system

Abstract

We provide the system. [Solution] A means for acquiring video data and analyzing the location of workers within the office, A means for designing the optimal traffic flow based on the above analysis results, A means of outputting the designed movement flow information, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Problems such as inefficiency in the movement lines of workers at business offices, inappropriate staffing, productivity decline caused by poor service in customer response, and lack of customer satisfaction have become issues. To solve this problem, optimization of real-time movement lines and work processes, effective staffing, and service provision based on understanding the emotions of customers are required.

Means for Solving the Problems

[0005] This invention provides a system that acquires video data to analyze the location of workers within a business office and designs the optimal movement patterns for workers based on the analysis results. Furthermore, it uses past external data to predict future personnel demand and optimizes personnel allocation based on the prediction results. The system also includes means for estimating customer emotions using video and audio data and generating appropriate response suggestions based on the estimation results.

[0006] "Video data" refers to a collection of continuous video information gathered by cameras and other video acquisition devices.

[0007] "Business office" refers to the physical location where business is conducted, including facilities for employees to perform their duties.

[0008] "Workers" refers to personnel employed within a business office to perform specific tasks.

[0009] "Means for analyzing location" refers to technical means for identifying the location of a specific object or person from acquired video data and processing that location information.

[0010] "Movement flow" refers to the routes that workers and customers take when moving around within a business premises.

[0011] "Means for designing movement paths" refers to technical means that optimize the movement paths of workers based on the results of positional analysis and set efficient routes.

[0012] "Means of output" refers to technical means for providing analysis results and design information to users visually or audibly.

[0013] "External data" refers to external environmental information such as weather information and past sales records, rather than data from within the sales office.

[0014] "Means of predicting personnel demand" refers to technical means of using external data to predict future personnel deployment needs.

[0015] The "means for optimizing personnel allocation" refers to technical means for planning an effective allocation according to the predicted personnel demand.

[0016] The "video and audio data" refers to the general term for information related to vision and hearing obtained using devices such as cameras and microphones.

[0017] The "means for estimating customer sentiment" refers to technical means for analyzing and judging the psychological state of customers based on video and audio data.

[0018] The "means for generating response plans" refers to technical means for devising appropriate customer service strategies based on the estimated customer sentiment.

Brief Description of Drawings

[0019] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9]Shows an emotion map to which a plurality of emotions are mapped. [Figure 10] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be described.

[0022] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] This invention provides a system for improving the operational efficiency of sales offices. The system mainly consists of three elements: a server, a terminal, and a user.

[0041] The server first acquires real-time video data from surveillance cameras within the store. Based on the video data, the server uses an image recognition algorithm to analyze the location of workers. Based on the analysis results, the server uses an AI model to design the optimal movement path and transmits this information to the employee's terminal. This movement path information supports the efficient execution of tasks. In addition, the server uses accumulated historical sales data and external weather data to predict future personnel demand using an AI model. The prediction results are transmitted to the administrator's terminal and used to optimize appropriate personnel allocation.

[0042] Furthermore, the server analyzes audio and video data from within the store to estimate customer emotions. Based on customer emotions, the server generates appropriate services and suggestions and issues instructions to the terminals held by the store staff. This function enables store staff to provide customers with appropriate and highly satisfying service.

[0043] The terminal provides information to workers and managers according to the workflow, staffing, and customer service instructions received from the server. By clearly communicating instructions visually or audibly, users can perform their tasks smoothly.

[0044] The user (worker) performs their duties according to the optimal workflow within the office based on instructions from the terminal. Furthermore, in customer service, they provide highly satisfactory service to customers based on directions provided by the terminal. Managers optimize on-site staffing by referring to shift suggestions from the terminal.

[0045] For example, if a queue is expected during lunchtime, the server predicts the peak time based on past data and notifies the terminal of the appropriate staffing levels, allowing managers to strategically allocate staff. Furthermore, new staff can receive real-time updates on traffic flow instructions from the terminal, enabling efficient work even in short periods. If a customer appears anxious, the server analyzes their emotions and prompts the staff via the terminal to ask, "Are you having any trouble?" This facilitates prompt customer support.

[0046] In this way, this system can maximize operational efficiency within sales offices and improve customer satisfaction.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server collects video data in real time from cameras installed within the store. This video data is used to understand the situation inside the store and the location of workers.

[0050] Step 2:

[0051] The server applies an image recognition algorithm based on the collected video data to analyze the worker's current location. This analysis visualizes the worker's movements and path.

[0052] Step 3:

[0053] The server identifies inefficiencies in existing traffic flow based on the analysis results. Furthermore, it uses an AI model to design the optimal traffic flow and sends it as instructions to the store staff's terminals.

[0054] Step 4:

[0055] The terminal displays movement instructions transmitted from the server to the worker visually and audibly. This allows store employees to proceed with their work according to the optimized movement path in real time.

[0056] Step 5:

[0057] The server uses sales data and external data such as weather information to predict future peak times using an AI model. This prediction is useful for analyzing staffing needs.

[0058] Step 6:

[0059] The server sends predicted peak time information and staffing schedules to the administrator's terminal. This allows the administrator to create appropriate shifts.

[0060] Step 7:

[0061] The server acquires customer voice and video data and uses an AI model to estimate emotions. This process analyzes the customer's facial expressions and tone of voice.

[0062] Step 8:

[0063] The server generates service suggestions tailored to the customer's emotions and sends them to the employee's terminal. These suggestions include specific actions and phrases.

[0064] Step 9:

[0065] The terminal transmits service suggestions to the staff, who then provide the appropriate service to the customer. The user (staff) uses the presented information to provide high-quality customer service.

[0066] (Example 1)

[0067] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0068] Modern commercial facilities and offices require optimized worker workflows, efficient staffing, and rapid customer service. However, these processes have traditionally relied heavily on human experience and judgment, making it difficult to consistently provide optimal responses tailored to individual situations. Furthermore, accurately understanding customer emotions and providing immediate, appropriate service also demands advanced response skills. To address these challenges, more automated systems are necessary.

[0069] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0070] In this invention, the server includes means for acquiring video information and analyzing the location of workers within a facility; means for designing an optimal route based on the analysis results; means for presenting the designed route information; means for predicting the personnel needs at any given time using past statistical information; means for adjusting personnel deployment based on the prediction results; means for estimating customer emotions using sound and video information; and means for generating appropriate countermeasures based on the estimation results. This enables efficient management of worker movement and optimization of personnel allocation, as well as the provision of prompt and appropriate services to customers.

[0071] "Video information" refers to all information, including video data and related still images, acquired within the facility.

[0072] "Workers" refers to individuals whose movement patterns within a facility are optimized in order to perform their duties.

[0073] "Location" refers to information used to identify the current physical position of a worker or object.

[0074] A "route" refers to the optimal travel path designed to allow workers to move efficiently.

[0075] "Statistical information" refers to all data, including past business data and external environmental information, and is used for future analysis and predictions.

[0076] "Necessity" refers to the degree to which the personnel and resources required to carry out the work are present.

[0077] "Deployment" refers to appropriately allocating personnel and resources according to anticipated needs.

[0078] "Audio information" refers to information that includes audio data, specifically audio records related to customer service and facility operations.

[0079] "Emotions" refers to information estimated to understand a customer's psychological state and is used to generate countermeasures.

[0080] "Countermeasures" refer to services or methods of dealing with customers based on their perceived emotions.

[0081] This invention aims to build a system for improving work efficiency within commercial facilities and offices. The system mainly consists of three components: a server, a terminal, and a user.

[0082] The server acquires video information in real time using multiple sensors and cameras installed within the facility and analyzes the location of workers using image processing software. Useful image processing tools include "OpenCV." Based on this recognized information, the server designs the optimal route using generative AI models such as "TENSORFLOW®." This route information is immediately delivered to a mobile device and presented visually to the user.

[0083] The server also retrieves historical statistical information from a database and uses machine learning libraries such as "scikit-learn" to predict staffing needs. Based on the prediction results, an appropriate staffing plan is created and notified to the management terminal. For example, if additional staff are needed during lunchtime, the server sends that information to the terminal to help users respond quickly.

[0084] Furthermore, the server acquires sound information from within the facility and analyzes it using speech recognition technologies such as "Google® Speech-to-Text." Combined with video information, it employs sentiment analysis tools such as "IBM Watson®" to estimate customer emotions. The AI ​​generates suggested solutions based on the customer's needs, and these suggestions are displayed as instructions on the employee's terminal. This function allows the employee to provide services that meet customer needs in real time.

[0085] Examples of prompt messages include specific instructions such as, "Analyze video data within the sales office and design the optimal workflow for workers," or "Predict future staffing needs and generate information to be sent to terminals." This enables efficient sales management and customer service.

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The server acquires video information in real time from sensors and cameras within the facility. This video information is first stored in a database as raw data. The server uses "OpenCV" to detect workers in the video and determine their location. This analysis process outputs the location information of the workers.

[0089] Step 2:

[0090] The server uses the location information of the worker identified in Step 1 as input and generates the optimal route using an AI model such as "TensorFlow". The model designs the route taking into account the facility layout and current congestion. The resulting route information is then ready to be sent to the terminal.

[0091] Step 3:

[0092] The terminal receives routing information from the server. This routing information is visually displayed on the screen to instruct the worker on how to proceed. By using an audio alert system in conjunction with this, it is possible to convey instructions to the user through both sight and sound.

[0093] Step 4:

[0094] The server retrieves statistical information such as historical sales data and weather information from a database and uses the machine learning model "scikit-learn" to predict future staffing needs. The data used as input is historical time-series data, and the output presents staffing needs for each time period.

[0095] Step 5:

[0096] The server transmits the personnel demand forecast information obtained in step 4 to the management terminal. The management terminal can then refer to this personnel allocation information to plan appropriate shifts. This enables efficient personnel allocation.

[0097] Step 6:

[0098] The server uses audio and video information to estimate the customer's emotions. It converts the audio information to text using "Google Speech-to-Text" and then performs emotion analysis using "IBM Watson." This analysis outputs the customer's emotion data.

[0099] Step 7:

[0100] The server generates a response plan based on the customer sentiment data obtained in step 6. This response plan is sent to the employee's terminal as a service or product suggestion, allowing the employee to respond to the customer quickly based on it.

[0101] (Application Example 1)

[0102] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0103] Modern facilities demand improved work efficiency and optimized staffing, but adequate means to achieve these goals are not yet fully established. In particular, the optimization of worker and equipment movement, as well as the management of worker stress, are insufficient, hindering efficient operation. Traditional methods fail to fully utilize the vast amount of data within the facility, making it difficult to provide optimal instructions in real time.

[0104] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0105] In this invention, the server includes means for acquiring video information and analyzing the position of workers within the facility, means for designing an optimal movement path based on the analysis results, means for outputting the designed movement path information, and means for optimizing the movement of work equipment based on the analysis of the information. This makes it possible to efficiently arrange workers and optimize their movement within the facility.

[0106] "Video information" refers to video data acquired within the facility, which is used to analyze the location and movements of workers.

[0107] "Within the facility" refers to the scope of the specific workspace or facility to which this invention applies, and is the scope of the analysis and optimization.

[0108] "Worker location" refers to the specific physical position of individual workers within the facility, and is analyzed from video information.

[0109] "Analysis" refers to the process of extracting specific information from acquired data and converting it into an understandable format.

[0110] A "movement route" refers to the optimal path that workers and work equipment should take when moving within a facility.

[0111] "Optimization" refers to the process of performing operations and making choices to achieve the most efficient state possible under certain conditions.

[0112] "Information analysis" refers to the process of deriving information useful for facility management and worker behavior based on collected data.

[0113] "Work equipment" refers to machinery and devices used to support specific tasks within a facility.

[0114] This invention is implemented primarily using a system configuration consisting of a server, a terminal, and a user. The server acquires video data in real time from surveillance cameras within the facility and uses OpenCV as image processing software to detect workers and work equipment frame by frame. The detected location information is used to design the optimal movement path using TensorFlow. This output is transferred to the terminal and notified to the worker via audio and visual means.

[0115] Furthermore, the server uses the pandas library to organize historical external information and statsmodels to forecast demand. Based on these forecast results, it sends the optimized worker allocation results to the terminal and provides information including appropriate break suggestions.

[0116] Furthermore, it has the ability to estimate the emotions of workers and customers using the Azure® Emotion API by analyzing video and audio data. Based on the obtained emotion data, the terminal provides instructions from the server regarding the need to interrupt work. This means that work within the facility can be streamlined and users can be responded to quickly.

[0117] As a concrete example, during peak hours at a logistics center, optimizing transport routes can shorten working time, and staff allocation can be optimized to meet high demand predicted from past shipping data. Furthermore, it can detect increases in workers' stress levels using emotional data and promptly suggest breaks.

[0118] An example of a prompt message that can be used is: "Based on shipping data from the past month and this week's weather forecast, there is a possibility of increased shipping volume from 2pm to 4pm next Monday. Please increase staff to accommodate this time."

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server acquires real-time video data from surveillance cameras within the facility and analyzes this data frame by frame using the OpenCV library. It detects the positions of workers and work equipment using an image recognition algorithm and outputs their location information. This information is used to optimize worker movement.

[0122] Step 2:

[0123] The server inputs the worker's location information obtained from Step 1 into a generative AI model using TensorFlow to design the optimal movement path. This generated movement path information is output to the terminal as an optimized movement route. As a result, the worker receives efficient movement guidance.

[0124] Step 3:

[0125] The server uses the pandas library to organize historical external information (sales data and weather information) from input and uses statsmodels to predict personnel demand for a given period. This prediction result is output to the terminal and used as foundational information to optimize worker allocation.

[0126] Step 4:

[0127] The server utilizes the Azure Emotion API to analyze audio and video data acquired within the facility as input, and estimates the emotions of workers and customers. Based on the emotion analysis results, it generates instructions for necessary work interruptions and appropriate response suggestions, and outputs them to the terminal. This allows workers to quickly manage stress and handle customer interactions.

[0128] Step 5:

[0129] The user, acting as the worker, performs their daily tasks based on movement route information and personnel allocation optimization instructions output from the terminal. They also receive notifications of sentiment analysis results, which they use to adjust their work and improve customer service. This results in the provision of efficient and highly customer-satisfying services.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] The system in this invention combines optimized worker movement and personnel demand forecasting with an emotion engine that analyzes user emotions to improve service quality, in order to improve work efficiency and customer satisfaction at sales offices. This system is realized through the interaction of a server, terminals, and users.

[0132] The server first collects video data from cameras installed at the sales office and analyzes the workers' locations in real time. Based on this analysis, the server uses AI to design the optimal movement patterns and transmits this information to the workers' terminals. This allows workers to perform their tasks efficiently. In addition, the server uses historical sales data and external environmental data stored in the database to predict personnel demand using an AI model and notifies managers' terminals of the optimal personnel allocation plan.

[0133] Furthermore, this invention uses an emotion engine to recognize customer emotions. The server inputs video and audio data acquired through cameras and microphones within the store into the emotion engine to estimate the customer's emotions. Based on this, the server generates response suggestions and service improvement suggestions that correspond to the customer's emotions and provides them to the store employee's terminal. The store employee can then follow the instructions on the terminal to provide appropriate service to the customer and improve customer satisfaction.

[0134] As a concrete example, when a customer's face is captured by a camera in a store, the server analyzes the customer's facial expression. If the system determines that the customer appears confused, a message such as "They may need help" is displayed on the terminal along with specific examples of how to respond. Store staff then use this information to approach and assist the customer. This allows customers to receive prompt and appropriate assistance, leading to increased customer satisfaction.

[0135] In this manner, the present invention provides a system that further improves work efficiency and service quality within a business office.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The server collects video data in real time from cameras installed within the office. This data is used to identify the location of workers.

[0139] Step 2:

[0140] The server applies an image recognition algorithm to the collected video data to analyze the worker's position. This analysis allows for an understanding of the current movement patterns.

[0141] Step 3:

[0142] The server uses an AI model to design the optimal workflow based on the analysis results. The designed workflow information is then sent to the worker's terminal.

[0143] Step 4:

[0144] The terminal visually displays movement information received from the server to the worker. This allows the worker to move more efficiently.

[0145] Step 5:

[0146] The server uses accumulated historical sales data and external environmental data to predict future personnel demand using an AI model.

[0147] Step 6:

[0148] The server generates an optimized staffing plan based on the predicted personnel demand and notifies the administrator's terminal of this plan.

[0149] Step 7:

[0150] The terminal displays the staffing plan received from the server to the administrator, providing it as reference information for shift adjustments.

[0151] Step 8:

[0152] The server inputs video and audio data acquired from cameras and microphones within the sales office into an emotion engine to estimate the customer's emotions.

[0153] Step 9:

[0154] The server generates appropriate response suggestions and service improvement proposals based on the estimated customer's emotions and sends them to the employee's terminal.

[0155] Step 10:

[0156] The terminal displays generated response suggestions to store staff in real time, allowing them to use these suggestions to provide service to customers.

[0157] Step 11:

[0158] The user (store clerk) can improve customer satisfaction by responding to customers based on instructions from the terminal and providing appropriate service.

[0159] (Example 2)

[0160] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0161] To improve the efficiency of business activities and customer satisfaction at sales offices, it is necessary to optimize worker movement paths, optimize staffing, and provide appropriate services based on customer sentiment. However, achieving these requires real-time, highly accurate data analysis and the presentation of concrete improvement proposals based on that analysis, which conventional systems are unable to adequately address.

[0162] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0163] In this invention, the server includes means for collecting motion information using an image acquisition device and analyzing the user's position in the workspace, means for planning an optimal motion path using a generative model, and means for providing the planned motion path information to the user's display device. This makes it possible to analyze the worker's movements in real time and quickly provide a path that achieves optimal work efficiency.

[0164] An "image acquisition device" is a photographic device used to collect operational information within a business office.

[0165] "Motion information" refers to data related to the user's position and movement patterns within the workspace.

[0166] "Analysis" is the process of determining the user's location and actions based on the acquired data.

[0167] A "generative model" is an algorithm that uses artificial intelligence technology to plan and propose the optimal action path and response plan.

[0168] A "movement path" is an optimized route for workers to efficiently carry out their tasks.

[0169] A "display device" is a device used to provide users with planned information visually.

[0170] "Sales information" refers to commercial data related to past business activities.

[0171] "Environmental information" refers to data about external environmental factors.

[0172] "Job needs" refers to predicted information regarding the workload and required personnel within a sales office.

[0173] A "service proposal" is a suggestion for appropriate service based on the user's emotional state.

[0174] The embodiments for carrying out the present invention will be described below.

[0175] This system is designed to improve operational efficiency within sales offices and maximize customer satisfaction. Specifically, it is achieved through the interaction of servers, terminals, and users.

[0176] The server collects worker motion information using image acquisition devices installed at the branch office. For image processing, software libraries such as "OpenCV" are used to analyze the motion information. Furthermore, based on the analyzed data, a generative model is used to plan the optimal motion path. This generative model is implemented using machine learning frameworks such as "PyTorch" or "TensorFlow." The generated motion path information is provided in real time to the worker's display device, encouraging efficient work performance.

[0177] Furthermore, the server integrates and analyzes past sales and environmental data to create a model for predicting future job needs. This prediction uses predictive analytics libraries such as "scikit-learn" and "Keras," resulting in the provision of optimal job placement proposals to administrators.

[0178] Furthermore, for sentiment analysis, the server collects video and audio data from within the store and estimates the customer's emotional state using sentiment analysis APIs such as "Microsoft® Azure Cognitive Services". Based on this, a generative model generates appropriate response suggestions, which are then provided to the employee's display device.

[0179] For example, if a camera captures a customer's confused expression in a sales office, the server analyzes this information in real time and notifies the staff with a suggested response, such as, "The customer appears confused. They may need assistance." This allows staff to respond to customers quickly and appropriately, leading to improved customer satisfaction.

[0180] Examples of prompt messages include, "Based on the current worker's location data, please suggest a workflow that optimizes work efficiency," and "Based on customer sentiment data, please suggest an appropriate response method."

[0181] In this way, the present invention intelligently manages various elements within a sales office and aims to improve the overall business process.

[0182] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0183] Step 1:

[0184] The server collects video data from image acquisition devices installed at the branch office. This data is used to capture the movements of workers. The server uses the collected video data as input and analyzes the workers' positions in real time using image processing libraries such as "OpenCV". As a result of the analysis, the specific location information and movement patterns of the workers are output as text data.

[0185] Step 2:

[0186] The server uses the worker's location information obtained in Step 1 as input and utilizes a generating AI model. Specifically, it uses the prompt message "Based on the current worker's location data, please suggest a movement path that optimizes work efficiency" to generate the optimal route. The generating model outputs the optimized route, which is then sent to the worker's terminal. The terminal visually displays this route information to the user and suggests a new work route.

[0187] Step 3:

[0188] The server analyzes historical sales information and external environment information stored in the database. Analysis libraries such as "scikit-learn" and "Keras" are used for the analysis. This data is used as input to predict future job needs. The predicted personnel needs and placement plans are output and notified to the administrator's terminal. The administrator then adjusts the personnel plan based on this information.

[0189] Step 4:

[0190] The server acquires video and audio data through cameras and microphones within the store and analyzes customer emotions using APIs such as "Microsoft Azure Cognitive Services". This data is used to understand the user's emotional state, and the analysis results output emotion evaluation data. The server inputs this emotion data into a generative model and generates appropriate response suggestions using the prompt message "Based on the customer's emotion data, please suggest an appropriate response method". The generated response suggestions are output to the terminal, providing instructions to the store staff. The store staff then handles customer interactions according to these instructions.

[0191] In each step, the server, terminal, and user collect, analyze, optimize, and display data based on their respective roles, aiming to improve operational efficiency within the sales office and enhance customer satisfaction.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] In modern work environments and customer service, there is a demand for quick and accurate responses to diverse customer needs. However, traditional systems have struggled to properly understand customer emotions and provide services accordingly. Furthermore, optimizing worker movement and staffing to improve operational efficiency is necessary, but achieving this in real time is also a challenging task.

[0195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0196] In this invention, the server includes means for acquiring visual and auditory information and analyzing the location of personnel within the work environment; means for designing an optimal movement path based on the analysis results; means for outputting the designed movement path information; means for estimating emotions based on a person's facial expressions and voice and generating response plans adapted to the visitor's emotions; means for outputting the generated response plans; means for predicting future personnel demand using previous external information; means for optimizing personnel allocation based on the prediction results; means for outputting the allocation information; and means for reporting customer service advice based on emotion analysis results in real time. This enables the provision of highly accurate services tailored to customer emotions and improves operational efficiency.

[0197] "Visual and auditory information" refers to the collective term for visual and audio data acquired using cameras and microphones.

[0198] "Means for analyzing the position of personnel within a work environment" refers to technologies that use visual information to detect and recognize the current position and movement of people within a work space.

[0199] "Methods for designing optimal travel routes" refers to a technology that calculates and proposes a route that allows workers to move efficiently, based on analysis results.

[0200] "Means for outputting designed travel path information" refers to methods or technologies for visually or audibly presenting the calculated optimal travel path to the worker.

[0201] "Means for estimating emotions based on a person's facial expressions and voice" refers to a technology that analyzes an individual's facial expressions and tone of voice to estimate their emotional state.

[0202] "Methods for generating response plans adapted to the visitor's emotions" refers to techniques that take estimated emotions into consideration and create appropriate countermeasures and customer service plans for that situation.

[0203] "Means for outputting generated response plans" refers to methods for displaying or communicating the created customer service plans to relevant staff or terminals.

[0204] "Methods for predicting future personnel demand using past external information" refers to techniques that statistically predict future personnel allocation needs using past data and external insights.

[0205] "Methods for optimizing staffing" refer to techniques for planning the optimal staffing arrangement based on predicted staffing needs.

[0206] A "means for outputting deployment information" refers to a mechanism for informing stakeholders and related systems of the details of the planned personnel deployment.

[0207] "A method for reporting customer service advice based on emotion analysis results in real time" refers to a technology that immediately communicates areas for improvement and recommended actions for customer service to the person in charge, based on the results of emotion analysis.

[0208] The system realizing this invention is designed to optimize personnel location, movement paths, customer sentiment, and staffing within a work environment using visual and auditory information. The server utilizes cameras and microphones to acquire video and audio from within the store. This allows for the analysis of worker and customer locations and the design of optimal movement paths. Software such as OpenCV and TensorFlow are used in this process.

[0209] The server also analyzes facial and audio data extracted from the video to estimate the customer's emotions. Based on the results obtained by the emotion engine, it generates service suggestions tailored to the customer's needs and notifies store staff via smart devices. Firebase is used for real-time notifications.

[0210] Users can visually receive these customer service suggestions through smart glasses or smartphones and respond immediately. For example, if the system determines that a customer is confused, the smart glasses display will show a message saying, "The customer may need help. Please speak to them."

[0211] The server further predicts future staffing needs based on past sales and customer data. Data analysis using Pandas and Scikit-learn optimizes staffing in real time. As a result, store managers can allocate staff efficiently. For example, it can predict staff shortages during peak seasons like the end of the year and take appropriate measures.

[0212] Example prompt: "Based on the latest sentiment analysis data, generate advice on recommended customer service actions when a customer's smile is detected."

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The server acquires video and audio data from inside the store via cameras and microphones. It receives this data as input and performs image analysis using OpenCV. The output is location information of workers and visitors. This location information is stored in a database.

[0216] Step 2:

[0217] The server uses TensorFlow to design the optimal travel path based on the location information obtained in Step 1. This design also takes into account past travel patterns and the store's layout. The server then generates the calculated travel path as output and prepares it for transmission to the smart device.

[0218] Step 3:

[0219] The server extracts facial expressions from video data and processes audio data to estimate the customer's emotions using an emotion engine. Inputs include specific facial patterns and voice tone, and the output is an estimated emotional state. Based on this, the server determines whether the customer is confused or satisfied.

[0220] Step 4:

[0221] The server uses a generative AI model, based on the estimated emotional state, to generate appropriate customer service suggestions for customers according to the prompt text. The input is the emotional state and standard customer service protocols, and the output is a specific response suggestion.

[0222] Step 5:

[0223] The server sends the generated customer service suggestions to the device via Firebase. The user receives the suggestions through smart glasses or a smartphone display and responds to the customer based on them. Here, the device receives input (receives the customer service suggestions) and presents them as visual output.

[0224] Step 6:

[0225] The server uses Pandas and Scikit-learn to analyze historical sales and customer data to predict future staffing needs. Historical datasets are used as input, and the output provides the number of staff required for the next shift. This output is sent to the administrator's terminal to help optimize staffing.

[0226] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0227] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0228] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0232] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0233] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0234] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0235] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0236] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0237] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0238] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0239] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0240] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0241] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0242] This invention provides a system for improving the operational efficiency of sales offices. The system mainly consists of three elements: a server, a terminal, and a user.

[0243] The server first acquires real-time video data from surveillance cameras within the store. Based on the video data, the server uses an image recognition algorithm to analyze the location of workers. Based on the analysis results, the server uses an AI model to design the optimal movement path and transmits this information to the employee's terminal. This movement path information supports the efficient execution of tasks. In addition, the server uses accumulated historical sales data and external weather data to predict future personnel demand using an AI model. The prediction results are transmitted to the administrator's terminal and used to optimize appropriate personnel allocation.

[0244] Furthermore, the server analyzes audio and video data from within the store to estimate customer emotions. Based on customer emotions, the server generates appropriate services and suggestions and issues instructions to the terminals held by the store staff. This function enables store staff to provide customers with appropriate and highly satisfying service.

[0245] The terminal provides information to workers and managers according to the workflow, staffing, and customer service instructions received from the server. By clearly communicating instructions visually or audibly, users can perform their tasks smoothly.

[0246] The user (worker) performs their duties according to the optimal workflow within the office based on instructions from the terminal. Furthermore, in customer service, they provide highly satisfactory service to customers based on directions provided by the terminal. Managers optimize on-site staffing by referring to shift suggestions from the terminal.

[0247] For example, if a queue is expected during lunchtime, the server predicts the peak time based on past data and notifies the terminal of the appropriate staffing levels, allowing managers to strategically allocate staff. Furthermore, new staff can receive real-time updates on traffic flow instructions from the terminal, enabling efficient work even in short periods. If a customer appears anxious, the server analyzes their emotions and prompts the staff via the terminal to ask, "Are you having any trouble?" This facilitates prompt customer support.

[0248] In this way, this system can maximize operational efficiency within sales offices and improve customer satisfaction.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The server collects video data in real time from cameras installed within the store. This video data is used to understand the situation inside the store and the location of workers.

[0252] Step 2:

[0253] The server applies an image recognition algorithm based on the collected video data to analyze the worker's current location. This analysis visualizes the worker's movements and path.

[0254] Step 3:

[0255] The server identifies inefficiencies in existing traffic flow based on the analysis results. Furthermore, it uses an AI model to design the optimal traffic flow and sends it as instructions to the store staff's terminals.

[0256] Step 4:

[0257] The terminal displays movement instructions transmitted from the server to the worker visually and audibly. This allows store employees to proceed with their work according to the optimized movement path in real time.

[0258] Step 5:

[0259] The server uses sales data and external data such as weather information to predict future peak times using an AI model. This prediction is useful for analyzing staffing needs.

[0260] Step 6:

[0261] The server sends predicted peak time information and staffing schedules to the administrator's terminal. This allows the administrator to create appropriate shifts.

[0262] Step 7:

[0263] The server acquires customer voice and video data and uses an AI model to estimate emotions. This process analyzes the customer's facial expressions and tone of voice.

[0264] Step 8:

[0265] The server generates service suggestions tailored to the customer's emotions and sends them to the employee's terminal. These suggestions include specific actions and phrases.

[0266] Step 9:

[0267] The terminal transmits service suggestions to the staff, who then provide the appropriate service to the customer. The user (staff) uses the presented information to provide high-quality customer service.

[0268] (Example 1)

[0269] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0270] Modern commercial facilities and offices require optimized worker workflows, efficient staffing, and rapid customer service. However, these processes have traditionally relied heavily on human experience and judgment, making it difficult to consistently provide optimal responses tailored to individual situations. Furthermore, accurately understanding customer emotions and providing immediate, appropriate service also demands advanced response skills. To address these challenges, more automated systems are necessary.

[0271] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0272] In this invention, the server includes means for acquiring video information and analyzing the location of workers within a facility; means for designing an optimal route based on the analysis results; means for presenting the designed route information; means for predicting the personnel needs at any given time using past statistical information; means for adjusting personnel deployment based on the prediction results; means for estimating customer emotions using sound and video information; and means for generating appropriate countermeasures based on the estimation results. This enables efficient management of worker movement and optimization of personnel allocation, as well as the provision of prompt and appropriate services to customers.

[0273] "Video information" refers to all information, including video data and related still images, acquired within the facility.

[0274] "Workers" refers to individuals whose movement patterns within a facility are optimized in order to perform their duties.

[0275] "Location" refers to information used to identify the current physical position of a worker or object.

[0276] A "route" refers to the optimal travel path designed to allow workers to move efficiently.

[0277] "Statistical information" refers to all data, including past business data and external environmental information, and is used for future analysis and predictions.

[0278] "Necessity" refers to the degree to which the personnel and resources required to carry out the work are present.

[0279] "Deployment" refers to appropriately allocating personnel and resources according to anticipated needs.

[0280] "Audio information" refers to information that includes audio data, specifically audio records related to customer service and facility operations.

[0281] "Emotion" refers to the information estimated to grasp the psychological state of customers and is used to generate countermeasures.

[0282] "Countermeasure" refers to the services or handling methods provided based on the estimated emotions of customers.

[0283] In this invention, a system for improving work efficiency in commercial facilities or business offices is constructed. The system mainly consists of three components: a server, a terminal, and a user.

[0284] The server acquires video information in real time using a plurality of sensors and camera devices installed in the facility, and analyzes the location of workers by utilizing image processing software. As the technology to be used, image processing tools such as "OpenCV" are useful. Based on this recognized information, the server uses a generative AI model such as "TensorFlow" to design an optimal route. This route information is immediately distributed to the portable terminal and visually presented to the user.

[0285] In addition, the server acquires past statistical information from the database and predicts the personnel requirements using a machine learning library such as "scikit-learn". Based on the prediction results, an appropriate personnel deployment is planned and notified to the management terminal. For example, when additional personnel are required during lunchtime, the server sends that information to the terminal to assist the user in responding quickly.

[0286] Furthermore, the server acquires the sound information in the facility and analyzes it using speech recognition technology such as "Google Speech-to-Text". In combination with the video information, an emotion analysis tool such as "IBM Watson" is adopted to estimate the emotions of customers. The countermeasures required by the customers are generated by AI, and the proposal is displayed as an instruction on the store staff terminal. With this function, the user, who is a store staff, can provide services in real time according to the needs of the customers.

[0287] Examples of prompt messages include specific instructions such as, "Analyze video data within the sales office and design the optimal workflow for workers," or "Predict future staffing needs and generate information to be sent to terminals." This enables efficient sales management and customer service.

[0288] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0289] Step 1:

[0290] The server acquires video information in real time from sensors and cameras within the facility. This video information is first stored in a database as raw data. The server uses "OpenCV" to detect workers in the video and determine their location. This analysis process outputs the location information of the workers.

[0291] Step 2:

[0292] The server uses the location information of the worker identified in Step 1 as input and generates the optimal route using an AI model such as "TensorFlow". The model designs the route taking into account the facility layout and current congestion. The resulting route information is then ready to be sent to the terminal.

[0293] Step 3:

[0294] The terminal receives routing information from the server. This routing information is visually displayed on the screen to instruct the worker on how to proceed. By using an audio alert system in conjunction with this, it is possible to convey instructions to the user through both sight and sound.

[0295] Step 4:

[0296] The server retrieves statistical information such as historical sales data and weather information from a database and uses the machine learning model "scikit-learn" to predict future staffing needs. The data used as input is historical time-series data, and the output presents staffing needs for each time period.

[0297] Step 5:

[0298] The server transmits the personnel demand forecast information obtained in step 4 to the management terminal. The management terminal can then refer to this personnel allocation information to plan appropriate shifts. This enables efficient personnel allocation.

[0299] Step 6:

[0300] The server uses audio and video information to estimate the customer's emotions. It converts the audio information to text using "Google Speech-to-Text" and then performs emotion analysis using "IBM Watson." This analysis outputs the customer's emotion data.

[0301] Step 7:

[0302] The server generates a response plan based on the customer sentiment data obtained in step 6. This response plan is sent to the employee's terminal as a service or product suggestion, allowing the employee to respond to the customer quickly based on it.

[0303] (Application Example 1)

[0304] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0305] In modern facilities, there is a demand for improved work efficiency and optimized personnel allocation, but appropriate means to achieve these have not been fully established. In particular, the optimization of the movement routes of workers and work devices, as well as the stress management of workers, are insufficient, hindering efficient operation. With conventional methods, there is a problem that the vast amount of data within the facility cannot be fully utilized, and it is difficult to give optimal instructions in real time.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0307] In this invention, the server includes means for acquiring video information and analyzing the positions of workers within the facility, means for designing an optimal movement route based on the above analysis results, means for outputting the designed movement route information, and means for optimizing the movement route of the work device based on the analysis of the information. Thereby, it becomes possible to achieve efficient allocation of workers and optimization of movement routes within the facility.

[0308] "Video information" refers to video data acquired within the facility and is used for analyzing the positions and movements of workers.

[0309] "Within the facility" refers to the scope of a specific working space or facility to which this invention is applied and is the target scope for analysis and optimization.

[0310] "The position of the worker" refers to the specific physical position of each worker within the facility and is analyzed from the video information.

[0311] "Analysis" refers to the process of extracting specific information based on the acquired data and converting it into an understandable form.

[0312] "Movement route" refers to the optimal route that workers and work devices should take when moving within the facility.

[0313] "Optimization" refers to the process of performing operations and selections to achieve the most efficient state possible under certain conditions.

[0314] "Information analysis" refers to the process of deriving information useful for facility management and worker behavior based on collected data.

[0315] "Work equipment" refers to machinery and devices used to support specific tasks within a facility.

[0316] This invention is implemented primarily using a system configuration consisting of a server, a terminal, and a user. The server acquires video data in real time from surveillance cameras within the facility and uses OpenCV as image processing software to detect workers and work equipment frame by frame. The detected location information is used to design the optimal movement path using TensorFlow. This output is transferred to the terminal and notified to the worker via audio and visual means.

[0317] Furthermore, the server uses the pandas library to organize historical external information and statsmodels to forecast demand. Based on these forecast results, it sends the optimized worker allocation results to the terminal and provides information including appropriate break suggestions.

[0318] Furthermore, it has the ability to estimate the emotions of workers and customers using the Azure Emotion API by analyzing video and audio data. Based on the obtained emotion data, the terminal provides instructions from the server regarding the need to interrupt work. This means that work can be streamlined within the facility and a rapid response to the emotions of users can be made.

[0319] As a concrete example, during peak hours at a logistics center, optimizing transport routes can shorten working time, and staff allocation can be optimized to meet high demand predicted from past shipping data. Furthermore, it can detect increases in workers' stress levels using emotional data and promptly suggest breaks.

[0320] An example of a prompt message that can be used is: "Based on shipping data from the past month and this week's weather forecast, there is a possibility of increased shipping volume from 2pm to 4pm next Monday. Please increase staff to accommodate this time."

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The server acquires real-time video data from surveillance cameras within the facility and analyzes this data frame by frame using the OpenCV library. It detects the positions of workers and work equipment using an image recognition algorithm and outputs their location information. This information is used to optimize worker movement.

[0324] Step 2:

[0325] The server inputs the worker's location information obtained from Step 1 into a generative AI model using TensorFlow to design the optimal movement path. This generated movement path information is output to the terminal as an optimized movement route. As a result, the worker receives efficient movement guidance.

[0326] Step 3:

[0327] The server uses the pandas library to organize historical external information (sales data and weather information) from input and uses statsmodels to predict personnel demand for a given period. This prediction result is output to the terminal and used as foundational information to optimize worker allocation.

[0328] Step 4:

[0329] The server utilizes the Azure Emotion API to analyze audio and video data acquired within the facility as input, and estimates the emotions of workers and customers. Based on the emotion analysis results, it generates instructions for necessary work interruptions and appropriate response suggestions, and outputs them to the terminal. This allows workers to quickly manage stress and handle customer interactions.

[0330] Step 5:

[0331] The user, acting as the worker, performs their daily tasks based on movement route information and personnel allocation optimization instructions output from the terminal. They also receive notifications of sentiment analysis results, which they use to adjust their work and improve customer service. This results in the provision of efficient and highly customer-satisfying services.

[0332] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0333] The system in this invention combines optimized worker movement and personnel demand forecasting with an emotion engine that analyzes user emotions to improve service quality, in order to improve work efficiency and customer satisfaction at sales offices. This system is realized through the interaction of a server, terminals, and users.

[0334] The server first collects video data from cameras installed at the sales office and analyzes the workers' locations in real time. Based on this analysis, the server uses AI to design the optimal movement patterns and transmits this information to the workers' terminals. This allows workers to perform their tasks efficiently. In addition, the server uses historical sales data and external environmental data stored in the database to predict personnel demand using an AI model and notifies managers' terminals of the optimal personnel allocation plan.

[0335] Furthermore, this invention uses an emotion engine to recognize customer emotions. The server inputs video and audio data acquired through cameras and microphones within the store into the emotion engine to estimate the customer's emotions. Based on this, the server generates response suggestions and service improvement suggestions that correspond to the customer's emotions and provides them to the store employee's terminal. The store employee can then follow the instructions on the terminal to provide appropriate service to the customer and improve customer satisfaction.

[0336] As a concrete example, when a customer's face is captured by a camera in a store, the server analyzes the customer's facial expression. If the system determines that the customer appears confused, a message such as "They may need help" is displayed on the terminal along with specific examples of how to respond. Store staff then use this information to approach and assist the customer. This allows customers to receive prompt and appropriate assistance, leading to increased customer satisfaction.

[0337] In this manner, the present invention provides a system that further improves work efficiency and service quality within a business office.

[0338] The following describes the processing flow.

[0339] Step 1:

[0340] The server collects video data in real time from cameras installed within the office. This data is used to identify the location of workers.

[0341] Step 2:

[0342] The server applies an image recognition algorithm to the collected video data to analyze the worker's position. This analysis allows for an understanding of the current movement patterns.

[0343] Step 3:

[0344] The server uses an AI model to design the optimal workflow based on the analysis results. The designed workflow information is then sent to the worker's terminal.

[0345] Step 4:

[0346] The terminal visually displays movement information received from the server to the worker. This allows the worker to move more efficiently.

[0347] Step 5:

[0348] The server uses accumulated historical sales data and external environmental data to predict future personnel demand using an AI model.

[0349] Step 6:

[0350] The server generates an optimized staffing plan based on the predicted personnel demand and notifies the administrator's terminal of this plan.

[0351] Step 7:

[0352] The terminal displays the staffing plan received from the server to the administrator, providing it as reference information for shift adjustments.

[0353] Step 8:

[0354] The server inputs video and audio data acquired from cameras and microphones within the sales office into an emotion engine to estimate the customer's emotions.

[0355] Step 9:

[0356] The server generates appropriate response suggestions and service improvement proposals based on the estimated customer's emotions and sends them to the employee's terminal.

[0357] Step 10:

[0358] The terminal displays generated response suggestions to store staff in real time, allowing them to use these suggestions to provide service to customers.

[0359] Step 11:

[0360] The user (store clerk) can improve customer satisfaction by responding to customers based on instructions from the terminal and providing appropriate service.

[0361] (Example 2)

[0362] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0363] To improve the efficiency of business activities and customer satisfaction at sales offices, it is necessary to optimize worker movement paths, optimize staffing, and provide appropriate services based on customer sentiment. However, achieving these requires real-time, highly accurate data analysis and the presentation of concrete improvement proposals based on that analysis, which conventional systems are unable to adequately address.

[0364] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0365] In this invention, the server includes means for collecting motion information using an image acquisition device and analyzing the user's position in the workspace, means for planning an optimal motion path using a generative model, and means for providing the planned motion path information to the user's display device. This makes it possible to analyze the worker's movements in real time and quickly provide a path that achieves optimal work efficiency.

[0366] An "image acquisition device" is a photographic device used to collect operational information within a business office.

[0367] "Motion information" refers to data related to the user's position and movement patterns within the workspace.

[0368] "Analysis" is the process of determining the user's location and actions based on the acquired data.

[0369] A "generative model" is an algorithm that uses artificial intelligence technology to plan and propose the optimal action path and response plan.

[0370] A "movement path" is an optimized route for workers to efficiently carry out their tasks.

[0371] A "display device" is a device used to provide users with planned information visually.

[0372] "Sales information" refers to commercial data related to past business activities.

[0373] "Environmental information" refers to data about external environmental factors.

[0374] "Job needs" refers to predicted information regarding the workload and required personnel within a sales office.

[0375] A "service proposal" is a suggestion for appropriate service based on the user's emotional state.

[0376] The embodiments for carrying out the present invention will be described below.

[0377] This system is designed to improve operational efficiency within sales offices and maximize customer satisfaction. Specifically, it is achieved through the interaction of servers, terminals, and users.

[0378] The server collects worker motion information using image acquisition devices installed at the branch office. For image processing, software libraries such as "OpenCV" are used to analyze the motion information. Furthermore, based on the analyzed data, a generative model is used to plan the optimal motion path. This generative model is implemented using machine learning frameworks such as "PyTorch" or "TensorFlow." The generated motion path information is provided in real time to the worker's display device, encouraging efficient work performance.

[0379] Furthermore, the server integrates and analyzes past sales and environmental data to create a model for predicting future job needs. This prediction uses predictive analytics libraries such as "scikit-learn" and "Keras," resulting in the provision of optimal job placement proposals to administrators.

[0380] Furthermore, for sentiment analysis, the server collects video and audio data from within the store and estimates the customer's emotional state using sentiment analysis APIs such as "Microsoft Azure Cognitive Services." Based on this, a generative model generates appropriate response suggestions, which are then provided to the employee's display device.

[0381] For example, if a camera captures a customer's confused expression in a sales office, the server analyzes this information in real time and notifies the staff with a suggested response, such as, "The customer appears confused. They may need assistance." This allows staff to respond to customers quickly and appropriately, leading to improved customer satisfaction.

[0382] Examples of prompt messages include, "Based on the current worker's location data, please suggest a workflow that optimizes work efficiency," and "Based on customer sentiment data, please suggest an appropriate response method."

[0383] In this way, the present invention intelligently manages various elements within a sales office and aims to improve the overall business process.

[0384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0385] Step 1:

[0386] The server collects video data from image acquisition devices installed at the branch office. This data is used to capture the movements of workers. The server uses the collected video data as input and analyzes the workers' positions in real time using image processing libraries such as "OpenCV". As a result of the analysis, the specific location information and movement patterns of the workers are output as text data.

[0387] Step 2:

[0388] The server uses the worker's location information obtained in Step 1 as input and utilizes a generating AI model. Specifically, it uses the prompt message "Based on the current worker's location data, please suggest a movement path that optimizes work efficiency" to generate the optimal route. The generating model outputs the optimized route, which is then sent to the worker's terminal. The terminal visually displays this route information to the user and suggests a new work route.

[0389] Step 3:

[0390] The server analyzes historical sales information and external environment information stored in the database. Analysis libraries such as "scikit-learn" and "Keras" are used for the analysis. This data is used as input to predict future job needs. The predicted personnel needs and placement plans are output and notified to the administrator's terminal. The administrator then adjusts the personnel plan based on this information.

[0391] Step 4:

[0392] The server acquires video and audio data through cameras and microphones within the store and analyzes customer emotions using APIs such as "Microsoft Azure Cognitive Services". This data is used to understand the user's emotional state, and the analysis results output emotion evaluation data. The server inputs this emotion data into a generative model and generates appropriate response suggestions using the prompt message "Based on the customer's emotion data, please suggest an appropriate response method". The generated response suggestions are output to the terminal, providing instructions to the store staff. The store staff then handles customer interactions according to these instructions.

[0393] In each step, the server, terminal, and user collect, analyze, optimize, and display data based on their respective roles, aiming to improve operational efficiency within the sales office and enhance customer satisfaction.

[0394] (Application Example 2)

[0395] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0396] In modern work environments and customer service, there is a demand for quick and accurate responses to diverse customer needs. However, traditional systems have struggled to properly understand customer emotions and provide services accordingly. Furthermore, optimizing worker movement and staffing to improve operational efficiency is necessary, but achieving this in real time is also a challenging task.

[0397] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0398] In this invention, the server includes means for acquiring visual and auditory information and analyzing the location of personnel within the work environment; means for designing an optimal movement path based on the analysis results; means for outputting the designed movement path information; means for estimating emotions based on a person's facial expressions and voice and generating response plans adapted to the visitor's emotions; means for outputting the generated response plans; means for predicting future personnel demand using previous external information; means for optimizing personnel allocation based on the prediction results; means for outputting the allocation information; and means for reporting customer service advice based on emotion analysis results in real time. This enables the provision of highly accurate services tailored to customer emotions and improves operational efficiency.

[0399] "Visual and auditory information" refers to the collective term for visual and audio data acquired using cameras and microphones.

[0400] "Means for analyzing the position of personnel within a work environment" refers to technologies that use visual information to detect and recognize the current position and movement of people within a work space.

[0401] "Methods for designing optimal travel routes" refers to a technology that calculates and proposes a route that allows workers to move efficiently, based on analysis results.

[0402] "Means for outputting designed travel path information" refers to methods or technologies for visually or audibly presenting the calculated optimal travel path to the worker.

[0403] "Means for estimating emotions based on a person's facial expressions and voice" refers to a technology that analyzes an individual's facial expressions and tone of voice to estimate their emotional state.

[0404] "Methods for generating response plans adapted to the visitor's emotions" refers to techniques that take estimated emotions into consideration and create appropriate countermeasures and customer service plans for that situation.

[0405] "Means for outputting generated response plans" refers to methods for displaying or communicating the created customer service plans to relevant staff or terminals.

[0406] "Methods for predicting future personnel demand using past external information" refers to techniques that statistically predict future personnel allocation needs using past data and external insights.

[0407] "Methods for optimizing staffing" refer to techniques for planning the optimal staffing arrangement based on predicted staffing needs.

[0408] A "means for outputting deployment information" refers to a mechanism for informing stakeholders and related systems of the details of the planned personnel deployment.

[0409] "A method for reporting customer service advice based on emotion analysis results in real time" refers to a technology that immediately communicates areas for improvement and recommended actions for customer service to the person in charge, based on the results of emotion analysis.

[0410] The system realizing this invention is designed to optimize personnel location, movement paths, customer sentiment, and staffing within a work environment using visual and auditory information. The server utilizes cameras and microphones to acquire video and audio from within the store. This allows for the analysis of worker and customer locations and the design of optimal movement paths. Software such as OpenCV and TensorFlow are used in this process.

[0411] The server also analyzes facial and audio data extracted from the video to estimate the customer's emotions. Based on the results obtained by the emotion engine, it generates service suggestions tailored to the customer's needs and notifies store staff via smart devices. Firebase is used for real-time notifications.

[0412] Users can visually receive these customer service suggestions through smart glasses or smartphones and respond immediately. For example, if the system determines that a customer is confused, the smart glasses display will show a message saying, "The customer may need help. Please speak to them."

[0413] The server further predicts future staffing needs based on past sales and customer data. Data analysis using Pandas and Scikit-learn optimizes staffing in real time. As a result, store managers can allocate staff efficiently. For example, it can predict staff shortages during peak seasons like the end of the year and take appropriate measures.

[0414] Example prompt: "Based on the latest sentiment analysis data, generate advice on recommended customer service actions when a customer's smile is detected."

[0415] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0416] Step 1:

[0417] The server acquires video and audio data from inside the store via cameras and microphones. It receives this data as input and performs image analysis using OpenCV. The output is location information of workers and visitors. This location information is stored in a database.

[0418] Step 2:

[0419] The server uses TensorFlow to design the optimal travel path based on the location information obtained in Step 1. This design also takes into account past travel patterns and the store's layout. The server then generates the calculated travel path as output and prepares it for transmission to the smart device.

[0420] Step 3:

[0421] The server extracts facial expressions from video data and processes audio data to estimate the customer's emotions using an emotion engine. Inputs include specific facial patterns and voice tone, and the output is an estimated emotional state. Based on this, the server determines whether the customer is confused or satisfied.

[0422] Step 4:

[0423] The server uses a generative AI model, based on the estimated emotional state, to generate appropriate customer service suggestions for customers according to the prompt text. The input is the emotional state and standard customer service protocols, and the output is a specific response suggestion.

[0424] Step 5:

[0425] The server sends the generated customer service suggestions to the device via Firebase. The user receives the suggestions through smart glasses or a smartphone display and responds to the customer based on them. Here, the device receives input (receives the customer service suggestions) and presents them as visual output.

[0426] Step 6:

[0427] The server uses Pandas and Scikit-learn to analyze historical sales and customer data to predict future staffing needs. Historical datasets are used as input, and the output provides the number of staff required for the next shift. This output is sent to the administrator's terminal to help optimize staffing.

[0428] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0429] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0430] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0431] [Third Embodiment]

[0432] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0433] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0434] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0435] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0436] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0437] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0438] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0439] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0440] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0441] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0442] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0443] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0444] This invention provides a system for improving the operational efficiency of sales offices. The system mainly consists of three elements: a server, a terminal, and a user.

[0445] The server first acquires real-time video data from surveillance cameras within the store. Based on the video data, the server uses an image recognition algorithm to analyze the location of workers. Based on the analysis results, the server uses an AI model to design the optimal movement path and transmits this information to the employee's terminal. This movement path information supports the efficient execution of tasks. In addition, the server uses accumulated historical sales data and external weather data to predict future personnel demand using an AI model. The prediction results are transmitted to the administrator's terminal and used to optimize appropriate personnel allocation.

[0446] Furthermore, the server analyzes audio and video data from within the store to estimate customer emotions. Based on customer emotions, the server generates appropriate services and suggestions and issues instructions to the terminals held by the store staff. This function enables store staff to provide customers with appropriate and highly satisfying service.

[0447] The terminal provides information to workers and managers according to the workflow, staffing, and customer service instructions received from the server. By clearly communicating instructions visually or audibly, users can perform their tasks smoothly.

[0448] The user (worker) performs their duties according to the optimal workflow within the office based on instructions from the terminal. Furthermore, in customer service, they provide highly satisfactory service to customers based on directions provided by the terminal. Managers optimize on-site staffing by referring to shift suggestions from the terminal.

[0449] For example, if a queue is expected during lunchtime, the server predicts the peak time based on past data and notifies the terminal of the appropriate staffing levels, allowing managers to strategically allocate staff. Furthermore, new staff can receive real-time updates on traffic flow instructions from the terminal, enabling efficient work even in short periods. If a customer appears anxious, the server analyzes their emotions and prompts the staff via the terminal to ask, "Are you having any trouble?" This facilitates prompt customer support.

[0450] In this way, this system can maximize operational efficiency within sales offices and improve customer satisfaction.

[0451] The following describes the processing flow.

[0452] Step 1:

[0453] The server collects video data in real time from cameras installed within the store. This video data is used to understand the situation inside the store and the location of workers.

[0454] Step 2:

[0455] The server applies an image recognition algorithm based on the collected video data to analyze the worker's current location. This analysis visualizes the worker's movements and path.

[0456] Step 3:

[0457] The server identifies inefficiencies in existing traffic flow based on the analysis results. Furthermore, it uses an AI model to design the optimal traffic flow and sends it as instructions to the store staff's terminals.

[0458] Step 4:

[0459] The terminal displays movement instructions transmitted from the server to the worker visually and audibly. This allows store employees to proceed with their work according to the optimized movement path in real time.

[0460] Step 5:

[0461] The server uses sales data and external data such as weather information to predict future peak times using an AI model. This prediction is useful for analyzing staffing needs.

[0462] Step 6:

[0463] The server sends predicted peak time information and staffing schedules to the administrator's terminal. This allows the administrator to create appropriate shifts.

[0464] Step 7:

[0465] The server acquires customer voice and video data and uses an AI model to estimate emotions. This process analyzes the customer's facial expressions and tone of voice.

[0466] Step 8:

[0467] The server generates service suggestions tailored to the customer's emotions and sends them to the employee's terminal. These suggestions include specific actions and phrases.

[0468] Step 9:

[0469] The terminal transmits service suggestions to the staff, who then provide the appropriate service to the customer. The user (staff) uses the presented information to provide high-quality customer service.

[0470] (Example 1)

[0471] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0472] Modern commercial facilities and offices require optimized worker workflows, efficient staffing, and rapid customer service. However, these processes have traditionally relied heavily on human experience and judgment, making it difficult to consistently provide optimal responses tailored to individual situations. Furthermore, accurately understanding customer emotions and providing immediate, appropriate service also demands advanced response skills. To address these challenges, more automated systems are necessary.

[0473] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0474] In this invention, the server includes means for acquiring video information and analyzing the location of workers within a facility; means for designing an optimal route based on the analysis results; means for presenting the designed route information; means for predicting the personnel needs at any given time using past statistical information; means for adjusting personnel deployment based on the prediction results; means for estimating customer emotions using sound and video information; and means for generating appropriate countermeasures based on the estimation results. This enables efficient management of worker movement and optimization of personnel allocation, as well as the provision of prompt and appropriate services to customers.

[0475] "Video information" refers to all information, including video data and related still images, acquired within the facility.

[0476] "Workers" refers to individuals whose movement patterns within a facility are optimized in order to perform their duties.

[0477] "Location" refers to information used to identify the current physical position of a worker or object.

[0478] A "route" refers to the optimal travel path designed to allow workers to move efficiently.

[0479] "Statistical information" refers to all data, including past business data and external environmental information, and is used for future analysis and predictions.

[0480] "Necessity" refers to the degree to which the personnel and resources required to carry out the work are present.

[0481] "Deployment" refers to appropriately allocating personnel and resources according to anticipated needs.

[0482] "Audio information" refers to information that includes audio data, specifically audio records related to customer service and facility operations.

[0483] "Emotions" refers to information estimated to understand a customer's psychological state and is used to generate countermeasures.

[0484] "Countermeasures" refer to services or methods of dealing with customers based on their perceived emotions.

[0485] This invention aims to build a system for improving work efficiency within commercial facilities and offices. The system mainly consists of three components: a server, a terminal, and a user.

[0486] The server acquires real-time video information using multiple sensors and cameras installed within the facility and analyzes the location of workers using image processing software. Image processing tools such as "OpenCV" are useful for this purpose. Based on this recognized information, the server designs the optimal route using generative AI models such as "TensorFlow." This route information is immediately delivered to a mobile device and presented visually to the user.

[0487] The server also retrieves historical statistical information from a database and uses machine learning libraries such as "scikit-learn" to predict staffing needs. Based on the prediction results, an appropriate staffing plan is created and notified to the management terminal. For example, if additional staff are needed during lunchtime, the server sends that information to the terminal to help users respond quickly.

[0488] Furthermore, the server acquires sound information from within the facility and analyzes it using speech recognition technologies such as "Google Speech-to-Text." Combined with video information, it employs sentiment analysis tools such as "IBM Watson" to estimate customer emotions. The AI ​​generates suggested solutions based on the customer's needs, and these suggestions are displayed as instructions on the employee's terminal. This function allows the employee to provide services that meet customer needs in real time.

[0489] Examples of prompt messages include specific instructions such as, "Analyze video data within the sales office and design the optimal workflow for workers," or "Predict future staffing needs and generate information to be sent to terminals." This enables efficient sales management and customer service.

[0490] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0491] Step 1:

[0492] The server acquires video information in real time from sensors and cameras within the facility. This video information is first stored in a database as raw data. The server uses "OpenCV" to detect workers in the video and determine their location. This analysis process outputs the location information of the workers.

[0493] Step 2:

[0494] The server uses the location information of the worker identified in Step 1 as input and generates the optimal route using an AI model such as "TensorFlow". The model designs the route taking into account the facility layout and current congestion. The resulting route information is then ready to be sent to the terminal.

[0495] Step 3:

[0496] The terminal receives routing information from the server. This routing information is visually displayed on the screen to instruct the worker on how to proceed. By using an audio alert system in conjunction with this, it is possible to convey instructions to the user through both sight and sound.

[0497] Step 4:

[0498] The server retrieves statistical information such as historical sales data and weather information from a database and uses the machine learning model "scikit-learn" to predict future staffing needs. The data used as input is historical time-series data, and the output presents staffing needs for each time period.

[0499] Step 5:

[0500] The server transmits the personnel demand forecast information obtained in step 4 to the management terminal. The management terminal can then refer to this personnel allocation information to plan appropriate shifts. This enables efficient personnel allocation.

[0501] Step 6:

[0502] The server uses audio and video information to estimate the customer's emotions. It converts the audio information to text using "Google Speech-to-Text" and then performs emotion analysis using "IBM Watson." This analysis outputs the customer's emotion data.

[0503] Step 7:

[0504] The server generates a response plan based on the customer sentiment data obtained in step 6. This response plan is sent to the employee's terminal as a service or product suggestion, allowing the employee to respond to the customer quickly based on it.

[0505] (Application Example 1)

[0506] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0507] Modern facilities demand improved work efficiency and optimized staffing, but adequate means to achieve these goals are not yet fully established. In particular, the optimization of worker and equipment movement, as well as the management of worker stress, are insufficient, hindering efficient operation. Traditional methods fail to fully utilize the vast amount of data within the facility, making it difficult to provide optimal instructions in real time.

[0508] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0509] In this invention, the server includes means for acquiring video information and analyzing the position of workers within the facility, means for designing an optimal movement path based on the analysis results, means for outputting the designed movement path information, and means for optimizing the movement of work equipment based on the analysis of the information. This makes it possible to efficiently arrange workers and optimize their movement within the facility.

[0510] "Video information" refers to video data acquired within the facility, which is used to analyze the location and movements of workers.

[0511] "Within the facility" refers to the scope of the specific workspace or facility to which this invention applies, and is the scope of the analysis and optimization.

[0512] "Worker location" refers to the specific physical position of individual workers within the facility, and is analyzed from video information.

[0513] "Analysis" refers to the process of extracting specific information from acquired data and converting it into an understandable format.

[0514] A "movement route" refers to the optimal path that workers and work equipment should take when moving within a facility.

[0515] "Optimization" refers to the process of performing operations and making choices to achieve the most efficient state possible under certain conditions.

[0516] "Information analysis" refers to the process of deriving information useful for facility management and worker behavior based on collected data.

[0517] "Work equipment" refers to machinery and devices used to support specific tasks within a facility.

[0518] This invention is implemented primarily using a system configuration consisting of a server, a terminal, and a user. The server acquires video data in real time from surveillance cameras within the facility and uses OpenCV as image processing software to detect workers and work equipment frame by frame. The detected location information is used to design the optimal movement path using TensorFlow. This output is transferred to the terminal and notified to the worker via audio and visual means.

[0519] Furthermore, the server uses the pandas library to organize historical external information and statsmodels to forecast demand. Based on these forecast results, it sends the optimized worker allocation results to the terminal and provides information including appropriate break suggestions.

[0520] Furthermore, it has the ability to estimate the emotions of workers and customers using the Azure Emotion API by analyzing video and audio data. Based on the obtained emotion data, the terminal provides instructions from the server regarding the need to interrupt work. This means that work can be streamlined within the facility and a rapid response to the emotions of users can be made.

[0521] As a concrete example, during peak hours at a logistics center, optimizing transport routes can shorten working time, and staff allocation can be optimized to meet high demand predicted from past shipping data. Furthermore, it can detect increases in workers' stress levels using emotional data and promptly suggest breaks.

[0522] An example of a prompt message that can be used is: "Based on shipping data from the past month and this week's weather forecast, there is a possibility of increased shipping volume from 2pm to 4pm next Monday. Please increase staff to accommodate this time."

[0523] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0524] Step 1:

[0525] The server acquires real-time video data from surveillance cameras within the facility and analyzes this data frame by frame using the OpenCV library. It detects the positions of workers and work equipment using an image recognition algorithm and outputs their location information. This information is used to optimize worker movement.

[0526] Step 2:

[0527] The server inputs the worker's location information obtained from Step 1 into a generative AI model using TensorFlow to design the optimal movement path. This generated movement path information is output to the terminal as an optimized movement route. As a result, the worker receives efficient movement guidance.

[0528] Step 3:

[0529] The server uses the pandas library to organize historical external information (sales data and weather information) from input and uses statsmodels to predict personnel demand for a given period. This prediction result is output to the terminal and used as foundational information to optimize worker allocation.

[0530] Step 4:

[0531] The server utilizes the Azure Emotion API to analyze audio and video data acquired within the facility as input, and estimates the emotions of workers and customers. Based on the emotion analysis results, it generates instructions for necessary work interruptions and appropriate response suggestions, and outputs them to the terminal. This allows workers to quickly manage stress and handle customer interactions.

[0532] Step 5:

[0533] The user, acting as the worker, performs their daily tasks based on movement route information and personnel allocation optimization instructions output from the terminal. They also receive notifications of sentiment analysis results, which they use to adjust their work and improve customer service. This results in the provision of efficient and highly customer-satisfying services.

[0534] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0535] The system in this invention combines optimized worker movement and personnel demand forecasting with an emotion engine that analyzes user emotions to improve service quality, in order to improve work efficiency and customer satisfaction at sales offices. This system is realized through the interaction of a server, terminals, and users.

[0536] The server first collects video data from cameras installed at the sales office and analyzes the workers' locations in real time. Based on this analysis, the server uses AI to design the optimal movement patterns and transmits this information to the workers' terminals. This allows workers to perform their tasks efficiently. In addition, the server uses historical sales data and external environmental data stored in the database to predict personnel demand using an AI model and notifies managers' terminals of the optimal personnel allocation plan.

[0537] Furthermore, this invention uses an emotion engine to recognize customer emotions. The server inputs video and audio data acquired through cameras and microphones within the store into the emotion engine to estimate the customer's emotions. Based on this, the server generates response suggestions and service improvement suggestions that correspond to the customer's emotions and provides them to the store employee's terminal. The store employee can then follow the instructions on the terminal to provide appropriate service to the customer and improve customer satisfaction.

[0538] As a concrete example, when a customer's face is captured by a camera in a store, the server analyzes the customer's facial expression. If the system determines that the customer appears confused, a message such as "They may need help" is displayed on the terminal along with specific examples of how to respond. Store staff then use this information to approach and assist the customer. This allows customers to receive prompt and appropriate assistance, leading to increased customer satisfaction.

[0539] In this manner, the present invention provides a system that further improves work efficiency and service quality within a business office.

[0540] The following describes the processing flow.

[0541] Step 1:

[0542] The server collects video data in real time from cameras installed within the office. This data is used to identify the location of workers.

[0543] Step 2:

[0544] The server applies an image recognition algorithm to the collected video data to analyze the worker's position. This analysis allows for an understanding of the current movement patterns.

[0545] Step 3:

[0546] The server uses an AI model to design the optimal workflow based on the analysis results. The designed workflow information is then sent to the worker's terminal.

[0547] Step 4:

[0548] The terminal visually displays movement information received from the server to the worker. This allows the worker to move more efficiently.

[0549] Step 5:

[0550] The server uses accumulated historical sales data and external environmental data to predict future personnel demand using an AI model.

[0551] Step 6:

[0552] The server generates an optimized staffing plan based on the predicted personnel demand and notifies the administrator's terminal of this plan.

[0553] Step 7:

[0554] The terminal displays the staffing plan received from the server to the administrator, providing it as reference information for shift adjustments.

[0555] Step 8:

[0556] The server inputs video and audio data acquired from cameras and microphones within the sales office into an emotion engine to estimate the customer's emotions.

[0557] Step 9:

[0558] The server generates appropriate response suggestions and service improvement proposals based on the estimated customer's emotions and sends them to the employee's terminal.

[0559] Step 10:

[0560] The terminal displays generated response suggestions to store staff in real time, allowing them to use these suggestions to provide service to customers.

[0561] Step 11:

[0562] The user (store clerk) can improve customer satisfaction by responding to customers based on instructions from the terminal and providing appropriate service.

[0563] (Example 2)

[0564] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0565] To improve the efficiency of business activities and customer satisfaction at sales offices, it is necessary to optimize worker movement paths, optimize staffing, and provide appropriate services based on customer sentiment. However, achieving these requires real-time, highly accurate data analysis and the presentation of concrete improvement proposals based on that analysis, which conventional systems are unable to adequately address.

[0566] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0567] In this invention, the server includes means for collecting motion information using an image acquisition device and analyzing the user's position in the workspace, means for planning an optimal motion path using a generative model, and means for providing the planned motion path information to the user's display device. This makes it possible to analyze the worker's movements in real time and quickly provide a path that achieves optimal work efficiency.

[0568] An "image acquisition device" is a photographic device used to collect operational information within a business office.

[0569] "Motion information" refers to data related to the user's position and movement patterns within the workspace.

[0570] "Analysis" is the process of determining the user's location and actions based on the acquired data.

[0571] A "generative model" is an algorithm that uses artificial intelligence technology to plan and propose the optimal action path and response plan.

[0572] A "movement path" is an optimized route for workers to efficiently carry out their tasks.

[0573] A "display device" is a device used to provide users with planned information visually.

[0574] "Sales information" refers to commercial data related to past business activities.

[0575] "Environmental information" refers to data about external environmental factors.

[0576] "Job needs" refers to predicted information regarding the workload and required personnel within a sales office.

[0577] A "service proposal" is a suggestion for appropriate service based on the user's emotional state.

[0578] The embodiments for carrying out the present invention will be described below.

[0579] This system is designed to improve operational efficiency within sales offices and maximize customer satisfaction. Specifically, it is achieved through the interaction of servers, terminals, and users.

[0580] The server collects worker motion information using image acquisition devices installed at the branch office. For image processing, software libraries such as "OpenCV" are used to analyze the motion information. Furthermore, based on the analyzed data, a generative model is used to plan the optimal motion path. This generative model is implemented using machine learning frameworks such as "PyTorch" or "TensorFlow." The generated motion path information is provided in real time to the worker's display device, encouraging efficient work performance.

[0581] Furthermore, the server integrates and analyzes past sales and environmental data to create a model for predicting future job needs. This prediction uses predictive analytics libraries such as "scikit-learn" and "Keras," resulting in the provision of optimal job placement proposals to administrators.

[0582] Furthermore, for sentiment analysis, the server collects video and audio data from within the store and estimates the customer's emotional state using sentiment analysis APIs such as "Microsoft Azure Cognitive Services." Based on this, a generative model generates appropriate response suggestions, which are then provided to the employee's display device.

[0583] For example, if a camera captures a customer's confused expression in a sales office, the server analyzes this information in real time and notifies the staff with a suggested response, such as, "The customer appears confused. They may need assistance." This allows staff to respond to customers quickly and appropriately, leading to improved customer satisfaction.

[0584] Examples of prompt messages include, "Based on the current worker's location data, please suggest a workflow that optimizes work efficiency," and "Based on customer sentiment data, please suggest an appropriate response method."

[0585] In this way, the present invention intelligently manages various elements within a sales office and aims to improve the overall business process.

[0586] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0587] Step 1:

[0588] The server collects video data from image acquisition devices installed at the branch office. This data is used to capture the movements of workers. The server uses the collected video data as input and analyzes the workers' positions in real time using image processing libraries such as "OpenCV". As a result of the analysis, the specific location information and movement patterns of the workers are output as text data.

[0589] Step 2:

[0590] The server uses the worker's location information obtained in Step 1 as input and utilizes a generating AI model. Specifically, it uses the prompt message "Based on the current worker's location data, please suggest a movement path that optimizes work efficiency" to generate the optimal route. The generating model outputs the optimized route, which is then sent to the worker's terminal. The terminal visually displays this route information to the user and suggests a new work route.

[0591] Step 3:

[0592] The server analyzes historical sales information and external environment information stored in the database. Analysis libraries such as "scikit-learn" and "Keras" are used for the analysis. This data is used as input to predict future job needs. The predicted personnel needs and placement plans are output and notified to the administrator's terminal. The administrator then adjusts the personnel plan based on this information.

[0593] Step 4:

[0594] The server acquires video and audio data through cameras and microphones within the store and analyzes customer emotions using APIs such as "Microsoft Azure Cognitive Services". This data is used to understand the user's emotional state, and the analysis results output emotion evaluation data. The server inputs this emotion data into a generative model and generates appropriate response suggestions using the prompt message "Based on the customer's emotion data, please suggest an appropriate response method". The generated response suggestions are output to the terminal, providing instructions to the store staff. The store staff then handles customer interactions according to these instructions.

[0595] In each step, the server, terminal, and user collect, analyze, optimize, and display data based on their respective roles, aiming to improve operational efficiency within the sales office and enhance customer satisfaction.

[0596] (Application Example 2)

[0597] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0598] In modern work environments and customer service, there is a demand for quick and accurate responses to diverse customer needs. However, traditional systems have struggled to properly understand customer emotions and provide services accordingly. Furthermore, optimizing worker movement and staffing to improve operational efficiency is necessary, but achieving this in real time is also a challenging task.

[0599] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0600] In this invention, the server includes means for acquiring visual and auditory information and analyzing the location of personnel within the work environment; means for designing an optimal movement path based on the analysis results; means for outputting the designed movement path information; means for estimating emotions based on a person's facial expressions and voice and generating response plans adapted to the visitor's emotions; means for outputting the generated response plans; means for predicting future personnel demand using previous external information; means for optimizing personnel allocation based on the prediction results; means for outputting the allocation information; and means for reporting customer service advice based on emotion analysis results in real time. This enables the provision of highly accurate services tailored to customer emotions and improves operational efficiency.

[0601] "Visual and auditory information" refers to the collective term for visual and audio data acquired using cameras and microphones.

[0602] "Means for analyzing the position of personnel within a work environment" refers to technologies that use visual information to detect and recognize the current position and movement of people within a work space.

[0603] "Methods for designing optimal travel routes" refers to a technology that calculates and proposes a route that allows workers to move efficiently, based on analysis results.

[0604] "Means for outputting designed travel path information" refers to methods or technologies for visually or audibly presenting the calculated optimal travel path to the worker.

[0605] "Means for estimating emotions based on a person's facial expressions and voice" refers to a technology that analyzes an individual's facial expressions and tone of voice to estimate their emotional state.

[0606] "Methods for generating response plans adapted to the visitor's emotions" refers to techniques that take estimated emotions into consideration and create appropriate countermeasures and customer service plans for that situation.

[0607] "Means for outputting generated response plans" refers to methods for displaying or communicating the created customer service plans to relevant staff or terminals.

[0608] "Methods for predicting future personnel demand using past external information" refers to techniques that statistically predict future personnel allocation needs using past data and external insights.

[0609] "Methods for optimizing staffing" refer to techniques for planning the optimal staffing arrangement based on predicted staffing needs.

[0610] A "means for outputting deployment information" refers to a mechanism for informing stakeholders and related systems of the details of the planned personnel deployment.

[0611] "A method for reporting customer service advice based on emotion analysis results in real time" refers to a technology that immediately communicates areas for improvement and recommended actions for customer service to the person in charge, based on the results of emotion analysis.

[0612] The system realizing this invention is designed to optimize personnel location, movement paths, customer sentiment, and staffing within a work environment using visual and auditory information. The server utilizes cameras and microphones to acquire video and audio from within the store. This allows for the analysis of worker and customer locations and the design of optimal movement paths. Software such as OpenCV and TensorFlow are used in this process.

[0613] The server also analyzes facial and audio data extracted from the video to estimate the customer's emotions. Based on the results obtained by the emotion engine, it generates service suggestions tailored to the customer's needs and notifies store staff via smart devices. Firebase is used for real-time notifications.

[0614] Users can visually receive these customer service suggestions through smart glasses or smartphones and respond immediately. For example, if the system determines that a customer is confused, the smart glasses display will show a message saying, "The customer may need help. Please speak to them."

[0615] The server further predicts future staffing needs based on past sales and customer data. Data analysis using Pandas and Scikit-learn optimizes staffing in real time. As a result, store managers can allocate staff efficiently. For example, it can predict staff shortages during peak seasons like the end of the year and take appropriate measures.

[0616] Example prompt: "Based on the latest sentiment analysis data, generate advice on recommended customer service actions when a customer's smile is detected."

[0617] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0618] Step 1:

[0619] The server acquires video and audio data from inside the store via cameras and microphones. It receives this data as input and performs image analysis using OpenCV. The output is location information of workers and visitors. This location information is stored in a database.

[0620] Step 2:

[0621] The server uses TensorFlow to design the optimal travel path based on the location information obtained in Step 1. This design also takes into account past travel patterns and the store's layout. The server then generates the calculated travel path as output and prepares it for transmission to the smart device.

[0622] Step 3:

[0623] The server extracts facial expressions from video data and processes audio data to estimate the customer's emotions using an emotion engine. Inputs include specific facial patterns and voice tone, and the output is an estimated emotional state. Based on this, the server determines whether the customer is confused or satisfied.

[0624] Step 4:

[0625] The server uses a generative AI model, based on the estimated emotional state, to generate appropriate customer service suggestions for customers according to the prompt text. The input is the emotional state and standard customer service protocols, and the output is a specific response suggestion.

[0626] Step 5:

[0627] The server sends the generated customer service suggestions to the device via Firebase. The user receives the suggestions through smart glasses or a smartphone display and responds to the customer based on them. Here, the device receives input (receives the customer service suggestions) and presents them as visual output.

[0628] Step 6:

[0629] The server uses Pandas and Scikit-learn to analyze historical sales and customer data to predict future staffing needs. Historical datasets are used as input, and the output provides the number of staff required for the next shift. This output is sent to the administrator's terminal to help optimize staffing.

[0630] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0631] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0632] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0633] [Fourth Embodiment]

[0634] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0635] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0636] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0637] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0638] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0639] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0640] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0641] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0642] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0643] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0644] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0645] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0646] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0647] This invention provides a system for improving the operational efficiency of sales offices. The system mainly consists of three elements: a server, a terminal, and a user.

[0648] The server first acquires real-time video data from surveillance cameras within the store. Based on the video data, the server uses an image recognition algorithm to analyze the location of workers. Based on the analysis results, the server uses an AI model to design the optimal movement path and transmits this information to the employee's terminal. This movement path information supports the efficient execution of tasks. In addition, the server uses accumulated historical sales data and external weather data to predict future personnel demand using an AI model. The prediction results are transmitted to the administrator's terminal and used to optimize appropriate personnel allocation.

[0649] Furthermore, the server analyzes audio and video data from within the store to estimate customer emotions. Based on customer emotions, the server generates appropriate services and suggestions and issues instructions to the terminals held by the store staff. This function enables store staff to provide customers with appropriate and highly satisfying service.

[0650] The terminal provides information to workers and managers according to the workflow, staffing, and customer service instructions received from the server. By clearly communicating instructions visually or audibly, users can perform their tasks smoothly.

[0651] The user (worker) performs their duties according to the optimal workflow within the office based on instructions from the terminal. Furthermore, in customer service, they provide highly satisfactory service to customers based on directions provided by the terminal. Managers optimize on-site staffing by referring to shift suggestions from the terminal.

[0652] For example, if a queue is expected during lunchtime, the server predicts the peak time based on past data and notifies the terminal of the appropriate staffing levels, allowing managers to strategically allocate staff. Furthermore, new staff can receive real-time updates on traffic flow instructions from the terminal, enabling efficient work even in short periods. If a customer appears anxious, the server analyzes their emotions and prompts the staff via the terminal to ask, "Are you having any trouble?" This facilitates prompt customer support.

[0653] In this way, this system can maximize operational efficiency within sales offices and improve customer satisfaction.

[0654] The following describes the processing flow.

[0655] Step 1:

[0656] The server collects video data in real time from cameras installed within the store. This video data is used to understand the situation inside the store and the location of workers.

[0657] Step 2:

[0658] The server applies an image recognition algorithm based on the collected video data to analyze the worker's current location. This analysis visualizes the worker's movements and path.

[0659] Step 3:

[0660] The server identifies inefficiencies in existing traffic flow based on the analysis results. Furthermore, it uses an AI model to design the optimal traffic flow and sends it as instructions to the store staff's terminals.

[0661] Step 4:

[0662] The terminal displays movement instructions transmitted from the server to the worker visually and audibly. This allows store employees to proceed with their work according to the optimized movement path in real time.

[0663] Step 5:

[0664] The server uses sales data and external data such as weather information to predict future peak times using an AI model. This prediction is useful for analyzing staffing needs.

[0665] Step 6:

[0666] The server sends predicted peak time information and staffing schedules to the administrator's terminal. This allows the administrator to create appropriate shifts.

[0667] Step 7:

[0668] The server acquires customer voice and video data and uses an AI model to estimate emotions. This process analyzes the customer's facial expressions and tone of voice.

[0669] Step 8:

[0670] The server generates service suggestions tailored to the customer's emotions and sends them to the employee's terminal. These suggestions include specific actions and phrases.

[0671] Step 9:

[0672] The terminal transmits service suggestions to the staff, who then provide the appropriate service to the customer. The user (staff) uses the presented information to provide high-quality customer service.

[0673] (Example 1)

[0674] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0675] Modern commercial facilities and offices require optimized worker workflows, efficient staffing, and rapid customer service. However, these processes have traditionally relied heavily on human experience and judgment, making it difficult to consistently provide optimal responses tailored to individual situations. Furthermore, accurately understanding customer emotions and providing immediate, appropriate service also demands advanced response skills. To address these challenges, more automated systems are necessary.

[0676] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0677] In this invention, the server includes means for acquiring video information and analyzing the location of workers within a facility; means for designing an optimal route based on the analysis results; means for presenting the designed route information; means for predicting the personnel needs at any given time using past statistical information; means for adjusting personnel deployment based on the prediction results; means for estimating customer emotions using sound and video information; and means for generating appropriate countermeasures based on the estimation results. This enables efficient management of worker movement and optimization of personnel allocation, as well as the provision of prompt and appropriate services to customers.

[0678] "Video information" refers to all information, including video data and related still images, acquired within the facility.

[0679] "Workers" refers to individuals whose movement patterns within a facility are optimized in order to perform their duties.

[0680] "Location" refers to information used to identify the current physical position of a worker or object.

[0681] A "route" refers to the optimal travel path designed to allow workers to move efficiently.

[0682] "Statistical information" refers to all data, including past business data and external environmental information, and is used for future analysis and predictions.

[0683] "Necessity" refers to the degree to which the personnel and resources required to carry out the work are present.

[0684] "Deployment" refers to appropriately allocating personnel and resources according to anticipated needs.

[0685] "Audio information" refers to information that includes audio data, specifically audio records related to customer service and facility operations.

[0686] "Emotions" refers to information estimated to understand a customer's psychological state and is used to generate countermeasures.

[0687] "Countermeasures" refer to services or methods of dealing with customers based on their perceived emotions.

[0688] This invention aims to build a system for improving work efficiency within commercial facilities and offices. The system mainly consists of three components: a server, a terminal, and a user.

[0689] The server acquires real-time video information using multiple sensors and cameras installed within the facility and analyzes the location of workers using image processing software. Image processing tools such as "OpenCV" are useful for this purpose. Based on this recognized information, the server designs the optimal route using generative AI models such as "TensorFlow." This route information is immediately delivered to a mobile device and presented visually to the user.

[0690] The server also retrieves historical statistical information from a database and uses machine learning libraries such as "scikit-learn" to predict staffing needs. Based on the prediction results, an appropriate staffing plan is created and notified to the management terminal. For example, if additional staff are needed during lunchtime, the server sends that information to the terminal to help users respond quickly.

[0691] Furthermore, the server acquires sound information from within the facility and analyzes it using speech recognition technologies such as "Google Speech-to-Text." Combined with video information, it employs sentiment analysis tools such as "IBM Watson" to estimate customer emotions. The AI ​​generates suggested solutions based on the customer's needs, and these suggestions are displayed as instructions on the employee's terminal. This function allows the employee to provide services that meet customer needs in real time.

[0692] Examples of prompt messages include specific instructions such as, "Analyze video data within the sales office and design the optimal workflow for workers," or "Predict future staffing needs and generate information to be sent to terminals." This enables efficient sales management and customer service.

[0693] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0694] Step 1:

[0695] The server acquires video information in real time from sensors and cameras within the facility. This video information is first stored in a database as raw data. The server uses "OpenCV" to detect workers in the video and determine their location. This analysis process outputs the location information of the workers.

[0696] Step 2:

[0697] The server uses the location information of the worker identified in Step 1 as input and generates the optimal route using an AI model such as "TensorFlow". The model designs the route taking into account the facility layout and current congestion. The resulting route information is then ready to be sent to the terminal.

[0698] Step 3:

[0699] The terminal receives routing information from the server. This routing information is visually displayed on the screen to instruct the worker on how to proceed. By using an audio alert system in conjunction with this, it is possible to convey instructions to the user through both sight and sound.

[0700] Step 4:

[0701] The server retrieves statistical information such as historical sales data and weather information from a database and uses the machine learning model "scikit-learn" to predict future staffing needs. The data used as input is historical time-series data, and the output presents staffing needs for each time period.

[0702] Step 5:

[0703] The server transmits the personnel demand forecast information obtained in step 4 to the management terminal. The management terminal can then refer to this personnel allocation information to plan appropriate shifts. This enables efficient personnel allocation.

[0704] Step 6:

[0705] The server uses audio and video information to estimate the customer's emotions. It converts the audio information to text using "Google Speech-to-Text" and then performs emotion analysis using "IBM Watson." This analysis outputs the customer's emotion data.

[0706] Step 7:

[0707] The server generates a response plan based on the customer sentiment data obtained in step 6. This response plan is sent to the employee's terminal as a service or product suggestion, allowing the employee to respond to the customer quickly based on it.

[0708] (Application Example 1)

[0709] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0710] Modern facilities demand improved work efficiency and optimized staffing, but adequate means to achieve these goals are not yet fully established. In particular, the optimization of worker and equipment movement, as well as the management of worker stress, are insufficient, hindering efficient operation. Traditional methods fail to fully utilize the vast amount of data within the facility, making it difficult to provide optimal instructions in real time.

[0711] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0712] In this invention, the server includes means for acquiring video information and analyzing the position of workers within the facility, means for designing an optimal movement path based on the analysis results, means for outputting the designed movement path information, and means for optimizing the movement of work equipment based on the analysis of the information. This makes it possible to efficiently arrange workers and optimize their movement within the facility.

[0713] "Video information" refers to video data acquired within the facility, which is used to analyze the location and movements of workers.

[0714] "Within the facility" refers to the scope of the specific workspace or facility to which this invention applies, and is the scope of the analysis and optimization.

[0715] "Worker location" refers to the specific physical position of individual workers within the facility, and is analyzed from video information.

[0716] "Analysis" refers to the process of extracting specific information from acquired data and converting it into an understandable format.

[0717] A "movement route" refers to the optimal path that workers and work equipment should take when moving within a facility.

[0718] "Optimization" refers to the process of performing operations and making choices to achieve the most efficient state possible under certain conditions.

[0719] "Information analysis" refers to the process of deriving information useful for facility management and worker behavior based on collected data.

[0720] "Work equipment" refers to machinery and devices used to support specific tasks within a facility.

[0721] This invention is implemented primarily using a system configuration consisting of a server, a terminal, and a user. The server acquires video data in real time from surveillance cameras within the facility and uses OpenCV as image processing software to detect workers and work equipment frame by frame. The detected location information is used to design the optimal movement path using TensorFlow. This output is transferred to the terminal and notified to the worker via audio and visual means.

[0722] Furthermore, the server uses the pandas library to organize historical external information and statsmodels to forecast demand. Based on these forecast results, it sends the optimized worker allocation results to the terminal and provides information including appropriate break suggestions.

[0723] Furthermore, it has the ability to estimate the emotions of workers and customers using the Azure Emotion API by analyzing video and audio data. Based on the obtained emotion data, the terminal provides instructions from the server regarding the need to interrupt work. This means that work can be streamlined within the facility and a rapid response to the emotions of users can be made.

[0724] As a concrete example, during peak hours at a logistics center, optimizing transport routes can shorten working time, and staff allocation can be optimized to meet high demand predicted from past shipping data. Furthermore, it can detect increases in workers' stress levels using emotional data and promptly suggest breaks.

[0725] An example of a prompt message that can be used is: "Based on shipping data from the past month and this week's weather forecast, there is a possibility of increased shipping volume from 2pm to 4pm next Monday. Please increase staff to accommodate this time."

[0726] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0727] Step 1:

[0728] The server acquires real-time video data from surveillance cameras within the facility and analyzes this data frame by frame using the OpenCV library. It detects the positions of workers and work equipment using an image recognition algorithm and outputs their location information. This information is used to optimize worker movement.

[0729] Step 2:

[0730] The server inputs the worker's location information obtained from Step 1 into a generative AI model using TensorFlow to design the optimal movement path. This generated movement path information is output to the terminal as an optimized movement route. As a result, the worker receives efficient movement guidance.

[0731] Step 3:

[0732] The server uses the pandas library to organize historical external information (sales data and weather information) from input and uses statsmodels to predict personnel demand for a given period. This prediction result is output to the terminal and used as foundational information to optimize worker allocation.

[0733] Step 4:

[0734] The server utilizes the Azure Emotion API to analyze audio and video data acquired within the facility as input, and estimates the emotions of workers and customers. Based on the emotion analysis results, it generates instructions for necessary work interruptions and appropriate response suggestions, and outputs them to the terminal. This allows workers to quickly manage stress and handle customer interactions.

[0735] Step 5:

[0736] The user, acting as the worker, performs their daily tasks based on movement route information and personnel allocation optimization instructions output from the terminal. They also receive notifications of sentiment analysis results, which they use to adjust their work and improve customer service. This results in the provision of efficient and highly customer-satisfying services.

[0737] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0738] The system in this invention combines optimized worker movement and personnel demand forecasting with an emotion engine that analyzes user emotions to improve service quality, in order to improve work efficiency and customer satisfaction at sales offices. This system is realized through the interaction of a server, terminals, and users.

[0739] The server first collects video data from cameras installed at the sales office and analyzes the workers' locations in real time. Based on this analysis, the server uses AI to design the optimal movement patterns and transmits this information to the workers' terminals. This allows workers to perform their tasks efficiently. In addition, the server uses historical sales data and external environmental data stored in the database to predict personnel demand using an AI model and notifies managers' terminals of the optimal personnel allocation plan.

[0740] Furthermore, this invention uses an emotion engine to recognize customer emotions. The server inputs video and audio data acquired through cameras and microphones within the store into the emotion engine to estimate the customer's emotions. Based on this, the server generates response suggestions and service improvement suggestions that correspond to the customer's emotions and provides them to the store employee's terminal. The store employee can then follow the instructions on the terminal to provide appropriate service to the customer and improve customer satisfaction.

[0741] As a concrete example, when a customer's face is captured by a camera in a store, the server analyzes the customer's facial expression. If the system determines that the customer appears confused, a message such as "They may need help" is displayed on the terminal along with specific examples of how to respond. Store staff then use this information to approach and assist the customer. This allows customers to receive prompt and appropriate assistance, leading to increased customer satisfaction.

[0742] In this manner, the present invention provides a system that further improves work efficiency and service quality within a business office.

[0743] The following describes the processing flow.

[0744] Step 1:

[0745] The server collects video data in real time from cameras installed within the office. This data is used to identify the location of workers.

[0746] Step 2:

[0747] The server applies an image recognition algorithm to the collected video data to analyze the worker's position. This analysis allows for an understanding of the current movement patterns.

[0748] Step 3:

[0749] The server uses an AI model to design the optimal workflow based on the analysis results. The designed workflow information is then sent to the worker's terminal.

[0750] Step 4:

[0751] The terminal visually displays movement information received from the server to the worker. This allows the worker to move more efficiently.

[0752] Step 5:

[0753] The server uses accumulated historical sales data and external environmental data to predict future personnel demand using an AI model.

[0754] Step 6:

[0755] The server generates an optimized staffing plan based on the predicted personnel demand and notifies the administrator's terminal of this plan.

[0756] Step 7:

[0757] The terminal displays the staffing plan received from the server to the administrator, providing it as reference information for shift adjustments.

[0758] Step 8:

[0759] The server inputs video and audio data acquired from cameras and microphones within the sales office into an emotion engine to estimate the customer's emotions.

[0760] Step 9:

[0761] The server generates appropriate response suggestions and service improvement proposals based on the estimated customer's emotions and sends them to the employee's terminal.

[0762] Step 10:

[0763] The terminal displays generated response suggestions to store staff in real time, allowing them to use these suggestions to provide service to customers.

[0764] Step 11:

[0765] The user (store clerk) can improve customer satisfaction by responding to customers based on instructions from the terminal and providing appropriate service.

[0766] (Example 2)

[0767] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0768] To improve the efficiency of business activities and customer satisfaction at sales offices, it is necessary to optimize worker movement paths, optimize staffing, and provide appropriate services based on customer sentiment. However, achieving these requires real-time, highly accurate data analysis and the presentation of concrete improvement proposals based on that analysis, which conventional systems are unable to adequately address.

[0769] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0770] In this invention, the server includes means for collecting motion information using an image acquisition device and analyzing the user's position in the workspace, means for planning an optimal motion path using a generative model, and means for providing the planned motion path information to the user's display device. This makes it possible to analyze the worker's movements in real time and quickly provide a path that achieves optimal work efficiency.

[0771] An "image acquisition device" is a photographic device used to collect operational information within a business office.

[0772] "Motion information" refers to data related to the user's position and movement patterns within the workspace.

[0773] "Analysis" is the process of determining the user's location and actions based on the acquired data.

[0774] A "generative model" is an algorithm that uses artificial intelligence technology to plan and propose the optimal action path and response plan.

[0775] A "movement path" is an optimized route for workers to efficiently carry out their tasks.

[0776] A "display device" is a device used to provide users with planned information visually.

[0777] "Sales information" refers to commercial data related to past business activities.

[0778] "Environmental information" refers to data about external environmental factors.

[0779] "Job needs" refers to predicted information regarding the workload and required personnel within a sales office.

[0780] A "service proposal" is a suggestion for appropriate service based on the user's emotional state.

[0781] The embodiments for carrying out the present invention will be described below.

[0782] This system is designed to improve operational efficiency within sales offices and maximize customer satisfaction. Specifically, it is achieved through the interaction of servers, terminals, and users.

[0783] The server collects worker motion information using image acquisition devices installed at the branch office. For image processing, software libraries such as "OpenCV" are used to analyze the motion information. Furthermore, based on the analyzed data, a generative model is used to plan the optimal motion path. This generative model is implemented using machine learning frameworks such as "PyTorch" or "TensorFlow." The generated motion path information is provided in real time to the worker's display device, encouraging efficient work performance.

[0784] Furthermore, the server integrates and analyzes past sales and environmental data to create a model for predicting future job needs. This prediction uses predictive analytics libraries such as "scikit-learn" and "Keras," resulting in the provision of optimal job placement proposals to administrators.

[0785] Furthermore, for sentiment analysis, the server collects video and audio data from within the store and estimates the customer's emotional state using sentiment analysis APIs such as "Microsoft Azure Cognitive Services." Based on this, a generative model generates appropriate response suggestions, which are then provided to the employee's display device.

[0786] For example, if a camera captures a customer's confused expression in a sales office, the server analyzes this information in real time and notifies the staff with a suggested response, such as, "The customer appears confused. They may need assistance." This allows staff to respond to customers quickly and appropriately, leading to improved customer satisfaction.

[0787] Examples of prompt messages include, "Based on the current worker's location data, please suggest a workflow that optimizes work efficiency," and "Based on customer sentiment data, please suggest an appropriate response method."

[0788] In this way, the present invention intelligently manages various elements within a sales office and aims to improve the overall business process.

[0789] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0790] Step 1:

[0791] The server collects video data from image acquisition devices installed at the branch office. This data is used to capture the movements of workers. The server uses the collected video data as input and analyzes the workers' positions in real time using image processing libraries such as "OpenCV". As a result of the analysis, the specific location information and movement patterns of the workers are output as text data.

[0792] Step 2:

[0793] The server uses the worker's location information obtained in Step 1 as input and utilizes a generating AI model. Specifically, it uses the prompt message "Based on the current worker's location data, please suggest a movement path that optimizes work efficiency" to generate the optimal route. The generating model outputs the optimized route, which is then sent to the worker's terminal. The terminal visually displays this route information to the user and suggests a new work route.

[0794] Step 3:

[0795] The server analyzes historical sales information and external environment information stored in the database. Analysis libraries such as "scikit-learn" and "Keras" are used for the analysis. This data is used as input to predict future job needs. The predicted personnel needs and placement plans are output and notified to the administrator's terminal. The administrator then adjusts the personnel plan based on this information.

[0796] Step 4:

[0797] The server acquires video and audio data through cameras and microphones within the store and analyzes customer emotions using APIs such as "Microsoft Azure Cognitive Services". This data is used to understand the user's emotional state, and the analysis results output emotion evaluation data. The server inputs this emotion data into a generative model and generates appropriate response suggestions using the prompt message "Based on the customer's emotion data, please suggest an appropriate response method". The generated response suggestions are output to the terminal, providing instructions to the store staff. The store staff then handles customer interactions according to these instructions.

[0798] In each step, the server, terminal, and user collect, analyze, optimize, and display data based on their respective roles, aiming to improve operational efficiency within the sales office and enhance customer satisfaction.

[0799] (Application Example 2)

[0800] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0801] In modern work environments and customer service, there is a demand for quick and accurate responses to diverse customer needs. However, traditional systems have struggled to properly understand customer emotions and provide services accordingly. Furthermore, optimizing worker movement and staffing to improve operational efficiency is necessary, but achieving this in real time is also a challenging task.

[0802] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0803] In this invention, the server includes means for acquiring visual and auditory information and analyzing the location of personnel within the work environment; means for designing an optimal movement path based on the analysis results; means for outputting the designed movement path information; means for estimating emotions based on a person's facial expressions and voice and generating response plans adapted to the visitor's emotions; means for outputting the generated response plans; means for predicting future personnel demand using previous external information; means for optimizing personnel allocation based on the prediction results; means for outputting the allocation information; and means for reporting customer service advice based on emotion analysis results in real time. This enables the provision of highly accurate services tailored to customer emotions and improves operational efficiency.

[0804] "Visual and auditory information" refers to the collective term for visual and audio data acquired using cameras and microphones.

[0805] "Means for analyzing the position of personnel within a work environment" refers to technologies that use visual information to detect and recognize the current position and movement of people within a work space.

[0806] "Methods for designing optimal travel routes" refers to a technology that calculates and proposes a route that allows workers to move efficiently, based on analysis results.

[0807] "Means for outputting designed travel path information" refers to methods or technologies for visually or audibly presenting the calculated optimal travel path to the worker.

[0808] "Means for estimating emotions based on a person's facial expressions and voice" refers to a technology that analyzes an individual's facial expressions and tone of voice to estimate their emotional state.

[0809] "Methods for generating response plans adapted to the visitor's emotions" refers to techniques that take estimated emotions into consideration and create appropriate countermeasures and customer service plans for that situation.

[0810] "Means for outputting generated response plans" refers to methods for displaying or communicating the created customer service plans to relevant staff or terminals.

[0811] "Methods for predicting future personnel demand using past external information" refers to techniques that statistically predict future personnel allocation needs using past data and external insights.

[0812] "Methods for optimizing staffing" refer to techniques for planning the optimal staffing arrangement based on predicted staffing needs.

[0813] A "means for outputting deployment information" refers to a mechanism for informing stakeholders and related systems of the details of the planned personnel deployment.

[0814] "A method for reporting customer service advice based on emotion analysis results in real time" refers to a technology that immediately communicates areas for improvement and recommended actions for customer service to the person in charge, based on the results of emotion analysis.

[0815] The system realizing this invention is designed to optimize personnel location, movement paths, customer sentiment, and staffing within a work environment using visual and auditory information. The server utilizes cameras and microphones to acquire video and audio from within the store. This allows for the analysis of worker and customer locations and the design of optimal movement paths. Software such as OpenCV and TensorFlow are used in this process.

[0816] The server also analyzes facial and audio data extracted from the video to estimate the customer's emotions. Based on the results obtained by the emotion engine, it generates service suggestions tailored to the customer's needs and notifies store staff via smart devices. Firebase is used for real-time notifications.

[0817] Users can visually receive these customer service suggestions through smart glasses or smartphones and respond immediately. For example, if the system determines that a customer is confused, the smart glasses display will show a message saying, "The customer may need help. Please speak to them."

[0818] The server further predicts future staffing needs based on past sales and customer data. Data analysis using Pandas and Scikit-learn optimizes staffing in real time. As a result, store managers can allocate staff efficiently. For example, it can predict staff shortages during peak seasons like the end of the year and take appropriate measures.

[0819] Example prompt: "Based on the latest sentiment analysis data, generate advice on recommended customer service actions when a customer's smile is detected."

[0820] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0821] Step 1:

[0822] The server acquires video and audio data from inside the store via cameras and microphones. It receives this data as input and performs image analysis using OpenCV. The output is location information of workers and visitors. This location information is stored in a database.

[0823] Step 2:

[0824] The server uses TensorFlow to design the optimal travel path based on the location information obtained in Step 1. This design also takes into account past travel patterns and the store's layout. The server then generates the calculated travel path as output and prepares it for transmission to the smart device.

[0825] Step 3:

[0826] The server extracts facial expressions from video data and processes audio data to estimate the customer's emotions using an emotion engine. Inputs include specific facial patterns and voice tone, and the output is an estimated emotional state. Based on this, the server determines whether the customer is confused or satisfied.

[0827] Step 4:

[0828] The server uses a generative AI model, based on the estimated emotional state, to generate appropriate customer service suggestions for customers according to the prompt text. The input is the emotional state and standard customer service protocols, and the output is a specific response suggestion.

[0829] Step 5:

[0830] The server sends the generated customer service suggestions to the device via Firebase. The user receives the suggestions through smart glasses or a smartphone display and responds to the customer based on them. Here, the device receives input (receives the customer service suggestions) and presents them as visual output.

[0831] Step 6:

[0832] The server uses Pandas and Scikit-learn to analyze historical sales and customer data to predict future staffing needs. Historical datasets are used as input, and the output provides the number of staff required for the next shift. This output is sent to the administrator's terminal to help optimize staffing.

[0833] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0834] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0835] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0836] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0837] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0838] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0839] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0840] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0841] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0842] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0843] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0844] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0845] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0846] 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.

[0847] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0848] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0849] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0850] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0851] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0852] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0853] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0854] The following is further disclosed regarding the embodiments described above.

[0855] (Claim 1)

[0856] A means for acquiring video data and analyzing the location of workers within the sales office,

[0857] A means for designing the optimal traffic flow based on the above analysis results,

[0858] A means of outputting the designed movement flow information,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] A method for predicting personnel demand at a given time using historical external data,

[0862] A means for optimizing personnel allocation based on the above prediction results,

[0863] A means for outputting the above-mentioned arrangement information,

[0864] The system according to claim 1, including the following:

[0865] (Claim 3)

[0866] A means of estimating customer emotions using video and audio data,

[0867] A means for generating appropriate response plans based on the above estimation results,

[0868] A means of outputting the generated response proposal,

[0869] The system according to claim 1, including the following:

[0870] "Example 1"

[0871] (Claim 1)

[0872] A means for acquiring video information and analyzing the location of workers within the facility,

[0873] A means for designing the optimal route based on the analysis results,

[0874] A means of presenting the designed route information,

[0875] A means of predicting the personnel needs at a given time using historical statistical information,

[0876] A means of adjusting personnel deployment based on the above prediction results,

[0877] A means of estimating customer emotions using sound and video information,

[0878] A means for generating appropriate countermeasures based on the above estimation results,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, which includes a technique for predicting personnel demand using past statistical information.

[0882] (Claim 3)

[0883] The system according to claim 1, comprising technology for estimating customer emotions and generating response suggestions based on the results.

[0884] "Application Example 1"

[0885] (Claim 1)

[0886] A means for acquiring video information and analyzing the location of workers within the facility,

[0887] A means for designing the optimal travel path based on the above analysis results,

[0888] A means for outputting designed travel path information,

[0889] A means for optimizing the movement of work equipment based on information analysis,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] A means of predicting personnel demand at a given time using past external information,

[0893] A means for optimizing personnel allocation based on the above prediction results,

[0894] A means for outputting the above-mentioned arrangement information,

[0895] A means of suggesting appropriate breaks to workers based on the analysis of information,

[0896] The system according to claim 1, including the following:

[0897] (Claim 3)

[0898] A means of estimating customer emotions using video and audio information,

[0899] A means for generating appropriate response plans based on the above estimation results,

[0900] A means of outputting the generated response proposal,

[0901] Based on the emotional analysis of workers within the facility, a means of instructing work to be suspended,

[0902] The system according to claim 1, including the following:

[0903] "Example 2 of combining an emotion engine"

[0904] (Claim 1)

[0905] A means for collecting motion information using an image acquisition device and analyzing the user's position in the workspace,

[0906] Based on the above analysis results, a means for planning the optimal operating path using a generative model,

[0907] Means for providing planned movement path information to the user's display device,

[0908] A system that includes this.

[0909] (Claim 2)

[0910] A system according to claim 1, which is a means of predicting future job needs and optimizing job placement by utilizing past sales information and environmental information, and which provides the above-mentioned optimization information.

[0911] (Claim 3)

[0912] The system according to claim 1, which uses a generative model that analyzes video and audio data to estimate the emotional state of a user and generates response suggestions based on the estimation results, and displays the generated response suggestions.

[0913] "Application example 2 when combining with an emotional engine"

[0914] (Claim 1)

[0915] A means for acquiring visual and auditory information and analyzing the position of personnel within the work environment,

[0916] A means for designing the optimal travel path based on the above analysis results,

[0917] A means for outputting designed travel path information,

[0918] A means for estimating emotions based on a person's facial expressions and voice, and generating response plans adapted to the visitor's emotions,

[0919] A means of outputting the generated countermeasures,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] A method for predicting future personnel demand using previous external information,

[0923] A means for optimizing personnel allocation based on the above prediction results,

[0924] A means for outputting the above-mentioned arrangement information,

[0925] A means of reporting customer service advice in real time based on the results of emotion analysis,

[0926] The system according to claim 1, including the following:

[0927] (Claim 3)

[0928] Includes means for analyzing visitors' emotions and suggesting recommended actions based on their emotional state.

[0929] The system according to claim 1. [Explanation of Symbols]

[0930] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring video data and analyzing the location of workers within the sales office, A means for designing the optimal traffic flow based on the above analysis results, A means of outputting the designed movement flow information, A system that includes this.

2. A method for predicting personnel demand at a given time using historical external data, A means for optimizing personnel allocation based on the above prediction results, A means for outputting the above-mentioned arrangement information, The system according to claim 1, including the following:

3. A means of estimating customer emotions using video and audio data, A means for generating appropriate response plans based on the above estimation results, A means of outputting the generated response proposal, The system according to claim 1, including the following:

Images