system

Abstract

We provide the system. [Solution] A means of collecting customer interaction data in real time, A means of analyzing collected data to evaluate customer emotions and satisfaction, A means to predict future customer satisfaction and issue alerts when a decline in satisfaction is predicted, A means of generating personalized sales scenarios based on customer characteristics, A system that includes this.

Description

Technical Field

[0005] ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object is to solve the problem that it is difficult to achieve efficient sales activities and high customer satisfaction due to the difficulty of making proposals according to new needs for a large customer base in a company and the difficulty of predicting in advance a decrease in customer satisfaction.

Means for Solving the Problems

[0005] The present invention provides a system that collects customer interaction data in real time and evaluates customer sentiment and satisfaction through analysis. This system has a function of predicting future customer satisfaction and sending an alert when there is a sign of decrease. Furthermore, by generating a sales scenario based on customer characteristics and enabling personalized proposals, customer engagement is improved.

[0006] "Customer interaction data" refers to information about interactions with customers, including text, audio, and video data formats.

[0007] "Collecting data in real time" refers to the process of immediately acquiring and recording events as they occur as data.

[0008] "Analysis" is the act of analyzing information based on collected data to derive specific conclusions or evaluations.

[0009] "Evaluating customer emotions and satisfaction" is the process of analyzing the attitudes and concerns that customers exhibit during their interaction with the system, and determining their underlying emotional state and level of satisfaction with the service.

[0010] "Predicting future customer satisfaction" refers to a technique that uses past data and current conditions to predict future trends in customer satisfaction.

[0011] "Issuing an alert" is a mechanism that sends a signal or notification to inform relevant parties when specific conditions are met.

[0012] "Generating sales scenarios based on customer characteristics" is a process that automatically creates optimal sales methods and proposals tailored to each customer's preferences and past behavioral patterns.

[0013] "Personalized suggestions" refer to suggestions that are customized based on the individual needs and preferences of each customer. [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

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

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

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

[0018] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[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] As an embodiment of this invention, a customer service system utilizing AI technology is provided. The core components of the system are a data analysis engine using a generative AI model and a customer satisfaction prediction engine using machine learning.

[0036] The system's construction primarily involves servers, terminals, and users. The server plays a central role in efficiently collecting customer interaction data and performing various analyses. In particular, it utilizes OCR and speech recognition technologies to process customer communication as text data.

[0037] The terminal provides the user interface, displaying analysis results and sales scenarios received from the server. This interface is updated in real time to support the user's decision-making.

[0038] Users make the most of the data collected via their devices through their daily sales activities and customer support work. The system supports the automation of analysis and proposals without wasting the interactions that users gain from their interactions with customers.

[0039] As a concrete example, if a user explains a new product to customer B, the content of the interaction is immediately sent to the server. The server analyzes this data and infers customer B's emotions and level of interest from the voice. If it determines that interest has decreased, the server sends an alert to the user's device and immediately suggests improvements. The user then uses the personalized scenario suggested by the server to approach customer B again. Through this process, the system promotes more efficient customer engagement.

[0040] Thus, this system provides a method for highly automating customer service and sales activities, resulting in an effective outcome.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server receives customer interaction data in real time in text, audio, and video formats. The data is received via API and immediately stored in the database.

[0044] Step 2:

[0045] The server places the received interaction data into an analysis queue. Natural language processing algorithms analyze the text data to classify the customer's emotions, while voice data is transcribed using speech recognition technology and similarly subjected to emotion analysis.

[0046] Step 3:

[0047] The server uses a facial recognition algorithm to analyze video data and infer emotions from the customer's facial expressions. This allows for a comprehensive emotional assessment based on text, audio, and video.

[0048] Step 4:

[0049] The server references past interaction history and uses a machine learning model to predict future customer satisfaction. This information is updated in real time and displayed on the dashboard.

[0050] Step 5:

[0051] The server sends alerts to customers whose satisfaction is predicted to decline. The alerts are displayed on the user's device, drawing their attention and suggesting countermeasures.

[0052] Step 6:

[0053] The server generates appropriate sales scenarios based on customer profile information and past behavioral data. These scenarios are then sent to the user's device as personalized proposals tailored to each individual customer.

[0054] Step 7:

[0055] Users utilize personalized sales scenarios displayed on their devices to further communicate with customers, thereby strengthening engagement and improving conversion rates.

[0056] (Example 1)

[0057] 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."

[0058] In customer interactions, there is a need for a system that can accurately grasp changes in customer sentiment and level of interest in real time and take swift action. However, conventional systems have difficulty meeting these requirements, and a particular challenge exists: if there is a delay in responding immediately to a decline in customer interest, customer satisfaction will decrease.

[0059] 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.

[0060] In this invention, the server includes means for converting customer interaction data into text in real time, means for analyzing the text data using a generation AI model to score the customer's emotions and level of interest, and means for sending an alert to the user's terminal when a decrease in interest is detected based on the scoring results. This makes it possible to quickly grasp changes in customer emotions and interests and take appropriate action.

[0061] "Interaction data" refers to information generated when a customer interacts with a system, and includes data in various formats such as audio, text, and video.

[0062] "Real-time" refers to a state where data collection, processing, and responses occur immediately, meaning they are carried out continuously without delay.

[0063] "Text conversion" is the process of converting non-textual information, such as audio and video, into textual information, and is a process that facilitates data analysis.

[0064] A "generative AI model" is an artificial intelligence algorithm that analyzes large amounts of data and generates results according to a specific purpose, and is used to evaluate customer sentiment and levels of interest.

[0065] "Scoring" is the process of making numerical evaluations based on analyzed data, and it is an indicator used to quantify the degree of customer emotion and interest.

[0066] An "alert" is a warning message that a system presents to a user under specific conditions, and is used to encourage a quick response.

[0067] A "personalized sales scenario" is a sales plan individually designed based on customer characteristics and past behavioral data, and is a strategy to enable effective customer service.

[0068] This invention is a system for streamlining customer service, in which the server, terminal, and user work in close cooperation.

[0069] First, the server collects customer interaction data in real time. This data includes audio, text, and video. The server utilizes OCR and speech recognition technologies to convert non-textual information into text. This allows customer interactions to be quickly processed as digital data.

[0070] Next, the server analyzes the transcribed data using a generation AI model. This analysis scores the customer's emotions and level of interest, and evaluates them numerically. An example of a prompt might be, "Evaluate this customer's level of interest."

[0071] Furthermore, if the server detects a decline in interest based on the scoring results, it sends an alert to the user's device. The alert provides suggestions for improvement and specific guidelines for dealing with the customer.

[0072] The terminal displays analysis results and alerts received from the server to the user in real time. This interface allows users to instantly grasp the information necessary for customer service and make appropriate decisions.

[0073] Users interact with customers based on information obtained through their devices. For example, if customer response to a new product is low, they can use feedback from the server to change their approach and implement measures to regain customer interest.

[0074] In this way, the system enables rapid analysis and response in customer interactions, helping to improve customer satisfaction.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server collects customer interaction data in real time. Inputs include audio, text, and video data from customers. The server uses OCR technology to convert handwritten information into text and speech recognition to convert audio data into text data. Outputs are standardized interaction data in text format.

[0078] Step 2:

[0079] The server analyzes the text data obtained in the previous step using a generative AI model. The input is standardized text data. The AI ​​model is instructed using the prompt "Evaluate the degree of this customer's emotion and interest." As a result of the data analysis, the server generates a score that quantifies the customer's emotion and interest as output.

[0080] Step 3:

[0081] The server sends an alert to the user's device if a decline in interest is detected based on the score evaluation. The input is the evaluated score, which determines whether the interest level falls below a predetermined threshold. The output is an alert displayed on the user's device, including suggestions for improvement.

[0082] Step 4:

[0083] The terminal displays alerts and analysis results from the server to the user in real time. Input consists of alert messages and scores sent from the server. It visually outputs information to help the user quickly understand the situation.

[0084] Step 5:

[0085] Users respond to customers based on information obtained from their devices. Input consists of alerts and suggested scenarios visualized on the device. Users utilize the outputted information to optimize their interaction with customers, such as by modifying their approach.

[0086] (Application Example 1)

[0087] 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."

[0088] In customer service using smart glasses, traditional methods made it difficult to immediately utilize information obtained from customer interactions, hindering the ability to take swift and appropriate actions to immediately improve customer satisfaction. In particular, it was difficult to grasp changes in customer emotions and interests in real time and provide the most appropriate response on the spot.

[0089] 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.

[0090] In this invention, the server includes means for collecting customer interaction data in real time, means for analyzing the collected data to evaluate customer emotions and satisfaction, and means for presenting proposals to customer service representatives in real time using a portable display device. This makes it possible to instantly grasp customer emotions and interests and provide appropriate responses immediately.

[0091] "Customer interaction data" is a general term for information such as voice, text, and images obtained when interacting with customers.

[0092] "Means of real-time data collection" refers to technical devices and methods for acquiring information immediately at the point of customer contact and transmitting it to a server.

[0093] "Methods for analyzing and evaluating customer emotions and satisfaction" refer to algorithms and software that analyze customers' psychological states and purchase intentions based on collected interaction data.

[0094] "A means of predicting future customer satisfaction and issuing alerts" refers to technology that predicts a future decline in customer satisfaction based on the customer's current state and issues warnings prompting necessary action.

[0095] "Methods for generating personalized sales scenarios" refer to technologies that automatically create sales strategies and proposals tailored to the individual characteristics and preferences of each customer.

[0096] "A means of presenting proposals to customer service representatives in real time using portable display devices" refers to a method of visually providing optimal proposal information immediately during a conversation with a customer, using smart glasses, tablets, etc.

[0097] The system for realizing this invention is built around a server, a portable display device, and a customer service representative. The server has the capability to collect customer interaction data in real time from multiple devices. This data collection uses speech recognition and OCR technologies and is stored on the server as text data, audio data, and image data.

[0098] The server analyzes collected interaction data and uses generative AI models and natural language processing algorithms to evaluate customer emotions and satisfaction. Based on this evaluation, it predicts future customer satisfaction and immediately issues an alert if a decline in satisfaction is predicted. Personalized sales scenarios are also generated, suggesting the optimal next action for the sales representative.

[0099] Smart glasses are used as a portable display device. Customer service representatives wear these glasses and visually receive real-time analysis and suggestions transmitted from the server. This portable display device allows them to instantly acquire information and apply the most appropriate response even during conversations with customers.

[0100] As a concrete example, when a customer shows interest in a product and a conversation begins, the server instantly transcribes the audio into text and performs sentiment analysis. If the customer says, "I want to know more about this product," the AI ​​identifies that need and displays suggestions on a portable display device, such as "Explain the product features in detail and show examples of its use." An example of a prompt to the generating AI model in this case is, "Present the key points to effectively explain the details and value of the product the customer has shown interest in."

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The server receives customer conversations as audio data through the smart glasses' microphone. The input is the customer's speech, and the output is raw audio data. This audio data is stored on the server in preparation for immediate conversion into text data.

[0104] Step 2:

[0105] The server uses speech recognition software (e.g., a speech recognition API) to convert the audio data into text data. This process allows the server to obtain the customer's speech as text data. The input is audio data, and the output is text data.

[0106] Step 3:

[0107] The server uses generative AI models and natural language processing to analyze text data and evaluate customer emotions and levels of interest. In this process, the server applies machine learning algorithms to quantify customer satisfaction. Input is text data, and output is evaluation data indicating emotions and satisfaction levels.

[0108] Step 4:

[0109] The server generates prompts and personalized sales scenarios based on emotion and satisfaction evaluation data, using a generative AI model. Here, an example prompt is used: "Present the key points to effectively explain the product details and value that the customer has shown interest in." The input is evaluation data, and the output is sales scenario data.

[0110] Step 5:

[0111] Users with portable display devices view sales scenarios received from the server on the smart glasses' display and take the most appropriate action with the customer based on the proposed scenarios. The input is sales scenario data, and the output is the action taken with the customer. This action allows users to effectively communicate with customers.

[0112] 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.

[0113] This invention provides an advanced customer service system utilizing AI, and in particular, includes a configuration that incorporates an emotion engine that recognizes user emotions. This enables real-time understanding of the emotions of both customers and users, and allows for optimal suggestions and responses based on this understanding.

[0114] First, the server collects interaction data with customers and users. This data is captured in three formats—text, audio, and video—and stored directly in the database. The server places the received data into an analysis queue and uses an emotion engine to recognize the emotions of users and customers. Text data is analyzed using natural language processing, and audio data is analyzed using speech recognition technology to identify emotions.

[0115] In addition, the server uses a facial recognition algorithm to analyze the facial expressions of users and customers in the video data and comprehensively evaluate their emotions. This evaluation is reflected on a dashboard and used in real-time sales activities and customer service.

[0116] Next, the server predicts future customer satisfaction based on past data and individual sentiment ratings. Based on this prediction data, if a decline in satisfaction is anticipated, an alert is immediately sent. Along with the alert, the user's device receives suggestions for action and guidelines.

[0117] As a concrete example of its use, a sales representative analyzes the emotions of both themselves and customer C during an online meeting. The server monitors customer C's tone, speaking style, and facial expressions, while simultaneously evaluating the user's own stress levels and concentration. The server combines this data to suggest conversation topics to maintain during the meeting and customer interest points to explore in more detail, in real time. Based on this, the user can effectively approach the customer and close the deal.

[0118] In this way, by incorporating an emotion engine, this system enables a level of emotional response previously unattainable in conventional systems, greatly improving the efficiency of sales activities and customer support.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The server collects customer and user interaction data in real time in text, audio, and video formats. The data is automatically stored in a secure database.

[0122] Step 2:

[0123] The server places the data stored in the database into an analysis queue for analysis. At this stage, natural language processing technology sends the text data to the sentiment engine, where the emotions of both the customer and the user are evaluated.

[0124] Step 3:

[0125] The audio data is input into the speech recognition system by the server and converted into text. Subsequently, the emotion engine analyzes the tone and speed of the speech as indicators of emotion.

[0126] Step 4:

[0127] The server uses a facial recognition algorithm to analyze customer and user facial expressions from video data and determine their emotional state. This determination is then integrated with evaluations from text and audio data.

[0128] Step 5:

[0129] The server predicts future customer satisfaction based on complex sentiment data. A machine learning model improves the accuracy of the prediction by referencing past data history.

[0130] Step 6:

[0131] If the server determines there is a risk of decreased user satisfaction, it will send an alert to the user. The alert will be sent to the device, and a summary of the countermeasures will be displayed.

[0132] Step 7:

[0133] The device presents emotion-based, personalized sales scenarios through its user interface. Users utilize these scenarios to engage with customers effectively and improve engagement.

[0134] (Example 2)

[0135] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0136] In modern business operations, accurately understanding customer and user emotions and satisfaction levels, and responding quickly and appropriately, is essential for improving competitiveness. However, conventional systems struggle with real-time analysis of emotions and satisfaction levels, and therefore lack the flexibility to respond to changes in customer emotions.

[0137] 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.

[0138] In this invention, the server includes means for collecting communication data with users and customers in real time, means for analyzing the collected data to identify the emotions of users and customers and perform emotion evaluations, and means for predicting future customer satisfaction and issuing warnings when a decline in satisfaction is predicted. This enables real-time analysis of customer emotions and satisfaction, as well as the suggestion of optimal countermeasures.

[0139] A "user" is the entity that operates the system and provides the service.

[0140] "Customer" refers to the person or organization that receives the service.

[0141] "Communication data" refers to records of information exchanged between users and customers, and typically includes text data, audio information, and video materials.

[0142] "Real-time" refers to a state where information is processed almost instantaneously, resulting in immediate responsiveness in communication and calculations.

[0143] "Emotional evaluation" is the process of quantifying and analyzing the emotions of users and customers.

[0144] A "warning" is a notification issued by the system when certain conditions are met, and its purpose is to draw attention to the issue.

[0145] "Natural language processing technology" refers to the field of computer science that analyzes and understands human language.

[0146] "Machine learning techniques" are technologies that use data to enable computers to automatically learn and make decisions.

[0147] The embodiments for carrying out the present invention are shown below.

[0148] This system is an advanced customer service system utilizing AI technology, equipped with an emotion engine to analyze the emotions of users and customers. The server collects communication data with users and customers in real time. This data includes three formats: text data, audio information, and video materials, each of which is analyzed using specialized technology.

[0149] Specifically, the server analyzes text data using natural language processing technology (libraries such as NLTK and spaCy), and identifies emotions in audio information using speech recognition technology (such as Google® Speech-to-Text). Furthermore, for video materials, it analyzes emotions from changes in the facial expressions of users and customers using facial recognition algorithms (such as OpenCV).

[0150] This sentiment analysis data is visualized as a dashboard and displayed in real time on the user's device. Based on the data obtained here, the server can use machine learning techniques (regression analysis and neural networks) to predict future customer satisfaction. If the prediction suggests a decline in satisfaction, the server immediately issues a warning and sends suggestions and action guidelines to the user's device.

[0151] As a concrete example, during an online meeting with a client, the server monitors the client's tone, speaking style, and facial expressions, while also evaluating the user's own stress levels and concentration. The server combines this data to provide the user with effective suggestions in real time during the meeting and present topics that will capture the client's interest.

[0152] An example of a prompt might be, "Please tell me how to analyze customer emotions during an online meeting and determine topics to suggest." In this way, the system is expected to improve the accuracy of emotion analysis and significantly enhance efficiency in customer service and sales activities.

[0153] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0154] Step 1:

[0155] The server collects communication data from users and customers. Inputs include text data, audio information, and video materials. The server stores this data in a database in real time and adds it to an analysis queue. Output is the storage of the collected data.

[0156] Step 2:

[0157] The server performs sentiment analysis using data from the analysis queue. The input is collected text data. The server analyzes the text using natural language processing techniques to identify the emotions of users and customers. Specifically, it infers emotions from keywords and context and outputs an emotion score.

[0158] Step 3:

[0159] The server uses sound information to recognize emotions from speech. The input is collected sound information. The server uses speech recognition technology to analyze emotions from the tone and speed of the voice. Specifically, it classifies emotional states based on factors such as pitch and volume, and outputs the result as an emotion score.

[0160] Step 4:

[0161] The server analyzes the facial expressions of users and customers using video footage. The input is the collected video footage. The server applies a facial recognition algorithm to capture changes in facial expressions. Specifically, it detects micro-expression changes, identifies emotions from them, and outputs an emotion score.

[0162] Step 5:

[0163] The server comprehensively evaluates the emotion scores obtained in steps 2 through 4. The input is each individual emotion score. The server integrates these to determine the overall emotional state. Specifically, it weights the individual emotion scores and outputs an evaluation score that can be displayed in real time on the dashboard.

[0164] Step 6:

[0165] The server predicts customer satisfaction using past sentiment evaluation data and current sentiment scores. The input consists of past data and an integrated sentiment score. The server uses machine learning techniques to calculate future evaluations. Specifically, it predicts fluctuations in satisfaction using an algorithm and outputs the prediction results.

[0166] Step 7:

[0167] The server immediately issues a warning if it determines that the predicted customer satisfaction level is declining. The input is the predicted satisfaction data. Based on this, the server sends a notification to the user's device. Specifically, it displays a warning message along with guidelines and suggestions for action to take, and outputs this information.

[0168] (Application Example 2)

[0169] 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."

[0170] In physical stores, it is difficult for staff to understand customers' emotions and interests in real time. This can potentially lead to decreased customer satisfaction. Furthermore, personalizing specific sales activities is not easy. Technology is needed to address these issues.

[0171] 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.

[0172] In this invention, the server includes means for collecting customer interaction information in real time, means for analyzing the collected information to evaluate the customer's emotions and notifying staff in real time of suggested approaches, and means for predicting future customer satisfaction and issuing an alert if a decline in satisfaction is predicted. This enables responses that take customer emotions into account, and allows staff to make suggestions at the appropriate time.

[0173] "Customer interaction information" refers to information exchanged between customers and staff in stores, including written, spoken, and visual information.

[0174] "Methods for collecting information in real time" refers to technological devices that instantly import information into a database the moment an interaction with a customer occurs.

[0175] "Methods for analyzing and evaluating customer emotions" refers to technologies that use natural language processing and facial recognition technology based on collected information to identify the customer's psychological state.

[0176] "A means of notifying staff of suggested approaches in real time" refers to a system that immediately provides staff with the optimal actions to take in customer service based on analysis results.

[0177] "A means of predicting future customer satisfaction and issuing warnings" refers to a technology that predicts future customer reactions based on past data and current analysis results, and provides warnings before problems occur.

[0178] "Means of personalizing sales activities" refers to a system that plans and executes sales strategies tailored to specific needs based on the characteristics and emotional analysis of individual customers.

[0179] Modes for carrying out the invention

[0180] This invention is a system that analyzes customer emotions in real time and suggests the optimal response when store staff wearing smart glasses interact with customers. The system includes several key components to effectively analyze customer-staff interactions and improve customer satisfaction.

[0181] The server incorporates mechanisms for collecting customer interaction information, which is captured in real time in text, audio, and visual formats. Audio information is handled using "Google Cloud Speech-to-Text," and the transcribed data is analyzed for sentiment using the "Google Natural Language API." Visual information is analyzed using "Microsoft® Azure® Face API," which identifies emotional states from facial expressions. Based on these analysis results, the optimal course of action is communicated to staff members via smart glasses.

[0182] The smart glasses, acting as a terminal, utilize collected information to predict customer satisfaction and issue alerts if a decline in satisfaction is predicted. This allows the terminal to use a generated AI model to suggest specific actions to staff, for example, prompting them with messages such as, "There are signs that the customer is interested in product X. Please suggest how to explain the details of this product."

[0183] As a concrete example, when a customer picks up a specific product in a store, the server analyzes the customer's facial expressions and tone of voice to identify signs of interest or dissatisfaction in real time. Based on this, the terminal suggests practical responses to staff, such as, "There is a coupon available for this product, please inform the staff." In this way, users can provide the most appropriate service to customers and improve customer satisfaction.

[0184] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0185] Step 1:

[0186] The server collects customer interaction information received via smart glasses in real time. The input consists of audio and video from the smart glasses' microphone and camera, and the initial objective is to store this information as digital data.

[0187] Step 2:

[0188] The server sends the collected audio data to the Google Cloud Speech-to-Text service. This process converts the audio data into text format. The input is audio data, and the output is text data, which is used in the next analysis step.

[0189] Step 3:

[0190] The server sends text data to the Google Natural Language API for natural language processing. Here, customer emotions are analyzed, and emotional states such as positive and negative are extracted. The input is text data converted from speech, and the output is an emotion score or rating.

[0191] Step 4:

[0192] The server sends the collected video data as visual information to the "Microsoft Azure Face API," where it analyzes emotions using facial recognition technology. The input is video data, and the output is emotional information derived from facial expressions.

[0193] Step 5:

[0194] The server integrates the analysis results from steps 3 and 4 to perform an overall customer sentiment assessment. Based on this assessment, it generates prompts for the next customer interaction for the generative AI model. For example, a possible message might be, "The customer has shown interest in product X."

[0195] Step 6:

[0196] The smart glasses, which act as the terminal, display approach suggestions notified from the server. Based on this real-time information, staff can take appropriate action towards customers. Here, the input is the notification from the server, and the output is the action guidelines presented to the staff.

[0197] Step 7:

[0198] Based on this information, users adjust their communication with customers and aim to improve customer satisfaction. Ultimately, customer responses are collected again on the server and used for evaluation. The input is the interaction with the customer, and the output is the data point for the next interaction.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] [Second Embodiment]

[0203] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0204] 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.

[0205] 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).

[0206] 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.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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".

[0215] As an embodiment of this invention, a customer service system utilizing AI technology is provided. The core components of the system are a data analysis engine using a generative AI model and a customer satisfaction prediction engine using machine learning.

[0216] The system's construction primarily involves servers, terminals, and users. The server plays a central role in efficiently collecting customer interaction data and performing various analyses. In particular, it utilizes OCR and speech recognition technologies to process customer communication as text data.

[0217] The terminal provides the user interface, displaying analysis results and sales scenarios received from the server. This interface is updated in real time to support the user's decision-making.

[0218] Users make the most of the data collected via their devices through their daily sales activities and customer support work. The system supports the automation of analysis and proposals without wasting the interactions that users gain from their interactions with customers.

[0219] As a concrete example, if a user explains a new product to customer B, the content of the interaction is immediately sent to the server. The server analyzes this data and infers customer B's emotions and level of interest from the voice. If it determines that interest has decreased, the server sends an alert to the user's device and immediately suggests improvements. The user then uses the personalized scenario suggested by the server to approach customer B again. Through this process, the system promotes more efficient customer engagement.

[0220] Thus, this system provides a method for highly automating customer service and sales activities, resulting in an effective outcome.

[0221] The following describes the processing flow.

[0222] Step 1:

[0223] The server receives customer interaction data in real time in text, audio, and video formats. The data is received via API and immediately stored in the database.

[0224] Step 2:

[0225] The server places the received interaction data into an analysis queue. Natural language processing algorithms analyze the text data to classify the customer's emotions, while voice data is transcribed using speech recognition technology and similarly subjected to emotion analysis.

[0226] Step 3:

[0227] The server uses a facial recognition algorithm to analyze video data and infer emotions from the customer's facial expressions. This allows for a comprehensive emotional assessment based on text, audio, and video.

[0228] Step 4:

[0229] The server references past interaction history and uses a machine learning model to predict future customer satisfaction. This information is updated in real time and displayed on the dashboard.

[0230] Step 5:

[0231] The server sends alerts to customers whose satisfaction is predicted to decline. The alerts are displayed on the user's device, drawing their attention and suggesting countermeasures.

[0232] Step 6:

[0233] The server generates appropriate sales scenarios based on customer profile information and past behavioral data. These scenarios are then sent to the user's device as personalized proposals tailored to each individual customer.

[0234] Step 7:

[0235] Users utilize personalized sales scenarios displayed on their devices to further communicate with customers, thereby strengthening engagement and improving conversion rates.

[0236] (Example 1)

[0237] 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."

[0238] In customer interactions, there is a need for a system that can accurately grasp changes in customer sentiment and level of interest in real time and take swift action. However, conventional systems have difficulty meeting these requirements, and a particular challenge exists: if there is a delay in responding immediately to a decline in customer interest, customer satisfaction will decrease.

[0239] 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.

[0240] In this invention, the server includes means for converting customer interaction data into text in real time, means for analyzing the text data using a generation AI model to score the customer's emotions and level of interest, and means for sending an alert to the user's terminal when a decrease in interest is detected based on the scoring results. This makes it possible to quickly grasp changes in customer emotions and interests and take appropriate action.

[0241] "Interaction data" refers to information generated when a customer interacts with a system, and includes data in various formats such as audio, text, and video.

[0242] "Real-time" refers to a state where data collection, processing, and responses occur immediately, meaning they are carried out continuously without delay.

[0243] "Text conversion" is the process of converting non-textual information, such as audio and video, into textual information, and is a process that facilitates data analysis.

[0244] A "generative AI model" is an artificial intelligence algorithm that analyzes large amounts of data and generates results according to a specific purpose, and is used to evaluate customer sentiment and levels of interest.

[0245] "Scoring" is the process of making numerical evaluations based on analyzed data, and it is an indicator used to quantify the degree of customer emotion and interest.

[0246] An "alert" is a warning message that a system presents to a user under specific conditions, and is used to encourage a quick response.

[0247] A "personalized sales scenario" is a sales plan individually designed based on customer characteristics and past behavioral data, and is a strategy to enable effective customer service.

[0248] This invention is a system for streamlining customer service, in which the server, terminal, and user work in close cooperation.

[0249] First, the server collects customer interaction data in real time. This data includes audio, text, and video. The server utilizes OCR and speech recognition technologies to convert non-textual information into text. This allows customer interactions to be quickly processed as digital data.

[0250] Next, the server analyzes the transcribed data using a generation AI model. This analysis scores the customer's emotions and level of interest, and evaluates them numerically. An example of a prompt might be, "Evaluate this customer's level of interest."

[0251] Furthermore, if the server detects a decline in interest based on the scoring results, it sends an alert to the user's device. The alert provides suggestions for improvement and specific guidelines for dealing with the customer.

[0252] The terminal displays analysis results and alerts received from the server to the user in real time. This interface allows users to instantly grasp the information necessary for customer service and make appropriate decisions.

[0253] Users interact with customers based on information obtained through their devices. For example, if customer response to a new product is low, they can use feedback from the server to change their approach and implement measures to regain customer interest.

[0254] In this way, the system enables rapid analysis and response in customer interactions, helping to improve customer satisfaction.

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] The server collects customer interaction data in real time. Inputs include audio, text, and video data from customers. The server uses OCR technology to convert handwritten information into text and speech recognition to convert audio data into text data. Outputs are standardized interaction data in text format.

[0258] Step 2:

[0259] The server analyzes the text data obtained in the previous step using a generative AI model. The input is standardized text data. The AI ​​model is instructed using the prompt "Evaluate the degree of this customer's emotion and interest." As a result of the data analysis, the server generates a score that quantifies the customer's emotion and interest as output.

[0260] Step 3:

[0261] The server sends an alert to the user's device if a decline in interest is detected based on the score evaluation. The input is the evaluated score, which determines whether the interest level falls below a predetermined threshold. The output is an alert displayed on the user's device, including suggestions for improvement.

[0262] Step 4:

[0263] The terminal displays alerts and analysis results from the server to the user in real time. Input consists of alert messages and scores sent from the server. It visually outputs information to help the user quickly understand the situation.

[0264] Step 5:

[0265] Users respond to customers based on information obtained from their devices. Input consists of alerts and suggested scenarios visualized on the device. Users utilize the outputted information to optimize their interaction with customers, such as by modifying their approach.

[0266] (Application Example 1)

[0267] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0268] In customer service using smart glasses, traditional methods made it difficult to immediately utilize information obtained from customer interactions, hindering the ability to take swift and appropriate actions to immediately improve customer satisfaction. In particular, it was difficult to grasp changes in customer emotions and interests in real time and provide the most appropriate response on the spot.

[0269] 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.

[0270] In this invention, the server includes means for collecting customer interaction data in real time, means for analyzing the collected data to evaluate customer emotions and satisfaction, and means for presenting proposals to customer service representatives in real time using a portable display device. This makes it possible to instantly grasp customer emotions and interests and provide appropriate responses immediately.

[0271] "Customer interaction data" is a general term for information such as voice, text, and images obtained when interacting with customers.

[0272] "Means of real-time data collection" refers to technical devices and methods for acquiring information immediately at the point of customer contact and transmitting it to a server.

[0273] "Methods for analyzing and evaluating customer emotions and satisfaction" refer to algorithms and software that analyze customers' psychological states and purchase intentions based on collected interaction data.

[0274] "A means of predicting future customer satisfaction and issuing alerts" refers to technology that predicts a future decline in customer satisfaction based on the customer's current state and issues warnings prompting necessary action.

[0275] "Methods for generating personalized sales scenarios" refer to technologies that automatically create sales strategies and proposals tailored to the individual characteristics and preferences of each customer.

[0276] "A means of presenting proposals to customer service representatives in real time using portable display devices" refers to a method of visually providing optimal proposal information immediately during a conversation with a customer, using smart glasses, tablets, etc.

[0277] The system for realizing this invention is built around a server, a portable display device, and a customer service representative. The server has the capability to collect customer interaction data in real time from multiple devices. This data collection uses speech recognition and OCR technologies and is stored on the server as text data, audio data, and image data.

[0278] The server analyzes collected interaction data and uses generative AI models and natural language processing algorithms to evaluate customer emotions and satisfaction. Based on this evaluation, it predicts future customer satisfaction and immediately issues an alert if a decline in satisfaction is predicted. Personalized sales scenarios are also generated, suggesting the optimal next action for the sales representative.

[0279] Smart glasses are used as a portable display device. Customer service representatives wear these glasses and visually receive real-time analysis and suggestions transmitted from the server. This portable display device allows them to instantly acquire information and apply the most appropriate response even during conversations with customers.

[0280] As a concrete example, when a customer shows interest in a product and a conversation begins, the server instantly transcribes the audio into text and performs sentiment analysis. If the customer says, "I want to know more about this product," the AI ​​identifies that need and displays suggestions on a portable display device, such as "Explain the product features in detail and show examples of its use." An example of a prompt to the generating AI model in this case is, "Present the key points to effectively explain the details and value of the product the customer has shown interest in."

[0281] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0282] Step 1:

[0283] The server receives the customer's conversation as voice data through the microphone of the smart glasses. The input is the customer's speech, and the output is the raw voice data. This voice data is stored on the server as preparation for immediate conversion to text data.

[0284] Step 2:

[0285] The server uses speech recognition software (e.g., speech recognition API) to convert the voice data into text data. Through this process, the server obtains the customer's utterance as character data. The input is voice data, and the output is text data.

[0286] Step 3:

[0287] The server analyzes the text data using a generative AI model and natural language processing to evaluate the customer's sentiment and level of interest. At this time, the server applies a machine learning algorithm to quantify the customer's satisfaction. The input is text data, and the output is evaluation data indicating sentiment and satisfaction.

[0288] Step 4:

[0289] The server creates a prompt sentence and generates a personalized sales scenario based on the evaluation data of sentiment and satisfaction through the generative AI model. Here, as an example of a prompt sentence, "Please present the key points for effectively explaining the details and value of the product that the customer is interested in" is used. The input is evaluation data, and the output is sales scenario data.

[0290] Step 5:

[0291] The user with a portable display device checks the sales scenario received from the server on the smart glasses' display and takes the optimal action towards the customer based on the proposed content. The input is sales scenario data, and the output is the action towards the customer. Through this action, the user can effectively advance communication with the customer.

[0292] 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.

[0293] This invention provides an advanced customer service system utilizing AI, and in particular, includes a configuration that incorporates an emotion engine that recognizes user emotions. This enables real-time understanding of the emotions of both customers and users, and allows for optimal suggestions and responses based on this understanding.

[0294] First, the server collects interaction data with customers and users. This data is captured in three formats—text, audio, and video—and stored directly in the database. The server places the received data into an analysis queue and uses an emotion engine to recognize the emotions of users and customers. Text data is analyzed using natural language processing, and audio data is analyzed using speech recognition technology to identify emotions.

[0295] In addition, the server uses a facial recognition algorithm to analyze the facial expressions of users and customers in the video data and comprehensively evaluate their emotions. This evaluation is reflected on a dashboard and used in real-time sales activities and customer service.

[0296] Next, the server predicts future customer satisfaction based on past data and individual sentiment ratings. Based on this prediction data, if a decline in satisfaction is anticipated, an alert is immediately sent. Along with the alert, the user's device receives suggestions for action and guidelines.

[0297] As a concrete example of its use, a sales representative analyzes the emotions of both themselves and customer C during an online meeting. The server monitors customer C's tone, speaking style, and facial expressions, while simultaneously evaluating the user's own stress levels and concentration. The server combines this data to suggest conversation topics to maintain during the meeting and customer interest points to explore in more detail, in real time. Based on this, the user can effectively approach the customer and close the deal.

[0298] In this way, by incorporating an emotion engine, this system enables a level of emotional response previously unattainable in conventional systems, greatly improving the efficiency of sales activities and customer support.

[0299] The following describes the processing flow.

[0300] Step 1:

[0301] The server collects customer and user interaction data in real time in text, audio, and video formats. The data is automatically stored in a secure database.

[0302] Step 2:

[0303] The server places the data stored in the database into an analysis queue for analysis. At this stage, natural language processing technology sends the text data to the sentiment engine, where the emotions of both the customer and the user are evaluated.

[0304] Step 3:

[0305] The audio data is input into the speech recognition system by the server and converted into text. Subsequently, the emotion engine analyzes the tone and speed of the speech as indicators of emotion.

[0306] Step 4:

[0307] The server uses a face recognition algorithm to analyze the expressions of customers and users from video data and determine their emotional states. This determination result is integrated with the evaluations from text and voice data.

[0308] Step 5:

[0309] Based on the comprehensive emotional data, the server predicts the future customer satisfaction. A machine learning model refers to the past data history to improve the accuracy of the prediction.

[0310] Step 6:

[0311] If the server determines that there is a risk of decreasing satisfaction, it sends an alert to the user. The alert is notified to the terminal and an overview of the countermeasures is displayed.

[0312] Step 7:

[0313] The terminal presents an emotion-based personalized sales scenario through the interface to the user. The user uses this scenario to conduct appropriate communication with the customer and improve engagement.

[0314] (Example 2)

[0315] Next, Example 2 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".

[0316] In modern corporate activities, accurately grasping the emotions and satisfaction of customers and users and responding quickly and appropriately is essential for improving competitiveness. However, conventional systems have the problem that it is difficult to perform real-time analysis of emotions and satisfaction, and flexible response according to changes in customer emotions cannot be achieved.

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

[0318] ") In this invention, the server includes means for collecting communication data with users and customers in real time, means for analyzing the collected data to identify the emotions of users and customers and perform emotion evaluations, and means for predicting future customer satisfaction and issuing warnings when a decline in satisfaction is predicted. This enables real-time analysis of customer emotions and satisfaction, as well as the suggestion of optimal countermeasures.

[0319] A "user" is the entity that operates the system and provides the service.

[0320] "Customer" refers to the person or organization that receives the service.

[0321] "Communication data" refers to records of information exchanged between users and customers, and typically includes text data, audio information, and video materials.

[0322] "Real-time" refers to a state where information is processed almost instantaneously, resulting in immediate responsiveness in communication and calculations.

[0323] "Emotional evaluation" is the process of quantifying and analyzing the emotions of users and customers.

[0324] A "warning" is a notification issued by the system when certain conditions are met, and its purpose is to draw attention to the issue.

[0325] "Natural language processing technology" refers to the field of computer science that analyzes and understands human language.

[0326] "Machine learning techniques" are technologies that use data to enable computers to automatically learn and make decisions.

[0327] The embodiments for carrying out the present invention are shown below.

[0328] This system is an advanced customer service system utilizing AI technology, equipped with an emotion engine to analyze the emotions of users and customers. The server collects communication data with users and customers in real time. This data includes three formats: text data, audio information, and video materials, each of which is analyzed using specialized technology.

[0329] Specifically, the server analyzes text data using natural language processing techniques (libraries such as NLTK and spaCy), and identifies emotions in audio information using speech recognition techniques (such as Google Speech-to-Text). For video materials, it analyzes emotions from changes in the facial expressions of users and customers using facial recognition algorithms (such as OpenCV).

[0330] This sentiment analysis data is visualized as a dashboard and displayed in real time on the user's device. Based on the data obtained here, the server can use machine learning techniques (regression analysis and neural networks) to predict future customer satisfaction. If the prediction suggests a decline in satisfaction, the server immediately issues a warning and sends suggestions and action guidelines to the user's device.

[0331] As a concrete example, during an online meeting with a client, the server monitors the client's tone, speaking style, and facial expressions, while also evaluating the user's own stress levels and concentration. The server combines this data to provide the user with effective suggestions in real time during the meeting and present topics that will capture the client's interest.

[0332] An example of a prompt might be, "Please tell me how to analyze customer emotions during an online meeting and determine topics to suggest." In this way, the system is expected to improve the accuracy of emotion analysis and significantly enhance efficiency in customer service and sales activities.

[0333] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0334] Step 1:

[0335] The server collects communication data from users and customers. Inputs include text data, audio information, and video materials. The server stores this data in a database in real time and adds it to an analysis queue. Output is the storage of the collected data.

[0336] Step 2:

[0337] The server performs sentiment analysis using data from the analysis queue. The input is collected text data. The server analyzes the text using natural language processing techniques to identify the emotions of users and customers. Specifically, it infers emotions from keywords and context and outputs an emotion score.

[0338] Step 3:

[0339] The server uses sound information to recognize emotions from speech. The input is collected sound information. The server uses speech recognition technology to analyze emotions from the tone and speed of the voice. Specifically, it classifies emotional states based on factors such as pitch and volume, and outputs the result as an emotion score.

[0340] Step 4:

[0341] The server analyzes the facial expressions of users and customers using video footage. The input is the collected video footage. The server applies a facial recognition algorithm to capture changes in facial expressions. Specifically, it detects micro-expression changes, identifies emotions from them, and outputs an emotion score.

[0342] Step 5:

[0343] The server comprehensively evaluates the emotion scores obtained in steps 2 through 4. The input is each individual emotion score. The server integrates these to determine the overall emotional state. Specifically, it weights the individual emotion scores and outputs an evaluation score that can be displayed in real time on the dashboard.

[0344] Step 6:

[0345] The server predicts customer satisfaction using past sentiment evaluation data and current sentiment scores. The input consists of past data and an integrated sentiment score. The server uses machine learning techniques to calculate future evaluations. Specifically, it predicts fluctuations in satisfaction using an algorithm and outputs the prediction results.

[0346] Step 7:

[0347] The server immediately issues a warning if it determines that the predicted customer satisfaction level is declining. The input is the predicted satisfaction data. Based on this, the server sends a notification to the user's device. Specifically, it displays a warning message along with guidelines and suggestions for action to take, and outputs this information.

[0348] (Application Example 2)

[0349] 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."

[0350] In physical stores, it is difficult for staff to understand customers' emotions and interests in real time. This can potentially lead to decreased customer satisfaction. Furthermore, personalizing specific sales activities is not easy. Technology is needed to address these issues.

[0351] 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.

[0352] In this invention, the server includes means for collecting customer interaction information in real time, means for analyzing the collected information to evaluate the customer's emotions and notifying staff in real time of suggested approaches, and means for predicting future customer satisfaction and issuing an alert if a decline in satisfaction is predicted. This enables responses that take customer emotions into account, and allows staff to make suggestions at the appropriate time.

[0353] "Customer interaction information" refers to information exchanged between customers and staff in stores, including written, spoken, and visual information.

[0354] "Methods for collecting information in real time" refers to technological devices that instantly import information into a database the moment an interaction with a customer occurs.

[0355] "Methods for analyzing and evaluating customer emotions" refers to technologies that use natural language processing and facial recognition technology based on collected information to identify the customer's psychological state.

[0356] "A means of notifying staff of suggested approaches in real time" refers to a system that immediately provides staff with the optimal actions to take in customer service based on analysis results.

[0357] "A means of predicting future customer satisfaction and issuing warnings" refers to a technology that predicts future customer reactions based on past data and current analysis results, and provides warnings before problems occur.

[0358] "Means of personalizing sales activities" refers to a system that plans and executes sales strategies tailored to specific needs based on the characteristics and emotional analysis of individual customers.

[0359] Modes for carrying out the invention

[0360] This invention is a system that analyzes customer emotions in real time and suggests the optimal response when store staff wearing smart glasses interact with customers. The system includes several key components to effectively analyze customer-staff interactions and improve customer satisfaction.

[0361] The server incorporates mechanisms for collecting customer interaction information, which is captured in real time in text, audio, and visual formats. Audio information is handled using "Google Cloud Speech-to-Text," and the transcribed data is analyzed for sentiment using the "Google Natural Language API." Visual information is analyzed using the "Microsoft Azure Face API," which identifies emotional states from facial expressions. Based on these analysis results, the optimal course of action is communicated to staff members via smart glasses.

[0362] The smart glasses, acting as a terminal, utilize collected information to predict customer satisfaction and issue alerts if a decline in satisfaction is predicted. This allows the terminal to use a generated AI model to suggest specific actions to staff, for example, prompting them with messages such as, "There are signs that the customer is interested in product X. Please suggest how to explain the details of this product."

[0363] As a concrete example, when a customer picks up a specific product in a store, the server analyzes the customer's facial expressions and tone of voice to identify signs of interest or dissatisfaction in real time. Based on this, the terminal suggests practical responses to staff, such as, "There is a coupon available for this product, please inform the staff." In this way, users can provide the most appropriate service to customers and improve customer satisfaction.

[0364] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0365] Step 1:

[0366] The server collects customer interaction information received via smart glasses in real time. The input consists of audio and video from the smart glasses' microphone and camera, and the initial objective is to store this information as digital data.

[0367] Step 2:

[0368] The server sends the collected audio data to the Google Cloud Speech-to-Text service. This process converts the audio data into text format. The input is audio data, and the output is text data, which is used in the next analysis step.

[0369] Step 3:

[0370] The server sends text data to the Google Natural Language API for natural language processing. Here, customer emotions are analyzed, and emotional states such as positive and negative are extracted. The input is text data converted from speech, and the output is an emotion score or rating.

[0371] Step 4:

[0372] The server sends the collected video data as visual information to the "Microsoft Azure Face API," where it analyzes emotions using facial recognition technology. The input is video data, and the output is emotional information derived from facial expressions.

[0373] Step 5:

[0374] The server integrates the analysis results from steps 3 and 4 to perform an overall customer sentiment assessment. Based on this assessment, it generates prompts for the next customer interaction for the generative AI model. For example, a possible message might be, "The customer has shown interest in product X."

[0375] Step 6:

[0376] The smart glasses, which act as the terminal, display approach suggestions notified from the server. Based on this real-time information, staff can take appropriate action towards customers. Here, the input is the notification from the server, and the output is the action guidelines presented to the staff.

[0377] Step 7:

[0378] Based on this information, users adjust their communication with customers and aim to improve customer satisfaction. Ultimately, customer responses are collected again on the server and used for evaluation. The input is the interaction with the customer, and the output is the data point for the next interaction.

[0379] 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.

[0380] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0381] 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.

[0382] [Third Embodiment]

[0383] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0384] 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.

[0385] 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).

[0386] 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.

[0387] 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.

[0388] 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).

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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".

[0395] As an embodiment of this invention, a customer service system utilizing AI technology is provided. The core components of the system are a data analysis engine using a generative AI model and a customer satisfaction prediction engine using machine learning.

[0396] The system's construction primarily involves servers, terminals, and users. The server plays a central role in efficiently collecting customer interaction data and performing various analyses. In particular, it utilizes OCR and speech recognition technologies to process customer communication as text data.

[0397] The terminal provides the user interface, displaying analysis results and sales scenarios received from the server. This interface is updated in real time to support the user's decision-making.

[0398] Users make the most of the data collected via their devices through their daily sales activities and customer support work. The system supports the automation of analysis and proposals without wasting the interactions that users gain from their interactions with customers.

[0399] As a concrete example, if a user explains a new product to customer B, the content of the interaction is immediately sent to the server. The server analyzes this data and infers customer B's emotions and level of interest from the voice. If it determines that interest has decreased, the server sends an alert to the user's device and immediately suggests improvements. The user then uses the personalized scenario suggested by the server to approach customer B again. Through this process, the system promotes more efficient customer engagement.

[0400] Thus, this system provides a method for highly automating customer service and sales activities, resulting in an effective outcome.

[0401] The following describes the processing flow.

[0402] Step 1:

[0403] The server receives customer interaction data in real time in text, audio, and video formats. The data is received via API and immediately stored in the database.

[0404] Step 2:

[0405] The server places the received interaction data into an analysis queue. Natural language processing algorithms analyze the text data to classify the customer's emotions, while voice data is transcribed using speech recognition technology and similarly subjected to emotion analysis.

[0406] Step 3:

[0407] The server uses a facial recognition algorithm to analyze video data and infer emotions from the customer's facial expressions. This allows for a comprehensive emotional assessment based on text, audio, and video.

[0408] Step 4:

[0409] The server references past interaction history and uses a machine learning model to predict future customer satisfaction. This information is updated in real time and displayed on the dashboard.

[0410] Step 5:

[0411] The server sends alerts to customers whose satisfaction is predicted to decline. The alerts are displayed on the user's device, drawing their attention and suggesting countermeasures.

[0412] Step 6:

[0413] The server generates appropriate sales scenarios based on customer profile information and past behavioral data. These scenarios are then sent to the user's device as personalized proposals tailored to each individual customer.

[0414] Step 7:

[0415] Users utilize personalized sales scenarios displayed on their devices to further communicate with customers, thereby strengthening engagement and improving conversion rates.

[0416] (Example 1)

[0417] 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."

[0418] In customer interactions, there is a need for a system that can accurately grasp changes in customer sentiment and level of interest in real time and take swift action. However, conventional systems have difficulty meeting these requirements, and a particular challenge exists: if there is a delay in responding immediately to a decline in customer interest, customer satisfaction will decrease.

[0419] 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.

[0420] In this invention, the server includes means for converting customer interaction data into text in real time, means for analyzing the text data using a generation AI model to score the customer's emotions and level of interest, and means for sending an alert to the user's terminal when a decrease in interest is detected based on the scoring results. This makes it possible to quickly grasp changes in customer emotions and interests and take appropriate action.

[0421] "Interaction data" refers to information generated when a customer interacts with a system, and includes data in various formats such as audio, text, and video.

[0422] "Real-time" refers to a state where data collection, processing, and responses occur immediately, meaning they are carried out continuously without delay.

[0423] "Text conversion" is the process of converting non-textual information, such as audio and video, into textual information, and is a process that facilitates data analysis.

[0424] A "generative AI model" is an artificial intelligence algorithm that analyzes large amounts of data and generates results according to a specific purpose, and is used to evaluate customer sentiment and levels of interest.

[0425] "Scoring" is the process of making numerical evaluations based on analyzed data, and it is an indicator used to quantify the degree of customer emotion and interest.

[0426] An "alert" is a warning message that a system presents to a user under specific conditions, and is used to encourage a quick response.

[0427] A "personalized sales scenario" is a sales plan individually designed based on customer characteristics and past behavioral data, and is a strategy to enable effective customer service.

[0428] This invention is a system for streamlining customer service, in which the server, terminal, and user work in close cooperation.

[0429] First, the server collects customer interaction data in real time. This data includes audio, text, and video. The server utilizes OCR and speech recognition technologies to convert non-textual information into text. This allows customer interactions to be quickly processed as digital data.

[0430] Next, the server analyzes the transcribed data using a generation AI model. This analysis scores the customer's emotions and level of interest, and evaluates them numerically. An example of a prompt might be, "Evaluate this customer's level of interest."

[0431] Furthermore, if the server detects a decline in interest based on the scoring results, it sends an alert to the user's device. The alert provides suggestions for improvement and specific guidelines for dealing with the customer.

[0432] The terminal displays analysis results and alerts received from the server to the user in real time. This interface allows users to instantly grasp the information necessary for customer service and make appropriate decisions.

[0433] Users interact with customers based on information obtained through their devices. For example, if customer response to a new product is low, they can use feedback from the server to change their approach and implement measures to regain customer interest.

[0434] In this way, the system enables rapid analysis and response in customer interactions, helping to improve customer satisfaction.

[0435] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0436] Step 1:

[0437] The server collects customer interaction data in real time. Inputs include audio, text, and video data from customers. The server uses OCR technology to convert handwritten information into text and speech recognition to convert audio data into text data. Outputs are standardized interaction data in text format.

[0438] Step 2:

[0439] The server analyzes the text data obtained in the previous step using a generative AI model. The input is standardized text data. The AI ​​model is instructed using the prompt "Evaluate the degree of this customer's emotion and interest." As a result of the data analysis, the server generates a score that quantifies the customer's emotion and interest as output.

[0440] Step 3:

[0441] The server sends an alert to the user's device if a decline in interest is detected based on the score evaluation. The input is the evaluated score, which determines whether the interest level falls below a predetermined threshold. The output is an alert displayed on the user's device, including suggestions for improvement.

[0442] Step 4:

[0443] The terminal displays alerts and analysis results from the server to the user in real time. Input consists of alert messages and scores sent from the server. It visually outputs information to help the user quickly understand the situation.

[0444] Step 5:

[0445] Users respond to customers based on information obtained from their devices. Input consists of alerts and suggested scenarios visualized on the device. Users utilize the outputted information to optimize their interaction with customers, such as by modifying their approach.

[0446] (Application Example 1)

[0447] 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."

[0448] In customer service using smart glasses, traditional methods made it difficult to immediately utilize information obtained from customer interactions, hindering the ability to take swift and appropriate actions to immediately improve customer satisfaction. In particular, it was difficult to grasp changes in customer emotions and interests in real time and provide the most appropriate response on the spot.

[0449] 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.

[0450] In this invention, the server includes means for collecting customer interaction data in real time, means for analyzing the collected data to evaluate customer emotions and satisfaction, and means for presenting proposals to customer service representatives in real time using a portable display device. This makes it possible to instantly grasp customer emotions and interests and provide appropriate responses immediately.

[0451] "Customer interaction data" is a general term for information such as voice, text, and images obtained when interacting with customers.

[0452] "Means of real-time data collection" refers to technical devices and methods for acquiring information immediately at the point of customer contact and transmitting it to a server.

[0453] "Methods for analyzing and evaluating customer emotions and satisfaction" refer to algorithms and software that analyze customers' psychological states and purchase intentions based on collected interaction data.

[0454] "A means of predicting future customer satisfaction and issuing alerts" refers to technology that predicts a future decline in customer satisfaction based on the customer's current state and issues warnings prompting necessary action.

[0455] "Methods for generating personalized sales scenarios" refer to technologies that automatically create sales strategies and proposals tailored to the individual characteristics and preferences of each customer.

[0456] "A means of presenting proposals to customer service representatives in real time using portable display devices" refers to a method of visually providing optimal proposal information immediately during a conversation with a customer, using smart glasses, tablets, etc.

[0457] The system for realizing this invention is built around a server, a portable display device, and a customer service representative. The server has the capability to collect customer interaction data in real time from multiple devices. This data collection uses speech recognition and OCR technologies and is stored on the server as text data, audio data, and image data.

[0458] The server analyzes collected interaction data and uses generative AI models and natural language processing algorithms to evaluate customer emotions and satisfaction. Based on this evaluation, it predicts future customer satisfaction and immediately issues an alert if a decline in satisfaction is predicted. Personalized sales scenarios are also generated, suggesting the optimal next action for the sales representative.

[0459] Smart glasses are used as a portable display device. Customer service representatives wear these glasses and visually receive real-time analysis and suggestions transmitted from the server. This portable display device allows them to instantly acquire information and apply the most appropriate response even during conversations with customers.

[0460] As a concrete example, when a customer shows interest in a product and a conversation begins, the server instantly transcribes the audio into text and performs sentiment analysis. If the customer says, "I want to know more about this product," the AI ​​identifies that need and displays suggestions on a portable display device, such as "Explain the product features in detail and show examples of its use." An example of a prompt to the generating AI model in this case is, "Present the key points to effectively explain the details and value of the product the customer has shown interest in."

[0461] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0462] Step 1:

[0463] The server receives customer conversations as audio data through the smart glasses' microphone. The input is the customer's speech, and the output is raw audio data. This audio data is stored on the server in preparation for immediate conversion into text data.

[0464] Step 2:

[0465] The server uses speech recognition software (e.g., a speech recognition API) to convert the audio data into text data. This process allows the server to obtain the customer's speech as text data. The input is audio data, and the output is text data.

[0466] Step 3:

[0467] The server uses generative AI models and natural language processing to analyze text data and evaluate customer emotions and levels of interest. In this process, the server applies machine learning algorithms to quantify customer satisfaction. Input is text data, and output is evaluation data indicating emotions and satisfaction levels.

[0468] Step 4:

[0469] The server generates prompts and personalized sales scenarios based on emotion and satisfaction evaluation data, using a generative AI model. Here, an example prompt is used: "Present the key points to effectively explain the product details and value that the customer has shown interest in." The input is evaluation data, and the output is sales scenario data.

[0470] Step 5:

[0471] Users with portable display devices view sales scenarios received from the server on the smart glasses' display and take the most appropriate action with the customer based on the proposed scenarios. The input is sales scenario data, and the output is the action taken with the customer. This action allows users to effectively communicate with customers.

[0472] 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.

[0473] This invention provides an advanced customer service system utilizing AI, and in particular, includes a configuration that incorporates an emotion engine that recognizes user emotions. This enables real-time understanding of the emotions of both customers and users, and allows for optimal suggestions and responses based on this understanding.

[0474] First, the server collects interaction data with customers and users. This data is captured in three formats—text, audio, and video—and stored directly in the database. The server places the received data into an analysis queue and uses an emotion engine to recognize the emotions of users and customers. Text data is analyzed using natural language processing, and audio data is analyzed using speech recognition technology to identify emotions.

[0475] In addition, the server uses a facial recognition algorithm to analyze the facial expressions of users and customers in the video data and comprehensively evaluate their emotions. This evaluation is reflected on a dashboard and used in real-time sales activities and customer service.

[0476] Next, the server predicts future customer satisfaction based on past data and individual sentiment ratings. Based on this prediction data, if a decline in satisfaction is anticipated, an alert is immediately sent. Along with the alert, the user's device receives suggestions for action and guidelines.

[0477] As a concrete example of its use, a sales representative analyzes the emotions of both themselves and customer C during an online meeting. The server monitors customer C's tone, speaking style, and facial expressions, while simultaneously evaluating the user's own stress levels and concentration. The server combines this data to suggest conversation topics to maintain during the meeting and customer interest points to explore in more detail, in real time. Based on this, the user can effectively approach the customer and close the deal.

[0478] In this way, by incorporating an emotion engine, this system enables a level of emotional response previously unattainable in conventional systems, greatly improving the efficiency of sales activities and customer support.

[0479] The following describes the processing flow.

[0480] Step 1:

[0481] The server collects customer and user interaction data in real time in text, audio, and video formats. The data is automatically stored in a secure database.

[0482] Step 2:

[0483] The server places the data stored in the database into an analysis queue for analysis. At this stage, natural language processing technology sends the text data to the sentiment engine, where the emotions of both the customer and the user are evaluated.

[0484] Step 3:

[0485] The audio data is input into the speech recognition system by the server and converted into text. Subsequently, the emotion engine analyzes the tone and speed of the speech as indicators of emotion.

[0486] Step 4:

[0487] The server uses a facial recognition algorithm to analyze customer and user facial expressions from video data and determine their emotional state. This determination is then integrated with evaluations from text and audio data.

[0488] Step 5:

[0489] The server predicts future customer satisfaction based on complex sentiment data. A machine learning model improves the accuracy of the prediction by referencing past data history.

[0490] Step 6:

[0491] If the server determines there is a risk of decreased user satisfaction, it will send an alert to the user. The alert will be sent to the device, and a summary of the countermeasures will be displayed.

[0492] Step 7:

[0493] The device presents emotion-based, personalized sales scenarios through its user interface. Users utilize these scenarios to engage with customers effectively and improve engagement.

[0494] (Example 2)

[0495] 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."

[0496] In modern business operations, accurately understanding customer and user emotions and satisfaction levels, and responding quickly and appropriately, is essential for improving competitiveness. However, conventional systems struggle with real-time analysis of emotions and satisfaction levels, and therefore lack the flexibility to respond to changes in customer emotions.

[0497] 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.

[0498] In this invention, the server includes means for collecting communication data with users and customers in real time, means for analyzing the collected data to identify the emotions of users and customers and perform emotion evaluations, and means for predicting future customer satisfaction and issuing warnings when a decline in satisfaction is predicted. This enables real-time analysis of customer emotions and satisfaction, as well as the suggestion of optimal countermeasures.

[0499] A "user" is the entity that operates the system and provides the service.

[0500] "Customer" refers to the person or organization that receives the service.

[0501] "Communication data" refers to records of information exchanged between users and customers, and typically includes text data, audio information, and video materials.

[0502] "Real-time" refers to a state where information is processed almost instantaneously, resulting in immediate responsiveness in communication and calculations.

[0503] "Emotional evaluation" is the process of quantifying and analyzing the emotions of users and customers.

[0504] A "warning" is a notification issued by the system when certain conditions are met, and its purpose is to draw attention to the issue.

[0505] "Natural language processing technology" refers to the field of computer science that analyzes and understands human language.

[0506] "Machine learning techniques" are technologies that use data to enable computers to automatically learn and make decisions.

[0507] The embodiments for carrying out the present invention are shown below.

[0508] This system is an advanced customer service system utilizing AI technology, equipped with an emotion engine to analyze the emotions of users and customers. The server collects communication data with users and customers in real time. This data includes three formats: text data, audio information, and video materials, each of which is analyzed using specialized technology.

[0509] Specifically, the server analyzes text data using natural language processing techniques (libraries such as NLTK and spaCy), and identifies emotions in audio information using speech recognition techniques (such as Google Speech-to-Text). For video materials, it analyzes emotions from changes in the facial expressions of users and customers using facial recognition algorithms (such as OpenCV).

[0510] This sentiment analysis data is visualized as a dashboard and displayed in real time on the user's device. Based on the data obtained here, the server can use machine learning techniques (regression analysis and neural networks) to predict future customer satisfaction. If the prediction suggests a decline in satisfaction, the server immediately issues a warning and sends suggestions and action guidelines to the user's device.

[0511] As a concrete example, during an online meeting with a client, the server monitors the client's tone, speaking style, and facial expressions, while also evaluating the user's own stress levels and concentration. The server combines this data to provide the user with effective suggestions in real time during the meeting and present topics that will capture the client's interest.

[0512] An example of a prompt might be, "Please tell me how to analyze customer emotions during an online meeting and determine topics to suggest." In this way, the system is expected to improve the accuracy of emotion analysis and significantly enhance efficiency in customer service and sales activities.

[0513] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0514] Step 1:

[0515] The server collects communication data from users and customers. Inputs include text data, audio information, and video materials. The server stores this data in a database in real time and adds it to an analysis queue. Output is the storage of the collected data.

[0516] Step 2:

[0517] The server performs sentiment analysis using data from the analysis queue. The input is collected text data. The server analyzes the text using natural language processing techniques to identify the emotions of users and customers. Specifically, it infers emotions from keywords and context and outputs an emotion score.

[0518] Step 3:

[0519] The server uses sound information to recognize emotions from speech. The input is collected sound information. The server uses speech recognition technology to analyze emotions from the tone and speed of the voice. Specifically, it classifies emotional states based on factors such as pitch and volume, and outputs the result as an emotion score.

[0520] Step 4:

[0521] The server analyzes the facial expressions of users and customers using video footage. The input is the collected video footage. The server applies a facial recognition algorithm to capture changes in facial expressions. Specifically, it detects micro-expression changes, identifies emotions from them, and outputs an emotion score.

[0522] Step 5:

[0523] The server comprehensively evaluates the emotion scores obtained in steps 2 through 4. The input is each individual emotion score. The server integrates these to determine the overall emotional state. Specifically, it weights the individual emotion scores and outputs an evaluation score that can be displayed in real time on the dashboard.

[0524] Step 6:

[0525] The server predicts customer satisfaction using past sentiment evaluation data and current sentiment scores. The input consists of past data and an integrated sentiment score. The server uses machine learning techniques to calculate future evaluations. Specifically, it predicts fluctuations in satisfaction using an algorithm and outputs the prediction results.

[0526] Step 7:

[0527] The server immediately issues a warning if it determines that the predicted customer satisfaction level is declining. The input is the predicted satisfaction data. Based on this, the server sends a notification to the user's device. Specifically, it displays a warning message along with guidelines and suggestions for action to take, and outputs this information.

[0528] (Application Example 2)

[0529] 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."

[0530] In physical stores, it is difficult for staff to understand customers' emotions and interests in real time. This can potentially lead to decreased customer satisfaction. Furthermore, personalizing specific sales activities is not easy. Technology is needed to address these issues.

[0531] 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.

[0532] In this invention, the server includes means for collecting customer interaction information in real time, means for analyzing the collected information to evaluate the customer's emotions and notifying staff in real time of suggested approaches, and means for predicting future customer satisfaction and issuing an alert if a decline in satisfaction is predicted. This enables responses that take customer emotions into account, and allows staff to make suggestions at the appropriate time.

[0533] "Customer interaction information" refers to information exchanged between customers and staff in stores, including written, spoken, and visual information.

[0534] "Methods for collecting information in real time" refers to technological devices that instantly import information into a database the moment an interaction with a customer occurs.

[0535] "Methods for analyzing and evaluating customer emotions" refers to technologies that use natural language processing and facial recognition technology based on collected information to identify the customer's psychological state.

[0536] "A means of notifying staff of suggested approaches in real time" refers to a system that immediately provides staff with the optimal actions to take in customer service based on analysis results.

[0537] "A means of predicting future customer satisfaction and issuing warnings" refers to a technology that predicts future customer reactions based on past data and current analysis results, and provides warnings before problems occur.

[0538] "Means of personalizing sales activities" refers to a system that plans and executes sales strategies tailored to specific needs based on the characteristics and emotional analysis of individual customers.

[0539] Modes for carrying out the invention

[0540] This invention is a system that analyzes customer emotions in real time and suggests the optimal response when store staff wearing smart glasses interact with customers. The system includes several key components to effectively analyze customer-staff interactions and improve customer satisfaction.

[0541] The server incorporates mechanisms for collecting customer interaction information, which is captured in real time in text, audio, and visual formats. Audio information is handled using "Google Cloud Speech-to-Text," and the transcribed data is analyzed for sentiment using the "Google Natural Language API." Visual information is analyzed using the "Microsoft Azure Face API," which identifies emotional states from facial expressions. Based on these analysis results, the optimal course of action is communicated to staff members via smart glasses.

[0542] The smart glasses, acting as a terminal, utilize collected information to predict customer satisfaction and issue alerts if a decline in satisfaction is predicted. This allows the terminal to use a generated AI model to suggest specific actions to staff, for example, prompting them with messages such as, "There are signs that the customer is interested in product X. Please suggest how to explain the details of this product."

[0543] As a concrete example, when a customer picks up a specific product in a store, the server analyzes the customer's facial expressions and tone of voice to identify signs of interest or dissatisfaction in real time. Based on this, the terminal suggests practical responses to staff, such as, "There is a coupon available for this product, please inform the staff." In this way, users can provide the most appropriate service to customers and improve customer satisfaction.

[0544] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0545] Step 1:

[0546] The server collects customer interaction information received via smart glasses in real time. The input consists of audio and video from the smart glasses' microphone and camera, and the initial objective is to store this information as digital data.

[0547] Step 2:

[0548] The server sends the collected audio data to the Google Cloud Speech-to-Text service. This process converts the audio data into text format. The input is audio data, and the output is text data, which is used in the next analysis step.

[0549] Step 3:

[0550] The server sends text data to the Google Natural Language API for natural language processing. Here, customer emotions are analyzed, and emotional states such as positive and negative are extracted. The input is text data converted from speech, and the output is an emotion score or rating.

[0551] Step 4:

[0552] The server sends the collected video data as visual information to the "Microsoft Azure Face API," where it analyzes emotions using facial recognition technology. The input is video data, and the output is emotional information derived from facial expressions.

[0553] Step 5:

[0554] The server integrates the analysis results from steps 3 and 4 to perform an overall customer sentiment assessment. Based on this assessment, it generates prompts for the next customer interaction for the generative AI model. For example, a possible message might be, "The customer has shown interest in product X."

[0555] Step 6:

[0556] The smart glasses, which act as the terminal, display approach suggestions notified from the server. Based on this real-time information, staff can take appropriate action towards customers. Here, the input is the notification from the server, and the output is the action guidelines presented to the staff.

[0557] Step 7:

[0558] Based on this information, users adjust their communication with customers and aim to improve customer satisfaction. Ultimately, customer responses are collected again on the server and used for evaluation. The input is the interaction with the customer, and the output is the data point for the next interaction.

[0559] 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.

[0560] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0561] 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.

[0562] [Fourth Embodiment]

[0563] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0564] 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.

[0565] 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).

[0566] 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.

[0567] 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.

[0568] 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).

[0569] 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.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] 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.

[0574] 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.

[0575] 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".

[0576] As an embodiment of this invention, a customer service system utilizing AI technology is provided. The core components of the system are a data analysis engine using a generative AI model and a customer satisfaction prediction engine using machine learning.

[0577] The system's construction primarily involves servers, terminals, and users. The server plays a central role in efficiently collecting customer interaction data and performing various analyses. In particular, it utilizes OCR and speech recognition technologies to process customer communication as text data.

[0578] The terminal provides the user interface, displaying analysis results and sales scenarios received from the server. This interface is updated in real time to support the user's decision-making.

[0579] Users make the most of the data collected via their devices through their daily sales activities and customer support work. The system supports the automation of analysis and proposals without wasting the interactions that users gain from their interactions with customers.

[0580] As a concrete example, if a user explains a new product to customer B, the content of the interaction is immediately sent to the server. The server analyzes this data and infers customer B's emotions and level of interest from the voice. If it determines that interest has decreased, the server sends an alert to the user's device and immediately suggests improvements. The user then uses the personalized scenario suggested by the server to approach customer B again. Through this process, the system promotes more efficient customer engagement.

[0581] Thus, this system provides a method for highly automating customer service and sales activities, resulting in an effective outcome.

[0582] The following describes the processing flow.

[0583] Step 1:

[0584] The server receives customer interaction data in real time in text, audio, and video formats. The data is received via API and immediately stored in the database.

[0585] Step 2:

[0586] The server places the received interaction data into an analysis queue. Natural language processing algorithms analyze the text data to classify the customer's emotions, while voice data is transcribed using speech recognition technology and similarly subjected to emotion analysis.

[0587] Step 3:

[0588] The server uses a facial recognition algorithm to analyze video data and infer emotions from the customer's facial expressions. This allows for a comprehensive emotional assessment based on text, audio, and video.

[0589] Step 4:

[0590] The server references past interaction history and uses a machine learning model to predict future customer satisfaction. This information is updated in real time and displayed on the dashboard.

[0591] Step 5:

[0592] The server sends alerts to customers whose satisfaction is predicted to decline. The alerts are displayed on the user's device, drawing their attention and suggesting countermeasures.

[0593] Step 6:

[0594] The server generates appropriate sales scenarios based on customer profile information and past behavioral data. These scenarios are then sent to the user's device as personalized proposals tailored to each individual customer.

[0595] Step 7:

[0596] Users utilize personalized sales scenarios displayed on their devices to further communicate with customers, thereby strengthening engagement and improving conversion rates.

[0597] (Example 1)

[0598] 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".

[0599] In customer interactions, there is a need for a system that can accurately grasp changes in customer sentiment and level of interest in real time and take swift action. However, conventional systems have difficulty meeting these requirements, and a particular challenge exists: if there is a delay in responding immediately to a decline in customer interest, customer satisfaction will decrease.

[0600] 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.

[0601] In this invention, the server includes means for converting customer interaction data into text in real time, means for analyzing the text data using a generation AI model to score the customer's emotions and level of interest, and means for sending an alert to the user's terminal when a decrease in interest is detected based on the scoring results. This makes it possible to quickly grasp changes in customer emotions and interests and take appropriate action.

[0602] "Interaction data" refers to information generated when a customer interacts with a system, and includes data in various formats such as audio, text, and video.

[0603] "Real-time" refers to a state where data collection, processing, and responses occur immediately, meaning they are carried out continuously without delay.

[0604] "Text conversion" is the process of converting non-textual information, such as audio and video, into textual information, and is a process that facilitates data analysis.

[0605] A "generative AI model" is an artificial intelligence algorithm that analyzes large amounts of data and generates results according to a specific purpose, and is used to evaluate customer sentiment and levels of interest.

[0606] "Scoring" is the process of making numerical evaluations based on analyzed data, and it is an indicator used to quantify the degree of customer emotion and interest.

[0607] An "alert" is a warning message that a system presents to a user under specific conditions, and is used to encourage a quick response.

[0608] A "personalized sales scenario" is a sales plan individually designed based on customer characteristics and past behavioral data, and is a strategy to enable effective customer service.

[0609] This invention is a system for streamlining customer service, in which the server, terminal, and user work in close cooperation.

[0610] First, the server collects customer interaction data in real time. This data includes audio, text, and video. The server utilizes OCR and speech recognition technologies to convert non-textual information into text. This allows customer interactions to be quickly processed as digital data.

[0611] Next, the server analyzes the transcribed data using a generation AI model. This analysis scores the customer's emotions and level of interest, and evaluates them numerically. An example of a prompt might be, "Evaluate this customer's level of interest."

[0612] Furthermore, if the server detects a decline in interest based on the scoring results, it sends an alert to the user's device. The alert provides suggestions for improvement and specific guidelines for dealing with the customer.

[0613] The terminal displays analysis results and alerts received from the server to the user in real time. This interface allows users to instantly grasp the information necessary for customer service and make appropriate decisions.

[0614] Users interact with customers based on information obtained through their devices. For example, if customer response to a new product is low, they can use feedback from the server to change their approach and implement measures to regain customer interest.

[0615] In this way, the system enables rapid analysis and response in customer interactions, helping to improve customer satisfaction.

[0616] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0617] Step 1:

[0618] The server collects customer interaction data in real time. Inputs include audio, text, and video data from customers. The server uses OCR technology to convert handwritten information into text and speech recognition to convert audio data into text data. Outputs are standardized interaction data in text format.

[0619] Step 2:

[0620] The server analyzes the text data obtained in the previous step using a generative AI model. The input is standardized text data. The AI ​​model is instructed using the prompt "Evaluate the degree of this customer's emotion and interest." As a result of the data analysis, the server generates a score that quantifies the customer's emotion and interest as output.

[0621] Step 3:

[0622] The server sends an alert to the user's device if a decline in interest is detected based on the score evaluation. The input is the evaluated score, which determines whether the interest level falls below a predetermined threshold. The output is an alert displayed on the user's device, including suggestions for improvement.

[0623] Step 4:

[0624] The terminal displays alerts and analysis results from the server to the user in real time. Input consists of alert messages and scores sent from the server. It visually outputs information to help the user quickly understand the situation.

[0625] Step 5:

[0626] Users respond to customers based on information obtained from their devices. Input consists of alerts and suggested scenarios visualized on the device. Users utilize the outputted information to optimize their interaction with customers, such as by modifying their approach.

[0627] (Application Example 1)

[0628] 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".

[0629] In customer service using smart glasses, traditional methods made it difficult to immediately utilize information obtained from customer interactions, hindering the ability to take swift and appropriate actions to immediately improve customer satisfaction. In particular, it was difficult to grasp changes in customer emotions and interests in real time and provide the most appropriate response on the spot.

[0630] 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.

[0631] In this invention, the server includes means for collecting customer interaction data in real time, means for analyzing the collected data to evaluate customer emotions and satisfaction, and means for presenting proposals to customer service representatives in real time using a portable display device. This makes it possible to instantly grasp customer emotions and interests and provide appropriate responses immediately.

[0632] "Customer interaction data" is a general term for information such as voice, text, and images obtained when interacting with customers.

[0633] "Means of real-time data collection" refers to technical devices and methods for acquiring information immediately at the point of customer contact and transmitting it to a server.

[0634] "Methods for analyzing and evaluating customer emotions and satisfaction" refer to algorithms and software that analyze customers' psychological states and purchase intentions based on collected interaction data.

[0635] "A means of predicting future customer satisfaction and issuing alerts" refers to technology that predicts a future decline in customer satisfaction based on the customer's current state and issues warnings prompting necessary action.

[0636] "Methods for generating personalized sales scenarios" refer to technologies that automatically create sales strategies and proposals tailored to the individual characteristics and preferences of each customer.

[0637] "A means of presenting proposals to customer service representatives in real time using portable display devices" refers to a method of visually providing optimal proposal information immediately during a conversation with a customer, using smart glasses, tablets, etc.

[0638] The system for realizing this invention is built around a server, a portable display device, and a customer service representative. The server has the capability to collect customer interaction data in real time from multiple devices. This data collection uses speech recognition and OCR technologies and is stored on the server as text data, audio data, and image data.

[0639] The server analyzes collected interaction data and uses generative AI models and natural language processing algorithms to evaluate customer emotions and satisfaction. Based on this evaluation, it predicts future customer satisfaction and immediately issues an alert if a decline in satisfaction is predicted. Personalized sales scenarios are also generated, suggesting the optimal next action for the sales representative.

[0640] Smart glasses are used as a portable display device. Customer service representatives wear these glasses and visually receive real-time analysis and suggestions transmitted from the server. This portable display device allows them to instantly acquire information and apply the most appropriate response even during conversations with customers.

[0641] As a concrete example, when a customer shows interest in a product and a conversation begins, the server instantly transcribes the audio into text and performs sentiment analysis. If the customer says, "I want to know more about this product," the AI ​​identifies that need and displays suggestions on a portable display device, such as "Explain the product features in detail and show examples of its use." An example of a prompt to the generating AI model in this case is, "Present the key points to effectively explain the details and value of the product the customer has shown interest in."

[0642] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0643] Step 1:

[0644] The server receives customer conversations as audio data through the smart glasses' microphone. The input is the customer's speech, and the output is raw audio data. This audio data is stored on the server in preparation for immediate conversion into text data.

[0645] Step 2:

[0646] The server uses speech recognition software (e.g., a speech recognition API) to convert the audio data into text data. This process allows the server to obtain the customer's speech as text data. The input is audio data, and the output is text data.

[0647] Step 3:

[0648] The server uses generative AI models and natural language processing to analyze text data and evaluate customer emotions and levels of interest. In this process, the server applies machine learning algorithms to quantify customer satisfaction. Input is text data, and output is evaluation data indicating emotions and satisfaction levels.

[0649] Step 4:

[0650] The server generates prompts and personalized sales scenarios based on emotion and satisfaction evaluation data, using a generative AI model. Here, an example prompt is used: "Present the key points to effectively explain the product details and value that the customer has shown interest in." The input is evaluation data, and the output is sales scenario data.

[0651] Step 5:

[0652] Users with portable display devices view sales scenarios received from the server on the smart glasses' display and take the most appropriate action with the customer based on the proposed scenarios. The input is sales scenario data, and the output is the action taken with the customer. This action allows users to effectively communicate with customers.

[0653] 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.

[0654] This invention provides an advanced customer service system utilizing AI, and in particular, includes a configuration that incorporates an emotion engine that recognizes user emotions. This enables real-time understanding of the emotions of both customers and users, and allows for optimal suggestions and responses based on this understanding.

[0655] First, the server collects interaction data with customers and users. This data is captured in three formats—text, audio, and video—and stored directly in the database. The server places the received data into an analysis queue and uses an emotion engine to recognize the emotions of users and customers. Text data is analyzed using natural language processing, and audio data is analyzed using speech recognition technology to identify emotions.

[0656] In addition, the server uses a facial recognition algorithm to analyze the facial expressions of users and customers in the video data and comprehensively evaluate their emotions. This evaluation is reflected on a dashboard and used in real-time sales activities and customer service.

[0657] Next, the server predicts future customer satisfaction based on past data and individual sentiment ratings. Based on this prediction data, if a decline in satisfaction is anticipated, an alert is immediately sent. Along with the alert, the user's device receives suggestions for action and guidelines.

[0658] As a concrete example of its use, a sales representative analyzes the emotions of both themselves and customer C during an online meeting. The server monitors customer C's tone, speaking style, and facial expressions, while simultaneously evaluating the user's own stress levels and concentration. The server combines this data to suggest conversation topics to maintain during the meeting and customer interest points to explore in more detail, in real time. Based on this, the user can effectively approach the customer and close the deal.

[0659] In this way, by incorporating an emotion engine, this system enables a level of emotional response previously unattainable in conventional systems, greatly improving the efficiency of sales activities and customer support.

[0660] The following describes the processing flow.

[0661] Step 1:

[0662] The server collects customer and user interaction data in real time in text, audio, and video formats. The data is automatically stored in a secure database.

[0663] Step 2:

[0664] The server places the data stored in the database into an analysis queue for analysis. At this stage, natural language processing technology sends the text data to the sentiment engine, where the emotions of both the customer and the user are evaluated.

[0665] Step 3:

[0666] The audio data is input into the speech recognition system by the server and converted into text. Subsequently, the emotion engine analyzes the tone and speed of the speech as indicators of emotion.

[0667] Step 4:

[0668] The server uses a facial recognition algorithm to analyze customer and user facial expressions from video data and determine their emotional state. This determination is then integrated with evaluations from text and audio data.

[0669] Step 5:

[0670] The server predicts future customer satisfaction based on complex sentiment data. A machine learning model improves the accuracy of the prediction by referencing past data history.

[0671] Step 6:

[0672] If the server determines there is a risk of decreased user satisfaction, it will send an alert to the user. The alert will be sent to the device, and a summary of the countermeasures will be displayed.

[0673] Step 7:

[0674] The device presents emotion-based, personalized sales scenarios through its user interface. Users utilize these scenarios to engage with customers effectively and improve engagement.

[0675] (Example 2)

[0676] 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".

[0677] In modern business operations, accurately understanding customer and user emotions and satisfaction levels, and responding quickly and appropriately, is essential for improving competitiveness. However, conventional systems struggle with real-time analysis of emotions and satisfaction levels, and therefore lack the flexibility to respond to changes in customer emotions.

[0678] 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.

[0679] In this invention, the server includes means for collecting communication data with users and customers in real time, means for analyzing the collected data to identify the emotions of users and customers and perform emotion evaluations, and means for predicting future customer satisfaction and issuing warnings when a decline in satisfaction is predicted. This enables real-time analysis of customer emotions and satisfaction, as well as the suggestion of optimal countermeasures.

[0680] A "user" is the entity that operates the system and provides the service.

[0681] "Customer" refers to the person or organization that receives the service.

[0682] "Communication data" refers to records of information exchanged between users and customers, and typically includes text data, audio information, and video materials.

[0683] "Real-time" refers to a state where information is processed almost instantaneously, resulting in immediate responsiveness in communication and calculations.

[0684] "Emotional evaluation" is the process of quantifying and analyzing the emotions of users and customers.

[0685] A "warning" is a notification issued by the system when certain conditions are met, and its purpose is to draw attention to the issue.

[0686] "Natural language processing technology" refers to the field of computer science that analyzes and understands human language.

[0687] "Machine learning techniques" are technologies that use data to enable computers to automatically learn and make decisions.

[0688] The embodiments for carrying out the present invention are shown below.

[0689] This system is an advanced customer service system utilizing AI technology, equipped with an emotion engine to analyze the emotions of users and customers. The server collects communication data with users and customers in real time. This data includes three formats: text data, audio information, and video materials, each of which is analyzed using specialized technology.

[0690] Specifically, the server analyzes text data using natural language processing techniques (libraries such as NLTK and spaCy), and identifies emotions in audio information using speech recognition techniques (such as Google Speech-to-Text). For video materials, it analyzes emotions from changes in the facial expressions of users and customers using facial recognition algorithms (such as OpenCV).

[0691] This sentiment analysis data is visualized as a dashboard and displayed in real time on the user's device. Based on the data obtained here, the server can use machine learning techniques (regression analysis and neural networks) to predict future customer satisfaction. If the prediction suggests a decline in satisfaction, the server immediately issues a warning and sends suggestions and action guidelines to the user's device.

[0692] As a concrete example, during an online meeting with a client, the server monitors the client's tone, speaking style, and facial expressions, while also evaluating the user's own stress levels and concentration. The server combines this data to provide the user with effective suggestions in real time during the meeting and present topics that will capture the client's interest.

[0693] An example of a prompt might be, "Please tell me how to analyze customer emotions during an online meeting and determine topics to suggest." In this way, the system is expected to improve the accuracy of emotion analysis and significantly enhance efficiency in customer service and sales activities.

[0694] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0695] Step 1:

[0696] The server collects communication data from users and customers. Inputs include text data, audio information, and video materials. The server stores this data in a database in real time and adds it to an analysis queue. Output is the storage of the collected data.

[0697] Step 2:

[0698] The server performs sentiment analysis using data from the analysis queue. The input is collected text data. The server analyzes the text using natural language processing techniques to identify the emotions of users and customers. Specifically, it infers emotions from keywords and context and outputs an emotion score.

[0699] Step 3:

[0700] The server uses sound information to recognize emotions from speech. The input is collected sound information. The server uses speech recognition technology to analyze emotions from the tone and speed of the voice. Specifically, it classifies emotional states based on factors such as pitch and volume, and outputs the result as an emotion score.

[0701] Step 4:

[0702] The server analyzes the facial expressions of users and customers using video footage. The input is the collected video footage. The server applies a facial recognition algorithm to capture changes in facial expressions. Specifically, it detects micro-expression changes, identifies emotions from them, and outputs an emotion score.

[0703] Step 5:

[0704] The server comprehensively evaluates the emotion scores obtained in steps 2 through 4. The input is each individual emotion score. The server integrates these to determine the overall emotional state. Specifically, it weights the individual emotion scores and outputs an evaluation score that can be displayed in real time on the dashboard.

[0705] Step 6:

[0706] The server predicts customer satisfaction using past sentiment evaluation data and current sentiment scores. The input consists of past data and an integrated sentiment score. The server uses machine learning techniques to calculate future evaluations. Specifically, it predicts fluctuations in satisfaction using an algorithm and outputs the prediction results.

[0707] Step 7:

[0708] The server immediately issues a warning if it determines that the predicted customer satisfaction level is declining. The input is the predicted satisfaction data. Based on this, the server sends a notification to the user's device. Specifically, it displays a warning message along with guidelines and suggestions for action to take, and outputs this information.

[0709] (Application Example 2)

[0710] 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".

[0711] In physical stores, it is difficult for staff to understand customers' emotions and interests in real time. This can potentially lead to decreased customer satisfaction. Furthermore, personalizing specific sales activities is not easy. Technology is needed to address these issues.

[0712] 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.

[0713] In this invention, the server includes means for collecting customer interaction information in real time, means for analyzing the collected information to evaluate the customer's emotions and notifying staff in real time of suggested approaches, and means for predicting future customer satisfaction and issuing an alert if a decline in satisfaction is predicted. This enables responses that take customer emotions into account, and allows staff to make suggestions at the appropriate time.

[0714] "Customer interaction information" refers to information exchanged between customers and staff in stores, including written, spoken, and visual information.

[0715] "Methods for collecting information in real time" refers to technological devices that instantly import information into a database the moment an interaction with a customer occurs.

[0716] "Methods for analyzing and evaluating customer emotions" refers to technologies that use natural language processing and facial recognition technology based on collected information to identify the customer's psychological state.

[0717] "A means of notifying staff of suggested approaches in real time" refers to a system that immediately provides staff with the optimal actions to take in customer service based on analysis results.

[0718] "A means of predicting future customer satisfaction and issuing warnings" refers to a technology that predicts future customer reactions based on past data and current analysis results, and provides warnings before problems occur.

[0719] "Means of personalizing sales activities" refers to a system that plans and executes sales strategies tailored to specific needs based on the characteristics and emotional analysis of individual customers.

[0720] Modes for carrying out the invention

[0721] This invention is a system that analyzes customer emotions in real time and suggests the optimal response when store staff wearing smart glasses interact with customers. The system includes several key components to effectively analyze customer-staff interactions and improve customer satisfaction.

[0722] The server incorporates mechanisms for collecting customer interaction information, which is captured in real time in text, audio, and visual formats. Audio information is handled using "Google Cloud Speech-to-Text," and the transcribed data is analyzed for sentiment using the "Google Natural Language API." Visual information is analyzed using the "Microsoft Azure Face API," which identifies emotional states from facial expressions. Based on these analysis results, the optimal course of action is communicated to staff members via smart glasses.

[0723] The smart glasses, acting as a terminal, utilize collected information to predict customer satisfaction and issue alerts if a decline in satisfaction is predicted. This allows the terminal to use a generated AI model to suggest specific actions to staff, for example, prompting them with messages such as, "There are signs that the customer is interested in product X. Please suggest how to explain the details of this product."

[0724] As a concrete example, when a customer picks up a specific product in a store, the server analyzes the customer's facial expressions and tone of voice to identify signs of interest or dissatisfaction in real time. Based on this, the terminal suggests practical responses to staff, such as, "There is a coupon available for this product, please inform the staff." In this way, users can provide the most appropriate service to customers and improve customer satisfaction.

[0725] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0726] Step 1:

[0727] The server collects customer interaction information received via smart glasses in real time. The input consists of audio and video from the smart glasses' microphone and camera, and the initial objective is to store this information as digital data.

[0728] Step 2:

[0729] The server sends the collected audio data to the Google Cloud Speech-to-Text service. This process converts the audio data into text format. The input is audio data, and the output is text data, which is used in the next analysis step.

[0730] Step 3:

[0731] The server sends text data to the Google Natural Language API for natural language processing. Here, customer emotions are analyzed, and emotional states such as positive and negative are extracted. The input is text data converted from speech, and the output is an emotion score or rating.

[0732] Step 4:

[0733] The server sends the collected video data as visual information to the "Microsoft Azure Face API," where it analyzes emotions using facial recognition technology. The input is video data, and the output is emotional information derived from facial expressions.

[0734] Step 5:

[0735] The server integrates the analysis results from steps 3 and 4 to perform an overall customer sentiment assessment. Based on this assessment, it generates prompts for the next customer interaction for the generative AI model. For example, a possible message might be, "The customer has shown interest in product X."

[0736] Step 6:

[0737] The smart glasses, which act as the terminal, display approach suggestions notified from the server. Based on this real-time information, staff can take appropriate action towards customers. Here, the input is the notification from the server, and the output is the action guidelines presented to the staff.

[0738] Step 7:

[0739] Based on this information, users adjust their communication with customers and aim to improve customer satisfaction. Ultimately, customer responses are collected again on the server and used for evaluation. The input is the interaction with the customer, and the output is the data point for the next interaction.

[0740] 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.

[0741] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0742] 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 robot 414.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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."

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] The following is further disclosed regarding the embodiments described above.

[0762] (Claim 1)

[0763] A means of collecting customer interaction data in real time,

[0764] A means of analyzing collected data to evaluate customer emotions and satisfaction,

[0765] A means to predict future customer satisfaction and issue alerts when a decline in satisfaction is predicted,

[0766] A means of generating personalized sales scenarios based on customer characteristics,

[0767] A system that includes this.

[0768] (Claim 2)

[0769] The system according to claim 1, which collects customer interaction data in the form of text data, audio data, and video data.

[0770] (Claim 3)

[0771] The system according to claim 1, which evaluates customer satisfaction using natural language processing and machine learning algorithms.

[0772] "Example 1"

[0773] (Claim 1)

[0774] A means of converting customer interaction data into text in real time,

[0775] A method for analyzing text-based data using a generation AI model to score customer emotions and levels of interest,

[0776] A means of sending an alert to the user's device when a decrease in interest is detected based on the scoring results,

[0777] A means of displaying personalized sales scenarios tailored to customer characteristics on a terminal,

[0778] A system that includes this.

[0779] (Claim 2)

[0780] The system according to claim 1, which collects customer interaction data in the form of text data, audio data, and visual data.

[0781] (Claim 3)

[0782] The system according to claim 1, which uses a generating AI model and machine learning algorithm to evaluate customer emotions and interests.

[0783] "Application Example 1"

[0784] (Claim 1)

[0785] A means of collecting customer interaction data in real time,

[0786] A means of analyzing collected data to evaluate customer emotions and satisfaction,

[0787] A means to predict future customer satisfaction and issue alerts when a decline in satisfaction is predicted,

[0788] A means of generating personalized sales scenarios based on customer characteristics,

[0789] A means of presenting proposals to customer service representatives in real time using a portable display device,

[0790] A system that includes this.

[0791] (Claim 2)

[0792] The system according to claim 1, which collects customer interaction data in the form of text data, audio data, and image data.

[0793] (Claim 3)

[0794] The system according to claim 1, which evaluates customer satisfaction using natural language processing and machine learning processing.

[0795] "Example 2 of combining an emotion engine"

[0796] (Claim 1)

[0797] A means of collecting communication data with users and customers in real time,

[0798] A means for analyzing collected data to identify and evaluate the emotions of users and customers,

[0799] A means of predicting future customer satisfaction and issuing warnings when a decline in satisfaction is predicted,

[0800] A means for generating suggestions to optimize the user's work based on past sentiment evaluation and prediction data,

[0801] A means of analyzing the facial expressions of users and customers and reflecting the results in an overall emotional evaluation,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, which collects communication data with users and customers in the form of text data, audio information, and video materials.

[0805] (Claim 3)

[0806] The system according to claim 1, which predicts customer satisfaction using natural language processing technology and machine learning methods.

[0807] "Application example 2 when combining with an emotional engine"

[0808] (Claim 1)

[0809] A means of collecting customer interaction information in real time,

[0810] A means of analyzing collected information to evaluate customer emotions and notifying staff in real time of suggested approaches,

[0811] A means of predicting future customer satisfaction and issuing an alert if a decline in satisfaction is predicted,

[0812] Means of personalizing sales activities based on customer characteristics,

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, which collects customer interaction information in the form of text information, audio information, and visual information.

[0816] (Claim 3)

[0817] The system according to claim 1, which evaluates customer satisfaction using a natural language processing device and a machine learning model. [Explanation of Symbols]

[0818] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting customer interaction data in real time, A means of analyzing collected data to evaluate customer emotions and satisfaction, A means to predict future customer satisfaction and issue alerts when a decline in satisfaction is predicted, A means of generating personalized sales scenarios based on customer characteristics, A system that includes this.

2. The system according to claim 1, which collects customer interaction data in the form of text data, audio data, and video data.

3. The system according to claim 1, which evaluates customer satisfaction using natural language processing and machine learning algorithms.

Images