system

Abstract

We provide the system. [Solution] Means for collecting customer interaction data, A means of training customer service skills using a machine learning algorithm based on the aforementioned collected data, A means for transmitting the trained customer service skills to a humanoid terminal, A humanoid terminal equipped with sensors for customer detection and recognition, The humanoid terminal provides a means for giving voice guidance to the customer, A means for collecting and analyzing feedback on the aforementioned customer service interactions to improve the customer service model, 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 method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the customer service industry, a shortage of staff and differences in customer service skills among staff affect customer satisfaction. In particular, it is difficult to maintain a certain level of customer service quality when there are peak seasons or frequent staff replacements. In addition, training new staff and inheriting customer service know-how require a lot of time and cost. An effective means to solve such problems is required.

Means for Solving the Problems

[0005] This invention provides a system that collects customer interaction data and uses machine learning algorithms to train customer service skills based on that data. The customer service skills trained from the collected data are transmitted and applied to a humanoid terminal. The humanoid terminal is equipped with sensors to detect and recognize customers and provides voice guidance to customers. Furthermore, it continuously improves the customer service model by collecting and analyzing feedback on customer service interactions. This means that effective new employee training and knowledge transfer are possible while maintaining a consistent level of customer service quality.

[0006] A "customer" is someone who uses a store or service, and is the target of customer service.

[0007] "Interaction data" refers to data about conversations and actions that take place between customers and humanoid terminals or staff.

[0008] A "machine learning algorithm" is a method in which a computer uses digital data to gain experience and predict patterns, and it is used in customer service skills training in this invention.

[0009] "Customer service skills" refer to the techniques and knowledge required for interacting with customers, explaining products, and answering their questions.

[0010] A "humanoid terminal" is a robot that resembles a human and has functions specifically designed for customer service.

[0011] A "sensor" is a device installed in a humanoid terminal that has the function of detecting and recognizing customers.

[0012] "Voice guidance" refers to the act of a humanoid terminal using voice to present information and guide customers.

[0013] "Feedback" refers to the reactions, opinions, and results obtained during customer service interactions, and is data used for system improvement. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This 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 a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

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

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

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

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

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

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

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

[0022] [First Embodiment]

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

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

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

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

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

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

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

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

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

[0035] This invention is a system for efficiently and effectively performing customer service in stores. Specifically, it collects customer service data through customer interaction, uses this data to train customer service skills using machine learning algorithms, and applies this training to a humanoid terminal. This can solve challenges in the customer service industry, such as staff shortages and inconsistent quality.

[0036] Data collection and learning

[0037] The server records conversations and actions between staff and customers within the store and collects this interaction data.

[0038] The server uses machine learning algorithms to extract effective patterns and skills in customer service from the collected interaction data and build a learning model.

[0039] Application to humanoid terminals

[0040] The terminal (humanoid) receives customer service skill models sent from the server and uses them to interact with customers.

[0041] The terminal uses its built-in sensors to recognize customers and approaches them within a specific operating range.

[0042] Customer support

[0043] When a user (customer) approaches the humanoid terminal, the terminal greets them and responds to their questions and requests.

[0044] The terminal provides product information through voice guidance and offers recommendations for products and promotional campaigns.

[0045] Feedback and model improvement

[0046] The server periodically collects digital data recorded during customer service interactions with the humanoid terminal and analyzes it as feedback data.

[0047] The server uses the feedback to improve its customer service model and incorporates that feedback into future interactions.

[0048] Specific example

[0049] For example, when a user asks, "Which items are on sale?", the terminal immediately replies, "The items on this shelf are currently on sale." For this response to function smoothly, data analysis on the server, learning of customer service skills, and application to the terminal must work together in coordination. This system allows customers to receive quick and accurate service, thus improving customer satisfaction.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The server collects conversation and behavioral data between staff and customers in the store in real time every day. This includes voice data and behavioral information, all stored in digital format.

[0053] Step 2:

[0054] The server inputs the collected data into a machine learning algorithm to learn effective communication patterns and response methods in customer service. Through data analysis, the customer service model is trained and becomes available for use.

[0055] Step 3:

[0056] The server transmits a trained customer service skills model to the humanoid terminal. This model is designed to handle various customer interaction scenarios.

[0057] Step 4:

[0058] The terminal receives the transmitted model and applies it to the system. The model is installed internally at startup, making it available for use at any time.

[0059] Step 5:

[0060] When a user enters the store, the terminal uses sensors to detect the customer and provides an appropriate greeting via voice, such as, "Hello, are you looking for something?"

[0061] Step 6:

[0062] When a user asks a question or makes a request, the device responds immediately based on a model trained on the server. This includes providing detailed product information or recommending specific products.

[0063] Step 7:

[0064] The terminal registers feedback data obtained during conversations with customers in real time, preparing to use it to improve customer service.

[0065] Step 8:

[0066] The server periodically collects feedback data and performs analysis to further improve the model. This process is essential for continuously evolving the customer service model.

[0067] (Example 1)

[0068] 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."

[0069] The challenges in the service industry include addressing labor shortages and inconsistencies in service quality, and providing a consistently high-quality customer experience. In particular, replicating and providing the customer service skills of excellent staff is essential for efficient and effective customer interaction.

[0070] 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.

[0071] In this invention, the server includes a device for collecting information, a device for learning skills using machine learning techniques based on the collected information, and a device for transmitting the learned skills to an automated device. This enables users to receive a stable service and improves the uniformity and quality of the service.

[0072] "Information" includes data and records related to the interaction between the user and the automated device.

[0073] "Machine learning techniques" are technologies that use algorithms to build learning models based on collected data, and then use those models to make predictions and decisions.

[0074] "Automated equipment" refers to devices such as robots that are designed to partially or completely replace human work.

[0075] "Device" refers to an entire machine or system designed to perform a specific function.

[0076] A "sensor" is a device that can detect changes in the environment and measure or record that information.

[0077] A "learning model" is a reference model based on rules and patterns derived from data using machine learning algorithms.

[0078] A "guide" is a means of providing information that uses audio or text to guide users and encourage desirable actions and decisions.

[0079] "Evaluation" is the process of measuring and analyzing the results of interactions with users.

[0080] "Person" refers to an individual who possesses excellent skills and experience in customer service.

[0081] This invention is a system for efficiently and effectively performing customer service tasks within a store. The embodiments for carrying out the invention are as follows:

[0082] The server collects customer-staff interaction data using microphones and cameras installed within the store. Specifically, it uses a speech recognition system to transcribe conversations into text and collects customer behavior data through cameras. This data is then converted into a format suitable for machine learning.

[0083] Subsequently, the server uses machine learning libraries such as Python's TENSORFLOW® and Scikit-learn to build a model that learns customer service skills from the collected data. The server combines multiple algorithms to select the optimal model and sends it to the automated terminal.

[0084] The terminal receives this model and uses its built-in sensors to recognize and detect customers within the store. The terminal can approach customers at an appropriate distance and provide product and promotional information through voice guidance. The voice recognition system used may include Google® Cloud Speech-to-Text.

[0085] Furthermore, the server collects the results of interactions with terminals as digital data and analyzes it as feedback. Based on this feedback data, the server further improves its learning model and aims to enhance its customer service skills.

[0086] For example, when a user asks, "Which items are on sale?", the device immediately replies, "The items on this shelf are currently on sale." This enables quick and appropriate responses.

[0087] An example of a prompt to input into a generative AI model would be, "Please tell me how to collect the data necessary to analyze customer conversations and behavior patterns in a store using speech recognition technology."

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] The server collects customer and staff interaction data from microphones and cameras installed within the store. Inputs include audio and video data, while outputs include text data and behavioral pattern data. A speech recognition system converts audio to text, and an image recognition algorithm analyzes actions and facial expressions, saving the data as structured data.

[0091] Step 2:

[0092] The server executes machine learning algorithms using the accumulated data. The input is previously collected interaction data, and the output is a trained customer service skills model. The algorithm is executed using the Python TensorFlow library to extract effective patterns in customer interactions and train the model.

[0093] Step 3:

[0094] The server sends the trained customer service skills model to the automated terminal. The input is the trained model, and the output is an update file in a format usable by the terminal. This file is transferred to the terminal over the network and applied to the terminal's memory.

[0095] Step 4:

[0096] The terminal uses its built-in sensors to detect and recognize users who visit the store. The input is environmental data acquired from the sensors, and the output is recognized customer information. In terms of operation, it measures distance using an infrared sensor and performs facial recognition of the customer using a camera.

[0097] Step 5:

[0098] The device interacts with the user and provides voice guidance. Input is voice instructions from the user, and output is the device's verbal response. Google Cloud Speech-to-Text is used to generate text from speech, and information is provided using a pre-trained model based on that text.

[0099] Step 6:

[0100] The server collects and analyzes feedback data from interactions performed by the terminal. The input is the result of each interaction, and the output is an evaluation of customer service and points for improvement. The collected data is statistically analyzed to generate insights for future model improvements.

[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 retail stores face challenges such as inconsistent customer service quality and the time and cost involved in improving staff skills. Furthermore, providing excellent customer service requires personalized attention, and a system is needed to efficiently achieve this.

[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 collecting customer interaction data, means for training customer service skills using a machine learning algorithm based on the collected data, and means for transmitting the trained customer service skills to a humanoid terminal. This enables store staff to provide efficient and high-quality personalized service.

[0106] "Customer interaction data" refers to digital information that records customers' actions within a store and the content of their conversations with store staff.

[0107] A "machine learning algorithm" is an algorithm that learns patterns from data and performs predictions and classifications.

[0108] "Customer service skills" refer to the techniques and knowledge used to improve the quality of services provided to customers.

[0109] A "humanoid terminal" is an autonomous device that mimics the form of a human being and interacts with customers through dialogue and actions.

[0110] A "detection device" is a device used to sense the surrounding environment or the presence of an object.

[0111] "Voice guidance" refers to a function that uses voice to transmit information and guide customers.

[0112] "Feedback" is a system that incorporates evaluations and opinions based on past actions and results.

[0113] A "glasses-type terminal" is a device that has the function of visually presenting information and is used by the wearer.

[0114] A "display device" is hardware used to visually display information.

[0115] "Product recommendation" is the activity of recommending products that meet customer needs.

[0116] This invention is a system for streamlining customer service operations within stores and providing effective customer service. The server collects customer-staff interaction data within the store and uses machine learning algorithms to train customer service skills based on this data. This method uses TensorFlow to build a model and extract effective patterns that improve staff responses.

[0117] The server transmits trained customer service skills to a humanoid terminal. This terminal uses OpenCV to detect and recognize customers and provides voice guidance to them. This voice guidance provides product information and service details tailored to the customer's needs in real time, aiming to improve customer satisfaction.

[0118] Furthermore, the server uses a glasses-type terminal to display customer information and product suggestions to staff. This glasses-type terminal uses Flask to receive data from the server and provides visual information to staff, thereby improving the efficiency of customer service.

[0119] As a concrete example, if a user enters a store and asks the humanoid terminal, "Which items are on sale today?", the terminal will respond, "These sneakers on this shelf are available at a special price." This stimulates the customer's desire to purchase, and allows store staff to quickly follow up. As an example of a prompt to be input to the generating AI model, information is input in the format of, "A woman in her 30s, generate a script to inform you about new products based on her past purchase history."

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The server collects real-time interaction data between users and humanoid terminals within the store. This input data includes voice, video, and text. The collected data is stored in a database and forms the basis for subsequent analysis.

[0123] Step 2:

[0124] The server executes machine learning algorithms using the collected interaction data. Using Python and TensorFlow, it extracts effective customer service patterns from the interaction data. This process involves data analysis and the generation of appropriate customer service skill models. The goal of these models is to improve customer service throughout the entire shop.

[0125] Step 3:

[0126] The server sends the generated customer service skill model to a humanoid terminal. Based on the received model, the terminal takes appropriate action when a customer approaches. The input is the customer service model, and the output is voice guidance and suggestions for the customer. The terminal uses speech synthesis technology to provide customer-friendly navigation.

[0127] Step 4:

[0128] The device sends feedback received during customer interactions to the server. This feedback includes customer facial expressions and tone of voice. This data is then fed back into the learning model to help provide a more optimal response in future interactions.

[0129] Step 5:

[0130] The server also provides information from the customer service model to the glasses-type terminal. Based on this information, the glasses-type terminal displays real-time customer suggestions to the store staff. Inputs include basic customer information and purchase history, while output is customized product suggestions. Flask is used to send this data to the glasses-type terminal, improving operational efficiency.

[0131] 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.

[0132] This invention is a system that enables more personalized responses by accurately recognizing customer emotions and combining them with an emotion engine when a humanoid terminal performs customer service tasks. The system includes an emotion engine for analyzing the customer's visual and auditory information, and dynamically optimizes customer service responses by detecting and analyzing the emotional state in real time.

[0133] Data collection and emotion recognition

[0134] The server stores customer interaction data collected within the store, which includes not only traditional customer service process data but also emotional data such as facial expressions and tone of voice.

[0135] The device uses its built-in emotion engine to recognize the user's emotions in real time. It also utilizes a facial expression analysis module and a voice analysis module to deepen its understanding of the customer's content.

[0136] Training and application of customer service skills

[0137] The server uses machine learning based on collected emotional data to train an advanced customer service skills model that includes emotional responses.

[0138] The terminal receives the latest model information from the server and uses it to interact with customers. It detects emotional changes in real time and adjusts the tone and content of the conversation as needed.

[0139] Examples of customer service

[0140] If the user has a depressed expression, the device uses an emotion engine to recognize this state and suggests encouraging words or relaxing services.

[0141] For example, you could change your approach, such as saying, "You seem a little down today. Please let me know if there's anything I can do to help."

[0142] Feedback and model improvement

[0143] The server collects and analyzes emotional feedback data obtained during customer service interactions with the humanoid terminal. This allows for continuous improvement of more accurate and personalized customer service skills.

[0144] This process ensures that the customer service model is constantly updated to accommodate real-world customer service scenarios.

[0145] As described above, the present invention enables customer service tailored to the customer's emotional state, thereby improving customer satisfaction.

[0146] The following describes the processing flow.

[0147] Step 1:

[0148] The server routinely collects audio and visual data to cover the entire interaction between staff and customers within the store. This includes not only conventional conversational data, but also emotional data such as customers' facial expressions and tone of voice.

[0149] Step 2:

[0150] The server feeds the collected data into machine learning algorithms to train customer service skill models. This enables responses that take customer emotions into account.

[0151] Step 3:

[0152] The server sends a trained customer service skills model to the humanoid terminal. The model is then ready to be applied in customer interactions.

[0153] Step 4:

[0154] The terminals are equipped with the latest models and are ready for customer service. This includes real-time emotion recognition capabilities using an emotion engine.

[0155] Step 5:

[0156] When a user approaches the device, the device detects the user using sensors and begins analyzing their facial expressions and tone of voice using its emotion engine.

[0157] Step 6:

[0158] Based on the results of emotion recognition, the device adjusts its tone of voice and message content to greet the user and answer questions. If the customer is feeling anxious, it will use reassuring words.

[0159] Step 7:

[0160] When a user asks a question or makes a request, the device considers the user's emotions and provides the most appropriate response. For example, it flexibly offers an emotionally sensitive answer such as, "Many people like this product."

[0161] Step 8:

[0162] The server periodically collects and analyzes feedback data on emotional interactions recorded by the humanoid terminals. This data is used to further improve the customer service skills model.

[0163] This will enable the provision of personalized customer service that takes emotions into account, which is expected to improve customer satisfaction.

[0164] (Example 2)

[0165] 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 will be referred to as the "terminal."

[0166] In modern customer service systems, accurately recognizing and responding appropriately to individual customer emotions and states is difficult. This can result in decreased customer satisfaction and inadequate service. Furthermore, traditional customer service methods often lack the real-time response needed to address changes in customer emotions.

[0167] 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.

[0168] In this invention, the server includes means for collecting information relating to customer interactions, means for training response techniques using a learning algorithm based on the collected information, and means for identifying customer emotions in real time and adjusting responses accordingly. This enables accurate recognition of the customer's emotional state and the provision of more appropriate and personalized services.

[0169] "Interaction information" refers to the record of all communication and interaction that takes place between the customer and the autonomous device, including the customer's facial expressions, tone of voice, and verbal responses.

[0170] A "learning algorithm" is a method used by computer systems to automatically acquire and apply patterns and rules based on collected data, thereby improving their response skills.

[0171] An "autonomous terminal" is a machine or device that uses built-in sensors and processing units to interact with customers without external instructions, and is designed to perform specific tasks.

[0172] A "sensing device" refers to a device installed on an autonomous terminal to physically detect information such as the presence, movement, voice, and facial expressions of a customer.

[0173] "Customer service techniques" is a general term for the skills and methods necessary to facilitate communication with customers and improve their satisfaction, and these are implemented using autonomous terminals.

[0174] "Feedback evaluation" refers to information such as opinions and impressions obtained after interactions with customers, which is data that can be used to improve customer service techniques and the overall system.

[0175] This system aims to instantly understand customer emotions and provide appropriate service in customer service operations by using autonomous terminals and emotion recognition technology.

[0176] First, the terminal is equipped with a high-precision camera and a voice recognition microphone, which collects information about interactions such as facial expressions and tone of voice as soon as a customer enters the store. The collected data is analyzed in real time to determine the customer's emotional state. An emotion recognition engine is used in this analysis. Specifically, the software could be a system equipped with advanced image analysis libraries and voice analysis algorithms.

[0177] Next, the acquired data is transferred to a server, which uses a learning algorithm to train its response technology. By analyzing the large amount of accumulated emotional data, the server builds a generative AI model and trains it to respond to diverse customer emotional states. This model is reflected on the terminal, enabling immediate, personalized responses to customers.

[0178] For example, if a user visits a store looking tired, the device can instantly detect their emotional state and suggest products with relaxation effects. An example of a prompt message could be, "Please suggest relaxing products to a tired customer," which can be used to instruct the AI ​​model.

[0179] This system enables the provision of flexible and appropriate services tailored to the customer's emotional state, thereby improving customer satisfaction.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The device collects visual and auditory information using a camera and microphone when a customer enters the store. Specifically, it captures the customer's face with the camera and records their voice tone and volume with the microphone. The input consists of the customer's facial expression data and audio data. The output is this data obtained in a format suitable for sentiment analysis.

[0183] Step 2:

[0184] The terminal inputs the collected data into the emotion recognition engine. The emotion recognition engine uses a facial expression analysis module to analyze facial features from the collected image data and a voice analysis module to analyze the tone of the recorded data. Specific data processing involves feature extraction and mapping to emotional states. The output is the customer's emotional state (e.g., joy, sadness, surprise).

[0185] Step 3:

[0186] The server receives emotional state data transmitted from the terminal. The input is emotional state data analyzed in real time. Based on this, the server applies a learning algorithm and trains a generative AI model with new response techniques. The specific data calculations include analysis using past datasets and construction of response patterns, and the output is an updated generative AI model.

[0187] Step 4:

[0188] The terminal receives the latest AI model from the server and uses it to interact with customers. The input is the updated model data of the interaction technology received from the server. Specifically, its actions include generating voice responses to customer questions and providing appropriate suggestions and guidance. The output is personalized voice-based interaction with the customer.

[0189] Step 5:

[0190] The server collects and analyzes feedback data after customer interactions. It uses customer feedback and terminal response evaluation data as input. Based on this, data calculations are performed to further improve response techniques. Specifically, the feedback is analyzed to identify areas for model improvement, and the output becomes an improvement plan for the next model update.

[0191] (Application Example 2)

[0192] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0193] Traditional customer service systems have a problem in that they have difficulty appropriately recognizing customer emotions and providing individualized responses. In particular, it is difficult to analyze customers' facial expressions and tone of voice in real time, which can result in delays in providing product recommendations and services that meet their needs, potentially leading to decreased customer satisfaction. Therefore, it is necessary to solve these problems.

[0194] 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.

[0195] In this invention, the server includes means for collecting interaction data with customers, means for training customer service skills using a machine learning algorithm based on the collected data, and means for transmitting the trained customer service skills to an autonomous device. This makes it possible to accurately recognize the emotional state of the customer and dynamically adjust product recommendations based on that emotion.

[0196] A "customer" is someone who receives goods or services, and is an important stakeholder for a company.

[0197] "Interaction data" refers to data related to various interactions that occur with customers, including information about their emotions and behaviors.

[0198] A "machine learning algorithm" is a computational method that automatically performs data analysis and prediction by finding patterns based on large amounts of data.

[0199] "Customer service skills" refer to the techniques used to introduce products and services to customers and increase their satisfaction.

[0200] An "autonomous device" is a mechanical device that can make its own decisions and perform various tasks in a self-contained manner.

[0201] A "sensory device" is equipment that senses information from the outside and processes it as digital data.

[0202] An "integration method" is a way of combining multiple pieces of information or functions to create an overall effective system.

[0203] "Feedback" refers to information that shows reactions to or evaluations of actions and results, and serves as a basis for improvement or change.

[0204] The system of the present invention is designed to efficiently collect and analyze customer interaction data and to provide personalized service based on emotions. The server first collects data obtained from the customer's facial expressions and voice. This data is acquired using a camera sensor and microphone as sensory devices. Based on the collected data, the server trains customer service skills using a machine learning algorithm and transmits these skills to an autonomous device (e.g., a customer service robot).

[0205] The autonomous terminal devices utilize trained customer service skills to analyze customer emotions in real time. Software such as OpenCV and Google Speech-to-Text API are used for facial expression and voice analysis. In particular, the system incorporates an integrated mechanism to dynamically adjust product recommendations based on customer emotions, providing the most appropriate language guidance to the customer.

[0206] For example, if the system detects that a customer is feeling stressed in a store, the autonomous device can make a customized suggestion in real time, such as, "You seem to be having a tough day. We have a new tea that can help you relax; would you like to try it?"

[0207] Throughout this process, customer feedback is collected again on the server and analyzed to improve the customer service model. This enables further improvements in customer service skills. As an example of a prompt for the generated AI model, an effective expression would be, "If the customer appears stressed, what suggestions can help them relax?"

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server collects customer facial and voice data using camera sensors and microphones. The input is the customer's face and voice, and the output is digitized facial image data and voice data. This data serves as foundational information for analyzing customer emotions.

[0211] Step 2:

[0212] The server inputs the collected digitized data into the emotion engine and applies facial expression analysis algorithms and voice analysis algorithms. The inputs are facial expression image data and voice data, and the outputs are parameters indicating the customer's emotional state. By recognizing the customer's emotions in real time using the emotion engine, the server quantifies how the customer is feeling.

[0213] Step 3:

[0214] The server trains its customer service skills using a machine learning algorithm based on emotional state parameters. The input is the customer's emotional state parameters, and the output is the updated customer service skill model. This model is constantly being improved to provide the optimal customer service method tailored to the customer's emotions.

[0215] Step 4:

[0216] The autonomous terminal device receives customer service technology models transmitted from the server and utilizes them for customer service. The input is the updated customer service technology model, and the output is an optimized response to the customer. In this process, product recommendations are dynamically adjusted according to the customer's real-time emotions.

[0217] Step 5:

[0218] An autonomous device collects feedback from users about their customer service experience and sends it back to the server. The input is feedback data obtained from the user, and the output is additional information for the customer service model, including suggestions for improvement. Based on this feedback, customer service skills are further improved and utilized in future interactions.

[0219] Step 6:

[0220] The server analyzes the collected feedback and updates the customer service model. The input is feedback data, and the output is an improved customer service technology model. This continuously improves customer service and increases customer satisfaction.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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".

[0237] This invention is a system for efficiently and effectively performing customer service in stores. Specifically, it collects customer service data through customer interaction, uses this data to train customer service skills using machine learning algorithms, and applies this training to a humanoid terminal. This can solve challenges in the customer service industry, such as staff shortages and inconsistent quality.

[0238] Data collection and learning

[0239] The server records conversations and actions between staff and customers within the store and collects this interaction data.

[0240] The server uses machine learning algorithms to extract effective patterns and skills in customer service from the collected interaction data and build a learning model.

[0241] Application to humanoid terminals

[0242] The terminal (humanoid) receives customer service skill models sent from the server and uses them to interact with customers.

[0243] The terminal uses its built-in sensors to recognize customers and approaches them within a specific operating range.

[0244] Customer support

[0245] When a user (customer) approaches the humanoid terminal, the terminal greets them and responds to their questions and requests.

[0246] The terminal provides product information through voice guidance and offers recommendations for products and promotional campaigns.

[0247] Feedback and model improvement

[0248] The server periodically collects digital data recorded during customer service interactions with the humanoid terminal and analyzes it as feedback data.

[0249] The server uses the feedback to improve its customer service model and incorporates that feedback into future interactions.

[0250] Specific example

[0251] For example, when a user asks, "Which items are on sale?", the terminal immediately replies, "The items on this shelf are currently on sale." For this response to function smoothly, data analysis on the server, learning of customer service skills, and application to the terminal must work together in coordination. This system allows customers to receive quick and accurate service, thus improving customer satisfaction.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The server collects conversation and behavioral data between staff and customers in the store in real time every day. This includes voice data and behavioral information, all stored in digital format.

[0255] Step 2:

[0256] The server inputs the collected data into a machine learning algorithm to learn effective communication patterns and response methods in customer service. Through data analysis, the customer service model is trained and becomes available for use.

[0257] Step 3:

[0258] The server transmits a trained customer service skills model to the humanoid terminal. This model is designed to handle various customer interaction scenarios.

[0259] Step 4:

[0260] The terminal receives the transmitted model and applies it to the system. The model is installed internally at startup, making it available for use at any time.

[0261] Step 5:

[0262] When a user enters the store, the terminal uses sensors to detect the customer and provides an appropriate greeting via voice, such as, "Hello, are you looking for something?"

[0263] Step 6:

[0264] When a user asks a question or makes a request, the device responds immediately based on a model trained on the server. This includes providing detailed product information or recommending specific products.

[0265] Step 7:

[0266] The terminal registers feedback data obtained during conversations with customers in real time, preparing to use it to improve customer service.

[0267] Step 8:

[0268] The server periodically collects feedback data and performs analysis to further improve the model. This process is essential for continuously evolving the customer service model.

[0269] (Example 1)

[0270] 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."

[0271] The challenges in the service industry include addressing labor shortages and inconsistencies in service quality, and providing a consistently high-quality customer experience. In particular, replicating and providing the customer service skills of excellent staff is essential for efficient and effective customer interaction.

[0272] 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.

[0273] In this invention, the server includes a device for collecting information, a device for learning skills using machine learning techniques based on the collected information, and a device for transmitting the learned skills to an automated device. This enables users to receive a stable service and improves the uniformity and quality of the service.

[0274] "Information" includes data and records related to the interaction between the user and the automated device.

[0275] "Machine learning techniques" are technologies that use algorithms to build learning models based on collected data, and then use those models to make predictions and decisions.

[0276] "Automated equipment" refers to devices such as robots that are designed to partially or completely replace human work.

[0277] "Device" refers to an entire machine or system designed to perform a specific function.

[0278] A "sensor" is a device that can detect changes in the environment and measure or record that information.

[0279] A "learning model" is a reference model based on rules and patterns derived from data using machine learning algorithms.

[0280] A "guide" is a means of providing information that uses audio or text to guide users and encourage desirable actions and decisions.

[0281] "Evaluation" is the process of measuring and analyzing the results of interactions with users.

[0282] "Person" refers to an individual who possesses excellent skills and experience in customer service.

[0283] This invention is a system for efficiently and high-qualityly implementing customer service operations within a store. The embodiments for implementing the invention are as follows.

[0284] The server collects customer-staff interaction data using microphones and cameras installed within the store. Specifically, it uses a speech recognition system to convert conversations into text and collects customer behavior data through cameras. This data is converted into a format suitable for machine learning.

[0285] After that, the server constructs a model for learning customer service skills from the collected data using machine learning libraries such as Python's TensorFlow and Scikit-learn. The server selects an optimal model by combining multiple algorithms and transmits it to an automated terminal.

[0286] The terminal receives this model and uses the installed sensors to recognize and detect customers within the store. The terminal can approach the customer at an appropriate distance and provide product information and campaign information through voice guidance. As the speech recognition system, Google Cloud Speech-to-Text, etc. are used.

[0287] Also, the server collects the results of the interaction by the terminal as digital data and analyzes it as feedback. Based on this feedback data, the server further improves the learning model to enhance customer service skills.

[0288] As a specific example, when the user asks "What products are on sale?", the terminal immediately answers "The products arranged on this shelf are currently on sale." Such quick and appropriate responses become possible.

[0289] Examples of prompt sentences input into the generative AI model may include content such as "Please teach me the method of collecting the data necessary for analyzing customer conversations and behavior patterns within the store using speech recognition technology."

[0290] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0291] Step 1:

[0292] The server collects customer and staff interaction data from microphones and cameras installed within the store. Inputs include audio and video data, while outputs include text data and behavioral pattern data. A speech recognition system converts audio to text, and an image recognition algorithm analyzes actions and facial expressions, saving the data as structured data.

[0293] Step 2:

[0294] The server executes machine learning algorithms using the accumulated data. The input is previously collected interaction data, and the output is a trained customer service skills model. The algorithm is executed using the Python TensorFlow library to extract effective patterns in customer interactions and train the model.

[0295] Step 3:

[0296] The server sends the trained customer service skills model to the automated terminal. The input is the trained model, and the output is an update file in a format usable by the terminal. This file is transferred to the terminal over the network and applied to the terminal's memory.

[0297] Step 4:

[0298] The terminal uses its built-in sensors to detect and recognize users who visit the store. The input is environmental data acquired from the sensors, and the output is recognized customer information. In terms of operation, it measures distance using an infrared sensor and performs facial recognition of the customer using a camera.

[0299] Step 5:

[0300] The terminal interacts with users to provide voice guidance. The input is voice instructions from users, and the output is the terminal's verbal response. Google Cloud Speech-to-Text is used to generate text from voice, and information is provided based on a pre-trained model using this text.

[0301] Step 6:

[0302] The server collects and analyzes feedback data on the interactions performed by the terminal. The input is the result for each interaction, and the output is the evaluation of customer service and improvement points. The collected data is statistically analyzed to generate insights for future model improvement.

[0303] (Application Example 1)

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

[0305] In modern stores, there are problems such as variations in the quality of customer service and the time and cost required for staff skill improvement. Furthermore, in order to provide excellent customer service, individual support is necessary, and a system for efficiently performing this is required. [[ID=二十二]]

[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 means.

[0307] In this invention, the server includes means for collecting interaction data with customers, means for training customer service skills using a machine learning algorithm based on the collected data, and means for transmitting the trained customer service skills to a humanoid terminal. This enables the store staff to provide efficient and high-quality individual support.

[0308] "Customer interaction data" refers to digital information that records customers' actions within a store and the content of their conversations with store staff.

[0309] A "machine learning algorithm" is an algorithm that learns patterns from data and performs predictions and classifications.

[0310] "Customer service skills" refer to the techniques and knowledge used to improve the quality of services provided to customers.

[0311] A "humanoid terminal" is an autonomous device that mimics the form of a human being and interacts with customers through dialogue and actions.

[0312] A "detection device" is a device used to sense the surrounding environment or the presence of an object.

[0313] "Voice guidance" refers to a function that uses voice to transmit information and guide customers.

[0314] "Feedback" is a system that incorporates evaluations and opinions based on past actions and results.

[0315] A "glasses-type terminal" is a device that has the function of visually presenting information and is used by the wearer.

[0316] A "display device" is hardware used to visually display information.

[0317] "Product recommendation" is the activity of recommending products that meet customer needs.

[0318] This invention is a system for streamlining customer service operations within stores and providing effective customer service. The server collects customer-staff interaction data within the store and uses machine learning algorithms to train customer service skills based on this data. This method uses TensorFlow to build a model and extract effective patterns that improve staff responses.

[0319] The server transmits trained customer service skills to a humanoid terminal. This terminal uses OpenCV to detect and recognize customers and provides voice guidance to them. This voice guidance provides product information and service details tailored to the customer's needs in real time, aiming to improve customer satisfaction.

[0320] Furthermore, the server uses a glasses-type terminal to display customer information and product suggestions to staff. This glasses-type terminal uses Flask to receive data from the server and provides visual information to staff, thereby improving the efficiency of customer service.

[0321] As a concrete example, if a user enters a store and asks the humanoid terminal, "Which items are on sale today?", the terminal will respond, "These sneakers on this shelf are available at a special price." This stimulates the customer's desire to purchase, and allows store staff to quickly follow up. As an example of a prompt to be input to the generating AI model, information is input in the format of, "A woman in her 30s, generate a script to inform you about new products based on her past purchase history."

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] The server collects real-time interaction data between users and humanoid terminals within the store. This input data includes voice, video, and text. The collected data is stored in a database and forms the basis for subsequent analysis.

[0325] Step 2:

[0326] The server executes machine learning algorithms using the collected interaction data. Using Python and TensorFlow, it extracts effective customer service patterns from the interaction data. This process involves data analysis and the generation of appropriate customer service skill models. The goal of these models is to improve customer service throughout the entire shop.

[0327] Step 3:

[0328] The server sends the generated customer service skill model to a humanoid terminal. Based on the received model, the terminal takes appropriate action when a customer approaches. The input is the customer service model, and the output is voice guidance and suggestions for the customer. The terminal uses speech synthesis technology to provide customer-friendly navigation.

[0329] Step 4:

[0330] The device sends feedback received during customer interactions to the server. This feedback includes customer facial expressions and tone of voice. This data is then fed back into the learning model to help provide a more optimal response in future interactions.

[0331] Step 5:

[0332] The server also provides information from the customer service model to the glasses-type terminal. Based on this information, the glasses-type terminal displays real-time customer suggestions to the store staff. Inputs include basic customer information and purchase history, while output is customized product suggestions. Flask is used to send this data to the glasses-type terminal, improving operational efficiency.

[0333] 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.

[0334] This invention is a system that enables more personalized responses by accurately recognizing customer emotions and combining them with an emotion engine when a humanoid terminal performs customer service tasks. The system includes an emotion engine for analyzing the customer's visual and auditory information, and dynamically optimizes customer service responses by detecting and analyzing the emotional state in real time.

[0335] Data collection and emotion recognition

[0336] The server stores customer interaction data collected within the store, which includes not only traditional customer service process data but also emotional data such as facial expressions and tone of voice.

[0337] The device uses its built-in emotion engine to recognize the user's emotions in real time. It also utilizes a facial expression analysis module and a voice analysis module to deepen its understanding of the customer's content.

[0338] Training and application of customer service skills

[0339] The server uses machine learning based on collected emotional data to train an advanced customer service skills model that includes emotional responses.

[0340] The terminal receives the latest model information from the server and uses it to interact with customers. It detects emotional changes in real time and adjusts the tone and content of the conversation as needed.

[0341] Examples of customer service

[0342] If the user has a depressed expression, the device uses an emotion engine to recognize this state and suggests encouraging words or relaxing services.

[0343] For example, you could change your approach, such as saying, "You seem a little down today. Please let me know if there's anything I can do to help."

[0344] Feedback and model improvement

[0345] The server collects and analyzes emotional feedback data obtained during customer service interactions with the humanoid terminal. This allows for continuous improvement of more accurate and personalized customer service skills.

[0346] This process ensures that the customer service model is constantly updated to accommodate real-world customer service scenarios.

[0347] As described above, the present invention enables customer service tailored to the customer's emotional state, thereby improving customer satisfaction.

[0348] The following describes the processing flow.

[0349] Step 1:

[0350] The server routinely collects audio and visual data to cover the entire interaction between staff and customers within the store. This includes not only conventional conversational data, but also emotional data such as customers' facial expressions and tone of voice.

[0351] Step 2:

[0352] The server feeds the collected data into machine learning algorithms to train customer service skill models. This enables responses that take customer emotions into account.

[0353] Step 3:

[0354] The server sends a trained customer service skills model to the humanoid terminal. The model is then ready to be applied in customer interactions.

[0355] Step 4:

[0356] The terminals are equipped with the latest models and are ready for customer service. This includes real-time emotion recognition capabilities using an emotion engine.

[0357] Step 5:

[0358] When a user approaches the device, the device detects the user using sensors and begins analyzing their facial expressions and tone of voice using its emotion engine.

[0359] Step 6:

[0360] Based on the results of emotion recognition, the device adjusts its tone of voice and message content to greet the user and answer questions. If the customer is feeling anxious, it will use reassuring words.

[0361] Step 7:

[0362] When a user asks a question or makes a request, the device considers the user's emotions and provides the most appropriate response. For example, it flexibly offers an emotionally sensitive answer such as, "Many people like this product."

[0363] Step 8:

[0364] The server periodically collects and analyzes feedback data on emotional interactions recorded by the humanoid terminals. This data is used to further improve the customer service skills model.

[0365] This will enable the provision of personalized customer service that takes emotions into account, which is expected to improve customer satisfaction.

[0366] (Example 2)

[0367] 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".

[0368] In modern customer service systems, accurately recognizing and responding appropriately to individual customer emotions and states is difficult. This can result in decreased customer satisfaction and inadequate service. Furthermore, traditional customer service methods often lack the real-time response needed to address changes in customer emotions.

[0369] 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.

[0370] In this invention, the server includes means for collecting information relating to customer interactions, means for training response techniques using a learning algorithm based on the collected information, and means for identifying customer emotions in real time and adjusting responses accordingly. This enables accurate recognition of the customer's emotional state and the provision of more appropriate and personalized services.

[0371] "Interaction information" refers to the record of all communication and interaction that takes place between the customer and the autonomous device, including the customer's facial expressions, tone of voice, and verbal responses.

[0372] A "learning algorithm" is a method used by computer systems to automatically acquire and apply patterns and rules based on collected data, thereby improving their response skills.

[0373] An "autonomous terminal" is a machine or device that uses built-in sensors and processing units to interact with customers without external instructions, and is designed to perform specific tasks.

[0374] A "sensing device" refers to a device installed on an autonomous terminal to physically detect information such as the presence, movement, voice, and facial expressions of a customer.

[0375] "Customer service techniques" is a general term for the skills and methods necessary to facilitate communication with customers and improve their satisfaction, and these are implemented using autonomous terminals.

[0376] "Feedback evaluation" refers to information such as opinions and impressions obtained after interactions with customers, which is data that can be used to improve customer service techniques and the overall system.

[0377] This system aims to instantly understand customer emotions and provide appropriate service in customer service operations by using autonomous terminals and emotion recognition technology.

[0378] First, the terminal is equipped with a high-precision camera and a voice recognition microphone, which collects information about interactions such as facial expressions and tone of voice as soon as a customer enters the store. The collected data is analyzed in real time to determine the customer's emotional state. An emotion recognition engine is used in this analysis. Specifically, the software could be a system equipped with advanced image analysis libraries and voice analysis algorithms.

[0379] Next, the acquired data is transferred to a server, which uses a learning algorithm to train its response technology. By analyzing the large amount of accumulated emotional data, the server builds a generative AI model and trains it to respond to diverse customer emotional states. This model is reflected on the terminal, enabling immediate, personalized responses to customers.

[0380] For example, if a user visits a store looking tired, the device can instantly detect their emotional state and suggest products with relaxation effects. An example of a prompt message could be, "Please suggest relaxing products to a tired customer," which can be used to instruct the AI ​​model.

[0381] This system enables the provision of flexible and appropriate services tailored to the customer's emotional state, thereby improving customer satisfaction.

[0382] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0383] Step 1:

[0384] The device collects visual and auditory information using a camera and microphone when a customer enters the store. Specifically, it captures the customer's face with the camera and records their voice tone and volume with the microphone. The input consists of the customer's facial expression data and audio data. The output is this data obtained in a format suitable for sentiment analysis.

[0385] Step 2:

[0386] The terminal inputs the collected data into the emotion recognition engine. The emotion recognition engine uses a facial expression analysis module to analyze facial features from the collected image data and a voice analysis module to analyze the tone of the recorded data. Specific data processing involves feature extraction and mapping to emotional states. The output is the customer's emotional state (e.g., joy, sadness, surprise).

[0387] Step 3:

[0388] The server receives emotional state data transmitted from the terminal. The input is emotional state data analyzed in real time. Based on this, the server applies a learning algorithm and trains a generative AI model with new response techniques. The specific data calculations include analysis using past datasets and construction of response patterns, and the output is an updated generative AI model.

[0389] Step 4:

[0390] The terminal receives the latest AI model from the server and uses it to interact with customers. The input is the updated model data of the interaction technology received from the server. Specifically, its actions include generating voice responses to customer questions and providing appropriate suggestions and guidance. The output is personalized voice-based interaction with the customer.

[0391] Step 5:

[0392] The server collects and analyzes feedback data after customer interactions. It uses customer feedback and terminal response evaluation data as input. Based on this, data calculations are performed to further improve response techniques. Specifically, the feedback is analyzed to identify areas for model improvement, and the output becomes an improvement plan for the next model update.

[0393] (Application Example 2)

[0394] 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."

[0395] Traditional customer service systems have a problem in that they have difficulty appropriately recognizing customer emotions and providing individualized responses. In particular, it is difficult to analyze customers' facial expressions and tone of voice in real time, which can result in delays in providing product recommendations and services that meet their needs, potentially leading to decreased customer satisfaction. Therefore, it is necessary to solve these problems.

[0396] 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.

[0397] In this invention, the server includes means for collecting interaction data with customers, means for training customer service skills using a machine learning algorithm based on the collected data, and means for transmitting the trained customer service skills to an autonomous device. This makes it possible to accurately recognize the emotional state of the customer and dynamically adjust product recommendations based on that emotion.

[0398] A "customer" is someone who receives goods or services, and is an important stakeholder for a company.

[0399] "Interaction data" refers to data related to various interactions that occur with customers, including information about their emotions and behaviors.

[0400] A "machine learning algorithm" is a computational method that automatically performs data analysis and prediction by finding patterns based on large amounts of data.

[0401] "Customer service skills" refer to the techniques used to introduce products and services to customers and increase their satisfaction.

[0402] An "autonomous device" is a mechanical device that can make its own decisions and perform various tasks in a self-contained manner.

[0403] A "sensory device" is equipment that senses information from the outside and processes it as digital data.

[0404] An "integration method" is a way of combining multiple pieces of information or functions to create an overall effective system.

[0405] "Feedback" refers to information that shows reactions to or evaluations of actions and results, and serves as a basis for improvement or change.

[0406] The system of the present invention is designed to efficiently collect and analyze customer interaction data and to provide personalized service based on emotions. The server first collects data obtained from the customer's facial expressions and voice. This data is acquired using a camera sensor and microphone as sensory devices. Based on the collected data, the server trains customer service skills using a machine learning algorithm and transmits these skills to an autonomous device (e.g., a customer service robot).

[0407] The autonomous terminal devices utilize trained customer service skills to analyze customer emotions in real time. Software such as OpenCV and Google Speech-to-Text API are used for facial expression and voice analysis. In particular, the system incorporates an integrated mechanism to dynamically adjust product recommendations based on customer emotions, providing the most appropriate language guidance to the customer.

[0408] For example, if the system detects that a customer is feeling stressed in a store, the autonomous device can make a customized suggestion in real time, such as, "You seem to be having a tough day. We have a new tea that can help you relax; would you like to try it?"

[0409] Throughout this process, customer feedback is collected again on the server and analyzed to improve the customer service model. This enables further improvements in customer service skills. As an example of a prompt for the generated AI model, an effective expression would be, "If the customer appears stressed, what suggestions can help them relax?"

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] The server collects customer facial and voice data using camera sensors and microphones. The input is the customer's face and voice, and the output is digitized facial image data and voice data. This data serves as foundational information for analyzing customer emotions.

[0413] Step 2:

[0414] The server inputs the collected digitized data into the emotion engine and applies facial expression analysis algorithms and voice analysis algorithms. The inputs are facial expression image data and voice data, and the outputs are parameters indicating the customer's emotional state. By recognizing the customer's emotions in real time using the emotion engine, the server quantifies how the customer is feeling.

[0415] Step 3:

[0416] The server trains its customer service skills using a machine learning algorithm based on emotional state parameters. The input is the customer's emotional state parameters, and the output is the updated customer service skill model. This model is constantly being improved to provide the optimal customer service method tailored to the customer's emotions.

[0417] Step 4:

[0418] The autonomous terminal device receives customer service technology models transmitted from the server and utilizes them for customer service. The input is the updated customer service technology model, and the output is an optimized response to the customer. In this process, product recommendations are dynamically adjusted according to the customer's real-time emotions.

[0419] Step 5:

[0420] An autonomous device collects feedback from users about their customer service experience and sends it back to the server. The input is feedback data obtained from the user, and the output is additional information for the customer service model, including suggestions for improvement. Based on this feedback, customer service skills are further improved and utilized in future interactions.

[0421] Step 6:

[0422] The server analyzes the collected feedback and updates the customer service model. The input is feedback data, and the output is an improved customer service technology model. This continuously improves customer service and increases customer satisfaction.

[0423] 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.

[0424] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0425] 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.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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".

[0439] This invention is a system for efficiently and effectively performing customer service in stores. Specifically, it collects customer service data through customer interaction, uses this data to train customer service skills using machine learning algorithms, and applies this training to a humanoid terminal. This can solve challenges in the customer service industry, such as staff shortages and inconsistent quality.

[0440] Data collection and learning

[0441] The server records conversations and actions between staff and customers within the store and collects this interaction data.

[0442] The server uses machine learning algorithms to extract effective patterns and skills in customer service from the collected interaction data and build a learning model.

[0443] Application to humanoid terminals

[0444] The terminal (humanoid) receives customer service skill models sent from the server and uses them to interact with customers.

[0445] The terminal uses its built-in sensors to recognize customers and approaches them within a specific operating range.

[0446] Customer support

[0447] When a user (customer) approaches the humanoid terminal, the terminal greets them and responds to their questions and requests.

[0448] The terminal provides product information through voice guidance and offers recommendations for products and promotional campaigns.

[0449] Feedback and model improvement

[0450] The server periodically collects digital data recorded during customer service interactions with the humanoid terminal and analyzes it as feedback data.

[0451] The server uses the feedback to improve its customer service model and incorporates that feedback into future interactions.

[0452] Specific example

[0453] For example, when a user asks, "Which items are on sale?", the terminal immediately replies, "The items on this shelf are currently on sale." For this response to function smoothly, data analysis on the server, learning of customer service skills, and application to the terminal must work together in coordination. This system allows customers to receive quick and accurate service, thus improving customer satisfaction.

[0454] The following describes the processing flow.

[0455] Step 1:

[0456] The server collects conversation and behavioral data between staff and customers in the store in real time every day. This includes voice data and behavioral information, all stored in digital format.

[0457] Step 2:

[0458] The server inputs the collected data into a machine learning algorithm to learn effective communication patterns and response methods in customer service. Through data analysis, the customer service model is trained and becomes available for use.

[0459] Step 3:

[0460] The server transmits a trained customer service skills model to the humanoid terminal. This model is designed to handle various customer interaction scenarios.

[0461] Step 4:

[0462] The terminal receives the transmitted model and applies it to the system. The model is installed internally at startup, making it available for use at any time.

[0463] Step 5:

[0464] When a user enters the store, the terminal uses sensors to detect the customer and provides an appropriate greeting via voice, such as, "Hello, are you looking for something?"

[0465] Step 6:

[0466] When a user asks a question or makes a request, the device responds immediately based on a model trained on the server. This includes providing detailed product information or recommending specific products.

[0467] Step 7:

[0468] The terminal registers feedback data obtained during conversations with customers in real time, preparing to use it to improve customer service.

[0469] Step 8:

[0470] The server periodically collects feedback data and performs analysis to further improve the model. This process is essential for continuously evolving the customer service model.

[0471] (Example 1)

[0472] 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."

[0473] The challenges in the service industry include addressing labor shortages and inconsistencies in service quality, and providing a consistently high-quality customer experience. In particular, replicating and providing the customer service skills of excellent staff is essential for efficient and effective customer interaction.

[0474] 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.

[0475] In this invention, the server includes a device for collecting information, a device for learning skills using machine learning techniques based on the collected information, and a device for transmitting the learned skills to an automated device. This enables users to receive a stable service and improves the uniformity and quality of the service.

[0476] "Information" includes data and records related to the interaction between the user and the automated device.

[0477] "Machine learning techniques" are technologies that use algorithms to build learning models based on collected data, and then use those models to make predictions and decisions.

[0478] "Automated equipment" refers to devices such as robots that are designed to partially or completely replace human work.

[0479] "Device" refers to an entire machine or system designed to perform a specific function.

[0480] A "sensor" is a device that can detect changes in the environment and measure or record that information.

[0481] A "learning model" is a reference model based on rules and patterns derived from data using machine learning algorithms.

[0482] A "guide" is a means of providing information that uses audio or text to guide users and encourage desirable actions and decisions.

[0483] "Evaluation" is the process of measuring and analyzing the results of interactions with users.

[0484] "Person" refers to an individual who possesses excellent skills and experience in customer service.

[0485] This invention is a system for efficiently and effectively performing customer service tasks within a store. The embodiments for carrying out the invention are as follows:

[0486] The server collects customer-staff interaction data using microphones and cameras installed within the store. Specifically, it uses a speech recognition system to transcribe conversations into text and collects customer behavior data through cameras. This data is then converted into a format suitable for machine learning.

[0487] Subsequently, the server uses machine learning libraries such as Python's TensorFlow and Scikit-learn to build a model that learns customer service skills from the collected data. The server combines multiple algorithms to select the optimal model and sends it to the automated terminal.

[0488] The terminal receives this model and uses its built-in sensors to recognize and detect customers within the store. The terminal can approach customers at an appropriate distance and provide product and promotional information through voice guidance. A voice recognition system such as Google Cloud Speech-to-Text is used.

[0489] Furthermore, the server collects the results of interactions with terminals as digital data and analyzes it as feedback. Based on this feedback data, the server further improves its learning model and aims to enhance its customer service skills.

[0490] For example, when a user asks, "Which items are on sale?", the device immediately replies, "The items on this shelf are currently on sale." This enables quick and appropriate responses.

[0491] An example of a prompt to input into a generative AI model would be, "Please tell me how to collect the data necessary to analyze customer conversations and behavior patterns in a store using speech recognition technology."

[0492] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0493] Step 1:

[0494] The server collects customer and staff interaction data from microphones and cameras installed within the store. Inputs include audio and video data, while outputs include text data and behavioral pattern data. A speech recognition system converts audio to text, and an image recognition algorithm analyzes actions and facial expressions, saving the data as structured data.

[0495] Step 2:

[0496] The server executes machine learning algorithms using the accumulated data. The input is previously collected interaction data, and the output is a trained customer service skills model. The algorithm is executed using the Python TensorFlow library to extract effective patterns in customer interactions and train the model.

[0497] Step 3:

[0498] The server sends the trained customer service skills model to the automated terminal. The input is the trained model, and the output is an update file in a format usable by the terminal. This file is transferred to the terminal over the network and applied to the terminal's memory.

[0499] Step 4:

[0500] The terminal uses its built-in sensors to detect and recognize users who visit the store. The input is environmental data acquired from the sensors, and the output is recognized customer information. In terms of operation, it measures distance using an infrared sensor and performs facial recognition of the customer using a camera.

[0501] Step 5:

[0502] The device interacts with the user and provides voice guidance. Input is voice instructions from the user, and output is the device's verbal response. Google Cloud Speech-to-Text is used to generate text from speech, and information is provided using a pre-trained model based on that text.

[0503] Step 6:

[0504] The server collects and analyzes feedback data from interactions performed by the terminal. The input is the result of each interaction, and the output is an evaluation of customer service and points for improvement. The collected data is statistically analyzed to generate insights for future model improvements.

[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 retail stores face challenges such as inconsistent customer service quality and the time and cost involved in improving staff skills. Furthermore, providing excellent customer service requires personalized attention, and a system is needed to efficiently achieve this.

[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 collecting customer interaction data, means for training customer service skills using a machine learning algorithm based on the collected data, and means for transmitting the trained customer service skills to a humanoid terminal. This enables store staff to provide efficient and high-quality personalized service.

[0510] "Customer interaction data" refers to digital information that records customers' actions within a store and the content of their conversations with store staff.

[0511] A "machine learning algorithm" is an algorithm that learns patterns from data and performs predictions and classifications.

[0512] "Customer service skills" refer to the techniques and knowledge used to improve the quality of services provided to customers.

[0513] A "humanoid terminal" is an autonomous device that mimics the form of a human being and interacts with customers through dialogue and actions.

[0514] A "detection device" is a device used to sense the surrounding environment or the presence of an object.

[0515] "Voice guidance" refers to a function that uses voice to transmit information and guide customers.

[0516] "Feedback" is a system that incorporates evaluations and opinions based on past actions and results.

[0517] A "glasses-type terminal" is a device that has the function of visually presenting information and is used by the wearer.

[0518] A "display device" is hardware used to visually display information.

[0519] "Product recommendation" is the activity of recommending products that meet customer needs.

[0520] This invention is a system for streamlining customer service operations within stores and providing effective customer service. The server collects customer-staff interaction data within the store and uses machine learning algorithms to train customer service skills based on this data. This method uses TensorFlow to build a model and extract effective patterns that improve staff responses.

[0521] The server transmits trained customer service skills to a humanoid terminal. This terminal uses OpenCV to detect and recognize customers and provides voice guidance to them. This voice guidance provides product information and service details tailored to the customer's needs in real time, aiming to improve customer satisfaction.

[0522] Furthermore, the server uses a glasses-type terminal to display customer information and product suggestions to staff. This glasses-type terminal uses Flask to receive data from the server and provides visual information to staff, thereby improving the efficiency of customer service.

[0523] As a concrete example, if a user enters a store and asks the humanoid terminal, "Which items are on sale today?", the terminal will respond, "These sneakers on this shelf are available at a special price." This stimulates the customer's desire to purchase, and allows store staff to quickly follow up. As an example of a prompt to be input to the generating AI model, information is input in the format of, "A woman in her 30s, generate a script to inform you about new products based on her past purchase history."

[0524] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0525] Step 1:

[0526] The server collects real-time interaction data between users and humanoid terminals within the store. This input data includes voice, video, and text. The collected data is stored in a database and forms the basis for subsequent analysis.

[0527] Step 2:

[0528] The server executes machine learning algorithms using the collected interaction data. Using Python and TensorFlow, it extracts effective customer service patterns from the interaction data. This process involves data analysis and the generation of appropriate customer service skill models. The goal of these models is to improve customer service throughout the entire shop.

[0529] Step 3:

[0530] The server sends the generated customer service skill model to a humanoid terminal. Based on the received model, the terminal takes appropriate action when a customer approaches. The input is the customer service model, and the output is voice guidance and suggestions for the customer. The terminal uses speech synthesis technology to provide customer-friendly navigation.

[0531] Step 4:

[0532] The device sends feedback received during customer interactions to the server. This feedback includes customer facial expressions and tone of voice. This data is then fed back into the learning model to help provide a more optimal response in future interactions.

[0533] Step 5:

[0534] The server also provides information from the customer service model to the glasses-type terminal. Based on this information, the glasses-type terminal displays real-time customer suggestions to the store staff. Inputs include basic customer information and purchase history, while output is customized product suggestions. Flask is used to send this data to the glasses-type terminal, improving operational efficiency.

[0535] 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.

[0536] This invention is a system that enables more personalized responses by accurately recognizing customer emotions and combining them with an emotion engine when a humanoid terminal performs customer service tasks. The system includes an emotion engine for analyzing the customer's visual and auditory information, and dynamically optimizes customer service responses by detecting and analyzing the emotional state in real time.

[0537] Data collection and emotion recognition

[0538] The server stores customer interaction data collected within the store, which includes not only traditional customer service process data but also emotional data such as facial expressions and tone of voice.

[0539] The device uses its built-in emotion engine to recognize the user's emotions in real time. It also utilizes a facial expression analysis module and a voice analysis module to deepen its understanding of the customer's content.

[0540] Training and application of customer service skills

[0541] The server uses machine learning based on collected emotional data to train an advanced customer service skills model that includes emotional responses.

[0542] The terminal receives the latest model information from the server and uses it to interact with customers. It detects emotional changes in real time and adjusts the tone and content of the conversation as needed.

[0543] Examples of customer service

[0544] If the user has a depressed expression, the device uses an emotion engine to recognize this state and suggests encouraging words or relaxing services.

[0545] For example, you could change your approach, such as saying, "You seem a little down today. Please let me know if there's anything I can do to help."

[0546] Feedback and model improvement

[0547] The server collects and analyzes emotional feedback data obtained during customer service interactions with the humanoid terminal. This allows for continuous improvement of more accurate and personalized customer service skills.

[0548] This process ensures that the customer service model is constantly updated to accommodate real-world customer service scenarios.

[0549] As described above, the present invention enables customer service tailored to the customer's emotional state, thereby improving customer satisfaction.

[0550] The following describes the processing flow.

[0551] Step 1:

[0552] The server routinely collects audio and visual data to cover the entire interaction between staff and customers within the store. This includes not only conventional conversational data, but also emotional data such as customers' facial expressions and tone of voice.

[0553] Step 2:

[0554] The server feeds the collected data into machine learning algorithms to train customer service skill models. This enables responses that take customer emotions into account.

[0555] Step 3:

[0556] The server sends a trained customer service skills model to the humanoid terminal. The model is then ready to be applied in customer interactions.

[0557] Step 4:

[0558] The terminals are equipped with the latest models and are ready for customer service. This includes real-time emotion recognition capabilities using an emotion engine.

[0559] Step 5:

[0560] When a user approaches the device, the device detects the user using sensors and begins analyzing their facial expressions and tone of voice using its emotion engine.

[0561] Step 6:

[0562] Based on the results of emotion recognition, the device adjusts its tone of voice and message content to greet the user and answer questions. If the customer is feeling anxious, it will use reassuring words.

[0563] Step 7:

[0564] When a user asks a question or makes a request, the device considers the user's emotions and provides the most appropriate response. For example, it flexibly offers an emotionally sensitive answer such as, "Many people like this product."

[0565] Step 8:

[0566] The server periodically collects and analyzes feedback data on emotional interactions recorded by the humanoid terminals. This data is used to further improve the customer service skills model.

[0567] This will enable the provision of personalized customer service that takes emotions into account, which is expected to improve customer satisfaction.

[0568] (Example 2)

[0569] 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."

[0570] In modern customer service systems, accurately recognizing and responding appropriately to individual customer emotions and states is difficult. This can result in decreased customer satisfaction and inadequate service. Furthermore, traditional customer service methods often lack the real-time response needed to address changes in customer emotions.

[0571] 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.

[0572] In this invention, the server includes means for collecting information relating to customer interactions, means for training response techniques using a learning algorithm based on the collected information, and means for identifying customer emotions in real time and adjusting responses accordingly. This enables accurate recognition of the customer's emotional state and the provision of more appropriate and personalized services.

[0573] "Interaction information" refers to the record of all communication and interaction that takes place between the customer and the autonomous device, including the customer's facial expressions, tone of voice, and verbal responses.

[0574] A "learning algorithm" is a method used by computer systems to automatically acquire and apply patterns and rules based on collected data, thereby improving their response skills.

[0575] An "autonomous terminal" is a machine or device that uses built-in sensors and processing units to interact with customers without external instructions, and is designed to perform specific tasks.

[0576] A "sensing device" refers to a device installed on an autonomous terminal to physically detect information such as the presence, movement, voice, and facial expressions of a customer.

[0577] "Customer service techniques" is a general term for the skills and methods necessary to facilitate communication with customers and improve their satisfaction, and these are implemented using autonomous terminals.

[0578] "Feedback evaluation" refers to information such as opinions and impressions obtained after interactions with customers, which is data that can be used to improve customer service techniques and the overall system.

[0579] This system aims to instantly understand customer emotions and provide appropriate service in customer service operations by using autonomous terminals and emotion recognition technology.

[0580] First, the terminal is equipped with a high-precision camera and a voice recognition microphone, which collects information about interactions such as facial expressions and tone of voice as soon as a customer enters the store. The collected data is analyzed in real time to determine the customer's emotional state. An emotion recognition engine is used in this analysis. Specifically, the software could be a system equipped with advanced image analysis libraries and voice analysis algorithms.

[0581] Next, the acquired data is transferred to a server, which uses a learning algorithm to train its response technology. By analyzing the large amount of accumulated emotional data, the server builds a generative AI model and trains it to respond to diverse customer emotional states. This model is reflected on the terminal, enabling immediate, personalized responses to customers.

[0582] For example, if a user visits a store looking tired, the device can instantly detect their emotional state and suggest products with relaxation effects. An example of a prompt message could be, "Please suggest relaxing products to a tired customer," which can be used to instruct the AI ​​model.

[0583] This system enables the provision of flexible and appropriate services tailored to the customer's emotional state, thereby improving customer satisfaction.

[0584] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0585] Step 1:

[0586] The device collects visual and auditory information using a camera and microphone when a customer enters the store. Specifically, it captures the customer's face with the camera and records their voice tone and volume with the microphone. The input consists of the customer's facial expression data and audio data. The output is this data obtained in a format suitable for sentiment analysis.

[0587] Step 2:

[0588] The terminal inputs the collected data into the emotion recognition engine. The emotion recognition engine uses a facial expression analysis module to analyze facial features from the collected image data and a voice analysis module to analyze the tone of the recorded data. Specific data processing involves feature extraction and mapping to emotional states. The output is the customer's emotional state (e.g., joy, sadness, surprise).

[0589] Step 3:

[0590] The server receives emotional state data transmitted from the terminal. The input is emotional state data analyzed in real time. Based on this, the server applies a learning algorithm and trains a generative AI model with new response techniques. The specific data calculations include analysis using past datasets and construction of response patterns, and the output is an updated generative AI model.

[0591] Step 4:

[0592] The terminal receives the latest AI model from the server and uses it to interact with customers. The input is the updated model data of the interaction technology received from the server. Specifically, its actions include generating voice responses to customer questions and providing appropriate suggestions and guidance. The output is personalized voice-based interaction with the customer.

[0593] Step 5:

[0594] The server collects and analyzes feedback data after customer interactions. It uses customer feedback and terminal response evaluation data as input. Based on this, data calculations are performed to further improve response techniques. Specifically, the feedback is analyzed to identify areas for model improvement, and the output becomes an improvement plan for the next model update.

[0595] (Application Example 2)

[0596] 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."

[0597] Traditional customer service systems have a problem in that they have difficulty appropriately recognizing customer emotions and providing individualized responses. In particular, it is difficult to analyze customers' facial expressions and tone of voice in real time, which can result in delays in providing product recommendations and services that meet their needs, potentially leading to decreased customer satisfaction. Therefore, it is necessary to solve these problems.

[0598] 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.

[0599] In this invention, the server includes means for collecting interaction data with customers, means for training customer service skills using a machine learning algorithm based on the collected data, and means for transmitting the trained customer service skills to an autonomous device. This makes it possible to accurately recognize the emotional state of the customer and dynamically adjust product recommendations based on that emotion.

[0600] A "customer" is someone who receives goods or services, and is an important stakeholder for a company.

[0601] "Interaction data" refers to data related to various interactions that occur with customers, including information about their emotions and behaviors.

[0602] A "machine learning algorithm" is a computational method that automatically performs data analysis and prediction by finding patterns based on large amounts of data.

[0603] "Customer service skills" refer to the techniques used to introduce products and services to customers and increase their satisfaction.

[0604] An "autonomous device" is a mechanical device that can make its own decisions and perform various tasks in a self-contained manner.

[0605] A "sensory device" is equipment that senses information from the outside and processes it as digital data.

[0606] An "integration method" is a way of combining multiple pieces of information or functions to create an overall effective system.

[0607] "Feedback" refers to information that shows reactions to or evaluations of actions and results, and serves as a basis for improvement or change.

[0608] The system of the present invention is designed to efficiently collect and analyze customer interaction data and to provide personalized service based on emotions. The server first collects data obtained from the customer's facial expressions and voice. This data is acquired using a camera sensor and microphone as sensory devices. Based on the collected data, the server trains customer service skills using a machine learning algorithm and transmits these skills to an autonomous device (e.g., a customer service robot).

[0609] The autonomous terminal devices utilize trained customer service skills to analyze customer emotions in real time. Software such as OpenCV and Google Speech-to-Text API are used for facial expression and voice analysis. In particular, the system incorporates an integrated mechanism to dynamically adjust product recommendations based on customer emotions, providing the most appropriate language guidance to the customer.

[0610] For example, if the system detects that a customer is feeling stressed in a store, the autonomous device can make a customized suggestion in real time, such as, "You seem to be having a tough day. We have a new tea that can help you relax; would you like to try it?"

[0611] Throughout this process, customer feedback is collected again on the server and analyzed to improve the customer service model. This enables further improvements in customer service skills. As an example of a prompt for the generated AI model, an effective expression would be, "If the customer appears stressed, what suggestions can help them relax?"

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0613] Step 1:

[0614] The server collects customer facial and voice data using camera sensors and microphones. The input is the customer's face and voice, and the output is digitized facial image data and voice data. This data serves as foundational information for analyzing customer emotions.

[0615] Step 2:

[0616] The server inputs the collected digitized data into the emotion engine and applies facial expression analysis algorithms and voice analysis algorithms. The inputs are facial expression image data and voice data, and the outputs are parameters indicating the customer's emotional state. By recognizing the customer's emotions in real time using the emotion engine, the server quantifies how the customer is feeling.

[0617] Step 3:

[0618] The server trains its customer service skills using a machine learning algorithm based on emotional state parameters. The input is the customer's emotional state parameters, and the output is the updated customer service skill model. This model is constantly being improved to provide the optimal customer service method tailored to the customer's emotions.

[0619] Step 4:

[0620] The autonomous terminal device receives customer service technology models transmitted from the server and utilizes them for customer service. The input is the updated customer service technology model, and the output is an optimized response to the customer. In this process, product recommendations are dynamically adjusted according to the customer's real-time emotions.

[0621] Step 5:

[0622] An autonomous device collects feedback from users about their customer service experience and sends it back to the server. The input is feedback data obtained from the user, and the output is additional information for the customer service model, including suggestions for improvement. Based on this feedback, customer service skills are further improved and utilized in future interactions.

[0623] Step 6:

[0624] The server analyzes the collected feedback and updates the customer service model. The input is feedback data, and the output is an improved customer service technology model. This continuously improves customer service and increases customer satisfaction.

[0625] 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.

[0626] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0627] 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.

[0628] [Fourth Embodiment]

[0629] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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).

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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".

[0642] This invention is a system for efficiently and effectively performing customer service in stores. Specifically, it collects customer service data through customer interaction, uses this data to train customer service skills using machine learning algorithms, and applies this training to a humanoid terminal. This can solve challenges in the customer service industry, such as staff shortages and inconsistent quality.

[0643] Data collection and learning

[0644] The server records conversations and actions between staff and customers within the store and collects this interaction data.

[0645] The server uses machine learning algorithms to extract effective patterns and skills in customer service from the collected interaction data and build a learning model.

[0646] Application to humanoid terminals

[0647] The terminal (humanoid) receives customer service skill models sent from the server and uses them to interact with customers.

[0648] The terminal uses its built-in sensors to recognize customers and approaches them within a specific operating range.

[0649] Customer support

[0650] When a user (customer) approaches the humanoid terminal, the terminal greets them and responds to their questions and requests.

[0651] The terminal provides product information through voice guidance and offers recommendations for products and promotional campaigns.

[0652] Feedback and model improvement

[0653] The server periodically collects digital data recorded during customer service interactions with the humanoid terminal and analyzes it as feedback data.

[0654] The server uses the feedback to improve its customer service model and incorporates that feedback into future interactions.

[0655] Specific example

[0656] For example, when a user asks, "Which items are on sale?", the terminal immediately replies, "The items on this shelf are currently on sale." For this response to function smoothly, data analysis on the server, learning of customer service skills, and application to the terminal must work together in coordination. This system allows customers to receive quick and accurate service, thus improving customer satisfaction.

[0657] The following describes the processing flow.

[0658] Step 1:

[0659] The server collects conversation and behavioral data between staff and customers in the store in real time every day. This includes voice data and behavioral information, all stored in digital format.

[0660] Step 2:

[0661] The server inputs the collected data into a machine learning algorithm to learn effective communication patterns and response methods in customer service. Through data analysis, the customer service model is trained and becomes available for use.

[0662] Step 3:

[0663] The server transmits a trained customer service skills model to the humanoid terminal. This model is designed to handle various customer interaction scenarios.

[0664] Step 4:

[0665] The terminal receives the transmitted model and applies it to the system. The model is installed internally at startup, making it available for use at any time.

[0666] Step 5:

[0667] When a user enters the store, the terminal uses sensors to detect the customer and provides an appropriate greeting via voice, such as, "Hello, are you looking for something?"

[0668] Step 6:

[0669] When a user asks a question or makes a request, the device responds immediately based on a model trained on the server. This includes providing detailed product information or recommending specific products.

[0670] Step 7:

[0671] The terminal registers feedback data obtained during conversations with customers in real time, preparing to use it to improve customer service.

[0672] Step 8:

[0673] The server periodically collects feedback data and performs analysis to further improve the model. This process is essential for continuously evolving the customer service model.

[0674] (Example 1)

[0675] 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".

[0676] The challenges in the service industry include addressing labor shortages and inconsistencies in service quality, and providing a consistently high-quality customer experience. In particular, replicating and providing the customer service skills of excellent staff is essential for efficient and effective customer interaction.

[0677] 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.

[0678] In this invention, the server includes a device for collecting information, a device for learning skills using machine learning techniques based on the collected information, and a device for transmitting the learned skills to an automated device. This enables users to receive a stable service and improves the uniformity and quality of the service.

[0679] "Information" includes data and records related to the interaction between the user and the automated device.

[0680] "Machine learning techniques" are technologies that use algorithms to build learning models based on collected data, and then use those models to make predictions and decisions.

[0681] "Automated equipment" refers to devices such as robots that are designed to partially or completely replace human work.

[0682] "Device" refers to an entire machine or system designed to perform a specific function.

[0683] A "sensor" is a device that can detect changes in the environment and measure or record that information.

[0684] A "learning model" is a reference model based on rules and patterns derived from data using machine learning algorithms.

[0685] A "guide" is a means of providing information that uses audio or text to guide users and encourage desirable actions and decisions.

[0686] "Evaluation" is the process of measuring and analyzing the results of interactions with users.

[0687] "Person" refers to an individual who possesses excellent skills and experience in customer service.

[0688] This invention is a system for efficiently and effectively performing customer service tasks within a store. The embodiments for carrying out the invention are as follows:

[0689] The server collects customer-staff interaction data using microphones and cameras installed within the store. Specifically, it uses a speech recognition system to transcribe conversations into text and collects customer behavior data through cameras. This data is then converted into a format suitable for machine learning.

[0690] Subsequently, the server uses machine learning libraries such as Python's TensorFlow and Scikit-learn to build a model that learns customer service skills from the collected data. The server combines multiple algorithms to select the optimal model and sends it to the automated terminal.

[0691] The terminal receives this model and uses its built-in sensors to recognize and detect customers within the store. The terminal can approach customers at an appropriate distance and provide product and promotional information through voice guidance. A voice recognition system such as Google Cloud Speech-to-Text is used.

[0692] Furthermore, the server collects the results of interactions with terminals as digital data and analyzes it as feedback. Based on this feedback data, the server further improves its learning model and aims to enhance its customer service skills.

[0693] For example, when a user asks, "Which items are on sale?", the device immediately replies, "The items on this shelf are currently on sale." This enables quick and appropriate responses.

[0694] An example of a prompt to input into a generative AI model would be, "Please tell me how to collect the data necessary to analyze customer conversations and behavior patterns in a store using speech recognition technology."

[0695] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0696] Step 1:

[0697] The server collects customer and staff interaction data from microphones and cameras installed within the store. Inputs include audio and video data, while outputs include text data and behavioral pattern data. A speech recognition system converts audio to text, and an image recognition algorithm analyzes actions and facial expressions, saving the data as structured data.

[0698] Step 2:

[0699] The server executes machine learning algorithms using the accumulated data. The input is previously collected interaction data, and the output is a trained customer service skills model. The algorithm is executed using the Python TensorFlow library to extract effective patterns in customer interactions and train the model.

[0700] Step 3:

[0701] The server sends the trained customer service skills model to the automated terminal. The input is the trained model, and the output is an update file in a format usable by the terminal. This file is transferred to the terminal over the network and applied to the terminal's memory.

[0702] Step 4:

[0703] The terminal uses its built-in sensors to detect and recognize users who visit the store. The input is environmental data acquired from the sensors, and the output is recognized customer information. In terms of operation, it measures distance using an infrared sensor and performs facial recognition of the customer using a camera.

[0704] Step 5:

[0705] The device interacts with the user and provides voice guidance. Input is voice instructions from the user, and output is the device's verbal response. Google Cloud Speech-to-Text is used to generate text from speech, and information is provided using a pre-trained model based on that text.

[0706] Step 6:

[0707] The server collects and analyzes feedback data from interactions performed by the terminal. The input is the result of each interaction, and the output is an evaluation of customer service and points for improvement. The collected data is statistically analyzed to generate insights for future model improvements.

[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 retail stores face challenges such as inconsistent customer service quality and the time and cost involved in improving staff skills. Furthermore, providing excellent customer service requires personalized attention, and a system is needed to efficiently achieve this.

[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 collecting customer interaction data, means for training customer service skills using a machine learning algorithm based on the collected data, and means for transmitting the trained customer service skills to a humanoid terminal. This enables store staff to provide efficient and high-quality personalized service.

[0713] "Customer interaction data" refers to digital information that records customers' actions within a store and the content of their conversations with store staff.

[0714] A "machine learning algorithm" is an algorithm that learns patterns from data and performs predictions and classifications.

[0715] "Customer service skills" refer to the techniques and knowledge used to improve the quality of services provided to customers.

[0716] A "humanoid terminal" is an autonomous device that mimics the form of a human being and interacts with customers through dialogue and actions.

[0717] A "detection device" is a device used to sense the surrounding environment or the presence of an object.

[0718] "Voice guidance" refers to a function that uses voice to transmit information and guide customers.

[0719] "Feedback" is a system that incorporates evaluations and opinions based on past actions and results.

[0720] A "glasses-type terminal" is a device that has the function of visually presenting information and is used by the wearer.

[0721] A "display device" is hardware used to visually display information.

[0722] "Product recommendation" is the activity of recommending products that meet customer needs.

[0723] This invention is a system for streamlining customer service operations within stores and providing effective customer service. The server collects customer-staff interaction data within the store and uses machine learning algorithms to train customer service skills based on this data. This method uses TensorFlow to build a model and extract effective patterns that improve staff responses.

[0724] The server transmits trained customer service skills to a humanoid terminal. This terminal uses OpenCV to detect and recognize customers and provides voice guidance to them. This voice guidance provides product information and service details tailored to the customer's needs in real time, aiming to improve customer satisfaction.

[0725] Furthermore, the server uses a glasses-type terminal to display customer information and product suggestions to staff. This glasses-type terminal uses Flask to receive data from the server and provides visual information to staff, thereby improving the efficiency of customer service.

[0726] As a concrete example, if a user enters a store and asks the humanoid terminal, "Which items are on sale today?", the terminal will respond, "These sneakers on this shelf are available at a special price." This stimulates the customer's desire to purchase, and allows store staff to quickly follow up. As an example of a prompt to be input to the generating AI model, information is input in the format of, "A woman in her 30s, generate a script to inform you about new products based on her past purchase history."

[0727] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0728] Step 1:

[0729] The server collects real-time interaction data between users and humanoid terminals within the store. This input data includes voice, video, and text. The collected data is stored in a database and forms the basis for subsequent analysis.

[0730] Step 2:

[0731] The server executes machine learning algorithms using the collected interaction data. Using Python and TensorFlow, it extracts effective customer service patterns from the interaction data. This process involves data analysis and the generation of appropriate customer service skill models. The goal of these models is to improve customer service throughout the entire shop.

[0732] Step 3:

[0733] The server sends the generated customer service skill model to a humanoid terminal. Based on the received model, the terminal takes appropriate action when a customer approaches. The input is the customer service model, and the output is voice guidance and suggestions for the customer. The terminal uses speech synthesis technology to provide customer-friendly navigation.

[0734] Step 4:

[0735] The device sends feedback received during customer interactions to the server. This feedback includes customer facial expressions and tone of voice. This data is then fed back into the learning model to help provide a more optimal response in future interactions.

[0736] Step 5:

[0737] The server also provides information from the customer service model to the glasses-type terminal. Based on this information, the glasses-type terminal displays real-time customer suggestions to the store staff. Inputs include basic customer information and purchase history, while output is customized product suggestions. Flask is used to send this data to the glasses-type terminal, improving operational efficiency.

[0738] 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.

[0739] This invention is a system that enables more personalized responses by accurately recognizing customer emotions and combining them with an emotion engine when a humanoid terminal performs customer service tasks. The system includes an emotion engine for analyzing the customer's visual and auditory information, and dynamically optimizes customer service responses by detecting and analyzing the emotional state in real time.

[0740] Data collection and emotion recognition

[0741] The server stores customer interaction data collected within the store, which includes not only traditional customer service process data but also emotional data such as facial expressions and tone of voice.

[0742] The device uses its built-in emotion engine to recognize the user's emotions in real time. It also utilizes a facial expression analysis module and a voice analysis module to deepen its understanding of the customer's content.

[0743] Training and application of customer service skills

[0744] The server uses machine learning based on collected emotional data to train an advanced customer service skills model that includes emotional responses.

[0745] The terminal receives the latest model information from the server and uses it to interact with customers. It detects emotional changes in real time and adjusts the tone and content of the conversation as needed.

[0746] Examples of customer service

[0747] If the user has a depressed expression, the device uses an emotion engine to recognize this state and suggests encouraging words or relaxing services.

[0748] For example, you could change your approach, such as saying, "You seem a little down today. Please let me know if there's anything I can do to help."

[0749] Feedback and model improvement

[0750] The server collects and analyzes emotional feedback data obtained during customer service interactions with the humanoid terminal. This allows for continuous improvement of more accurate and personalized customer service skills.

[0751] This process ensures that the customer service model is constantly updated to accommodate real-world customer service scenarios.

[0752] As described above, the present invention enables customer service tailored to the customer's emotional state, thereby improving customer satisfaction.

[0753] The following describes the processing flow.

[0754] Step 1:

[0755] The server routinely collects audio and visual data to cover the entire interaction between staff and customers within the store. This includes not only conventional conversational data, but also emotional data such as customers' facial expressions and tone of voice.

[0756] Step 2:

[0757] The server feeds the collected data into machine learning algorithms to train customer service skill models. This enables responses that take customer emotions into account.

[0758] Step 3:

[0759] The server sends a trained customer service skills model to the humanoid terminal. The model is then ready to be applied in customer interactions.

[0760] Step 4:

[0761] The terminals are equipped with the latest models and are ready for customer service. This includes real-time emotion recognition capabilities using an emotion engine.

[0762] Step 5:

[0763] When a user approaches the device, the device detects the user using sensors and begins analyzing their facial expressions and tone of voice using its emotion engine.

[0764] Step 6:

[0765] Based on the results of emotion recognition, the device adjusts its tone of voice and message content to greet the user and answer questions. If the customer is feeling anxious, it will use reassuring words.

[0766] Step 7:

[0767] When a user asks a question or makes a request, the device considers the user's emotions and provides the most appropriate response. For example, it flexibly offers an emotionally sensitive answer such as, "Many people like this product."

[0768] Step 8:

[0769] The server periodically collects and analyzes feedback data on emotional interactions recorded by the humanoid terminals. This data is used to further improve the customer service skills model.

[0770] This will enable the provision of personalized customer service that takes emotions into account, which is expected to improve customer satisfaction.

[0771] (Example 2)

[0772] 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".

[0773] In modern customer service systems, accurately recognizing and responding appropriately to individual customer emotions and states is difficult. This can result in decreased customer satisfaction and inadequate service. Furthermore, traditional customer service methods often lack the real-time response needed to address changes in customer emotions.

[0774] 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.

[0775] In this invention, the server includes means for collecting information relating to customer interactions, means for training response techniques using a learning algorithm based on the collected information, and means for identifying customer emotions in real time and adjusting responses accordingly. This enables accurate recognition of the customer's emotional state and the provision of more appropriate and personalized services.

[0776] "Interaction information" refers to the record of all communication and interaction that takes place between the customer and the autonomous device, including the customer's facial expressions, tone of voice, and verbal responses.

[0777] A "learning algorithm" is a method used by computer systems to automatically acquire and apply patterns and rules based on collected data, thereby improving their response skills.

[0778] An "autonomous terminal" is a machine or device that uses built-in sensors and processing units to interact with customers without external instructions, and is designed to perform specific tasks.

[0779] A "sensing device" refers to a device installed on an autonomous terminal to physically detect information such as the presence, movement, voice, and facial expressions of a customer.

[0780] "Customer service techniques" is a general term for the skills and methods necessary to facilitate communication with customers and improve their satisfaction, and these are implemented using autonomous terminals.

[0781] "Feedback evaluation" refers to information such as opinions and impressions obtained after interactions with customers, which is data that can be used to improve customer service techniques and the overall system.

[0782] This system aims to instantly understand customer emotions and provide appropriate service in customer service operations by using autonomous terminals and emotion recognition technology.

[0783] First, the terminal is equipped with a high-precision camera and a voice recognition microphone, which collects information about interactions such as facial expressions and tone of voice as soon as a customer enters the store. The collected data is analyzed in real time to determine the customer's emotional state. An emotion recognition engine is used in this analysis. Specifically, the software could be a system equipped with advanced image analysis libraries and voice analysis algorithms.

[0784] Next, the acquired data is transferred to a server, which uses a learning algorithm to train its response technology. By analyzing the large amount of accumulated emotional data, the server builds a generative AI model and trains it to respond to diverse customer emotional states. This model is reflected on the terminal, enabling immediate, personalized responses to customers.

[0785] For example, if a user visits a store looking tired, the device can instantly detect their emotional state and suggest products with relaxation effects. An example of a prompt message could be, "Please suggest relaxing products to a tired customer," which can be used to instruct the AI ​​model.

[0786] This system enables the provision of flexible and appropriate services tailored to the customer's emotional state, thereby improving customer satisfaction.

[0787] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0788] Step 1:

[0789] The device collects visual and auditory information using a camera and microphone when a customer enters the store. Specifically, it captures the customer's face with the camera and records their voice tone and volume with the microphone. The input consists of the customer's facial expression data and audio data. The output is this data obtained in a format suitable for sentiment analysis.

[0790] Step 2:

[0791] The terminal inputs the collected data into the emotion recognition engine. The emotion recognition engine uses a facial expression analysis module to analyze facial features from the collected image data and a voice analysis module to analyze the tone of the recorded data. Specific data processing involves feature extraction and mapping to emotional states. The output is the customer's emotional state (e.g., joy, sadness, surprise).

[0792] Step 3:

[0793] The server receives emotional state data transmitted from the terminal. The input is emotional state data analyzed in real time. Based on this, the server applies a learning algorithm and trains a generative AI model with new response techniques. The specific data calculations include analysis using past datasets and construction of response patterns, and the output is an updated generative AI model.

[0794] Step 4:

[0795] The terminal receives the latest AI model from the server and uses it to interact with customers. The input is the updated model data of the interaction technology received from the server. Specifically, its actions include generating voice responses to customer questions and providing appropriate suggestions and guidance. The output is personalized voice-based interaction with the customer.

[0796] Step 5:

[0797] The server collects and analyzes feedback data after customer interactions. It uses customer feedback and terminal response evaluation data as input. Based on this, data calculations are performed to further improve response techniques. Specifically, the feedback is analyzed to identify areas for model improvement, and the output becomes an improvement plan for the next model update.

[0798] (Application Example 2)

[0799] 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".

[0800] Traditional customer service systems have a problem in that they have difficulty appropriately recognizing customer emotions and providing individualized responses. In particular, it is difficult to analyze customers' facial expressions and tone of voice in real time, which can result in delays in providing product recommendations and services that meet their needs, potentially leading to decreased customer satisfaction. Therefore, it is necessary to solve these problems.

[0801] 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.

[0802] In this invention, the server includes means for collecting interaction data with customers, means for training customer service skills using a machine learning algorithm based on the collected data, and means for transmitting the trained customer service skills to an autonomous device. This makes it possible to accurately recognize the emotional state of the customer and dynamically adjust product recommendations based on that emotion.

[0803] A "customer" is someone who receives goods or services, and is an important stakeholder for a company.

[0804] "Interaction data" refers to data related to various interactions that occur with customers, including information about their emotions and behaviors.

[0805] A "machine learning algorithm" is a computational method that automatically performs data analysis and prediction by finding patterns based on large amounts of data.

[0806] "Customer service skills" refer to the techniques used to introduce products and services to customers and increase their satisfaction.

[0807] An "autonomous device" is a mechanical device that can make its own decisions and perform various tasks in a self-contained manner.

[0808] A "sensory device" is equipment that senses information from the outside and processes it as digital data.

[0809] An "integration method" is a way of combining multiple pieces of information or functions to create an overall effective system.

[0810] "Feedback" refers to information that shows reactions to or evaluations of actions and results, and serves as a basis for improvement or change.

[0811] The system of the present invention is designed to efficiently collect and analyze customer interaction data and to provide personalized service based on emotions. The server first collects data obtained from the customer's facial expressions and voice. This data is acquired using a camera sensor and microphone as sensory devices. Based on the collected data, the server trains customer service skills using a machine learning algorithm and transmits these skills to an autonomous device (e.g., a customer service robot).

[0812] The autonomous terminal devices utilize trained customer service skills to analyze customer emotions in real time. Software such as OpenCV and Google Speech-to-Text API are used for facial expression and voice analysis. In particular, the system incorporates an integrated mechanism to dynamically adjust product recommendations based on customer emotions, providing the most appropriate language guidance to the customer.

[0813] For example, if the system detects that a customer is feeling stressed in a store, the autonomous device can make a customized suggestion in real time, such as, "You seem to be having a tough day. We have a new tea that can help you relax; would you like to try it?"

[0814] Throughout this process, customer feedback is collected again on the server and analyzed to improve the customer service model. This enables further improvements in customer service skills. As an example of a prompt for the generated AI model, an effective expression would be, "If the customer appears stressed, what suggestions can help them relax?"

[0815] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0816] Step 1:

[0817] The server collects customer facial and voice data using camera sensors and microphones. The input is the customer's face and voice, and the output is digitized facial image data and voice data. This data serves as foundational information for analyzing customer emotions.

[0818] Step 2:

[0819] The server inputs the collected digitized data into the emotion engine and applies facial expression analysis algorithms and voice analysis algorithms. The inputs are facial expression image data and voice data, and the outputs are parameters indicating the customer's emotional state. By recognizing the customer's emotions in real time using the emotion engine, the server quantifies how the customer is feeling.

[0820] Step 3:

[0821] The server trains its customer service skills using a machine learning algorithm based on emotional state parameters. The input is the customer's emotional state parameters, and the output is the updated customer service skill model. This model is constantly being improved to provide the optimal customer service method tailored to the customer's emotions.

[0822] Step 4:

[0823] The autonomous terminal device receives customer service technology models transmitted from the server and utilizes them for customer service. The input is the updated customer service technology model, and the output is an optimized response to the customer. In this process, product recommendations are dynamically adjusted according to the customer's real-time emotions.

[0824] Step 5:

[0825] An autonomous device collects feedback from users about their customer service experience and sends it back to the server. The input is feedback data obtained from the user, and the output is additional information for the customer service model, including suggestions for improvement. Based on this feedback, customer service skills are further improved and utilized in future interactions.

[0826] Step 6:

[0827] The server analyzes the collected feedback and updates the customer service model. The input is feedback data, and the output is an improved customer service technology model. This continuously improves customer service and increases customer satisfaction.

[0828] 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.

[0829] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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."

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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 to be incorporated by reference.

[0849] The following is further disclosed regarding the embodiments described above.

[0850] (Claim 1)

[0851] Means for collecting customer interaction data,

[0852] A means of training customer service skills using a machine learning algorithm based on the aforementioned collected data,

[0853] A means for transmitting the trained customer service skills to a humanoid terminal,

[0854] A humanoid terminal equipped with sensors for customer detection and recognition,

[0855] The humanoid terminal provides a means for giving voice guidance to the customer,

[0856] A means for collecting and analyzing feedback on the aforementioned customer service interactions to improve the customer service model,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, wherein the humanoid terminal analyzes the customer's facial expressions and tone of voice in real time and dynamically adjusts its response.

[0860] (Claim 3)

[0861] The system according to claim 1, wherein the customer service model is trained based on the customer service methods of excellent staff.

[0862] "Example 1"

[0863] (Claim 1)

[0864] A device for collecting information,

[0865] A device that learns skills using machine learning techniques based on the information collected above,

[0866] A device for transmitting the learned skills to an automated device,

[0867] An automated device equipped with sensors for detecting and identifying users,

[0868] The automated device provides voice guidance to the user,

[0869] A device that collects and analyzes evaluations of the aforementioned interactions to improve the learning model,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, wherein the automated device evaluates the user's expression and tone of voice in real time and dynamically adapts its response.

[0873] (Claim 3)

[0874] The system according to claim 1, wherein the learning model is learned based on the methods of excellent individuals.

[0875] "Application Example 1"

[0876] (Claim 1)

[0877] Means for collecting customer interaction data,

[0878] A means of training customer service skills using a machine learning algorithm based on the aforementioned collected data,

[0879] A means for transmitting the trained customer service skills to a humanoid terminal,

[0880] A humanoid terminal equipped with a detection device for detecting and recognizing customers,

[0881] The humanoid terminal provides a means for giving voice guidance to the customer,

[0882] A means for collecting and analyzing feedback on the aforementioned customer service interactions to improve the customer service model,

[0883] A means of using glasses-type terminals equipped with a display device that shows customer information and product information, for making appropriate product suggestions,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, which uses feedback data from the aforementioned humanoid terminal to dynamically update the customer service model and guides store staff through glasses-type terminals to suggest products suitable for the customer.

[0887] (Claim 3)

[0888] The system according to claim 1, wherein the customer service model is trained based on the customer service methods of excellent store managers and is presented to store employees in a manner that is easy for them to implement using a glasses-type terminal.

[0889] "Example 2 of combining an emotion engine"

[0890] (Claim 1)

[0891] Means for collecting information about customer interactions,

[0892] A means for training response skills using a learning algorithm based on the information collected above,

[0893] A means for transferring the aforementioned trained response techniques to an autonomous terminal,

[0894] An autonomous terminal equipped with a sensing device for detecting and recognizing customers,

[0895] The autonomous terminal provides a means for giving voice instructions to the customer,

[0896] A means for collecting and analyzing evaluations related to the aforementioned interaction to improve the response model,

[0897] A means to identify customer emotions in real time and adjust responses accordingly,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] The system according to claim 1, wherein the autonomous terminal evaluates the customer's facial expressions and tone of voice in real time and dynamically optimizes its response.

[0901] (Claim 3)

[0902] The system according to claim 1, wherein the response model is trained based on the response methods of skilled staff.

[0903] "Application example 2 when combining with an emotional engine"

[0904] (Claim 1)

[0905] Means for collecting customer interaction data,

[0906] A means of training customer service skills using a machine learning algorithm based on the aforementioned collected data,

[0907] A means for transmitting the trained customer service skills to an autonomous device,

[0908] An autonomous device equipped with sensory devices to recognize the emotional state of a customer,

[0909] The autonomous device provides a means for giving verbal guidance to the customer,

[0910] A means for collecting and analyzing feedback on the aforementioned customer service interactions to improve the customer service model,

[0911] An integrated means for dynamically adjusting product recommendations based on customer emotions,

[0912] A system that includes this.

[0913] (Claim 2)

[0914] The system according to claim 1, wherein the autonomous device analyzes the customer's facial expressions and voice characteristics in real time and dynamically adjusts its response.

[0915] (Claim 3)

[0916] The system according to claim 1, wherein the customer service model is trained based on the customer service methods of excellent employees and provides suggestions that respond to the customer's emotions. [Explanation of symbols]

[0917] 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. Means for collecting customer interaction data, A means of training customer service skills using a machine learning algorithm based on the aforementioned collected data, A means for transmitting the trained customer service skills to a humanoid terminal, A humanoid terminal equipped with sensors for customer detection and recognition, The humanoid terminal provides a means for giving voice guidance to the customer, A means for collecting and analyzing feedback on the aforementioned customer service interactions to improve the customer service model, A system that includes this.

2. The system according to claim 1, wherein the humanoid terminal analyzes the customer's facial expressions and tone of voice in real time and dynamically adjusts its response.

3. The system according to claim 1, wherein the customer service model is trained based on the customer service methods of excellent staff.

Images