efficiency and worker working styles.

[1361] "Store operation status data" refers to data related to store operations, such as sales performance at the store, the number of customers visiting the store, and trends in product sales.

[1362] "Worker productivity data" is data that indicates the performance of each worker, such as the number of tasks processed, the number of sales, and the time spent responding to customers.

[1363] "Preprocessed data" refers to data that has been processed into a format suitable for analysis, such as by filling in missing values, removing outliers, and standardizing numerical data.

[1364] The "busy season" refers to the period when a store is most active and when the number of customers visiting the store and sales increase.

[1365] A "slow season" is a period when store operations are slow and customer traffic and sales decline.

[1366] A "shift" refers to the time period during which store workers work and their placement.

[1367] "Means of notification" refers to the method of conveying information to workers via smartphones, computers, or other devices.

[1368] The "means for receiving adjustment requests" refers to the method for receiving requests for shift changes and vacation from workers.

[1369] "Actual operational results" refers to feedback data regarding store operations and worker performance.

[1370] "Feedback data" refers to data that records in real time what workers feel and accomplishments while working.

[1371] A "generative AI model" is a model that uses machine learning algorithms to analyze data and predict future states.

[1372] A "prompt" refers to a sentence of instructions or questions that is input to a generative AI model.

[1373] The present invention is a system for optimizing store shift allocation using an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. Specific embodiments of the present invention are described below.

[1374] System Configuration

[1375] The present invention is composed of the following elements: a server, a terminal (such as a worker's smartphone), and a user (worker). The system achieves shift optimization through the following steps:

[1376] Data collection and preprocessing

[1377] server:

[1378] Store operation status data and worker productivity data are collected. Store operation status data includes past sales performance, number of customer visits, and product sales trends. Worker productivity data includes each worker's number of tasks processed, number of sales, and customer response time. The collected data is preprocessed, including missing value completion and standardization, and then formatted into a format suitable for analysis.

[1379] Training an AI model

[1380] server:

[1381] The preprocessed data is used to train a generative AI model. For training, a machine learning algorithm (such as Scikit-Learn or TensorFlow) is used to create a model that predicts peak and off-peak seasons. Specifically, a classification model using random forests or a neural network can be used.

[1382] Shift planning and notifications

[1383] server:

[1384] Shifts are designed based on the learning results of the AI ​​model. During busy periods, many highly productive workers are assigned, and during slow periods, training of new workers is encouraged and workers are encouraged to take vacations. The designed shifts are saved in a database and notifications are sent to workers' devices (smartphones and PCs).

[1385] Terminal (Worker):

[1386] Each worker uses their own device to check their next shift schedule, which includes details of busy and slow periods as well as specific work instructions for each worker.

[1387] Feedback and Adjustments

[1388] User (operator):

[1389] If a worker is dissatisfied with their shift, they can use their terminal to request a shift adjustment. For example, they can send a request to the system saying, "I have a family appointment on this day, so I would like to take the day off."

[1390] server:

[1391] Upon receiving the adjustment request, the shift schedule is regenerated. This process includes readjusting the arrival times of other workers and making unplanned shift changes. The updated shift schedule is then notified to the workers again.

[1392] Production Feedback

[1393] Terminal (Worker):

[1394] Workers work according to their shifts and provide feedback on their actual work performance to the server via their terminals, such as "Friday afternoon was busier than expected."

[1395] server:

[1396] The collected feedback is reflected in the next shift generation, improving the effectiveness and flexibility of shift allocation and optimizing the overall operational efficiency of the store.

[1397] Specific examples

[1398] For example, data shows that Monday mornings are always the busiest period at a certain store. Based on this information, the server assigns many of the most productive workers to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet period, the server can set them as training days for new employees and recommend paid vacation for experienced workers. In this way, the system of the present invention enables optimal shift planning based on real-time data, improving store operational efficiency and employee working styles.

[1399] Prompt Sentence Examples

[1400] Monday mornings are always busy and we deploy the most productive crews. Tuesday afternoons are slower and are used as training days for new crew members and to encourage paid time off for veteran crew members.

[1401] The above is a specific embodiment of the present invention.

[1402] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1403] Step 1: Data collection and preprocessing

[1404] server:

[1405] Input: Store operation status data (past sales performance, number of customers visiting the store, product sales trends, etc.) and worker productivity data (number of transactions, number of sales, customer response time, etc.).

[1406] The server collects this data and performs preprocessing such as filling in missing values, removing outliers, and standardizing numerical data, preparing it in a format suitable for analysis.

[1407] Output: Preprocessed store utilization data and worker productivity data.

[1408] Step 2: Training the AI ​​model

[1409] server:

[1410] Input: Preprocessed data.

[1411] The server uses machine learning algorithms such as Scikit-Learn and TensorFlow to train a generative AI model, specifically using random forests and neural networks to create a model that predicts peak and off-peak seasons.

[1412] Output: The trained AI model.

[1413] Step 3: Design the shift

[1414] server:

[1415] Inputs: Trained AI model, latest operating status and productivity data.

[1416] Based on the predictions of the AI ​​model, the server designs shifts that assign many highly productive workers during busy periods and encourage training of new workers and taking vacations during slow periods.

[1417] Output: The created shift schedule.

[1418] Step 4: Shift Notification

[1419] server:

[1420] Input: The created shift schedule.

[1421] The server uses a notification service such as Firebase Cloud Messaging to notify workers of the planned shifts on their devices (smartphones or PCs).

[1422] Output: Shift notification sent to worker's device.

[1423] Step 5: Accepting a shift adjustment request

[1424] User (operator):

[1425] Input: Shift adjustment request sent by the user from the terminal.

[1426] If a user is dissatisfied with a shift, the user uses the terminal to send a request to the server for a shift adjustment, such as "I have family plans on this day, so I would like to take the day off."

[1427] Output: Shift adjustment request received by the server.

[1428] Step 6: Realign your shifts

[1429] server:

[1430] Inputs: Received shift adjustment requests, latest utilization and productivity data.

[1431] Based on the shift adjustment request, the server readjusts the arrival times of other workers and makes unscheduled shift changes, and regenerates the shift schedule.

[1432] Output: Rescaled shift table.

[1433] Step 7: Notification of rearranged shifts

[1434] server:

[1435] Input: Rebalanced shift table.

[1436] The server notifies the worker's terminal of the regenerated shift schedule again.

[1437] Output: Rearranged shift notification sent to worker's device.

[1438] Step 8: Gather production feedback

[1439] User (operator):

[1440] Input: Work performance feedback sent by the user from the device.

[1441] Users work according to their shifts and provide feedback to the server via their devices about their impressions and performance during work, such as "Friday afternoon was busier than expected."

[1442] Output: The feedback data received by the server.

[1443] Step 9: Incorporating feedback

[1444] server:

[1445] Input: Received feedback data.

[1446] The server reflects the feedback data in the next shift generation, improving the effectiveness and flexibility of shift allocation.

[1447] Output: Data for designing the next shift that reflects the feedback.

[1448] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1449] System Overview

[1450] This invention is a system for optimizing store shift allocation. It collects and analyzes store operating status data, crew productivity data, and crew emotion data to design effective shifts. The system is composed of a server, terminals, and user elements, and achieves shift optimization through multiple processing procedures. In addition, by utilizing an emotion engine, it is possible to adjust shifts taking into account the emotional state of crew members.

[1451] Program processing

[1452] Data collection and preprocessing

[1453] Server: First, it collects data on the store's operational status. This data includes past sales performance, the number of customers visiting the store, and trends in product sales. At the same time, it also collects crew productivity data, such as the number of sales made by each crew member, the time spent serving customers, and the number of tasks processed. Furthermore, it periodically collects crew emotional data using an emotion engine. This emotional data records the crew member's daily stress level and emotional fluctuations.

[1454] These data are then formatted for analysis by imputing missing values, removing outliers, and so on, for example, standardizing numerical data and identifying anomalous data points and treating them appropriately.

[1455] Training an AI model

[1456] Server: The preprocessed data is used to prepare the AI ​​model for training. Features include sales data for each time period and day of the week, crew productivity indicators, and sentiment data. Machine learning algorithms (e.g., random forests and neural networks) are used to build a model that predicts peak and off-peak seasons.

[1457] Shift planning and notifications

[1458] Server: Designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or giving them time off on slow days. It also takes into account emotional data and provides appropriate rest for stressed crew members. The designed shift schedule is appropriately divided for each crew member and notified to their device (smartphone or PC).

[1459] Terminal (Crew): Each crew member uses their own terminal to check their upcoming shift schedule. The shift schedule includes details of busy and slow periods, as well as specific work instructions for each crew member.

[1460] Shift adjustment based on emotion data

[1461] User (Crew): If the crew is dissatisfied with their shift or if their emotional state is different from usual, they can use their device to request a shift adjustment. The emotion engine analyzes the crew's emotional state in real time, and if improvements are needed, the system automatically proposes adjustments.

[1462] Server: Receives the adjustment request and regenerates the shift schedule. Based on the emotional data, it assigns lighter tasks to stressed crew members or provides them with rest days. The re-adjusted shift schedule is then notified to the crew members again.

[1463] Production Feedback

[1464] Terminal (Crew): Crew members work their shifts and provide feedback to the server on their actual work performance and emotional state via their terminals. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[1465] Server: Receives feedback and reflects it in the next shift generation. Analyzes the information obtained and incorporates suggestions for improving shift allocation and emotional management to optimize store operational efficiency and crew comfort.

[1466] Specific examples

[1467] Consider the following scenario: Data reveals that Monday mornings are always the busiest time at a certain store. Using this information, the server allocates more of its most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet time, the server can use them as training days for new crew members and recommend paid time off for veteran crew members. Using the emotion engine, if the server detects that a particular crew member is feeling stressed, the server can adjust their shifts to allow them a rest day.

[1468] In this way, the system of the present invention realizes data-driven shift optimization and contributes to improving store productivity and work styles, including crew emotional management.

[1469] The processing flow will be explained below.

[1470] Step 1: Data collection

[1471] Server: Collects store operation status data (e.g., past sales performance, number of customers, sales data by product, etc.) from a database. In addition, it also collects crew productivity data (e.g., number of customers served, number of sales, working hours, etc.). Furthermore, it periodically collects crew emotion data through an emotion engine. This emotion data includes the crew's daily stress level and emotional fluctuations.

[1472] Step 2: Data Preprocessing

[1473] Server: Preprocesses the collected data. Specifically, missing values ​​are filled with the mean or median, and outliers are removed as appropriate. The data format is standardized and sorted as time-series data. The data is organized by crew ID and date and time to make it easier to analyze.

[1474] Step 3: Feature selection

[1475] Server: Selects effective features from the preprocessed data. Specifically, the server selects sales figures, number of customers, productivity indicators for each crew member, and emotional data. Based on these features, it prepares training data for the AI ​​model.

[1476] Step 4: Model training

[1477] Server: Trains an AI model using machine learning algorithms (e.g., random forests or neural networks). Using the training data, it builds a model that predicts peak and slow periods for the store. It evaluates the accuracy of the model using validation data and retrains it as needed.

[1478] Step 5: Shift Generation

[1479] Server: Based on the learning results, the next shift schedule is automatically generated. On busy days, more highly productive crew members are assigned, and on slow days, new crew members are trained and existing crew members are encouraged to take paid vacation. Emotional data is also taken into consideration, and appropriate rest periods are provided for stressed crew members.

[1480] Step 6: Shift Notification

[1481] Server: Divides the generated shift schedule into individual crew members' groups and prepares for notification. The shift schedule is distributed to crew members' devices via email or a dedicated shift management application.

[1482] Terminal (Crew): Crew members use their terminals to view their upcoming shift schedule, which includes work days, work hours, tasks, and considerations based on emotional state.

[1483] Step 7: Request a shift adjustment

[1484] User (Crew): If adjustments to the shift are necessary, the user requests them via a terminal. The emotion engine analyzes the crew's emotional state in real time and automatically proposes adjustments if necessary. For example, a request might be, "I have family plans on this day, so I would like to take time off," or "I've been stressed lately, so I would like to have lighter work."

[1485] Server: Receives the adjustment request and regenerates the shift schedule based on the emotion data and existing shift data. It readjusts the arrival times and work contents of other crew members and notifies the crew of the adjusted shift schedule.

[1486] Step 8: Production and feedback

[1487] Terminal (Crew): Crew members work based on the notified shift. They use their terminals to provide feedback to the server on their actual work performance and emotional state. For example, they may provide feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[1488] Server: Collects feedback and reflects it in the next shift generation. Analyzes the feedback and incorporates improvements in shift allocation and emotional management to optimize store operational efficiency and crew comfort.

[1489] Specific examples

[1490] For example, if data shows that Monday mornings are always the busiest at a particular store, the server will use that information to assign the most productive crew members to Monday mornings. If Tuesday afternoons are predicted to be a relatively quiet period, the server will use that as a training day for new crew members and recommend paid vacation for veteran crew members. Furthermore, if the emotion engine detects that a particular crew member is feeling stressed, the server will adjust that crew member's shift and provide them with an appropriate rest day.

[1491] This enables the system to realize data-driven shift optimization, contributing to increased store productivity and improved working styles, including the emotional state of crew members.

[1492] Example 2

[1493] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1494] Store shift management requires optimal crew allocation according to busy and slow seasons, but conventional systems are limited to simple predictions based on operating status data and productivity data, making it difficult to flexibly adjust shifts that take into account the actual operational results of cloud services and the emotional state of crew members. Furthermore, it was not possible to utilize crew emotional data or real-time feedback, resulting in a lack of shift design that would improve crew work efficiency. This resulted in problems such as reduced store operational efficiency and reduced crew satisfaction.

[1495] The identification processing by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting store operation status data, means for collecting crew productivity data, means for collecting crew emotion data, means for pre-processing the collected data, means for identifying busy and slow seasons of the store using the pre-processed data and designing shifts, means for notifying crews of the designed shifts, means for receiving shift adjustment requests from crews and readjusting the shifts, and means for feeding back actual operation results and reflecting them in the next shift design. This enables advanced shift management that integrates multiple data sources and combines crew productivity and emotional states.

[1496] "Store operation status data" refers to data related to store operations, including past sales performance, the number of customers visiting the store, and trends in product sales.

[1497] "Crew productivity data" refers to data on the work performance of crew members, such as the number of sales made by each crew member, the time spent responding to customers, and the number of transactions processed.

[1498] "Crew emotional data" is data that records the crew's daily stress levels and emotional fluctuations.

[1499] "Preprocessing" is the process of converting collected data into a format suitable for analysis, such as filling in missing values, removing outliers, and standardizing data.

[1500] An "AI model" is a predictive model that uses machine learning algorithms and is used to predict peak and off-peak seasons.

[1501] "Shift design" is the process of optimizing crew working hours and roles based on store operating status, crew productivity, and emotional data.

[1502] "Shift notification" is the process of distributing the designed shift schedule to the crew, and is mainly done via terminals.

[1503] A "shift adjustment request" is a request made by a crew member for a change or adjustment to a shift.

[1504] "Performance feedback" refers to crew members providing feedback on their actual work performance and emotional state, which is reflected in the design of the next shift.

[1505] System Overview

[1506] This invention is a system for optimizing store shift allocation, collecting and analyzing store operating status data, crew productivity data, and crew emotion data to design effective shifts. The system is composed of a server, terminals, and user elements, and centrally manages shift design, notifications, and adjustments.

[1507] Hardware / Software used

[1508] The server collects and preprocesses data, trains the AI ​​model, designs shifts, and processes feedback. It uses software such as Python scripts, machine learning frameworks (TensorFlow, Scikit-Learn), and Emotion AI. A database (e.g., PostgreSQL) is used to store the data.

[1509] Crew members use the devices to check their shift schedules and provide feedback. The devices can be smartphones or PCs, and use the Google Calendar app or a dedicated application.

[1510] Users (crew members) provide feedback on their work performance and emotional state, and also request shift adjustments.

[1511] Data collection details

[1512] The server collects the following data:

[1513] Store operation data: past sales performance, customer visits, product sales trends, etc.

[1514] Crew productivity data: sales volume, customer service time, transaction volume, etc. for each crew member.

[1515] Crew Emotion Data: Emotion AI is used to record crew members' daily stress levels and emotional fluctuations.

[1516] Data preprocessing details

[1517] The server performs the following data preprocessing:

[1518] Imputing missing values: for example, imputing with the mean or estimated value.

[1519] Outlier removal: Remove statistically abnormal data using box plots and Z scores.

[1520] Data standardization: Converting numerical data to a consistent scale.

[1521] Training an AI model

[1522] The server uses machine learning algorithms to train the AI ​​model. Algorithms used include random forests and neural networks, and the features used include sales data for each time period and day of the week, crew productivity indicators, and emotional data. This allows the creation of a model that predicts peak and off-peak seasons.

[1523] Shift Design

[1524] The server designs shifts based on the learning results of the AI ​​model. Specifically, it assigns more highly productive crew members during busy periods, and recommends training new crew members and taking vacations during slow periods. It also takes emotional data into account and provides appropriate rest for stressed crew members.

[1525] Shift notifications

[1526] The server converts the designed shift schedule into Google Calendar format and notifies each crew member via email or a dedicated application, allowing them to check their shift schedule on their own devices.

[1527] Shift adjustment based on emotion data

[1528] If a user (crew member) is dissatisfied with their shift or feels unwell, they can request a shift adjustment using their device. The emotion engine then analyzes the crew member's emotional state in real time, and the system automatically proposes adjustments.

[1529] The server receives the adjustment request and regenerates the shift schedule based on the emotion data. The re-adjusted shift schedule is also notified to the crew.

[1530] Production Feedback

[1531] Users (crew members) work according to their shifts and provide feedback to the server on their actual work performance and emotional state via their devices. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[1532] The server receives this feedback and reflects it in the next shift generation. The feedback information is analyzed and suggestions for improving shift allocation and emotion management are incorporated to optimize store operational efficiency and crew work comfort.

[1533] Specific examples

[1534] For example, data might reveal that Monday mornings are a busy time for a particular store. The server can then use this information to allocate more of its most productive crew members to that time. Alternatively, if Tuesday afternoons are predicted to be a slower time, the server can use them as training days for new crew members and recommend paid time off for veteran crew members. If the emotion engine detects that a particular crew member is stressed, the server can adjust their shifts to accommodate a rest day.

[1535] Example prompts to input to the generative AI model

[1536] "Use past store operation data, crew productivity data, and sentiment data to design the next shift schedule. Monday morning is the busiest time, so assign many highly productive crew members to that time. Also, Tuesday afternoon is predicted to be a slow period, so use it as a training day for new crew members and recommend paid vacation for veteran crew members."

[1537] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1538] The flow of this system's program processing

[1539] Step 1: Data collection

[1540] The server retrieves store operation status data from the database and saves it in JSON format. This data includes past sales performance, customer visits, and product sales trends. It also aggregates each crew member's productivity data, such as sales volume, customer service time, and number of transactions, from daily reports and stores the data in Excel files. Furthermore, an emotion engine is used to collect crew member emotional data (stress levels, emotional fluctuations) via sensors and apps.

[1541] Input: Store operation status data, crew productivity data, crew emotion data

[1542] Output: Raw data for preprocessing

[1543] Step 2: Data Preprocessing

[1544] The server uses Python scripts to impute and standardize the collected data, imputing missing values ​​with means or estimated values, statistically identifying and removing outliers using box plots and Z-scores, and converting and standardizing numerical data to a consistent scale.

[1545] Input: Raw data collected

[1546] Output: Preprocessed data

[1547] Step 3: Training the AI ​​model

[1548] The server uses machine learning algorithms (such as random forests and neural networks) to train an AI model based on the preprocessed data. The features used in this process include sales data for each time period and day of the week, crew productivity indicators, and emotional data. This allows the creation of a model that predicts peak and off-peak seasons.

[1549] Input: Preprocessed data

[1550] Output: Trained AI model

[1551] Step 4: Design the shift

[1552] The server uses the results of the trained AI model to design shifts. Specifically, it assigns more highly productive crew members during busy periods and recommends training new crew members or giving crew members time off during slow periods. It also takes emotional data into account and applies algorithms (e.g., linear programming) to ensure that stressed crew members receive adequate rest time.

[1553] Input: Trained AI model, latest store operation status data, crew productivity data, crew emotion data

[1554] Output: Designed shift table

[1555] Step 5: Shift Notification

[1556] The server converts the designed shift schedule into Google Calendar format and notifies each crew member via email or a dedicated application. Crew members can then check their shift schedules on their own devices using the Google Calendar app or a dedicated application.

[1557] Input: Designed shift schedule

[1558] Output: Shift schedule notified to crew

[1559] Step 6: Accepting and rescheduling shift adjustment requests

[1560] If a user (crew member) is dissatisfied with their shift or feels unwell, they can request a shift adjustment from their device. The server receives this adjustment request and recalculates the shift schedule based on the emotion data and crew member feedback. The recalculated shift schedule is also notified to the crew member.

[1561] Input: Shift adjustment request, crew emotion data, feedback data

[1562] Output: Reworked shift schedule, crew notification

[1563] Step 7: Production Feedback

[1564] Users (crew members) work according to their shifts and provide feedback to the server via their devices about their actual work performance and emotional state. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support."

[1565] Input: Actual work data, crew feedback

[1566] Output: Feedback data

[1567] Step 8: Improve shift generation

[1568] The server analyzes the collected feedback data and reflects it in the next shift generation. New algorithms and methods are introduced to continuously optimize the shifts.

[1569] Input: Feedback data

[1570] Output: Improved shift generation model

[1571] (Application example 2)

[1572] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1573] Conventional store shift management systems design shifts taking into account store operating conditions and crew productivity, but it is difficult to ensure that these shifts reflect the emotional state of crew members and adjust shifts in real time. Furthermore, there is a lack of efficient means for notifying on-site crew members of shifts and accepting crew requests. This has led to problems such as lower labor productivity and reduced crew satisfaction.

[1574] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting store operation status data, means for collecting crew productivity data, means for collecting crew emotional states, means for pre-processing the collected data, means for identifying busy and slow seasons for the store using the pre-processed data and designing shifts, means for notifying crew members of the designed shifts, means for receiving shift adjustment requests from crew members and readjusting the shifts, means for feeding back actual operation results and reflecting them in the next shift design, and means for notifying shift schedules as an application installed on a smartphone. This enables shift design and real-time shift adjustment that takes crew emotional states into consideration, and effective shift notification to each crew member.

[1575] "Store operating status data" refers to data relating to the store's operating status, such as sales, number of customers, and product sales trends while the store is open.

[1576] "Crew productivity data" is data that indicates the work efficiency of each crew member, such as the number of sales made by each crew member, the time spent responding to customers, and the number of transactions processed.

[1577] "Crew emotional state" refers to data on the crew's daily stress levels and emotional fluctuations.

[1578] "Preprocessing" refers to the process of preparing collected data in a format suitable for analysis by completing missing values, removing outliers, standardizing, and so on.

[1579] An "AI model" is a model built using machine learning algorithms to predict busy and slow seasons for a store.

[1580] "Shift design" is the act of creating a schedule to optimize crew working hours and deployment based on collected and analyzed data.

[1581] "Notification means" refers to the method of communicating the designed shift schedule to crew members, using smartphones or other devices.

[1582] "Shift Adjustment Request" means a request by a crew member for a change to their shift schedule.

[1583] "Feedback" is an information gathering and analysis process that collects information about actual operational results and the emotional state of the crew and reflects it in the design of the next shift.

[1584] The "application installed on a smartphone" is software that notifies employees of shift schedules and accepts adjustment requests.

[1585]

[1586] System Overview

[1587] The system of this invention collects and analyzes store operation status data, crew productivity data, and crew emotional states to design optimal shifts. The system is composed of a server, terminals, and user elements.

[1588] Data collection and preprocessing

[1589] The server first collects data on the store's operational status. This data includes past sales performance, the number of customers visiting the store, and trends in product sales. At the same time, crew productivity data is collected, including each crew member's sales volume, customer service time, and number of transactions. Furthermore, crew members' emotional states are periodically collected. This emotional data records the crew member's daily stress level and emotional fluctuations. This data is then formatted for analysis by completing missing values ​​and removing outliers. StandardScaler is used to standardize the data.

[1590] AI model training and prediction

[1591] The server uses the preprocessed data to train an AI model. Feature values ​​include sales data for each time period and day of the week, crew productivity indicators, and emotional data. Machine learning algorithms such as random forests and neural networks are used. The server then uses this model to predict peak and off-peak periods.

[1592] Shift planning and notifications

[1593] The server designs shifts based on the learning results. Specifically, it assigns more highly productive crew members on busy days, and recommends training new crew members or giving them time off on slow days. It also takes into account emotional data and provides appropriate rest for stressed crew members. The designed shift schedule is divided into sections for each crew member and notified to their device (smartphone or PC).

[1594] Crew members who are users use their devices to check their next shift schedule. The shift schedule they receive includes details of busy and slow periods, as well as specific work instructions for each crew member.

[1595] Shift Adjustment and Feedback

[1596] If a crew member is dissatisfied with their shift or if their emotional state is different from usual, they can use their device to request a shift adjustment. The server receives this request and regenerates the shift schedule. Based on the emotional data, stressed crew members can be assigned lighter tasks or given rest days. The re-adjusted shift schedule is then notified to the crew again.

[1597] Using the terminals, crew members provide feedback to the server about their actual work performance and emotional state. For example, they can provide specific feedback such as, "Friday afternoon was busier than expected, but I felt less stressed because I had appropriate support." The server receives the feedback and reflects it in the generation of the next shift.

[1598] Specific examples and examples of AI prompts

[1599] For example, if data shows that Monday mornings are always busy, the server will use that information to allocate more of the most productive crew members to those times. If a slower period is predicted, the server will recommend training days for new crew members and paid vacation days for veteran crew members. If the emotion engine detects that a particular crew member is stressed, the server will adjust their shifts to allow them a rest day.

[1600] Example prompt for a generative AI model:

[1601] "Design the most efficient shift schedule using store sales data, crew productivity data, and emotional data for Monday morning and Tuesday afternoon. In particular, take into consideration the emotional data of crew members and include shift adjustments that reduce stress levels."

[1602] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1603] Step 1: Data collection and preprocessing

[1604] The server collects store operation status data, crew productivity data, and crew emotional state data. The collected data input includes past sales performance, customer visits, product sales trends, sales volume for each crew member, customer service time, number of transactions, crew member daily stress levels and emotional fluctuations, etc. The server imputes missing values ​​and removes outliers, and converts the data into a standardized format (specifically, using StandardScaler). This results in clean, standardized data being output.

[1605] Step 2: Training the AI ​​model

[1606] The server uses the preprocessed data to train an AI model. The input data is store operation status data, crew productivity data, and emotion data. The server uses machine learning algorithms such as random forests and neural networks. The output is a trained model for predicting the store's peak and slack periods.

[1607] Step 3: Shift design

[1608] The server designs shifts based on the prediction results of the trained model. The inputs are the trained model, current store operating status data, and crew productivity and emotion data. Based on the prediction results, the server assigns more highly productive crew members to busy days and recommends training new crew members or taking time off on slow days. This outputs a specific shift schedule for each crew member.

[1609] Step 4: Shift Notification

[1610] The server notifies the terminal of the designed shift schedule. The input is the shift schedule, and the output is the shift information notified to the crew's terminal (smartphone, etc.). This allows each crew member to check the next shift schedule through their own terminal.

[1611] Step 5: Receive a shift adjustment request

[1612] The user (crew member) uses a terminal to request a shift adjustment. The input is the crew member's request, and an adjustment request based on the crew member's emotional data and physical condition is sent to the server. The output is the shift adjustment request information.

[1613] Step 6: Shifting

[1614] The server readjusts the shift schedule based on the received shift adjustment request. The input is the shift adjustment request information and real-time emotion data. The server assigns lighter tasks to stressed crew members and provides rest days as necessary. The output is the adjusted shift schedule, which is notified to the crew again.

[1615] Step 7: Production Feedback

[1616] Using terminals, crew members provide feedback on their actual work performance and emotional state to the server. The input is specific feedback information from the crew, such as "Friday afternoon was busier than expected, but with appropriate support, it was less stressful." The server receives this feedback. The output is feedback information that will be reflected in the next shift plan.

[1617] Step 8: Reflection in next shift generation

[1618] The server reflects the feedback information in the generation of the next shift schedule. The input is the feedback information and all the data mentioned above. This generates a new shift schedule that takes into account improvements to shift allocation and emotion management. The output is the next shift schedule.

[1619] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1620] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1621] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1622] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1623] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1624] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1625] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1626] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1627] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1628] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1629] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1630] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1631] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1632] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1633] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1634] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1635] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1636] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1637] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1638] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1639] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1640] The following is further disclosed regarding the above embodiment.

[1641] (Claim 1)

[1642] a means for collecting store operation status data;

[1643] a means for collecting crew productivity data;

[1644] a means for pre-processing the collected data;

[1645] A means of identifying busy and slow periods in stores and designing shifts using pre-processed data;

[1646] A means of informing crews of the planned shifts;

[1647] A means of receiving crew member requests for shift adjustments and rearranging shifts;

[1648] A method to feed back actual operational results and reflect them in the next shift design,

[1649] A system including:

[1650] (Claim 2)

[1651] The system of claim 1, further comprising means for training an AI model based on the preprocessed data and predicting peak and slack seasons for the store using the training results.

[1652] (Claim 3)

[1653] The system of claim 1, further comprising means for assigning appropriate crew members during busy periods based on the skill level and years of experience of the crew members, and for training new crew members and recommending crew members take vacations during slow periods.

[1654] "Example 1"

[1655] (Claim 1)

[1656] a means of collecting store hourly operating status data;

[1657] a means of collecting crew performance efficiency data;

[1658] A means for pre-processing the collected data to extract necessary information and remove outliers;

[1659] Based on the pre-processed data, a shift planning method is used to identify busy and slow periods in stores using AI models and determine appropriate crew allocation.

[1660] A means of displaying the designed shifts to the crew;

[1661] A means for receiving a shift adjustment request from a crew member and readjusting the shift in accordance with the request;

[1662] A means to collect feedback on crew performance and reflect it in the next shift design,

[1663] A system including:

[1664] (Claim 2)

[1665] The system of claim 1 further includes means for learning a shift design method using a generative AI model based on the preprocessed data and predicting busy and slow seasons for the store based on the learning results.

[1666] (Claim 3)

[1667] The system of claim 1 further comprises means for assigning crew members with high operational efficiency during busy periods based on the skill level and work experience of the crew members, and for training new crew members and recommending crew members take vacation during slow periods.

[1668] "Application Example 1"

[1669] (Claim 1)

[1670] a means for collecting store operation status data;

[1671] a means for collecting worker productivity data;

[1672] a means for pre-processing the collected data;

[1673] A means of identifying busy and slow periods in stores and designing shifts using pre-processed data;

[1674] a means for notifying workers of the designed shift;

[1675] a means for receiving a shift adjustment request from a worker and readjusting the shift;

[1676] A method to feed back actual operational results and reflect them in the next shift design,

[1677] a means for readjusting shifts based on feedback data collected from an application installed on a smartphone, smart glasses, a head-mounted display, or a robot;

[1678] A system including:

[1679] (Claim 2)

[1680] The method further includes a means for training a generative AI model based on the preprocessed data and using the training results to predict busy and slow seasons for the store.

[1681] 10. The system of claim 1.

[1682] (Claim 3)

[1683] Further, measures are included to assign appropri...

Claims

1. a means for collecting store operation status data; a means for collecting crew productivity data; a means for pre-processing the collected data; A means of identifying busy and slow periods in stores and designing shifts using pre-processed data; A means of informing crews of the planned shifts; A means of receiving crew member requests for shift adjustments and rearranging shifts; A method to feed back actual operational results and reflect them in the next shift design, A system including:

2. The system of claim 1 further comprising means for training an AI model based on the preprocessed data and predicting busy and slow seasons for the store using the training results.

3. The system according to claim 1, further comprising means for allocating appropriate crew members during busy periods based on the skill level and years of experience of the crew members, and for recommending training of new crew members and taking vacations for crew members during slow periods.

Images