system

Abstract

Provide a system. A means for acquiring a conversation between a crew member and a customer as a voice input; means for transmitting the acquired voice data to a server; A means for converting voice data into text data on a server; A means of analyzing customer interests and requests from text data, A means for selecting the optimal model based on the analysis results; A means for checking stock information for the selected model; A means for generating a candidate list of optimal models; The system includes means for displaying the candidate list on a terminal.

Description

[Technical Field]

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

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

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

[0004] In today's society, many customers find it difficult to choose the smartphone that best suits their needs. This is because the smartphone market is so diverse that it is extremely difficult to understand and compare the specific features of each model. Furthermore, it takes time and expertise for store staff to accurately understand customers' needs and recommend the appropriate model. This can result in lower customer satisfaction and missed sales opportunities. There is a need for a system that can solve these issues and quickly and accurately recommend the best smartphone for each customer. [Means for solving the problem]

[0005] The present invention provides a system including a processing step of acquiring a conversation between a crew member and a customer as voice input and transmitting the acquired voice data to a server. The server converts the received voice data into text data and analyzes the customer's preferences and requirements using natural language processing. The server selects an optimal model based on the analysis results and checks inventory information for the selected model. Finally, a candidate list of optimal models is generated and displayed on the terminal, thereby enabling a smartphone suitable for the customer to be quickly and accurately recommended. Specifically, the system includes means for capturing the conversation between the crew member and the customer, means for transmitting the voice data to a server, means for converting the voice data into text data, means for analyzing the text data, means for selecting a model based on the analysis results, means for checking inventory information, and means for generating and displaying the candidate list.

[0006] "Crew" refers to staff who deal with customers at stores and service centers.

[0007] "Customer" means the individual or entity receiving the Services.

[0008] "Audio input" refers to audio data acquired through a microphone.

[0009] "Server" refers to a central computer system that processes and stores data.

[0010] "Audio data" refers to conversations and audio information captured through a microphone.

[0011] "Text data" refers to information obtained by converting voice data into a string of characters.

[0012] "Natural language processing" refers to technology for analyzing and understanding human language.

[0013] "Analysis" refers to the process of processing data and extracting meaning and patterns.

[0014] "Hobbies" refer to activities that customers engage in out of personal interest.

[0015] "Requirements" refer to specific conditions or features that a customer desires.

[0016] "Models" refers to the various types of smartphones available on the market.

[0017] "Inventory Information" refers to data indicating the availability of a particular product.

[0018] "Candidate list" refers to a list of models selected based on analysis results and other criteria.

[0019] "Terminal" refers to the electronic device that handles conversations between crew members and customers. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] The present invention is a system that acquires voice input from conversations between crew members and customers and recommends the most suitable smartphone. This system performs processing in the following steps.

[0042] The terminal captures the conversation between the crew and the customer as voice input. A microphone installed on the terminal captures the conversation in real time and saves it as audio data. The captured audio data is sent to the server via an HTTPS request. This voice input capture step requires the terminal to have a high-performance microphone and a stable network connection in order to quickly record the conversation.

[0043] The server converts the received voice data into text data using voice recognition technology. By utilizing a voice recognition service such as Google® Cloud Speech-to-Text API, voice can be converted into text with high accuracy. During this process, the quality of the voice data is checked, noise is removed, and it is converted into an appropriate format.

[0044] The converted text data is analyzed using a natural language processing (NLP) model. The server uses the NLP engine to extract customer interests and requirements from the text data. This analysis uses machine learning models and deep learning techniques to identify important keywords and phrases within the text. For example, interests and requirements such as "camera performance," "long battery life," and "gaming use" are extracted.

[0045] Based on the analysis results, the server selects the most suitable smartphone candidate from the database. The server generates a query and retrieves the corresponding model from the database. This database contains the specifications and features of a wide variety of smartphones on the market, allowing the most suitable model to be extracted quickly.

[0046] The server checks the inventory information for the selected models. The server connects to the inventory management system via API to obtain the inventory status of each candidate model. This process checks whether the model is in stock, and if not, the inventory status of nearby stores.

[0047] The server generates a list of optimal models, including recommendations for each model. This list includes specific features of each smartphone and features that match the customer's requirements. For example, "iPhone® 14 Pro - High-performance camera and long battery life" or "Samsung Galaxy S21 - Excellent gaming performance."

[0048] The generated candidate list is sent to the device, which displays the results in a visually easy-to-understand format to the customer. The user, the crew, then recommends the optimal model to the customer based on the displayed list. The crew explains the features of smartphones that meet the customer's requirements and supports the customer in making the final purchase decision.

[0049] In this way, the system of the present invention receives voice input, analyzes the voice data, and recommends the most suitable smartphone for the customer. By accurately understanding customer needs and making prompt and accurate recommendations, customer satisfaction can be improved and sales opportunities can be maximized. For example, for a customer whose hobby is traveling and who places importance on camera performance, a smartphone equipped with a high-performance camera can be recommended, and by checking stock availability, the system can inform the customer whether it is available for immediate purchase. This system realizes efficient sales support and improved customer satisfaction.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The terminal captures the conversation between the crew and the customer as audio.

[0053] When the crew and customer start talking, the device's microphone captures the audio in real time, which is then recorded in a high-quality format (such as WAV or MP3).

[0054] Step 2:

[0055] The device sends the acquired audio data to the server via an HTTPS request.

[0056] The device stores the recorded voice data in temporary memory and uploads the voice file to the server's voice recognition processing endpoint using the HTTPS protocol.

[0057] Step 3:

[0058] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API or similar.

[0059] The server then sends the received audio file to the Google Cloud Speech-to-Text API, which converts the audio data into text data, which is then returned to the server for further analysis.

[0060] Step 4:

[0061] The server preprocesses the text data.

[0062] The server performs preprocessing on the received text data, such as removing spaces and line breaks and normalizing the text, to prepare for improved analysis accuracy.

[0063] Step 5:

[0064] The server analyzes the text data using a natural language processing (NLP) model.

[0065] The server inputs the text data into an NLP model to extract customer preferences and requirements, using machine learning algorithms to extract keywords such as "camera performance" and "battery life."

[0066] Step 6:

[0067] The server selects the optimal model from the database based on the analysis results.

[0068] The server queries the database using the extracted keywords to generate a list of smartphones that match the customer's requirements, such as "high-performance camera" or "large battery capacity."

[0069] Step 7:

[0070] Check the stock information for the model for which the server has been selected.

[0071] The server sends a request to the inventory management system's API to collect the current stock status of the selected model and stock information for each store.

[0072] Step 8:

[0073] The server generates a candidate list including the recommended points of each model.

[0074] The server lists the collected inventory information along with recommended points that explain the features of each model, and creates a final candidate list to provide to customers.

[0075] Step 9:

[0076] The server transmits the generated candidate list to the terminal.

[0077] The server sends the final candidate list to the terminal in a standard data format such as JSON.

[0078] Step 10:

[0079] The device displays the candidate list on the screen.

[0080] The terminal analyzes the received data and displays it in a visually easy-to-understand format for the crew and customer, allowing the crew to explain the features and inventory information of each model to the customer and make suggestions.

[0081] This allows the system of the present invention to efficiently propose smartphones that meet the needs of customers.

[0082] Example 1

[0083] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0084] With the current sales system, it is difficult to make proposals that reflect individual customer needs in real time, and there are issues such as not being able to fully improve customer satisfaction or maximize sales opportunities.In addition, checking inventory information takes time, and appropriate product recommendations are not made smoothly.

[0085] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0086] In this invention, the server includes means for acquiring a conversation between a crew member and a customer as voice input, means for transmitting the acquired voice data as a request, means for converting the voice data into text data on the server, means for analyzing the customer's interests and requests from the text data, means for selecting an optimal mobile communication terminal based on the analysis results, means for checking inventory information for the selected mobile communication terminal, means for generating a candidate list of optimal mobile communication terminals, and means for displaying the candidate list on the terminal. This enables proposals that quickly and accurately reflect customer needs, thereby maximizing sales opportunities and improving customer satisfaction.

[0087] "Crew" refers to staff members in charge of sales and support duties.

[0088] "Customer" means a consumer who intends to purchase or use a product or service.

[0089] "Voice input" refers to conversation content acquired as voice data.

[0090] "Data" refers to information handled within a computer system, and includes various formats such as audio, text, and images.

[0091] A "server" is a computer system that provides services to clients over a network.

[0092] "Text data" is character information converted using voice recognition technology.

[0093] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0094] A "mobile communication terminal" is a device capable of mobile communication, such as a smartphone or tablet.

[0095] "Inventory information" is data that indicates whether a product is currently available.

[0096] A "candidate list" is a list of multiple mobile communication terminals that are proposed based on the analysis results.

[0097] The present invention provides a system that acquires voice input from conversations between crew members and customers and proposes mobile communication devices that best suit the customer's needs. This system is realized by a combination of hardware and software. Specific embodiments are described below.

[0098] The device is equipped with a high-sensitivity microphone that captures the conversation between the crew and the customer as voice input in real time. The captured voice data is temporarily stored on the device and then sent to the server via an HTTPS request. During this process, the device must maintain a stable network connection.

[0099] The server converts the received voice data into text data using speech recognition technology. Specifically, it uses a speech recognition service such as Google Cloud Speech-to-Text API. The speech recognition technology converts the voice data into text with high accuracy. During this process, noise is removed and the data is converted into an appropriate format.

[0100] The converted text data is analyzed by a natural language processing (NLP) engine on the server. The NLP engine extracts customer preferences and requirements from the text data. Using a deep learning model, important keywords and phrases within the text are identified. For example, keywords such as "camera performance" and "long battery life" are extracted.

[0101] Based on the analysis results, the server selects the most suitable candidate mobile communication device from the database. The database contains the specifications and features of various mobile communication devices, and the server generates queries to access this database. As a result, devices that meet the customer's needs are quickly extracted.

[0102] The server checks the stock information of the selected devices by linking with the inventory management system, obtaining the stock status of each candidate model via API, and checking whether it is in stock and the stock status of nearby stores.

[0103] The server generates a list of suitable mobile devices, including recommendations for each device. This list includes specific features and functions that meet customer requirements, such as "models with high-performance cameras" or "models with long-life batteries."

[0104] The generated candidate list is sent to the terminal, where it is displayed in a visually easy-to-understand format. The crew, who is the user, proposes the most suitable mobile communication terminal to the customer based on the displayed list. The crew explains the features of the terminal that meet the customer's requirements and supports the final purchase decision.

[0105] For example, if a customer enjoys traveling and places importance on camera performance, the following prompt sentences could be input into the generative AI model:

[0106] "My client enjoys traveling and wants high-quality camera performance. Please suggest the best mobile device for him."

[0107] This system will enable efficient sales support and improved customer satisfaction.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] The terminal receives the conversation between the crew and the customer as voice input. Specifically, a high-sensitivity microphone installed on the terminal captures the conversation in real time. The input is the conversation itself, and the output is generated as voice data. This voice data is temporarily stored on the terminal.

[0111] Step 2:

[0112] The device sends the captured audio data to the server via an HTTPS request. The input is the audio data stored on the device, and the output is the audio data sent to the server. During this process, the device maintains a stable network connection.

[0113] Step 3:

[0114] The server converts the received voice data into text data using speech recognition technology. Specifically, the voice data is passed as input to the Google Cloud Speech-to-Text API, and text data is obtained as output. During this process, noise is removed and the data is converted into an appropriate format.

[0115] Step 4:

[0116] The server analyzes the converted text data using a natural language processing (NLP) engine. The converted text data is given as input, and the customer's interests and requirements are extracted as output. Specifically, machine learning and deep learning models are used to identify important keywords within the text.

[0117] Step 5:

[0118] The server selects the optimal mobile communication device based on the analysis results. The analysis results are input, and a list of candidate mobile communication devices is generated as output. The server accesses the specification information of various devices in the database, generates a query, and extracts the optimal device.

[0119] Step 6:

[0120] The server checks the inventory information for the selected mobile communication devices. It receives a list of candidate mobile communication devices as input and generates a list with the inventory status as output. During this process, the server connects with the inventory management system via API to obtain the inventory status of each candidate model.

[0121] Step 7:

[0122] The server generates a list of optimal mobile communication devices, including the recommended features of each device. The input is the list of devices after checking their stock availability, and the output is a final list to be proposed to the customer. The list includes the features of each device and functions that match the customer's requirements.

[0123] Step 8:

[0124] The terminal visually displays the generated candidate list. The user, or crew member, uses this list to propose the optimal mobile communication terminal to the customer. The final candidate list is the input, and the visually displayed list is the output. The crew member provides support for the purchase, explaining in detail the features of the terminal that meets the customer's requirements.

[0125] (Application example 1)

[0126] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0127] In recent years, it has become increasingly important to quickly and accurately recommend products that customers need in physical stores. However, manually having a salesperson listen to a customer's requests and suggest the best products based on them takes time and can lead to misunderstandings. In particular, when using new interfaces such as smart glasses, an efficient system is required to display products that meet customer needs in real time. The challenge is to improve this situation and provide a system that can quickly suggest products that meet customer requirements.

[0128] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0129] In this invention, the server includes means for acquiring voice input, means for transmitting the voice data via a communication network, means for converting the voice data into text data, means for using natural language processing to analyze the customer's preferences and requests, means for selecting the most suitable device based on the analysis results, means for linking with an inventory management system to check inventory information, means for generating a candidate list of the most suitable devices, means for using a generative AI model, and means for generating prompt sentences to display the candidate list in a visually easy-to-understand format. This makes it possible to analyze customer needs in real time and quickly suggest the most suitable products.

[0130] A "crew" is a store clerk who handles customer service in a physical store.

[0131] A "customer" is someone who visits a store and intends to purchase a product.

[0132] "Audio input" refers to audio data captured using a device such as a microphone.

[0133] A "server" is a computer system that processes and analyzes audio data.

[0134] A "communications network" is an infrastructure for transmitting and receiving data.

[0135] "Audio data" refers to an acoustic signal obtained as an audio input.

[0136] "Text data" refers to character string information obtained by converting voice data.

[0137] "Natural language processing" refers to the techniques and methodologies for analyzing text data and understanding its content.

[0138] "Analysis" refers to analyzing data to extract meaning and information.

[0139] "Devices" refer to products that the system proposes to customers.

[0140] An "inventory management system" is an information system for managing product inventory status.

[0141] An "information display device" is a device that visually displays information, such as smart glasses or a display.

[0142] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and generate optimal results.

[0143] A "prompt" is an explanation or recommendation generated by the system.

[0144] This invention is a system that analyzes conversations between crew members and customers in real time and suggests optimal products to customers. This system uses high-performance smart glasses to enable crew members to suggest optimal smartphones while serving customers.

[0145] The device uses a microphone built into the smart glasses to capture conversations between the crew and the customer in real time, and the captured audio data is transmitted to a server via a stable communication network to ensure appropriate quality at all times.

[0146] The server receives the captured voice data and converts it into text using speech recognition technology. To achieve this, it uses a speech recognition service such as Google Cloud Speech-to-Text API. The server then analyzes the text data using a natural language processing (NLP) model to extract the customer's interests and requirements. This analysis uses a generative AI model to identify key keywords and phrases based on the customer's requirements.

[0147] Based on the extracted information, the server selects the most suitable candidate device (e.g., a smartphone) from the database. At this time, the server connects to the inventory management system via API to check the inventory information of each candidate device. This allows the server to check whether the device is in stock, and if not, to check the inventory status of nearby stores.

[0148] A list of selected devices is generated based on the features of each device and the customer's requirements. This includes the process of generating prompts using a generative AI model. For example, if a customer requests a model with a high-performance camera, the model generates a prompt such as, "This model is ideal for your needs. It has a high-performance camera and excellent battery life."

[0149] This candidate list is then displayed on the smart glasses display, allowing the crew to suggest suitable smartphones to the customer in real time.

[0150] Customer: "I want a smartphone with a good camera and long battery life."

[0151] The system captures and analyzes these requirements to extract keywords such as "camera performance" and "battery life." The server queries the database and inventory system to list "models with excellent camera performance and battery life," and displays the following prompt on the smart glasses:

[0152] "Model A - High-performance camera and excellent battery life" "Model B - Outstanding camera performance and battery life"

[0153] The prompt in this example has the form:

[0154] Customer: "I want a smartphone with a good camera and long battery life."

[0155] System: "Model A - High-performance camera and excellent battery life"

[0156] System: "Model B - Outstanding camera performance and battery life"

[0157] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0158] Step 1:

[0159] The terminal (smart glasses) receives voice input from a microphone during the conversation between the crew and the customer. The input is the actual conversational voice, and the output is captured as voice data. This voice data includes the customer's request.

[0160] Step 2:

[0161] The terminal transmits the acquired voice data to the server via a stable communication network. The input is the collected voice data, and the output is the voice data sent to the server. This procedure prepares the voice data for processing by the server.

[0162] Step 3:

[0163] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API. The input is voice data, and the output is the converted text data. During this process, the voice data is obtained as a string, which can be analyzed later.

[0164] Step 4:

[0165] The server analyzes the text data using a natural language processing (NLP) model. The input is text data, and the output is information extracted from the customer's interests and requirements. This analysis utilizes a generative AI model to identify important keywords and phrases to fulfill the customer's requirements.

[0166] Step 5:

[0167] The server selects the optimal equipment candidates from the database based on the analysis results. The input is information extracted from the customer's requirements, and the output is a list of optimal equipment candidates. The server generates a query and executes the selection process against the database.

[0168] Step 6:

[0169] The server communicates with the inventory management system via an API to check the inventory information for the selected devices. The input is a list of candidate devices, and the output is a list of devices whose inventory has been confirmed. This process ensures that the inventory status is up-to-date.

[0170] Step 7:

[0171] The server generates a list of optimal device candidates and uses an AI model to generate prompts to present the features of each device in a visually easy-to-understand format. The input is a list of devices whose inventory has been confirmed, and the output is a final list including the prompts to be displayed.

[0172] Step 8:

[0173] The terminal displays the generated candidate list on the smart glasses display and presents it to the crew. The input is the final list including the prompt text to be displayed, and the output is the visually displayed information. Based on this information, the crew can recommend the most suitable equipment for the customer.

[0174] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0175] This invention combines an emotion engine with a system that acquires voice input from conversations between crew members and customers and recommends the most suitable smartphone. This system performs processing in the following steps.

[0176] The device receives voice input from the conversation between the crew and the customer. When the crew and the customer start talking, the device's microphone captures the voice in real time and saves it as audio data. This audio is recorded in a high-quality format (WAV, MP3, etc.).

[0177] The device sends the captured audio data to the server via an HTTPS request. The device stores the recorded audio data in temporary memory and uploads the audio file to the server's speech recognition processing endpoint using the HTTPS protocol.

[0178] The server converts the received audio data into text data using the Google Cloud Speech-to-Text API, etc. The server then sends the received audio file to the Google Cloud Speech-to-Text API, which converts the audio data into text data. The converted text is returned to the server and passed on to the next analysis step.

[0179] The server preprocesses the text data. The server performs preprocessing on the received text data, such as removing spaces and line breaks and normalizing the text, to prepare it for analysis with higher accuracy.

[0180] The server analyzes the text data using a natural language processing (NLP) model. The server then inputs the text data into the NLP model to extract customer preferences and requirements. During this process, machine learning algorithms are used to extract keywords such as "camera performance" and "battery life."

[0181] The server selects the optimal model from the database based on the analysis results. The server queries the database using the extracted keywords and generates a list of smartphones that meet the customer's requirements. For example, models that meet criteria such as "high-performance camera" and "large battery capacity" are listed.

[0182] The server checks the stock information for the selected model. The server sends a request to the inventory management system's API to collect the current stock status of the selected model and stock information for each store.

[0183] The server generates a candidate list including the recommended points for each model. The server lists the recommended points that explain the features of each model together with the collected inventory information, and forms the final candidate list to be provided to customers.

[0184] The generated candidate list is sent to the device, which displays the results in a visually easy-to-understand format to the customer. The user, the crew, then recommends the optimal model to the customer based on the displayed list. The crew explains the features of smartphones that meet the customer's requirements and supports the customer in making the final purchase decision.

[0185] The system of the present invention also incorporates an emotion engine, which analyzes the user's emotions. The server uses the emotion engine when analyzing the voice data to identify the user's emotional state. This emotion analysis makes it possible to grasp emotional situations, such as whether the customer is interested or anxious. Furthermore, the system adjusts the candidate list of optimal models based on the user's emotions. For example, if a customer not only values ​​camera performance but also shows a strong interest in it, models with particularly excellent camera performance will be placed at the top of the list.

[0186] As a specific example, for a customer who enjoys traveling and prioritizes camera performance, the device captures the conversation and the server converts the speech into text. Keywords such as "travel" and "camera performance" are extracted using an NLP model, and an emotion engine analyzes the customer's "excited voice." The server then selects a model with high camera performance and checks whether it is in stock. Finally, a list of recommended models, such as "iPhone 14 Pro - High-Performance Camera and Night Mode," can be generated and displayed on the device.

[0187] In this way, the system of the present invention utilizes voice input and emotion analysis to efficiently recommend smartphones that meet customer needs, thereby achieving higher customer satisfaction.

[0188] The processing flow will be explained below.

[0189] Step 1:

[0190] The terminal captures the conversation between the crew and the customer as audio.

[0191] A microphone installed in the terminal captures the conversation between the crew and the customer in real time, recording audio data that is saved in high-quality formats such as WAV and MP3.

[0192] Step 2:

[0193] The device sends the acquired audio data to the server via an HTTPS request.

[0194] The device uploads the recorded audio data to the server via the HTTPS protocol, where it is encrypted and securely transmitted to the server.

[0195] Step 3:

[0196] The server converts the received voice data into text data using voice recognition technology.

[0197] The server uses a speech recognition engine such as Google Cloud Speech-to-Text API to convert the audio data into text data, which is then passed on to the next step.

[0198] Step 4:

[0199] The server preprocesses the text data.

[0200] As a preprocessing step, the server removes unnecessary spaces and line breaks and normalizes the text, making the subsequent analysis process smoother.

[0201] Step 5:

[0202] The server analyzes the text data using a natural language processing (NLP) model.

[0203] The server uses natural language processing technology to extract keywords from the text data, such as "camera performance," "battery life," and "gaming use," which are related to the customer's interests and requirements.

[0204] Step 6:

[0205] The server uses an emotion engine to analyze the customer's emotions based on the analysis results.

[0206] The server uses an emotion engine to identify the customer's emotional state from the voice data and extracted keywords. For example, emotions such as "excitement" or "anxiety" can be detected from the customer's speaking style and tone.

[0207] Step 7:

[0208] The server selects the most suitable model from the database based on the analysis results and emotional information.

[0209] The server queries the database based on the keywords and the customer's emotional state, selecting smartphones that meet certain criteria, such as a high-performance camera and a long battery life.

[0210] Step 8:

[0211] Check the stock information for the model for which the server has been selected.

[0212] The server works in conjunction with the inventory management system to obtain the stock status of the selected model at the store and nearby stores via API.

[0213] Step 9:

[0214] The server generates a candidate list including recommended points based on the customer's sentiment.

[0215] The server generates a list of candidates, describing each model's recommended features and specific characteristics based on sentiment analysis, such as "This smartphone features a high-performance camera, making it ideal for your travel photos."

[0216] Step 10:

[0217] The server transmits the generated candidate list to the terminal.

[0218] The server sends the final candidate list to the terminal in JSON format or similar, so that it can be displayed on the terminal.

[0219] Step 11:

[0220] The device displays the candidate list on the screen.

[0221] The terminal analyzes the received data and displays it in a visually easy-to-understand format for the crew and customer. The crew can then explain the features of the model that best suits the customer based on the displayed list.

[0222] In this way, the system of the present invention analyzes the customer's voice and emotions, and quickly and accurately recommends the most suitable smartphone. It also enables support that is tailored to the customer's emotional state.

[0223] Example 2

[0224] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0225] Conventional smartphone recommendation systems have difficulty accurately understanding customer needs and recommending the most suitable model. They also lack the ability to take into account the customer's emotional state, resulting in lower customer satisfaction. Furthermore, there was a risk of running out of stock due to insufficient means for checking inventory information in real time.

[0226] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0227] In this invention, the server includes a means for converting voice data into text data, a means for preprocessing the text data, a means for analyzing the customer's interests and requests, a means for using an emotion engine for analyzing the customer's emotional state, and a means for adjusting a list of optimal model candidates based on the customer's emotional state. This makes it possible to accurately understand the customer's emotions and requests and to propose the optimal smartphone based on them.

[0228] "Voice input" refers to capturing conversations between crew members and customers in real time using a microphone and obtaining them as voice data.

[0229] "Voice Data" means audio information captured and stored in digital form during conversations between Crew Members and Customers.

[0230] The "server" is a central processing unit that receives, converts, analyzes, and selects the most suitable smartphone for voice data.

[0231] "Text data" is voice data converted into character information, and is data to be analyzed.

[0232] "Preprocessing" refers to data processing carried out to remove unnecessary spaces and line breaks from text data and improve the accuracy of analysis.

[0233] "Natural language processing" is a technology used to analyze customer preferences and requirements from text data, and is a process that includes machine learning algorithms.

[0234] An "emotion engine" is a technology for analyzing a customer's emotional state from voice data, and is an engine that identifies and analyzes emotions.

[0235] A "candidate list" is a list of optimal smartphones generated based on the analyzed customer's tastes, requirements, and emotional state.

[0236] "Stock information" refers to the current stock status of the selected model and stock information for each store.

[0237] A "terminal" is a device that captures conversations between crew members and customers and displays a list of candidates.

[0238] This system proposes the optimal smartphone for a customer by acquiring voice input from a conversation between a crew member and a customer, analyzing and converting the voice data. This system is composed of multiple components including voice input, voice data transmission, text data conversion and preprocessing, analysis of the customer's hobbies and requests, analysis of the customer's emotional state, selection of the optimal model, confirmation of inventory information, and generation and display of a candidate list.

[0239] First, the terminal receives the conversation between the crew and the customer as voice input. The terminal's microphone captures the voice data in real time and saves it digitally in WAV or MP3 format. This voice data is stored in the terminal's temporary memory.

[0240] The device then sends the captured audio data to the server via an HTTPS request, using a secure communications protocol to upload the audio file to the server's speech recognition processing endpoint.

[0241] The server converts the received voice data into text data using speech recognition technology such as the Google Cloud Speech-to-Text API, which is then returned to the server for further analysis.

[0242] The server preprocesses the text data, removing spaces and line breaks, normalizing the text, and so on, to improve the quality of the data.

[0243] The server then uses a natural language processing (NLP) model to analyze customer preferences and requirements from the preprocessed text data. Specifically, machine learning algorithms are used to extract keywords such as "camera performance" and "battery life."

[0244] In addition, the server uses an emotion engine to analyze the customer's emotional state from the voice data. For example, if the customer speaks with an excited voice, it will interpret this as positive interest and adjust the list accordingly.

[0245] The server selects the most suitable smartphone from a database based on the analyzed hobbies, needs, and emotional state, and then connects the selected model to an inventory management system to check the inventory information of each store.

[0246] Finally, the server generates a list of the best models, including each model's recommended features, such as specific suggestions like "a smartphone with a high-performance camera and night mode."

[0247] The generated candidate list is sent to the terminal, which displays the results in a visually easy-to-understand format. Based on this display, the crew, who are the users, can propose the most suitable model to the customer.

[0248] For example, if a customer enjoys traveling and prioritizes camera performance, the device captures the conversation and the server converts the speech into text. Keywords like "travel" and "camera performance" are extracted using an NLP model, and an emotion engine analyzes the customer's excited voice to select a model with high camera performance and check whether it is in stock. Finally, a list of recommended models, such as "iPhone 14 Pro - High-Performance Camera and Night Mode," is generated and displayed on the device.

[0249] By utilizing a generative AI model, these steps can be executed efficiently and accurately. An example of a useful prompt would be, "Design a system that analyzes voice data and recommends smartphones based on customer needs."

[0250] In this way, by combining voice input and emotion analysis, the system of the present invention can recommend the smartphone that best suits the customer's needs and increase customer satisfaction.

[0251] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0252] Step 1:

[0253] The terminal receives the conversation between the crew and the customer as audio input. Specifically, it captures the audio in real time through the terminal's microphone and digitally stores it in high-quality WAV or MP3 format. The input is an audio signal, and the output is a digital audio file.

[0254] Step 2:

[0255] The device stores the captured voice data in temporary memory and sends it to the server via an HTTPS request. Specifically, the audio file is uploaded to the server's voice recognition processing endpoint using the HTTPS protocol. The input is the digital audio file, and the output is the upload status to the server via the HTTPS request.

[0256] Step 3:

[0257] The server converts the received audio data into text data using the Google Cloud Speech-to-Text API. Specifically, the audio file is sent to the API, and a machine learning algorithm converts the audio into text. The input is an audio file, and the output is text data.

[0258] Step 4:

[0259] The server preprocesses the text data it receives. Specifically, it removes spaces and line breaks, normalizes the text, etc. The input is unprocessed text data, and the output is preprocessed text data.

[0260] Step 5:

[0261] The server analyzes the preprocessed text data using a natural language processing (NLP) model. Specifically, it uses a machine learning algorithm to extract keywords such as "camera performance" and "battery life." The input is the preprocessed text data, and the output is the extracted keywords.

[0262] Step 6:

[0263] The server selects the optimal model from the database based on the analysis results. Specifically, it queries the database using the extracted keywords and generates a list of related smartphones. The input is the extracted keywords, and the output is a list of candidate smartphones.

[0264] Step 7:

[0265] The server checks the stock information of the selected model. Specifically, it sends a request to the inventory management system's API to collect the current stock status. The input is a list of candidate smartphones, and the output is stock information.

[0266] Step 8:

[0267] The server uses an emotion engine to analyze the customer's emotional state from the voice data. Specifically, the voice data is input into the emotion engine, and the emotion engine analyzes the customer's emotions, such as excitement, interest, and anxiety. The input is the voice data, and the output is the emotion analysis result.

[0268] Step 9:

[0269] The server adjusts the candidate list of optimal models based on the customer's emotional state. Specifically, based on the results of emotion analysis, models that the customer is particularly interested in are placed at the top of the list. The input is the emotion analysis results and inventory information, and the output is the adjusted candidate list.

[0270] Step 10:

[0271] The server generates a candidate list of optimal models, including the recommended points for each model. Specifically, it lists the recommended points that explain the features of each model along with the collected inventory information. The input is the adjusted candidate list and inventory information, and the output is the final candidate list.

[0272] Step 11:

[0273] The terminal displays the generated candidate list in a visually easy-to-understand format. Specifically, it provides an interface that allows the crew (user) to refer to the list and displays it to the customer. The input is the final candidate list, and the output is display information that can be visually confirmed by the crew and customer.

[0274] (Application example 2)

[0275] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0276] While conventional systems can suggest the appropriate smartphone based on customer needs, they are unable to take customer emotions into consideration when making suggestions, which means they are unable to sufficiently improve customer satisfaction. Furthermore, there is a lack of an effective means for analyzing conversations in real time and quickly providing a list of optimal models.

[0277] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0278] In this invention, the server includes means for acquiring a conversation between a crew member and a customer as voice input, means for transmitting the acquired voice data to the server, means for converting the voice data into text data on the server, means for analyzing the customer's preferences and requests from the text data, means for selecting an optimal model based on the analysis results, means for checking inventory information for the selected model, means for generating a candidate list of optimal models, means for displaying the candidate list on a terminal, means for analyzing the customer's emotions and adjusting the candidate list of optimal models based on the emotions, and means for analyzing the conversation in real time and visually presenting the results. This makes it possible to recommend the optimal smartphone in real time while taking the customer's emotions into consideration, thereby increasing customer satisfaction.

[0279] "Means for acquiring conversations between staff and customers as audio input" refers to a device or method for recording conversations between staff and customers using an audio input device such as a microphone and acquiring the audio data.

[0280] The "means for transmitting acquired voice data to a server" refers to a communication means or protocol for transferring voice data acquired by a voice input device to a remote server via the Internet or a local network.

[0281] "Means for converting voice data into text data on a server" refers to the process and device that converts transmitted voice data into text format using voice recognition software or an API.

[0282] "Means for analyzing customer interests and needs from text data" refers to algorithms and software that analyze text data using natural language processing (NLP) to identify customer interests and needs.

[0283] The "means for selecting the optimal model based on the analysis results" refers to a database query and selection algorithm for selecting the optimal smartphone model based on customer requirements extracted by text data analysis.

[0284] The "means for checking stock information for the selected model" refers to an API or protocol that works with an inventory management system to check the stock status of the selected smartphone model.

[0285] The "means for generating a candidate list of optimal models" is software for generating a candidate list including the features and recommended points of smartphone models that have been selected and stock confirmed.

[0286] The "means for displaying the candidate list on the terminal" refers to a display screen or application for visually presenting the generated smartphone model candidate list to the user.

[0287] "Means for analyzing customer sentiment and adjusting a candidate list of optimal models based on the sentiment" refers to algorithms and software that analyze sentiment from customer voice data and dynamically sort or filter the candidate list according to the sentiment.

[0288] "Means for analyzing conversations in real time and providing the results visually" refers to technology and applications for analyzing conversations between crew members and customers in real time and displaying the results on a screen in a timely manner.

[0289] This invention is a system that acquires voice input from conversations between crew members and customers, combines it with emotion analysis, and proposes the most suitable smartphone. This system is mainly built by combining a voice input device, a server, a terminal, and various APIs.

[0290] First, the conversation between the crew and the customer is captured using a voice input device, i.e., a smartphone microphone. High-quality audio data (e.g., WAV or MP3 format) is captured in real time and sent to a server via HTTPS protocol. This process is performed using a data communication method.

[0291] The server uses speech recognition software such as the Google Cloud Speech-to-Text API to convert the received voice data into text data. This converted text data is preprocessed on the server to remove spaces and line breaks and normalize the sentences. The preprocessed text data is then input into a natural language processing (NLP) model to extract customer preferences and requirements (e.g., "camera performance," "battery life," etc.).

[0292] Furthermore, the server uses an emotion recognition engine to analyze the customer's emotional state from the text data. The text data is used to identify emotional situations such as "the customer is interested" or "the customer is anxious." Based on the results of this emotion analysis, the candidate list of optimal models is adjusted.

[0293] The server then executes a database query based on the extracted keywords and the results of sentiment analysis to generate a list of smartphones that meet the customer's needs. After generating the list, it connects with an inventory management system to check stock information and confirm the availability of the most suitable models. Finally, a list of recommended models that meet criteria such as "high-performance camera" or "high battery capacity" is generated and displayed on the device.

[0294] The device presents the user with a list of smartphones in a visually easy-to-understand format. The crew then uses the list to explain the features of suitable smartphones to the customer and helps them make a purchasing decision. The crew can also dynamically update the recommended smartphone models based on the customer's real-time conversation analysis and emotional feedback.

[0295] As a specific example, for a customer who enjoys traveling and places importance on camera performance, the system will capture the customer's conversation through the smartphone's microphone, analyze their emotions, and then recommend the most suitable smartphone, such as the ``iPhone 14 Pro - High-Performance Camera and Night Mode.''

[0296] Here are some examples of prompts to input to the generative AI model:

[0297] "For a customer who enjoys traveling and prioritizes camera performance, capture their conversation through the smartphone's microphone, analyze their emotions, and then recommend the best smartphone for them."

[0298] By implementing this system, it will be possible to take into account customer emotions and make optimal smartphone recommendations in real time, thereby improving customer satisfaction.

[0299] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0300] Step 1:

[0301] Capture conversations between crew and customers as voice input.

[0302] (Specific actions)

[0303] The device (smartphone) uses a microphone to record conversations in real time.

[0304] (input)

[0305] Audio data

[0306] (output)

[0307] Recorded audio files (high quality formats, e.g. WAV, MP3)

[0308] Step 2:

[0309] The acquired voice data is sent to the server.

[0310] (Specific actions)

[0311] The device stores the audio file in temporary memory and uploads it to the server's speech recognition processing endpoint using the HTTPS protocol.

[0312] (input)

[0313] Audio files

[0314] (output)

[0315] Uploading audio files to the server

[0316] Step 3:

[0317] The voice data is converted into text data on the server.

[0318] (Specific actions)

[0319] The server sends the received audio file to the Google Cloud Speech-to-Text API, which automatically converts it into text data.

[0320] (input)

[0321] Audio files

[0322] (output)

[0323] Converted text data

[0324] Step 4:

[0325] Preprocess text data.

[0326] (Specific actions)

[0327] The server performs preprocessing on the text data, such as removing spaces and line breaks and normalizing the text.

[0328] (input)

[0329] Converted text data

[0330] (output)

[0331] Preprocessed text data

[0332] Step 5:

[0333] Analyze customer interests and requests from text data.

[0334] (Specific actions)

[0335] The server inputs the preprocessed text data into an NLP model, which uses machine learning algorithms to extract keywords (e.g., "camera performance," "battery life," etc.).

[0336] (input)

[0337] Preprocessed text data

[0338] (output)

[0339] Extracted keywords

[0340] Step 6:

[0341] Analyze customer sentiment.

[0342] (Specific actions)

[0343] The server inputs the converted text data into an emotion analysis engine, which identifies the customer's emotional state based on the voice data.

[0344] (input)

[0345] Preprocessed text data

[0346] (output)

[0347] Customer sentiment data

[0348] Step 7:

[0349] The optimal model is selected based on the analysis results.

[0350] (Specific actions)

[0351] The server runs a database query based on the extracted keywords and emotion data to generate a list of smartphones that meet the user's needs.

[0352] (input)

[0353] Extracted keywords and sentiment data

[0354] (output)

[0355] A list of the best models

[0356] Step 8:

[0357] Check the stock information for the selected model.

[0358] (Specific actions)

[0359] The server sends a request to the inventory management system API to check the stock status of the selected model.

[0360] (input)

[0361] A list of the best models

[0362] (output)

[0363] Suggestion list with stock information

[0364] Step 9:

[0365] Generate a list of optimal models.

[0366] (Specific actions)

[0367] The server creates a final candidate list that includes inventory and feature information.

[0368] (input)

[0369] Suggestion list with stock information

[0370] (output)

[0371] Final candidate list

[0372] Step 10:

[0373] Display the candidate list on the terminal.

[0374] (Specific actions)

[0375] The device visually displays the generated candidate list, allowing the crew to suggest the best smartphone for the customer.

[0376] (input)

[0377] Final candidate list

[0378] (output)

[0379] Candidate list displayed on device

[0380] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0381] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0382] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0383] [Second embodiment]

[0384] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0385] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0386] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0387] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0388] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0389] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0390] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0391] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0392] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0393] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0394] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0395] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0396] The present invention is a system that acquires voice input from conversations between crew members and customers and recommends the most suitable smartphone. This system performs processing in the following steps.

[0397] The terminal captures the conversation between the crew and the customer as voice input. A microphone installed on the terminal captures the conversation in real time and saves it as audio data. The captured audio data is sent to the server via an HTTPS request. This voice input capture step requires the terminal to have a high-performance microphone and a stable network connection in order to quickly record the conversation.

[0398] The server converts the received voice data into text data using speech recognition technology. By utilizing speech recognition services such as the Google Cloud Speech-to-Text API, speech can be converted into text with high accuracy. During this process, the quality of the voice data is checked, noise is removed, and it is converted into an appropriate format.

[0399] The converted text data is analyzed using a natural language processing (NLP) model. The server uses the NLP engine to extract customer interests and requirements from the text data. This analysis uses machine learning models and deep learning techniques to identify important keywords and phrases within the text. For example, interests and requirements such as "camera performance," "long battery life," and "gaming use" are extracted.

[0400] Based on the analysis results, the server selects the most suitable smartphone candidate from the database. The server generates a query and retrieves the corresponding model from the database. This database contains the specifications and features of a wide variety of smartphones on the market, allowing the most suitable model to be extracted quickly.

[0401] The server checks the inventory information for the selected models. The server connects to the inventory management system via API to obtain the inventory status of each candidate model. This process checks whether the model is in stock, and if not, the inventory status of nearby stores.

[0402] The server generates a list of optimal models, including recommendations for each model. This list includes specific features of each smartphone and features that match the customer's requirements. For example, "iPhone 14 Pro - high-performance camera and long battery life" or "Samsung Galaxy S21 - excellent gaming performance."

[0403] The generated candidate list is sent to the device, which displays the results in a visually easy-to-understand format to the customer. The user, the crew, then recommends the optimal model to the customer based on the displayed list. The crew explains the features of smartphones that meet the customer's requirements and supports the customer in making the final purchase decision.

[0404] In this way, the system of the present invention receives voice input, analyzes the voice data, and recommends the most suitable smartphone for the customer. By accurately understanding customer needs and making prompt and accurate recommendations, customer satisfaction can be improved and sales opportunities can be maximized. For example, for a customer whose hobby is traveling and who places importance on camera performance, a smartphone equipped with a high-performance camera can be recommended, and by checking stock availability, the system can inform the customer whether it is available for immediate purchase. This system realizes efficient sales support and improved customer satisfaction.

[0405] The processing flow will be explained below.

[0406] Step 1:

[0407] The terminal captures the conversation between the crew and the customer as audio.

[0408] When the crew and customer start talking, the device's microphone captures the audio in real time, which is then recorded in a high-quality format (such as WAV or MP3).

[0409] Step 2:

[0410] The device sends the acquired audio data to the server via an HTTPS request.

[0411] The device stores the recorded voice data in temporary memory and uploads the voice file to the server's voice recognition processing endpoint using the HTTPS protocol.

[0412] Step 3:

[0413] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API or similar.

[0414] The server then sends the received audio file to the Google Cloud Speech-to-Text API, which converts the audio data into text data, which is then returned to the server for further analysis.

[0415] Step 4:

[0416] The server preprocesses the text data.

[0417] The server performs preprocessing on the received text data, such as removing spaces and line breaks and normalizing the text, to prepare for improved analysis accuracy.

[0418] Step 5:

[0419] The server analyzes the text data using a natural language processing (NLP) model.

[0420] The server inputs the text data into an NLP model to extract customer preferences and requirements, using machine learning algorithms to extract keywords such as "camera performance" and "battery life."

[0421] Step 6:

[0422] The server selects the optimal model from the database based on the analysis results.

[0423] The server queries the database using the extracted keywords to generate a list of smartphones that match the customer's requirements, such as "high-performance camera" or "large battery capacity."

[0424] Step 7:

[0425] Check the stock information for the model for which the server has been selected.

[0426] The server sends a request to the inventory management system's API to collect the current stock status of the selected model and stock information for each store.

[0427] Step 8:

[0428] The server generates a candidate list including the recommended points of each model.

[0429] The server lists the collected inventory information along with recommended points that explain the features of each model, and creates a final candidate list to provide to customers.

[0430] Step 9:

[0431] The server transmits the generated candidate list to the terminal.

[0432] The server sends the final candidate list to the terminal in a standard data format such as JSON.

[0433] Step 10:

[0434] The device displays the candidate list on the screen.

[0435] The terminal analyzes the received data and displays it in a visually easy-to-understand format for the crew and customer, allowing the crew to explain the features and inventory information of each model to the customer and make suggestions.

[0436] This allows the system of the present invention to efficiently propose smartphones that meet the needs of customers.

[0437] Example 1

[0438] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0439] With the current sales system, it is difficult to make proposals that reflect individual customer needs in real time, and there are issues such as not being able to fully improve customer satisfaction or maximize sales opportunities.In addition, checking inventory information takes time, and appropriate product recommendations are not made smoothly.

[0440] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0441] In this invention, the server includes means for acquiring a conversation between a crew member and a customer as voice input, means for transmitting the acquired voice data as a request, means for converting the voice data into text data on the server, means for analyzing the customer's interests and requests from the text data, means for selecting an optimal mobile communication terminal based on the analysis results, means for checking inventory information for the selected mobile communication terminal, means for generating a candidate list of optimal mobile communication terminals, and means for displaying the candidate list on the terminal. This enables proposals that quickly and accurately reflect customer needs, thereby maximizing sales opportunities and improving customer satisfaction.

[0442] "Crew" refers to staff members in charge of sales and support duties.

[0443] "Customer" means a consumer who intends to purchase or use a product or service.

[0444] "Voice input" refers to conversation content acquired as voice data.

[0445] "Data" refers to information handled within a computer system, and includes various formats such as audio, text, and images.

[0446] A "server" is a computer system that provides services to clients over a network.

[0447] "Text data" is character information converted using voice recognition technology.

[0448] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0449] A "mobile communication terminal" is a device capable of mobile communication, such as a smartphone or tablet.

[0450] "Inventory information" is data that indicates whether a product is currently available.

[0451] A "candidate list" is a list of multiple mobile communication terminals that are proposed based on the analysis results.

[0452] The present invention provides a system that acquires voice input from conversations between crew members and customers and proposes mobile communication devices that best suit the customer's needs. This system is realized by a combination of hardware and software. Specific embodiments are described below.

[0453] The device is equipped with a high-sensitivity microphone that captures the conversation between the crew and the customer as voice input in real time. The captured voice data is temporarily stored on the device and then sent to the server via an HTTPS request. During this process, the device must maintain a stable network connection.

[0454] The server converts the received voice data into text data using speech recognition technology. Specifically, it uses a speech recognition service such as Google Cloud Speech-to-Text API. The speech recognition technology converts the voice data into text with high accuracy. During this process, noise is removed and the data is converted into an appropriate format.

[0455] The converted text data is analyzed by a natural language processing (NLP) engine on the server. The NLP engine extracts customer preferences and requirements from the text data. Using a deep learning model, important keywords and phrases within the text are identified. For example, keywords such as "camera performance" and "long battery life" are extracted.

[0456] Based on the analysis results, the server selects the most suitable candidate mobile communication device from the database. The database contains the specifications and features of various mobile communication devices, and the server generates queries to access this database. As a result, devices that meet the customer's needs are quickly extracted.

[0457] The server checks the stock information of the selected devices by linking with the inventory management system, obtaining the stock status of each candidate model via API, and checking whether it is in stock and the stock status of nearby stores.

[0458] The server generates a list of suitable mobile devices, including recommendations for each device. This list includes specific features and functions that meet customer requirements, such as "models with high-performance cameras" or "models with long-life batteries."

[0459] The generated candidate list is sent to the terminal, where it is displayed in a visually easy-to-understand format. The crew, who is the user, proposes the most suitable mobile communication terminal to the customer based on the displayed list. The crew explains the features of the terminal that meet the customer's requirements and supports the final purchase decision.

[0460] For example, if a customer enjoys traveling and places importance on camera performance, the following prompt sentences could be input into the generative AI model:

[0461] "My client enjoys traveling and wants high-quality camera performance. Please suggest the best mobile device for him."

[0462] This system will enable efficient sales support and improved customer satisfaction.

[0463] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0464] Step 1:

[0465] The terminal receives the conversation between the crew and the customer as voice input. Specifically, a high-sensitivity microphone installed on the terminal captures the conversation in real time. The input is the conversation itself, and the output is generated as voice data. This voice data is temporarily stored on the terminal.

[0466] Step 2:

[0467] The device sends the captured audio data to the server via an HTTPS request. The input is the audio data stored on the device, and the output is the audio data sent to the server. During this process, the device maintains a stable network connection.

[0468] Step 3:

[0469] The server converts the received voice data into text data using speech recognition technology. Specifically, the voice data is passed as input to the Google Cloud Speech-to-Text API, and text data is obtained as output. During this process, noise is removed and the data is converted into an appropriate format.

[0470] Step 4:

[0471] The server analyzes the converted text data using a natural language processing (NLP) engine. The converted text data is given as input, and the customer's interests and requirements are extracted as output. Specifically, machine learning and deep learning models are used to identify important keywords within the text.

[0472] Step 5:

[0473] The server selects the optimal mobile communication device based on the analysis results. The analysis results are input, and a list of candidate mobile communication devices is generated as output. The server accesses the specification information of various devices in the database, generates a query, and extracts the optimal device.

[0474] Step 6:

[0475] The server checks the inventory information for the selected mobile communication devices. It receives a list of candidate mobile communication devices as input and generates a list with the inventory status as output. During this process, the server connects with the inventory management system via API to obtain the inventory status of each candidate model.

[0476] Step 7:

[0477] The server generates a list of optimal mobile communication devices, including the recommended features of each device. The input is the list of devices after checking their stock availability, and the output is a final list to be proposed to the customer. The list includes the features of each device and functions that match the customer's requirements.

[0478] Step 8:

[0479] The terminal visually displays the generated candidate list. The user, or crew member, uses this list to propose the optimal mobile communication terminal to the customer. The final candidate list is the input, and the visually displayed list is the output. The crew member provides support for the purchase, explaining in detail the features of the terminal that meets the customer's requirements.

[0480] (Application example 1)

[0481] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0482] In recent years, it has become increasingly important to quickly and accurately recommend products that customers need in physical stores. However, manually having a salesperson listen to a customer's requests and suggest the best products based on them takes time and can lead to misunderstandings. In particular, when using new interfaces such as smart glasses, an efficient system is required to display products that meet customer needs in real time. The challenge is to improve this situation and provide a system that can quickly suggest products that meet customer requirements.

[0483] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0484] In this invention, the server includes means for acquiring voice input, means for transmitting the voice data via a communication network, means for converting the voice data into text data, means for using natural language processing to analyze the customer's preferences and requests, means for selecting the most suitable device based on the analysis results, means for linking with an inventory management system to check inventory information, means for generating a candidate list of the most suitable devices, means for using a generative AI model, and means for generating prompt sentences to display the candidate list in a visually easy-to-understand format. This makes it possible to analyze customer needs in real time and quickly suggest the most suitable products.

[0485] A "crew" is a store clerk who handles customer service in a physical store.

[0486] A "customer" is someone who visits a store and intends to purchase a product.

[0487] "Audio input" refers to audio data captured using a device such as a microphone.

[0488] A "server" is a computer system that processes and analyzes audio data.

[0489] A "communications network" is an infrastructure for transmitting and receiving data.

[0490] "Audio data" refers to an acoustic signal obtained as an audio input.

[0491] "Text data" refers to character string information obtained by converting voice data.

[0492] "Natural language processing" refers to the techniques and methodologies for analyzing text data and understanding its content.

[0493] "Analysis" refers to analyzing data to extract meaning and information.

[0494] "Devices" refer to products that the system proposes to customers.

[0495] An "inventory management system" is an information system for managing product inventory status.

[0496] An "information display device" is a device that visually displays information, such as smart glasses or a display.

[0497] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and generate optimal results.

[0498] A "prompt" is an explanation or recommendation generated by the system.

[0499] This invention is a system that analyzes conversations between crew members and customers in real time and suggests optimal products to customers. This system uses high-performance smart glasses to enable crew members to suggest optimal smartphones while serving customers.

[0500] The device uses a microphone built into the smart glasses to capture conversations between the crew and the customer in real time, and the captured audio data is transmitted to a server via a stable communication network to ensure appropriate quality at all times.

[0501] The server receives the captured voice data and converts it into text using speech recognition technology. To achieve this, it uses a speech recognition service such as Google Cloud Speech-to-Text API. The server then analyzes the text data using a natural language processing (NLP) model to extract the customer's interests and requirements. This analysis uses a generative AI model to identify key keywords and phrases based on the customer's requirements.

[0502] Based on the extracted information, the server selects the most suitable candidate device (e.g., a smartphone) from the database. At this time, the server connects to the inventory management system via API to check the inventory information of each candidate device. This allows the server to check whether the device is in stock, and if not, to check the inventory status of nearby stores.

[0503] A list of selected devices is generated based on the features of each device and the customer's requirements. This includes the process of generating prompts using a generative AI model. For example, if a customer requests a model with a high-performance camera, the model generates a prompt such as, "This model is ideal for your needs. It has a high-performance camera and excellent battery life."

[0504] This candidate list is then displayed on the smart glasses display, allowing the crew to suggest suitable smartphones to the customer in real time.

[0505] Customer: "I want a smartphone with a good camera and long battery life."

[0506] The system captures and analyzes these requirements to extract keywords such as "camera performance" and "battery life." The server queries the database and inventory system to list "models with excellent camera performance and battery life," and displays the following prompt on the smart glasses:

[0507] "Model A - High-performance camera and excellent battery life" "Model B - Outstanding camera performance and battery life"

[0508] The prompt in this example has the form:

[0509] Customer: "I want a smartphone with a good camera and long battery life."

[0510] System: "Model A - High-performance camera and excellent battery life"

[0511] System: "Model B - Outstanding camera performance and battery life"

[0512] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0513] Step 1:

[0514] The terminal (smart glasses) receives voice input from a microphone during the conversation between the crew and the customer. The input is the actual conversational voice, and the output is captured as voice data. This voice data includes the customer's request.

[0515] Step 2:

[0516] The terminal transmits the acquired voice data to the server via a stable communication network. The input is the collected voice data, and the output is the voice data sent to the server. This procedure prepares the voice data for processing by the server.

[0517] Step 3:

[0518] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API. The input is voice data, and the output is the converted text data. During this process, the voice data is obtained as a string, which can be analyzed later.

[0519] Step 4:

[0520] The server analyzes the text data using a natural language processing (NLP) model. The input is text data, and the output is information extracted from the customer's interests and requirements. This analysis utilizes a generative AI model to identify important keywords and phrases to fulfill the customer's requirements.

[0521] Step 5:

[0522] The server selects the optimal equipment candidates from the database based on the analysis results. The input is information extracted from the customer's requirements, and the output is a list of optimal equipment candidates. The server generates a query and executes the selection process against the database.

[0523] Step 6:

[0524] The server communicates with the inventory management system via an API to check the inventory information for the selected devices. The input is a list of candidate devices, and the output is a list of devices whose inventory has been confirmed. This process ensures that the inventory status is up-to-date.

[0525] Step 7:

[0526] The server generates a list of optimal device candidates and uses an AI model to generate prompts to present the features of each device in a visually easy-to-understand format. The input is a list of devices whose inventory has been confirmed, and the output is a final list including the prompts to be displayed.

[0527] Step 8:

[0528] The terminal displays the generated candidate list on the smart glasses display and presents it to the crew. The input is the final list including the prompt text to be displayed, and the output is the visually displayed information. Based on this information, the crew can recommend the most suitable equipment for the customer.

[0529] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0530] This invention combines an emotion engine with a system that acquires voice input from conversations between crew members and customers and recommends the most suitable smartphone. This system performs processing in the following steps.

[0531] The device receives voice input from the conversation between the crew and the customer. When the crew and the customer start talking, the device's microphone captures the voice in real time and saves it as audio data. This audio is recorded in a high-quality format (WAV, MP3, etc.).

[0532] The device sends the captured audio data to the server via an HTTPS request. The device stores the recorded audio data in temporary memory and uploads the audio file to the server's speech recognition processing endpoint using the HTTPS protocol.

[0533] The server converts the received audio data into text data using the Google Cloud Speech-to-Text API, etc. The server then sends the received audio file to the Google Cloud Speech-to-Text API, which converts the audio data into text data. The converted text is returned to the server and passed on to the next analysis step.

[0534] The server preprocesses the text data. The server performs preprocessing on the received text data, such as removing spaces and line breaks and normalizing the text, to prepare it for analysis with higher accuracy.

[0535] The server analyzes the text data using a natural language processing (NLP) model. The server then inputs the text data into the NLP model to extract customer preferences and requirements. During this process, machine learning algorithms are used to extract keywords such as "camera performance" and "battery life."

[0536] The server selects the optimal model from the database based on the analysis results. The server queries the database using the extracted keywords and generates a list of smartphones that meet the customer's requirements. For example, models that meet criteria such as "high-performance camera" and "large battery capacity" are listed.

[0537] The server checks the stock information for the selected model. The server sends a request to the inventory management system's API to collect the current stock status of the selected model and stock information for each store.

[0538] The server generates a candidate list including the recommended points for each model. The server lists the recommended points that explain the features of each model together with the collected inventory information, and forms the final candidate list to be provided to customers.

[0539] The generated candidate list is sent to the device, which displays the results in a visually easy-to-understand format to the customer. The user, the crew, then recommends the optimal model to the customer based on the displayed list. The crew explains the features of smartphones that meet the customer's requirements and supports the customer in making the final purchase decision.

[0540] The system of the present invention also incorporates an emotion engine, which analyzes the user's emotions. The server uses the emotion engine when analyzing the voice data to identify the user's emotional state. This emotion analysis makes it possible to grasp emotional situations, such as whether the customer is interested or anxious. Furthermore, the system adjusts the candidate list of optimal models based on the user's emotions. For example, if a customer not only values ​​camera performance but also shows a strong interest in it, models with particularly excellent camera performance will be placed at the top of the list.

[0541] As a specific example, for a customer who enjoys traveling and prioritizes camera performance, the device captures the conversation and the server converts the speech into text. Keywords such as "travel" and "camera performance" are extracted using an NLP model, and an emotion engine analyzes the customer's "excited voice." The server then selects a model with high camera performance and checks whether it is in stock. Finally, a list of recommended models, such as "iPhone 14 Pro - High-Performance Camera and Night Mode," can be generated and displayed on the device.

[0542] In this way, the system of the present invention utilizes voice input and emotion analysis to efficiently recommend smartphones that meet customer needs, thereby achieving higher customer satisfaction.

[0543] The processing flow will be explained below.

[0544] Step 1:

[0545] The terminal captures the conversation between the crew and the customer as audio.

[0546] A microphone installed in the terminal captures the conversation between the crew and the customer in real time, recording audio data that is saved in high-quality formats such as WAV and MP3.

[0547] Step 2:

[0548] The device sends the acquired audio data to the server via an HTTPS request.

[0549] The device uploads the recorded audio data to the server via the HTTPS protocol, where it is encrypted and securely transmitted to the server.

[0550] Step 3:

[0551] The server converts the received voice data into text data using voice recognition technology.

[0552] The server uses a speech recognition engine such as Google Cloud Speech-to-Text API to convert the audio data into text data, which is then passed on to the next step.

[0553] Step 4:

[0554] The server preprocesses the text data.

[0555] As a preprocessing step, the server removes unnecessary spaces and line breaks and normalizes the text, making the subsequent analysis process smoother.

[0556] Step 5:

[0557] The server analyzes the text data using a natural language processing (NLP) model.

[0558] The server uses natural language processing technology to extract keywords from the text data, such as "camera performance," "battery life," and "gaming use," which are related to the customer's interests and requirements.

[0559] Step 6:

[0560] The server uses an emotion engine to analyze the customer's emotions based on the analysis results.

[0561] The server uses an emotion engine to identify the customer's emotional state from the voice data and extracted keywords. For example, emotions such as "excitement" or "anxiety" can be detected from the customer's speaking style and tone.

[0562] Step 7:

[0563] The server selects the most suitable model from the database based on the analysis results and emotional information.

[0564] The server queries the database based on the keywords and the customer's emotional state, selecting smartphones that meet certain criteria, such as a high-performance camera and a long battery life.

[0565] Step 8:

[0566] Check the stock information for the model for which the server has been selected.

[0567] The server works in conjunction with the inventory management system to obtain the stock status of the selected model at the store and nearby stores via API.

[0568] Step 9:

[0569] The server generates a candidate list including recommended points based on the customer's sentiment.

[0570] The server generates a list of candidates, describing each model's recommended features and specific characteristics based on sentiment analysis, such as "This smartphone features a high-performance camera, making it ideal for your travel photos."

[0571] Step 10:

[0572] The server transmits the generated candidate list to the terminal.

[0573] The server sends the final candidate list to the terminal in JSON format or similar, so that it can be displayed on the terminal.

[0574] Step 11:

[0575] The device displays the candidate list on the screen.

[0576] The terminal analyzes the received data and displays it in a visually easy-to-understand format for the crew and customer. The crew can then explain the features of the model that best suits the customer based on the displayed list.

[0577] In this way, the system of the present invention analyzes the customer's voice and emotions, and quickly and accurately recommends the most suitable smartphone. It also enables support that is tailored to the customer's emotional state.

[0578] Example 2

[0579] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0580] Conventional smartphone recommendation systems have difficulty accurately understanding customer needs and recommending the most suitable model. They also lack the ability to take into account the customer's emotional state, resulting in lower customer satisfaction. Furthermore, there was a risk of running out of stock due to insufficient means for checking inventory information in real time.

[0581] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0582] In this invention, the server includes a means for converting voice data into text data, a means for preprocessing the text data, a means for analyzing the customer's interests and requests, a means for using an emotion engine for analyzing the customer's emotional state, and a means for adjusting a list of optimal model candidates based on the customer's emotional state. This makes it possible to accurately understand the customer's emotions and requests and to propose the optimal smartphone based on them.

[0583] "Voice input" refers to capturing conversations between crew members and customers in real time using a microphone and obtaining them as voice data.

[0584] "Voice Data" means audio information captured and stored in digital form during conversations between Crew Members and Customers.

[0585] The "server" is a central processing unit that receives, converts, analyzes, and selects the most suitable smartphone for voice data.

[0586] "Text data" is voice data converted into character information, and is data to be analyzed.

[0587] "Preprocessing" refers to data processing carried out to remove unnecessary spaces and line breaks from text data and improve the accuracy of analysis.

[0588] "Natural language processing" is a technology used to analyze customer preferences and requirements from text data, and is a process that includes machine learning algorithms.

[0589] An "emotion engine" is a technology for analyzing a customer's emotional state from voice data, and is an engine that identifies and analyzes emotions.

[0590] A "candidate list" is a list of optimal smartphones generated based on the analyzed customer's tastes, requirements, and emotional state.

[0591] "Stock information" refers to the current stock status of the selected model and stock information for each store.

[0592] A "terminal" is a device that captures conversations between crew members and customers and displays a list of candidates.

[0593] This system proposes the optimal smartphone for a customer by acquiring voice input from a conversation between a crew member and a customer, analyzing and converting the voice data. This system is composed of multiple components including voice input, voice data transmission, text data conversion and preprocessing, analysis of the customer's hobbies and requests, analysis of the customer's emotional state, selection of the optimal model, confirmation of inventory information, and generation and display of a candidate list.

[0594] First, the terminal receives the conversation between the crew and the customer as voice input. The terminal's microphone captures the voice data in real time and saves it digitally in WAV or MP3 format. This voice data is stored in the terminal's temporary memory.

[0595] The device then sends the captured audio data to the server via an HTTPS request, using a secure communications protocol to upload the audio file to the server's speech recognition processing endpoint.

[0596] The server converts the received voice data into text data using speech recognition technology such as the Google Cloud Speech-to-Text API, which is then returned to the server for further analysis.

[0597] The server preprocesses the text data, removing spaces and line breaks, normalizing the text, and so on, to improve the quality of the data.

[0598] The server then uses a natural language processing (NLP) model to analyze customer preferences and requirements from the preprocessed text data. Specifically, machine learning algorithms are used to extract keywords such as "camera performance" and "battery life."

[0599] In addition, the server uses an emotion engine to analyze the customer's emotional state from the voice data. For example, if the customer speaks with an excited voice, it will interpret this as positive interest and adjust the list accordingly.

[0600] The server selects the most suitable smartphone from a database based on the analyzed hobbies, needs, and emotional state, and then connects the selected model to an inventory management system to check the inventory information of each store.

[0601] Finally, the server generates a list of the best models, including each model's recommended features, such as specific suggestions like "a smartphone with a high-performance camera and night mode."

[0602] The generated candidate list is sent to the terminal, which displays the results in a visually easy-to-understand format. Based on this display, the crew, who are the users, can propose the most suitable model to the customer.

[0603] For example, if a customer enjoys traveling and prioritizes camera performance, the device captures the conversation and the server converts the speech into text. Keywords like "travel" and "camera performance" are extracted using an NLP model, and an emotion engine analyzes the customer's excited voice to select a model with high camera performance and check whether it is in stock. Finally, a list of recommended models, such as "iPhone 14 Pro - High-Performance Camera and Night Mode," is generated and displayed on the device.

[0604] By utilizing a generative AI model, these steps can be executed efficiently and accurately. An example of a useful prompt would be, "Design a system that analyzes voice data and recommends smartphones based on customer needs."

[0605] In this way, by combining voice input and emotion analysis, the system of the present invention can recommend the smartphone that best suits the customer's needs and increase customer satisfaction.

[0606] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0607] Step 1:

[0608] The terminal receives the conversation between the crew and the customer as audio input. Specifically, it captures the audio in real time through the terminal's microphone and digitally stores it in high-quality WAV or MP3 format. The input is an audio signal, and the output is a digital audio file.

[0609] Step 2:

[0610] The device stores the captured voice data in temporary memory and sends it to the server via an HTTPS request. Specifically, the audio file is uploaded to the server's voice recognition processing endpoint using the HTTPS protocol. The input is the digital audio file, and the output is the upload status to the server via the HTTPS request.

[0611] Step 3:

[0612] The server converts the received audio data into text data using the Google Cloud Speech-to-Text API. Specifically, the audio file is sent to the API, and a machine learning algorithm converts the audio into text. The input is an audio file, and the output is text data.

[0613] Step 4:

[0614] The server preprocesses the text data it receives. Specifically, it removes spaces and line breaks, normalizes the text, etc. The input is unprocessed text data, and the output is preprocessed text data.

[0615] Step 5:

[0616] The server analyzes the preprocessed text data using a natural language processing (NLP) model. Specifically, it uses a machine learning algorithm to extract keywords such as "camera performance" and "battery life." The input is the preprocessed text data, and the output is the extracted keywords.

[0617] Step 6:

[0618] The server selects the optimal model from the database based on the analysis results. Specifically, it queries the database using the extracted keywords and generates a list of related smartphones. The input is the extracted keywords, and the output is a list of candidate smartphones.

[0619] Step 7:

[0620] The server checks the stock information of the selected model. Specifically, it sends a request to the inventory management system's API to collect the current stock status. The input is a list of candidate smartphones, and the output is stock information.

[0621] Step 8:

[0622] The server uses an emotion engine to analyze the customer's emotional state from the voice data. Specifically, the voice data is input into the emotion engine, and the emotion engine analyzes the customer's emotions, such as excitement, interest, and anxiety. The input is the voice data, and the output is the emotion analysis result.

[0623] Step 9:

[0624] The server adjusts the candidate list of optimal models based on the customer's emotional state. Specifically, based on the results of emotion analysis, models that the customer is particularly interested in are placed at the top of the list. The input is the emotion analysis results and inventory information, and the output is the adjusted candidate list.

[0625] Step 10:

[0626] The server generates a candidate list of optimal models, including the recommended points for each model. Specifically, it lists the recommended points that explain the features of each model along with the collected inventory information. The input is the adjusted candidate list and inventory information, and the output is the final candidate list.

[0627] Step 11:

[0628] The terminal displays the generated candidate list in a visually easy-to-understand format. Specifically, it provides an interface that allows the crew (user) to refer to the list and displays it to the customer. The input is the final candidate list, and the output is display information that can be visually confirmed by the crew and customer.

[0629] (Application example 2)

[0630] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0631] While conventional systems can suggest the appropriate smartphone based on customer needs, they are unable to take customer emotions into consideration when making suggestions, which means they are unable to sufficiently improve customer satisfaction. Furthermore, there is a lack of an effective means for analyzing conversations in real time and quickly providing a list of optimal models.

[0632] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0633] In this invention, the server includes means for acquiring a conversation between a crew member and a customer as voice input, means for transmitting the acquired voice data to the server, means for converting the voice data into text data on the server, means for analyzing the customer's preferences and requests from the text data, means for selecting an optimal model based on the analysis results, means for checking inventory information for the selected model, means for generating a candidate list of optimal models, means for displaying the candidate list on a terminal, means for analyzing the customer's emotions and adjusting the candidate list of optimal models based on the emotions, and means for analyzing the conversation in real time and visually presenting the results. This makes it possible to recommend the optimal smartphone in real time while taking the customer's emotions into consideration, thereby increasing customer satisfaction.

[0634] "Means for acquiring conversations between staff and customers as audio input" refers to a device or method for recording conversations between staff and customers using an audio input device such as a microphone and acquiring the audio data.

[0635] The "means for transmitting acquired voice data to a server" refers to a communication means or protocol for transferring voice data acquired by a voice input device to a remote server via the Internet or a local network.

[0636] "Means for converting voice data into text data on a server" refers to the process and device that converts transmitted voice data into text format using voice recognition software or an API.

[0637] "Means for analyzing customer interests and needs from text data" refers to algorithms and software that analyze text data using natural language processing (NLP) to identify customer interests and needs.

[0638] The "means for selecting the optimal model based on the analysis results" refers to a database query and selection algorithm for selecting the optimal smartphone model based on customer requirements extracted by text data analysis.

[0639] The "means for checking stock information for the selected model" refers to an API or protocol that works with an inventory management system to check the stock status of the selected smartphone model.

[0640] The "means for generating a candidate list of optimal models" is software for generating a candidate list including the features and recommended points of smartphone models that have been selected and stock confirmed.

[0641] The "means for displaying the candidate list on the terminal" refers to a display screen or application for visually presenting the generated smartphone model candidate list to the user.

[0642] "Means for analyzing customer sentiment and adjusting a candidate list of optimal models based on the sentiment" refers to algorithms and software that analyze sentiment from customer voice data and dynamically sort or filter the candidate list according to the sentiment.

[0643] "Means for analyzing conversations in real time and providing the results visually" refers to technology and applications for analyzing conversations between crew members and customers in real time and displaying the results on a screen in a timely manner.

[0644] This invention is a system that acquires voice input from conversations between crew members and customers, combines it with emotion analysis, and proposes the most suitable smartphone. This system is mainly built by combining a voice input device, a server, a terminal, and various APIs.

[0645] First, the conversation between the crew and the customer is captured using a voice input device, i.e., a smartphone microphone. High-quality audio data (e.g., WAV or MP3 format) is captured in real time and sent to a server via HTTPS protocol. This process is performed using a data communication method.

[0646] The server uses speech recognition software such as the Google Cloud Speech-to-Text API to convert the received voice data into text data. This converted text data is preprocessed on the server to remove spaces and line breaks and normalize the sentences. The preprocessed text data is then input into a natural language processing (NLP) model to extract customer preferences and requirements (e.g., "camera performance," "battery life," etc.).

[0647] Furthermore, the server uses an emotion recognition engine to analyze the customer's emotional state from the text data. The text data is used to identify emotional situations such as "the customer is interested" or "the customer is anxious." Based on the results of this emotion analysis, the candidate list of optimal models is adjusted.

[0648] The server then executes a database query based on the extracted keywords and the results of sentiment analysis to generate a list of smartphones that meet the customer's needs. After generating the list, it connects with an inventory management system to check stock information and confirm the availability of the most suitable models. Finally, a list of recommended models that meet criteria such as "high-performance camera" or "high battery capacity" is generated and displayed on the device.

[0649] The device presents the user with a list of smartphones in a visually easy-to-understand format. The crew then uses the list to explain the features of suitable smartphones to the customer and helps them make a purchasing decision. The crew can also dynamically update the recommended smartphone models based on the customer's real-time conversation analysis and emotional feedback.

[0650] As a specific example, for a customer who enjoys traveling and places importance on camera performance, the system will capture the customer's conversation through the smartphone's microphone, analyze their emotions, and then recommend the most suitable smartphone, such as the ``iPhone 14 Pro - High-Performance Camera and Night Mode.''

[0651] Here are some examples of prompts to input to the generative AI model:

[0652] "For a customer who enjoys traveling and prioritizes camera performance, capture their conversation through the smartphone's microphone, analyze their emotions, and then recommend the best smartphone for them."

[0653] By implementing this system, it will be possible to take into account customer emotions and make optimal smartphone recommendations in real time, thereby improving customer satisfaction.

[0654] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0655] Step 1:

[0656] Capture conversations between crew and customers as voice input.

[0657] (Specific actions)

[0658] The device (smartphone) uses a microphone to record conversations in real time.

[0659] (input)

[0660] Audio data

[0661] (output)

[0662] Recorded audio files (high quality formats, e.g. WAV, MP3)

[0663] Step 2:

[0664] The acquired voice data is sent to the server.

[0665] (Specific actions)

[0666] The device stores the audio file in temporary memory and uploads it to the server's speech recognition processing endpoint using the HTTPS protocol.

[0667] (input)

[0668] Audio files

[0669] (output)

[0670] Uploading audio files to the server

[0671] Step 3:

[0672] The voice data is converted into text data on the server.

[0673] (Specific actions)

[0674] The server sends the received audio file to the Google Cloud Speech-to-Text API, which automatically converts it into text data.

[0675] (input)

[0676] Audio files

[0677] (output)

[0678] Converted text data

[0679] Step 4:

[0680] Preprocess text data.

[0681] (Specific actions)

[0682] The server performs preprocessing on the text data, such as removing spaces and line breaks and normalizing the text.

[0683] (input)

[0684] Converted text data

[0685] (output)

[0686] Preprocessed text data

[0687] Step 5:

[0688] Analyze customer interests and requests from text data.

[0689] (Specific actions)

[0690] The server inputs the preprocessed text data into an NLP model, which uses machine learning algorithms to extract keywords (e.g., "camera performance," "battery life," etc.).

[0691] (input)

[0692] Preprocessed text data

[0693] (output)

[0694] Extracted keywords

[0695] Step 6:

[0696] Analyze customer sentiment.

[0697] (Specific actions)

[0698] The server inputs the converted text data into an emotion analysis engine, which identifies the customer's emotional state based on the voice data.

[0699] (input)

[0700] Preprocessed text data

[0701] (output)

[0702] Customer sentiment data

[0703] Step 7:

[0704] The optimal model is selected based on the analysis results.

[0705] (Specific actions)

[0706] The server runs a database query based on the extracted keywords and emotion data to generate a list of smartphones that meet the user's needs.

[0707] (input)

[0708] Extracted keywords and sentiment data

[0709] (output)

[0710] A list of the best models

[0711] Step 8:

[0712] Check the stock information for the selected model.

[0713] (Specific actions)

[0714] The server sends a request to the inventory management system API to check the stock status of the selected model.

[0715] (input)

[0716] A list of the best models

[0717] (output)

[0718] Suggestion list with stock information

[0719] Step 9:

[0720] Generate a list of optimal models.

[0721] (Specific actions)

[0722] The server creates a final candidate list that includes inventory and feature information.

[0723] (input)

[0724] Suggestion list with stock information

[0725] (output)

[0726] Final candidate list

[0727] Step 10:

[0728] Display the candidate list on the terminal.

[0729] (Specific actions)

[0730] The device visually displays the generated candidate list, allowing the crew to suggest the best smartphone for the customer.

[0731] (input)

[0732] Final candidate list

[0733] (output)

[0734] Candidate list displayed on device

[0735] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0736] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0737] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0738] [Third embodiment]

[0739] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0740] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0741] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0742] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0743] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0744] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0745] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0746] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0747] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0748] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0749] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0750] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0751] The present invention is a system that acquires voice input from conversations between crew members and customers and recommends the most suitable smartphone. This system performs processing in the following steps.

[0752] The terminal captures the conversation between the crew and the customer as voice input. A microphone installed on the terminal captures the conversation in real time and saves it as audio data. The captured audio data is sent to the server via an HTTPS request. This voice input capture step requires the terminal to have a high-performance microphone and a stable network connection in order to quickly record the conversation.

[0753] The server converts the received voice data into text data using speech recognition technology. By utilizing speech recognition services such as the Google Cloud Speech-to-Text API, speech can be converted into text with high accuracy. During this process, the quality of the voice data is checked, noise is removed, and it is converted into an appropriate format.

[0754] The converted text data is analyzed using a natural language processing (NLP) model. The server uses the NLP engine to extract customer interests and requirements from the text data. This analysis uses machine learning models and deep learning techniques to identify important keywords and phrases within the text. For example, interests and requirements such as "camera performance," "long battery life," and "gaming use" are extracted.

[0755] Based on the analysis results, the server selects the most suitable smartphone candidate from the database. The server generates a query and retrieves the corresponding model from the database. This database contains the specifications and features of a wide variety of smartphones on the market, allowing the most suitable model to be extracted quickly.

[0756] The server checks the inventory information for the selected models. The server connects to the inventory management system via API to obtain the inventory status of each candidate model. This process checks whether the model is in stock, and if not, the inventory status of nearby stores.

[0757] The server generates a list of optimal models, including recommendations for each model. This list includes specific features of each smartphone and features that match the customer's requirements. For example, "iPhone 14 Pro - high-performance camera and long battery life" or "Samsung Galaxy S21 - excellent gaming performance."

[0758] The generated candidate list is sent to the device, which displays the results in a visually easy-to-understand format to the customer. The user, the crew, then recommends the optimal model to the customer based on the displayed list. The crew explains the features of smartphones that meet the customer's requirements and supports the customer in making the final purchase decision.

[0759] In this way, the system of the present invention receives voice input, analyzes the voice data, and recommends the most suitable smartphone for the customer. By accurately understanding customer needs and making prompt and accurate recommendations, customer satisfaction can be improved and sales opportunities can be maximized. For example, for a customer whose hobby is traveling and who places importance on camera performance, a smartphone equipped with a high-performance camera can be recommended, and by checking stock availability, the system can inform the customer whether it is available for immediate purchase. This system realizes efficient sales support and improved customer satisfaction.

[0760] The processing flow will be explained below.

[0761] Step 1:

[0762] The terminal captures the conversation between the crew and the customer as audio.

[0763] When the crew and customer start talking, the device's microphone captures the audio in real time, which is then recorded in a high-quality format (such as WAV or MP3).

[0764] Step 2:

[0765] The device sends the acquired audio data to the server via an HTTPS request.

[0766] The device stores the recorded voice data in temporary memory and uploads the voice file to the server's voice recognition processing endpoint using the HTTPS protocol.

[0767] Step 3:

[0768] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API or similar.

[0769] The server then sends the received audio file to the Google Cloud Speech-to-Text API, which converts the audio data into text data, which is then returned to the server for further analysis.

[0770] Step 4:

[0771] The server preprocesses the text data.

[0772] The server performs preprocessing on the received text data, such as removing spaces and line breaks and normalizing the text, to prepare for improved analysis accuracy.

[0773] Step 5:

[0774] The server analyzes the text data using a natural language processing (NLP) model.

[0775] The server inputs the text data into an NLP model to extract customer preferences and requirements, using machine learning algorithms to extract keywords such as "camera performance" and "battery life."

[0776] Step 6:

[0777] The server selects the optimal model from the database based on the analysis results.

[0778] The server queries the database using the extracted keywords to generate a list of smartphones that match the customer's requirements, such as "high-performance camera" or "large battery capacity."

[0779] Step 7:

[0780] Check the stock information for the model for which the server has been selected.

[0781] The server sends a request to the inventory management system's API to collect the current stock status of the selected model and stock information for each store.

[0782] Step 8:

[0783] The server generates a candidate list including the recommended points of each model.

[0784] The server lists the collected inventory information along with recommended points that explain the features of each model, and creates a final candidate list to provide to customers.

[0785] Step 9:

[0786] The server transmits the generated candidate list to the terminal.

[0787] The server sends the final candidate list to the terminal in a standard data format such as JSON.

[0788] Step 10:

[0789] The device displays the candidate list on the screen.

[0790] The terminal analyzes the received data and displays it in a visually easy-to-understand format for the crew and customer, allowing the crew to explain the features and inventory information of each model to the customer and make suggestions.

[0791] This allows the system of the present invention to efficiently propose smartphones that meet the needs of customers.

[0792] Example 1

[0793] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0794] With the current sales system, it is difficult to make proposals that reflect individual customer needs in real time, and there are issues such as not being able to fully improve customer satisfaction or maximize sales opportunities.In addition, checking inventory information takes time, and appropriate product recommendations are not made smoothly.

[0795] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0796] In this invention, the server includes means for acquiring a conversation between a crew member and a customer as voice input, means for transmitting the acquired voice data as a request, means for converting the voice data into text data on the server, means for analyzing the customer's interests and requests from the text data, means for selecting an optimal mobile communication terminal based on the analysis results, means for checking inventory information for the selected mobile communication terminal, means for generating a candidate list of optimal mobile communication terminals, and means for displaying the candidate list on the terminal. This enables proposals that quickly and accurately reflect customer needs, thereby maximizing sales opportunities and improving customer satisfaction.

[0797] "Crew" refers to staff members in charge of sales and support duties.

[0798] "Customer" means a consumer who intends to purchase or use a product or service.

[0799] "Voice input" refers to conversation content acquired as voice data.

[0800] "Data" refers to information handled within a computer system, and includes various formats such as audio, text, and images.

[0801] A "server" is a computer system that provides services to clients over a network.

[0802] "Text data" is character information converted using voice recognition technology.

[0803] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0804] A "mobile communication terminal" is a device capable of mobile communication, such as a smartphone or tablet.

[0805] "Inventory information" is data that indicates whether a product is currently available.

[0806] A "candidate list" is a list of multiple mobile communication terminals that are proposed based on the analysis results.

[0807] The present invention provides a system that acquires voice input from conversations between crew members and customers and proposes mobile communication devices that best suit the customer's needs. This system is realized by a combination of hardware and software. Specific embodiments are described below.

[0808] The device is equipped with a high-sensitivity microphone that captures the conversation between the crew and the customer as voice input in real time. The captured voice data is temporarily stored on the device and then sent to the server via an HTTPS request. During this process, the device must maintain a stable network connection.

[0809] The server converts the received voice data into text data using speech recognition technology. Specifically, it uses a speech recognition service such as Google Cloud Speech-to-Text API. The speech recognition technology converts the voice data into text with high accuracy. During this process, noise is removed and the data is converted into an appropriate format.

[0810] The converted text data is analyzed by a natural language processing (NLP) engine on the server. The NLP engine extracts customer preferences and requirements from the text data. Using a deep learning model, important keywords and phrases within the text are identified. For example, keywords such as "camera performance" and "long battery life" are extracted.

[0811] Based on the analysis results, the server selects the most suitable candidate mobile communication device from the database. The database contains the specifications and features of various mobile communication devices, and the server generates queries to access this database. As a result, devices that meet the customer's needs are quickly extracted.

[0812] The server checks the stock information of the selected devices by linking with the inventory management system, obtaining the stock status of each candidate model via API, and checking whether it is in stock and the stock status of nearby stores.

[0813] The server generates a list of suitable mobile devices, including recommendations for each device. This list includes specific features and functions that meet customer requirements, such as "models with high-performance cameras" or "models with long-life batteries."

[0814] The generated candidate list is sent to the terminal, where it is displayed in a visually easy-to-understand format. The crew, who is the user, proposes the most suitable mobile communication terminal to the customer based on the displayed list. The crew explains the features of the terminal that meet the customer's requirements and supports the final purchase decision.

[0815] For example, if a customer enjoys traveling and places importance on camera performance, the following prompt sentences could be input into the generative AI model:

[0816] "My client enjoys traveling and wants high-quality camera performance. Please suggest the best mobile device for him."

[0817] This system will enable efficient sales support and improved customer satisfaction.

[0818] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0819] Step 1:

[0820] The terminal receives the conversation between the crew and the customer as voice input. Specifically, a high-sensitivity microphone installed on the terminal captures the conversation in real time. The input is the conversation itself, and the output is generated as voice data. This voice data is temporarily stored on the terminal.

[0821] Step 2:

[0822] The device sends the captured audio data to the server via an HTTPS request. The input is the audio data stored on the device, and the output is the audio data sent to the server. During this process, the device maintains a stable network connection.

[0823] Step 3:

[0824] The server converts the received voice data into text data using speech recognition technology. Specifically, the voice data is passed as input to the Google Cloud Speech-to-Text API, and text data is obtained as output. During this process, noise is removed and the data is converted into an appropriate format.

[0825] Step 4:

[0826] The server analyzes the converted text data using a natural language processing (NLP) engine. The converted text data is given as input, and the customer's interests and requirements are extracted as output. Specifically, machine learning and deep learning models are used to identify important keywords within the text.

[0827] Step 5:

[0828] The server selects the optimal mobile communication device based on the analysis results. The analysis results are input, and a list of candidate mobile communication devices is generated as output. The server accesses the specification information of various devices in the database, generates a query, and extracts the optimal device.

[0829] Step 6:

[0830] The server checks the inventory information for the selected mobile communication devices. It receives a list of candidate mobile communication devices as input and generates a list with the inventory status as output. During this process, the server connects with the inventory management system via API to obtain the inventory status of each candidate model.

[0831] Step 7:

[0832] The server generates a list of optimal mobile communication devices, including the recommended features of each device. The input is the list of devices after checking their stock availability, and the output is a final list to be proposed to the customer. The list includes the features of each device and functions that match the customer's requirements.

[0833] Step 8:

[0834] The terminal visually displays the generated candidate list. The user, or crew member, uses this list to propose the optimal mobile communication terminal to the customer. The final candidate list is the input, and the visually displayed list is the output. The crew member provides support for the purchase, explaining in detail the features of the terminal that meets the customer's requirements.

[0835] (Application example 1)

[0836] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0837] In recent years, it has become increasingly important to quickly and accurately recommend products that customers need in physical stores. However, manually having a salesperson listen to a customer's requests and suggest the best products based on them takes time and can lead to misunderstandings. In particular, when using new interfaces such as smart glasses, an efficient system is required to display products that meet customer needs in real time. The challenge is to improve this situation and provide a system that can quickly suggest products that meet customer requirements.

[0838] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0839] In this invention, the server includes means for acquiring voice input, means for transmitting the voice data via a communication network, means for converting the voice data into text data, means for using natural language processing to analyze the customer's preferences and requests, means for selecting the most suitable device based on the analysis results, means for linking with an inventory management system to check inventory information, means for generating a candidate list of the most suitable devices, means for using a generative AI model, and means for generating prompt sentences to display the candidate list in a visually easy-to-understand format. This makes it possible to analyze customer needs in real time and quickly suggest the most suitable products.

[0840] A "crew" is a store clerk who handles customer service in a physical store.

[0841] A "customer" is someone who visits a store and intends to purchase a product.

[0842] "Audio input" refers to audio data captured using a device such as a microphone.

[0843] A "server" is a computer system that processes and analyzes audio data.

[0844] A "communications network" is an infrastructure for transmitting and receiving data.

[0845] "Audio data" refers to an acoustic signal obtained as an audio input.

[0846] "Text data" refers to character string information obtained by converting voice data.

[0847] "Natural language processing" refers to the techniques and methodologies for analyzing text data and understanding its content.

[0848] "Analysis" refers to analyzing data to extract meaning and information.

[0849] "Devices" refer to products that the system proposes to customers.

[0850] An "inventory management system" is an information system for managing product inventory status.

[0851] An "information display device" is a device that visually displays information, such as smart glasses or a display.

[0852] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and generate optimal results.

[0853] A "prompt" is an explanation or recommendation generated by the system.

[0854] This invention is a system that analyzes conversations between crew members and customers in real time and suggests optimal products to customers. This system uses high-performance smart glasses to enable crew members to suggest optimal smartphones while serving customers.

[0855] The device uses a microphone built into the smart glasses to capture conversations between the crew and the customer in real time, and the captured audio data is transmitted to a server via a stable communication network to ensure appropriate quality at all times.

[0856] The server receives the captured voice data and converts it into text using speech recognition technology. To achieve this, it uses a speech recognition service such as Google Cloud Speech-to-Text API. The server then analyzes the text data using a natural language processing (NLP) model to extract the customer's interests and requirements. This analysis uses a generative AI model to identify key keywords and phrases based on the customer's requirements.

[0857] Based on the extracted information, the server selects the most suitable candidate device (e.g., a smartphone) from the database. At this time, the server connects to the inventory management system via API to check the inventory information of each candidate device. This allows the server to check whether the device is in stock, and if not, to check the inventory status of nearby stores.

[0858] A list of selected devices is generated based on the features of each device and the customer's requirements. This includes the process of generating prompts using a generative AI model. For example, if a customer requests a model with a high-performance camera, the model generates a prompt such as, "This model is ideal for your needs. It has a high-performance camera and excellent battery life."

[0859] This candidate list is then displayed on the smart glasses display, allowing the crew to suggest suitable smartphones to the customer in real time.

[0860] Customer: "I want a smartphone with a good camera and long battery life."

[0861] The system captures and analyzes these requirements to extract keywords such as "camera performance" and "battery life." The server queries the database and inventory system to list "models with excellent camera performance and battery life," and displays the following prompt on the smart glasses:

[0862] "Model A - High-performance camera and excellent battery life" "Model B - Outstanding camera performance and battery life"

[0863] The prompt in this example has the form:

[0864] Customer: "I want a smartphone with a good camera and long battery life."

[0865] System: "Model A - High-performance camera and excellent battery life"

[0866] System: "Model B - Outstanding camera performance and battery life"

[0867] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0868] Step 1:

[0869] The terminal (smart glasses) receives voice input from a microphone during the conversation between the crew and the customer. The input is the actual conversational voice, and the output is captured as voice data. This voice data includes the customer's request.

[0870] Step 2:

[0871] The terminal transmits the acquired voice data to the server via a stable communication network. The input is the collected voice data, and the output is the voice data sent to the server. This procedure prepares the voice data for processing by the server.

[0872] Step 3:

[0873] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API. The input is voice data, and the output is the converted text data. During this process, the voice data is obtained as a string, which can be analyzed later.

[0874] Step 4:

[0875] The server analyzes the text data using a natural language processing (NLP) model. The input is text data, and the output is information extracted from the customer's interests and requirements. This analysis utilizes a generative AI model to identify important keywords and phrases to fulfill the customer's requirements.

[0876] Step 5:

[0877] The server selects the optimal equipment candidates from the database based on the analysis results. The input is information extracted from the customer's requirements, and the output is a list of optimal equipment candidates. The server generates a query and executes the selection process against the database.

[0878] Step 6:

[0879] The server communicates with the inventory management system via an API to check the inventory information for the selected devices. The input is a list of candidate devices, and the output is a list of devices whose inventory has been confirmed. This process ensures that the inventory status is up-to-date.

[0880] Step 7:

[0881] The server generates a list of optimal device candidates and uses an AI model to generate prompts to present the features of each device in a visually easy-to-understand format. The input is a list of devices whose inventory has been confirmed, and the output is a final list including the prompts to be displayed.

[0882] Step 8:

[0883] The terminal displays the generated candidate list on the smart glasses display and presents it to the crew. The input is the final list including the prompt text to be displayed, and the output is the visually displayed information. Based on this information, the crew can recommend the most suitable equipment for the customer.

[0884] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0885] This invention combines an emotion engine with a system that acquires voice input from conversations between crew members and customers and recommends the most suitable smartphone. This system performs processing in the following steps.

[0886] The device receives voice input from the conversation between the crew and the customer. When the crew and the customer start talking, the device's microphone captures the voice in real time and saves it as audio data. This audio is recorded in a high-quality format (WAV, MP3, etc.).

[0887] The device sends the captured audio data to the server via an HTTPS request. The device stores the recorded audio data in temporary memory and uploads the audio file to the server's speech recognition processing endpoint using the HTTPS protocol.

[0888] The server converts the received audio data into text data using the Google Cloud Speech-to-Text API, etc. The server then sends the received audio file to the Google Cloud Speech-to-Text API, which converts the audio data into text data. The converted text is returned to the server and passed on to the next analysis step.

[0889] The server preprocesses the text data. The server performs preprocessing on the received text data, such as removing spaces and line breaks and normalizing the text, to prepare it for analysis with higher accuracy.

[0890] The server analyzes the text data using a natural language processing (NLP) model. The server then inputs the text data into the NLP model to extract customer preferences and requirements. During this process, machine learning algorithms are used to extract keywords such as "camera performance" and "battery life."

[0891] The server selects the optimal model from the database based on the analysis results. The server queries the database using the extracted keywords and generates a list of smartphones that meet the customer's requirements. For example, models that meet criteria such as "high-performance camera" and "large battery capacity" are listed.

[0892] The server checks the stock information for the selected model. The server sends a request to the inventory management system's API to collect the current stock status of the selected model and stock information for each store.

[0893] The server generates a candidate list including the recommended points for each model. The server lists the recommended points that explain the features of each model together with the collected inventory information, and forms the final candidate list to be provided to customers.

[0894] The generated candidate list is sent to the device, which displays the results in a visually easy-to-understand format to the customer. The user, the crew, then recommends the optimal model to the customer based on the displayed list. The crew explains the features of smartphones that meet the customer's requirements and supports the customer in making the final purchase decision.

[0895] The system of the present invention also incorporates an emotion engine, which analyzes the user's emotions. The server uses the emotion engine when analyzing the voice data to identify the user's emotional state. This emotion analysis makes it possible to grasp emotional situations, such as whether the customer is interested or anxious. Furthermore, the system adjusts the candidate list of optimal models based on the user's emotions. For example, if a customer not only values ​​camera performance but also shows a strong interest in it, models with particularly excellent camera performance will be placed at the top of the list.

[0896] As a specific example, for a customer who enjoys traveling and prioritizes camera performance, the device captures the conversation and the server converts the speech into text. Keywords such as "travel" and "camera performance" are extracted using an NLP model, and an emotion engine analyzes the customer's "excited voice." The server then selects a model with high camera performance and checks whether it is in stock. Finally, a list of recommended models, such as "iPhone 14 Pro - High-Performance Camera and Night Mode," can be generated and displayed on the device.

[0897] In this way, the system of the present invention utilizes voice input and emotion analysis to efficiently recommend smartphones that meet customer needs, thereby achieving higher customer satisfaction.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] The terminal captures the conversation between the crew and the customer as audio.

[0901] A microphone installed in the terminal captures the conversation between the crew and the customer in real time, recording audio data that is saved in high-quality formats such as WAV and MP3.

[0902] Step 2:

[0903] The device sends the acquired audio data to the server via an HTTPS request.

[0904] The device uploads the recorded audio data to the server via the HTTPS protocol, where it is encrypted and securely transmitted to the server.

[0905] Step 3:

[0906] The server converts the received voice data into text data using voice recognition technology.

[0907] The server uses a speech recognition engine such as Google Cloud Speech-to-Text API to convert the audio data into text data, which is then passed on to the next step.

[0908] Step 4:

[0909] The server preprocesses the text data.

[0910] As a preprocessing step, the server removes unnecessary spaces and line breaks and normalizes the text, making the subsequent analysis process smoother.

[0911] Step 5:

[0912] The server analyzes the text data using a natural language processing (NLP) model.

[0913] The server uses natural language processing technology to extract keywords from the text data, such as "camera performance," "battery life," and "gaming use," which are related to the customer's interests and requirements.

[0914] Step 6:

[0915] The server uses an emotion engine to analyze the customer's emotions based on the analysis results.

[0916] The server uses an emotion engine to identify the customer's emotional state from the voice data and extracted keywords. For example, emotions such as "excitement" or "anxiety" can be detected from the customer's speaking style and tone.

[0917] Step 7:

[0918] The server selects the most suitable model from the database based on the analysis results and emotional information.

[0919] The server queries the database based on the keywords and the customer's emotional state, selecting smartphones that meet certain criteria, such as a high-performance camera and a long battery life.

[0920] Step 8:

[0921] Check the stock information for the model for which the server has been selected.

[0922] The server works in conjunction with the inventory management system to obtain the stock status of the selected model at the store and nearby stores via API.

[0923] Step 9:

[0924] The server generates a candidate list including recommended points based on the customer's sentiment.

[0925] The server generates a list of candidates, describing each model's recommended features and specific characteristics based on sentiment analysis, such as "This smartphone features a high-performance camera, making it ideal for your travel photos."

[0926] Step 10:

[0927] The server transmits the generated candidate list to the terminal.

[0928] The server sends the final candidate list to the terminal in JSON format or similar, so that it can be displayed on the terminal.

[0929] Step 11:

[0930] The device displays the candidate list on the screen.

[0931] The terminal analyzes the received data and displays it in a visually easy-to-understand format for the crew and customer. The crew can then explain the features of the model that best suits the customer based on the displayed list.

[0932] In this way, the system of the present invention analyzes the customer's voice and emotions, and quickly and accurately recommends the most suitable smartphone. It also enables support that is tailored to the customer's emotional state.

[0933] Example 2

[0934] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0935] Conventional smartphone recommendation systems have difficulty accurately understanding customer needs and recommending the most suitable model. They also lack the ability to take into account the customer's emotional state, resulting in lower customer satisfaction. Furthermore, there was a risk of running out of stock due to insufficient means for checking inventory information in real time.

[0936] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0937] In this invention, the server includes a means for converting voice data into text data, a means for preprocessing the text data, a means for analyzing the customer's interests and requests, a means for using an emotion engine for analyzing the customer's emotional state, and a means for adjusting a list of optimal model candidates based on the customer's emotional state. This makes it possible to accurately understand the customer's emotions and requests and to propose the optimal smartphone based on them.

[0938] "Voice input" refers to capturing conversations between crew members and customers in real time using a microphone and obtaining them as voice data.

[0939] "Voice Data" means audio information captured and stored in digital form during conversations between Crew Members and Customers.

[0940] The "server" is a central processing unit that receives, converts, analyzes, and selects the most suitable smartphone for voice data.

[0941] "Text data" is voice data converted into character information, and is data to be analyzed.

[0942] "Preprocessing" refers to data processing carried out to remove unnecessary spaces and line breaks from text data and improve the accuracy of analysis.

[0943] "Natural language processing" is a technology used to analyze customer preferences and requirements from text data, and is a process that includes machine learning algorithms.

[0944] An "emotion engine" is a technology for analyzing a customer's emotional state from voice data, and is an engine that identifies and analyzes emotions.

[0945] A "candidate list" is a list of optimal smartphones generated based on the analyzed customer's tastes, requirements, and emotional state.

[0946] "Stock information" refers to the current stock status of the selected model and stock information for each store.

[0947] A "terminal" is a device that captures conversations between crew members and customers and displays a list of candidates.

[0948] This system proposes the optimal smartphone for a customer by acquiring voice input from a conversation between a crew member and a customer, analyzing and converting the voice data. This system is composed of multiple components including voice input, voice data transmission, text data conversion and preprocessing, analysis of the customer's hobbies and requests, analysis of the customer's emotional state, selection of the optimal model, confirmation of inventory information, and generation and display of a candidate list.

[0949] First, the terminal receives the conversation between the crew and the customer as voice input. The terminal's microphone captures the voice data in real time and saves it digitally in WAV or MP3 format. This voice data is stored in the terminal's temporary memory.

[0950] The device then sends the captured audio data to the server via an HTTPS request, using a secure communications protocol to upload the audio file to the server's speech recognition processing endpoint.

[0951] The server converts the received voice data into text data using speech recognition technology such as the Google Cloud Speech-to-Text API, which is then returned to the server for further analysis.

[0952] The server preprocesses the text data, removing spaces and line breaks, normalizing the text, and so on, to improve the quality of the data.

[0953] The server then uses a natural language processing (NLP) model to analyze customer preferences and requirements from the preprocessed text data. Specifically, machine learning algorithms are used to extract keywords such as "camera performance" and "battery life."

[0954] In addition, the server uses an emotion engine to analyze the customer's emotional state from the voice data. For example, if the customer speaks with an excited voice, it will interpret this as positive interest and adjust the list accordingly.

[0955] The server selects the most suitable smartphone from a database based on the analyzed hobbies, needs, and emotional state, and then connects the selected model to an inventory management system to check the inventory information of each store.

[0956] Finally, the server generates a list of the best models, including each model's recommended features, such as specific suggestions like "a smartphone with a high-performance camera and night mode."

[0957] The generated candidate list is sent to the terminal, which displays the results in a visually easy-to-understand format. Based on this display, the crew, who are the users, can propose the most suitable model to the customer.

[0958] For example, if a customer enjoys traveling and prioritizes camera performance, the device captures the conversation and the server converts the speech into text. Keywords like "travel" and "camera performance" are extracted using an NLP model, and an emotion engine analyzes the customer's excited voice to select a model with high camera performance and check whether it is in stock. Finally, a list of recommended models, such as "iPhone 14 Pro - High-Performance Camera and Night Mode," is generated and displayed on the device.

[0959] By utilizing a generative AI model, these steps can be executed efficiently and accurately. An example of a useful prompt would be, "Design a system that analyzes voice data and recommends smartphones based on customer needs."

[0960] In this way, by combining voice input and emotion analysis, the system of the present invention can recommend the smartphone that best suits the customer's needs and increase customer satisfaction.

[0961] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0962] Step 1:

[0963] The terminal receives the conversation between the crew and the customer as audio input. Specifically, it captures the audio in real time through the terminal's microphone and digitally stores it in high-quality WAV or MP3 format. The input is an audio signal, and the output is a digital audio file.

[0964] Step 2:

[0965] The device stores the captured voice data in temporary memory and sends it to the server via an HTTPS request. Specifically, the audio file is uploaded to the server's voice recognition processing endpoint using the HTTPS protocol. The input is the digital audio file, and the output is the upload status to the server via the HTTPS request.

[0966] Step 3:

[0967] The server converts the received audio data into text data using the Google Cloud Speech-to-Text API. Specifically, the audio file is sent to the API, and a machine learning algorithm converts the audio into text. The input is an audio file, and the output is text data.

[0968] Step 4:

[0969] The server preprocesses the text data it receives. Specifically, it removes spaces and line breaks, normalizes the text, etc. The input is unprocessed text data, and the output is preprocessed text data.

[0970] Step 5:

[0971] The server analyzes the preprocessed text data using a natural language processing (NLP) model. Specifically, it uses a machine learning algorithm to extract keywords such as "camera performance" and "battery life." The input is the preprocessed text data, and the output is the extracted keywords.

[0972] Step 6:

[0973] The server selects the optimal model from the database based on the analysis results. Specifically, it queries the database using the extracted keywords and generates a list of related smartphones. The input is the extracted keywords, and the output is a list of candidate smartphones.

[0974] Step 7:

[0975] The server checks the stock information of the selected model. Specifically, it sends a request to the inventory management system's API to collect the current stock status. The input is a list of candidate smartphones, and the output is stock information.

[0976] Step 8:

[0977] The server uses an emotion engine to analyze the customer's emotional state from the voice data. Specifically, the voice data is input into the emotion engine, and the emotion engine analyzes the customer's emotions, such as excitement, interest, and anxiety. The input is the voice data, and the output is the emotion analysis result.

[0978] Step 9:

[0979] The server adjusts the candidate list of optimal models based on the customer's emotional state. Specifically, based on the results of emotion analysis, models that the customer is particularly interested in are placed at the top of the list. The input is the emotion analysis results and inventory information, and the output is the adjusted candidate list.

[0980] Step 10:

[0981] The server generates a candidate list of optimal models, including the recommended points for each model. Specifically, it lists the recommended points that explain the features of each model along with the collected inventory information. The input is the adjusted candidate list and inventory information, and the output is the final candidate list.

[0982] Step 11:

[0983] The terminal displays the generated candidate list in a visually easy-to-understand format. Specifically, it provides an interface that allows the crew (user) to refer to the list and displays it to the customer. The input is the final candidate list, and the output is display information that can be visually confirmed by the crew and customer.

[0984] (Application example 2)

[0985] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0986] While conventional systems can suggest the appropriate smartphone based on customer needs, they are unable to take customer emotions into consideration when making suggestions, which means they are unable to sufficiently improve customer satisfaction. Furthermore, there is a lack of an effective means for analyzing conversations in real time and quickly providing a list of optimal models.

[0987] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0988] In this invention, the server includes means for acquiring a conversation between a crew member and a customer as voice input, means for transmitting the acquired voice data to the server, means for converting the voice data into text data on the server, means for analyzing the customer's preferences and requests from the text data, means for selecting an optimal model based on the analysis results, means for checking inventory information for the selected model, means for generating a candidate list of optimal models, means for displaying the candidate list on a terminal, means for analyzing the customer's emotions and adjusting the candidate list of optimal models based on the emotions, and means for analyzing the conversation in real time and visually presenting the results. This makes it possible to recommend the optimal smartphone in real time while taking the customer's emotions into consideration, thereby increasing customer satisfaction.

[0989] "Means for acquiring conversations between staff and customers as audio input" refers to a device or method for recording conversations between staff and customers using an audio input device such as a microphone and acquiring the audio data.

[0990] The "means for transmitting acquired voice data to a server" refers to a communication means or protocol for transferring voice data acquired by a voice input device to a remote server via the Internet or a local network.

[0991] "Means for converting voice data into text data on a server" refers to the process and device that converts transmitted voice data into text format using voice recognition software or an API.

[0992] "Means for analyzing customer interests and needs from text data" refers to algorithms and software that analyze text data using natural language processing (NLP) to identify customer interests and needs.

[0993] The "means for selecting the optimal model based on the analysis results" refers to a database query and selection algorithm for selecting the optimal smartphone model based on customer requirements extracted by text data analysis.

[0994] The "means for checking stock information for the selected model" refers to an API or protocol that works with an inventory management system to check the stock status of the selected smartphone model.

[0995] The "means for generating a candidate list of optimal models" is software for generating a candidate list including the features and recommended points of smartphone models that have been selected and stock confirmed.

[0996] The "means for displaying the candidate list on the terminal" refers to a display screen or application for visually presenting the generated smartphone model candidate list to the user.

[0997] "Means for analyzing customer sentiment and adjusting a candidate list of optimal models based on the sentiment" refers to algorithms and software that analyze sentiment from customer voice data and dynamically sort or filter the candidate list according to the sentiment.

[0998] "Means for analyzing conversations in real time and providing the results visually" refers to technology and applications for analyzing conversations between crew members and customers in real time and displaying the results on a screen in a timely manner.

[0999] This invention is a system that acquires voice input from conversations between crew members and customers, combines it with emotion analysis, and proposes the most suitable smartphone. This system is mainly built by combining a voice input device, a server, a terminal, and various APIs.

[1000] First, the conversation between the crew and the customer is captured using a voice input device, i.e., a smartphone microphone. High-quality audio data (e.g., WAV or MP3 format) is captured in real time and sent to a server via HTTPS protocol. This process is performed using a data communication method.

[1001] The server uses speech recognition software such as the Google Cloud Speech-to-Text API to convert the received voice data into text data. This converted text data is preprocessed on the server to remove spaces and line breaks and normalize the sentences. The preprocessed text data is then input into a natural language processing (NLP) model to extract customer preferences and requirements (e.g., "camera performance," "battery life," etc.).

[1002] Furthermore, the server uses an emotion recognition engine to analyze the customer's emotional state from the text data. The text data is used to identify emotional situations such as "the customer is interested" or "the customer is anxious." Based on the results of this emotion analysis, the candidate list of optimal models is adjusted.

[1003] The server then executes a database query based on the extracted keywords and the results of sentiment analysis to generate a list of smartphones that meet the customer's needs. After generating the list, it connects with an inventory management system to check stock information and confirm the availability of the most suitable models. Finally, a list of recommended models that meet criteria such as "high-performance camera" or "high battery capacity" is generated and displayed on the device.

[1004] The device presents the user with a list of smartphones in a visually easy-to-understand format. The crew then uses the list to explain the features of suitable smartphones to the customer and helps them make a purchasing decision. The crew can also dynamically update the recommended smartphone models based on the customer's real-time conversation analysis and emotional feedback.

[1005] As a specific example, for a customer who enjoys traveling and places importance on camera performance, the system will capture the customer's conversation through the smartphone's microphone, analyze their emotions, and then recommend the most suitable smartphone, such as the ``iPhone 14 Pro - High-Performance Camera and Night Mode.''

[1006] Here are some examples of prompts to input to the generative AI model:

[1007] "For a customer who enjoys traveling and prioritizes camera performance, capture their conversation through the smartphone's microphone, analyze their emotions, and then recommend the best smartphone for them."

[1008] By implementing this system, it will be possible to take into account customer emotions and make optimal smartphone recommendations in real time, thereby improving customer satisfaction.

[1009] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1010] Step 1:

[1011] Capture conversations between crew and customers as voice input.

[1012] (Specific actions)

[1013] The device (smartphone) uses a microphone to record conversations in real time.

[1014] (input)

[1015] Audio data

[1016] (output)

[1017] Recorded audio files (high quality formats, e.g. WAV, MP3)

[1018] Step 2:

[1019] The acquired voice data is sent to the server.

[1020] (Specific actions)

[1021] The device stores the audio file in temporary memory and uploads it to the server's speech recognition processing endpoint using the HTTPS protocol.

[1022] (input)

[1023] Audio files

[1024] (output)

[1025] Uploading audio files to the server

[1026] Step 3:

[1027] The voice data is converted into text data on the server.

[1028] (Specific actions)

[1029] The server sends the received audio file to the Google Cloud Speech-to-Text API, which automatically converts it into text data.

[1030] (input)

[1031] Audio files

[1032] (output)

[1033] Converted text data

[1034] Step 4:

[1035] Preprocess text data.

[1036] (Specific actions)

[1037] The server performs preprocessing on the text data, such as removing spaces and line breaks and normalizing the text.

[1038] (input)

[1039] Converted text data

[1040] (output)

[1041] Preprocessed text data

[1042] Step 5:

[1043] Analyze customer interests and requests from text data.

[1044] (Specific actions)

[1045] The server inputs the preprocessed text data into an NLP model, which uses machine learning algorithms to extract keywords (e.g., "camera performance," "battery life," etc.).

[1046] (input)

[1047] Preprocessed text data

[1048] (output)

[1049] Extracted keywords

[1050] Step 6:

[1051] Analyze customer sentiment.

[1052] (Specific actions)

[1053] The server inputs the converted text data into an emotion analysis engine, which identifies the customer's emotional state based on the voice data.

[1054] (input)

[1055] Preprocessed text data

[1056] (output)

[1057] Customer sentiment data

[1058] Step 7:

[1059] The optimal model is selected based on the analysis results.

[1060] (Specific actions)

[1061] The server runs a database query based on the extracted keywords and emotion data to generate a list of smartphones that meet the user's needs.

[1062] (input)

[1063] Extracted keywords and sentiment data

[1064] (output)

[1065] A list of the best models

[1066] Step 8:

[1067] Check the stock information for the selected model.

[1068] (Specific actions)

[1069] The server sends a request to the inventory management system API to check the stock status of the selected model.

[1070] (input)

[1071] A list of the best models

[1072] (output)

[1073] Suggestion list with stock information

[1074] Step 9:

[1075] Generate a list of optimal models.

[1076] (Specific actions)

[1077] The server creates a final candidate list that includes inventory and feature information.

[1078] (input)

[1079] Suggestion list with stock information

[1080] (output)

[1081] Final candidate list

[1082] Step 10:

[1083] Display the candidate list on the terminal.

[1084] (Specific actions)

[1085] The device visually displays the generated candidate list, allowing the crew to suggest the best smartphone for the customer.

[1086] (input)

[1087] Final candidate list

[1088] (output)

[1089] Candidate list displayed on device

[1090] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1091] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1092] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1093] [Fourth embodiment]

[1094] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1095] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1096] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1097] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1098] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1099] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1100] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1101] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1102] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1103] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1104] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1105] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1106] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1107] The present invention is a system that acquires voice input from conversations between crew members and customers and recommends the most suitable smartphone. This system performs processing in the following steps.

[1108] The terminal captures the conversation between the crew and the customer as voice input. A microphone installed on the terminal captures the conversation in real time and saves it as audio data. The captured audio data is sent to the server via an HTTPS request. This voice input capture step requires the terminal to have a high-performance microphone and a stable network connection in order to quickly record the conversation.

[1109] The server converts the received voice data into text data using speech recognition technology. By utilizing speech recognition services such as the Google Cloud Speech-to-Text API, speech can be converted into text with high accuracy. During this process, the quality of the voice data is checked, noise is removed, and it is converted into an appropriate format.

[1110] The converted text data is analyzed using a natural language processing (NLP) model. The server uses the NLP engine to extract customer interests and requirements from the text data. This analysis uses machine learning models and deep learning techniques to identify important keywords and phrases within the text. For example, interests and requirements such as "camera performance," "long battery life," and "gaming use" are extracted.

[1111] Based on the analysis results, the server selects the most suitable smartphone candidate from the database. The server generates a query and retrieves the corresponding model from the database. This database contains the specifications and features of a wide variety of smartphones on the market, allowing the most suitable model to be extracted quickly.

[1112] The server checks the inventory information for the selected models. The server connects to the inventory management system via API to obtain the inventory status of each candidate model. This process checks whether the model is in stock, and if not, the inventory status of nearby stores.

[1113] The server generates a list of optimal models, including recommendations for each model. This list includes specific features of each smartphone and features that match the customer's requirements. For example, "iPhone 14 Pro - high-performance camera and long battery life" or "Samsung Galaxy S21 - excellent gaming performance."

[1114] The generated candidate list is sent to the device, which displays the results in a visually easy-to-understand format to the customer. The user, the crew, then recommends the optimal model to the customer based on the displayed list. The crew explains the features of smartphones that meet the customer's requirements and supports the customer in making the final purchase decision.

[1115] In this way, the system of the present invention receives voice input, analyzes the voice data, and recommends the most suitable smartphone for the customer. By accurately understanding customer needs and making prompt and accurate recommendations, customer satisfaction can be improved and sales opportunities can be maximized. For example, for a customer whose hobby is traveling and who places importance on camera performance, a smartphone equipped with a high-performance camera can be recommended, and by checking stock availability, the system can inform the customer whether it is available for immediate purchase. This system realizes efficient sales support and improved customer satisfaction.

[1116] The processing flow will be explained below.

[1117] Step 1:

[1118] The terminal captures the conversation between the crew and the customer as audio.

[1119] When the crew and customer start talking, the device's microphone captures the audio in real time, which is then recorded in a high-quality format (such as WAV or MP3).

[1120] Step 2:

[1121] The device sends the acquired audio data to the server via an HTTPS request.

[1122] The device stores the recorded voice data in temporary memory and uploads the voice file to the server's voice recognition processing endpoint using the HTTPS protocol.

[1123] Step 3:

[1124] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API or similar.

[1125] The server then sends the received audio file to the Google Cloud Speech-to-Text API, which converts the audio data into text data, which is then returned to the server for further analysis.

[1126] Step 4:

[1127] The server preprocesses the text data.

[1128] The server performs preprocessing on the received text data, such as removing spaces and line breaks and normalizing the text, to prepare for improved analysis accuracy.

[1129] Step 5:

[1130] The server analyzes the text data using a natural language processing (NLP) model.

[1131] The server inputs the text data into an NLP model to extract customer preferences and requirements, using machine learning algorithms to extract keywords such as "camera performance" and "battery life."

[1132] Step 6:

[1133] The server selects the optimal model from the database based on the analysis results.

[1134] The server queries the database using the extracted keywords to generate a list of smartphones that match the customer's requirements, such as "high-performance camera" or "large battery capacity."

[1135] Step 7:

[1136] Check the stock information for the model for which the server has been selected.

[1137] The server sends a request to the inventory management system's API to collect the current stock status of the selected model and stock information for each store.

[1138] Step 8:

[1139] The server generates a candidate list including the recommended points of each model.

[1140] The server lists the collected inventory information along with recommended points that explain the features of each model, and creates a final candidate list to provide to customers.

[1141] Step 9:

[1142] The server transmits the generated candidate list to the terminal.

[1143] The server sends the final candidate list to the terminal in a standard data format such as JSON.

[1144] Step 10:

[1145] The device displays the candidate list on the screen.

[1146] The terminal analyzes the received data and displays it in a visually easy-to-understand format for the crew and customer, allowing the crew to explain the features and inventory information of each model to the customer and make suggestions.

[1147] This allows the system of the present invention to efficiently propose smartphones that meet the needs of customers.

[1148] Example 1

[1149] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1150] With the current sales system, it is difficult to make proposals that reflect individual customer needs in real time, and there are issues such as not being able to fully improve customer satisfaction or maximize sales opportunities.In addition, checking inventory information takes time, and appropriate product recommendations are not made smoothly.

[1151] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1152] In this invention, the server includes means for acquiring a conversation between a crew member and a customer as voice input, means for transmitting the acquired voice data as a request, means for converting the voice data into text data on the server, means for analyzing the customer's interests and requests from the text data, means for selecting an optimal mobile communication terminal based on the analysis results, means for checking inventory information for the selected mobile communication terminal, means for generating a candidate list of optimal mobile communication terminals, and means for displaying the candidate list on the terminal. This enables proposals that quickly and accurately reflect customer needs, thereby maximizing sales opportunities and improving customer satisfaction.

[1153] "Crew" refers to staff members in charge of sales and support duties.

[1154] "Customer" means a consumer who intends to purchase or use a product or service.

[1155] "Voice input" refers to conversation content acquired as voice data.

[1156] "Data" refers to information handled within a computer system, and includes various formats such as audio, text, and images.

[1157] A "server" is a computer system that provides services to clients over a network.

[1158] "Text data" is character information converted using voice recognition technology.

[1159] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[1160] A "mobile communication terminal" is a device capable of mobile communication, such as a smartphone or tablet.

[1161] "Inventory information" is data that indicates whether a product is currently available.

[1162] A "candidate list" is a list of multiple mobile communication terminals that are proposed based on the analysis results.

[1163] The present invention provides a system that acquires voice input from conversations between crew members and customers and proposes mobile communication devices that best suit the customer's needs. This system is realized by a combination of hardware and software. Specific embodiments are described below.

[1164] The device is equipped with a high-sensitivity microphone that captures the conversation between the crew and the customer as voice input in real time. The captured voice data is temporarily stored on the device and then sent to the server via an HTTPS request. During this process, the device must maintain a stable network connection.

[1165] The server converts the received voice data into text data using speech recognition technology. Specifically, it uses a speech recognition service such as Google Cloud Speech-to-Text API. The speech recognition technology converts the voice data into text with high accuracy. During this process, noise is removed and the data is converted into an appropriate format.

[1166] The converted text data is analyzed by a natural language processing (NLP) engine on the server. The NLP engine extracts customer preferences and requirements from the text data. Using a deep learning model, important keywords and phrases within the text are identified. For example, keywords such as "camera performance" and "long battery life" are extracted.

[1167] Based on the analysis results, the server selects the most suitable candidate mobile communication device from the database. The database contains the specifications and features of various mobile communication devices, and the server generates queries to access this database. As a result, devices that meet the customer's needs are quickly extracted.

[1168] The server checks the stock information of the selected devices by linking with the inventory management system, obtaining the stock status of each candidate model via API, and checking whether it is in stock and the stock status of nearby stores.

[1169] The server generates a list of suitable mobile devices, including recommendations for each device. This list includes specific features and functions that meet customer requirements, such as "models with high-performance cameras" or "models with long-life batteries."

[1170] The generated candidate list is sent to the terminal, where it is displayed in a visually easy-to-understand format. The crew, who is the user, proposes the most suitable mobile communication terminal to the customer based on the displayed list. The crew explains the features of the terminal that meet the customer's requirements and supports the final purchase decision.

[1171] For example, if a customer enjoys traveling and places importance on camera performance, the following prompt sentences could be input into the generative AI model:

[1172] "My client enjoys traveling and wants high-quality camera performance. Please suggest the best mobile device for him."

[1173] This system will enable efficient sales support and improved customer satisfaction.

[1174] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1175] Step 1:

[1176] The terminal receives the conversation between the crew and the customer as voice input. Specifically, a high-sensitivity microphone installed on the terminal captures the conversation in real time. The input is the conversation itself, and the output is generated as voice data. This voice data is temporarily stored on the terminal.

[1177] Step 2:

[1178] The device sends the captured audio data to the server via an HTTPS request. The input is the audio data stored on the device, and the output is the audio data sent to the server. During this process, the device maintains a stable network connection.

[1179] Step 3:

[1180] The server converts the received voice data into text data using speech recognition technology. Specifically, the voice data is passed as input to the Google Cloud Speech-to-Text API, and text data is obtained as output. During this process, noise is removed and the data is converted into an appropriate format.

[1181] Step 4:

[1182] The server analyzes the converted text data using a natural language processing (NLP) engine. The converted text data is given as input, and the customer's interests and requirements are extracted as output. Specifically, machine learning and deep learning models are used to identify important keywords within the text.

[1183] Step 5:

[1184] The server selects the optimal mobile communication device based on the analysis results. The analysis results are input, and a list of candidate mobile communication devices is generated as output. The server accesses the specification information of various devices in the database, generates a query, and extracts the optimal device.

[1185] Step 6:

[1186] The server checks the inventory information for the selected mobile communication devices. It receives a list of candidate mobile communication devices as input and generates a list with the inventory status as output. During this process, the server connects with the inventory management system via API to obtain the inventory status of each candidate model.

[1187] Step 7:

[1188] The server generates a list of optimal mobile communication devices, including the recommended features of each device. The input is the list of devices after checking their stock availability, and the output is a final list to be proposed to the customer. The list includes the features of each device and functions that match the customer's requirements.

[1189] Step 8:

[1190] The terminal visually displays the generated candidate list. The user, or crew member, uses this list to propose the optimal mobile communication terminal to the customer. The final candidate list is the input, and the visually displayed list is the output. The crew member provides support for the purchase, explaining in detail the features of the terminal that meets the customer's requirements.

[1191] (Application example 1)

[1192] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1193] In recent years, it has become increasingly important to quickly and accurately recommend products that customers need in physical stores. However, manually having a salesperson listen to a customer's requests and suggest the best products based on them takes time and can lead to misunderstandings. In particular, when using new interfaces such as smart glasses, an efficient system is required to display products that meet customer needs in real time. The challenge is to improve this situation and provide a system that can quickly suggest products that meet customer requirements.

[1194] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1195] In this invention, the server includes means for acquiring voice input, means for transmitting the voice data via a communication network, means for converting the voice data into text data, means for using natural language processing to analyze the customer's preferences and requests, means for selecting the most suitable device based on the analysis results, means for linking with an inventory management system to check inventory information, means for generating a candidate list of the most suitable devices, means for using a generative AI model, and means for generating prompt sentences to display the candidate list in a visually easy-to-understand format. This makes it possible to analyze customer needs in real time and quickly suggest the most suitable products.

[1196] A "crew" is a store clerk who handles customer service in a physical store.

[1197] A "customer" is someone who visits a store and intends to purchase a product.

[1198] "Audio input" refers to audio data captured using a device such as a microphone.

[1199] A "server" is a computer system that processes and analyzes audio data.

[1200] A "communications network" is an infrastructure for transmitting and receiving data.

[1201] "Audio data" refers to an acoustic signal obtained as an audio input.

[1202] "Text data" refers to character string information obtained by converting voice data.

[1203] "Natural language processing" refers to the techniques and methodologies for analyzing text data and understanding its content.

[1204] "Analysis" refers to analyzing data to extract meaning and information.

[1205] "Devices" refer to products that the system proposes to customers.

[1206] An "inventory management system" is an information system for managing product inventory status.

[1207] An "information display device" is a device that visually displays information, such as smart glasses or a display.

[1208] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to analyze data and generate optimal results.

[1209] A "prompt" is an explanation or recommendation generated by the system.

[1210] This invention is a system that analyzes conversations between crew members and customers in real time and suggests optimal products to customers. This system uses high-performance smart glasses to enable crew members to suggest optimal smartphones while serving customers.

[1211] The device uses a microphone built into the smart glasses to capture conversations between the crew and the customer in real time, and the captured audio data is transmitted to a server via a stable communication network to ensure appropriate quality at all times.

[1212] The server receives the captured voice data and converts it into text using speech recognition technology. To achieve this, it uses a speech recognition service such as Google Cloud Speech-to-Text API. The server then analyzes the text data using a natural language processing (NLP) model to extract the customer's interests and requirements. This analysis uses a generative AI model to identify key keywords and phrases based on the customer's requirements.

[1213] Based on the extracted information, the server selects the most suitable candidate device (e.g., a smartphone) from the database. At this time, the server connects to the inventory management system via API to check the inventory information of each candidate device. This allows the server to check whether the device is in stock, and if not, to check the inventory status of nearby stores.

[1214] A list of selected devices is generated based on the features of each device and the customer's requirements. This includes the process of generating prompts using a generative AI model. For example, if a customer requests a model with a high-performance camera, the model generates a prompt such as, "This model is ideal for your needs. It has a high-performance camera and excellent battery life."

[1215] This candidate list is then displayed on the smart glasses display, allowing the crew to suggest suitable smartphones to the customer in real time.

[1216] Customer: "I want a smartphone with a good camera and long battery life."

[1217] The system captures and analyzes these requirements to extract keywords such as "camera performance" and "battery life." The server queries the database and inventory system to list "models with excellent camera performance and battery life," and displays the following prompt on the smart glasses:

[1218] "Model A - High-performance camera and excellent battery life" "Model B - Outstanding camera performance and battery life"

[1219] The prompt in this example has the form:

[1220] Customer: "I want a smartphone with a good camera and long battery life."

[1221] System: "Model A - High-performance camera and excellent battery life"

[1222] System: "Model B - Outstanding camera performance and battery life"

[1223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1224] Step 1:

[1225] The terminal (smart glasses) receives voice input from a microphone during the conversation between the crew and the customer. The input is the actual conversational voice, and the output is captured as voice data. This voice data includes the customer's request.

[1226] Step 2:

[1227] The terminal transmits the acquired voice data to the server via a stable communication network. The input is the collected voice data, and the output is the voice data sent to the server. This procedure prepares the voice data for processing by the server.

[1228] Step 3:

[1229] The server converts the received voice data into text data using the Google Cloud Speech-to-Text API. The input is voice data, and the output is the converted text data. During this process, the voice data is obtained as a string, which can be analyzed later.

[1230] Step 4:

[1231] The server analyzes the text data using a natural language processing (NLP) model. The input is text data, and the output is information extracted from the customer's interests and requirements. This analysis utilizes a generative AI model to identify important keywords and phrases to fulfill the customer's requirements.

[1232] Step 5:

[1233] The server selects the optimal equipment candidates from the database based on the analysis results. The input is information extracted from the customer's requirements, and the output is a list of optimal equipment candidates. The server generates a query and executes the selection process against the database.

[1234] Step 6:

[1235] The server communicates with the inventory management system via an API to check the inventory information for the selected devices. The input is a list of candidate devices, and the output is a list of devices whose inventory has been confirmed. This process ensures that the inventory status is up-to-date.

[1236] Step 7:

[1237] The server generates a list of optimal device candidates and uses an AI model to generate prompts to present the features of each device in a visually easy-to-understand format. The input is a list of devices whose inventory has been confirmed, and the output is a final list including the prompts to be displayed.

[1238] Step 8:

[1239] The terminal displays the generated candidate list on the smart glasses display and presents it to the crew. The input is the final list including the prompt text to be displayed, and the output is the visually displayed information. Based on this information, the crew can recommend the most suitable equipment for the customer.

[1240] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1241] This invention combines an emotion engine with a system that acquires voice input from conversations between crew members and customers and recommends the most suitable smartphone. This system performs processing in the following steps.

[1242] The device receives voice input from the conversation between the crew and the customer. When the crew and the customer start talking, the device's microphone captures the voice in real time and saves it as audio data. This audio is recorded in a high-quality format (WAV, MP3, etc.).

[1243] The device sends the captured audio data to the server via an HTTPS request. The device stores the recorded audio data in temporary memory and uploads the audio file to the server's speech recognition processing endpoint using the HTTPS protocol.

[1244] The server converts the received audio data into text data using the Google Cloud Speech-to-Text API, etc. The server then sends the received audio file to the Google Cloud Speech-to-Text API, which converts the audio data into text data. The converted text is returned to the server and passed on to the next analysis step.

[1245] The server preprocesses the text data. The server performs preprocessing on the received text data, such as removing spaces and line breaks and normalizing the text, to prepare it for analysis with higher accuracy.

[1246] The server analyzes the text data using a natural language processing (NLP) model. The server then inputs the text data into the NLP model to extract customer preferences and requirements. During this process, machine learning algorithms are used to extract keywords such as "camera performance" and "battery life."

[1247] The server selects the optimal model from the database based on the analysis results. The server queries the database using the extracted keywords and generates a list of smartphones that meet the customer's requirements. For example, models that meet criteria such as "high-performance camera" and "large battery capacity" are listed.

[1248] The server checks the stock information for the selected model. The server sends a request to the inventory management system's API to collect the current stock status of the selected model and stock information for each store.

[1249] The server generates a candidate list including the recommended points for each model. The server lists the recommended points that explain the features of each model together with the collected inventory information, and forms the final candidate list to be provided to customers.

[1250] The generated candidate list is sent to the device, which displays the results in a visually easy-to-understand format to the customer. The user, the crew, then recommends the optimal model to the customer based on the displayed list. The crew explains the features of smartphones that meet the customer's requirements and supports the customer in making the final purchase decision.

[1251] The system of the present invention also incorporates an emotion engine, which analyzes the user's emotions. The server uses the emotion engine when analyzing the voice data to identify the user's emotional state. This emotion analysis makes it possible to grasp emotional situations, such as whether the customer is interested or anxious. Furthermore, the system adjusts the candidate list of optimal models based on the user's emotions. For example, if a customer not only values ​​camera performance but also shows a strong interest in it, models with particularly excellent camera performance will be placed at the top of the list.

[1252] As a specific example, for a customer who enjoys traveling and prioritizes camera performance, the device captures the conversation and the server converts the speech into text. Keywords such as "travel" and "camera performance" are extracted using an NLP model, and an emotion engine analyzes the customer's "excited voice." The server then selects a model with high camera performance and checks whether it is in stock. Finally, a list of recommended models, such as "iPhone 14 Pro - High-Performance Camera and Night Mode," can be generated and displayed on the device.

[1253] In this way, the system of the present invention utilizes voice input and emotion analysis to efficiently recommend smartphones that meet customer needs, thereby achieving higher customer satisfaction.

[1254] The processing flow will be explained below.

[1255] Step 1:

[1256] The terminal captures the conversation between the crew and the customer as audio.

[1257] A microphone installed in the terminal captures the conversation between the crew and the customer in real time, recording audio data that is saved in high-quality formats such as WAV and MP3.

[1258] Step 2:

[1259] The device sends the acquired audio data to the server via an HTTPS request.

[1260] The device uploads the recorded audio data to the server via the HTTPS protocol, where it is encrypted and securely transmitted to the server.

[1261] Step 3:

[1262] The server converts the received voice data into text data using voice recognition technology.

[1263] The server uses a speech recognition engine such as Google Cloud Speech-to-Text API to convert the audio data into text data, which is then passed on to the next step.

[1264] Step 4:

[1265] The server preprocesses the text data.

[1266] As a preprocessing step, the server removes unnecessary spaces and line breaks and normalizes the text, making the subsequent analysis process smoother.

[1267] Step 5:

[1268] The server analyzes the text data using a natural language processing (NLP) model.

[1269] The server uses natural language processing technology to extract keywords from the text data, such as "camera performance," "battery life," and "gaming use," which are related to the customer's interests and requirements.

[1270] Step 6:

[1271] The server uses an emotion engine to analyze the customer's emotions based on the analysis results.

[1272] The server uses an emotion engine to identify the customer's emotional state from the voice data and extracted keywords. For example, emotions such as "excitement" or "anxiety" can be detected from the customer's speaking style and tone.

[1273] Step 7:

[1274] The server selects the most suitable model from the database based on the analysis results and emotional information.

[1275] The server queries the database based on the keywords and the customer's emotional state, selecting smartphones that meet certain criteria, such as a high-performance camera and a long battery life.

[1276] Step 8:

[1277] Check the stock information for the model for which the server has been selected.

[1278] The server works in conjunction with the inventory management system to obtain the stock status of the selected model at the store and nearby stores via API.

[1279] Step 9:

[1280] The server generates a candidate list including recommended points based on the customer's sentiment.

[1281] The server generates a list of candidates, describing each model's recommended features and specific characteristics based on sentiment analysis, such as "This smartphone features a high-performance camera, making it ideal for your travel photos."

[1282] Step 10:

[1283] The server transmits the generated candidate list to the terminal.

[1284] The server sends the final candidate list to the terminal in JSON format or similar, so that it can be displayed on the terminal.

[1285] Step 11:

[1286] The device displays the candidate list on the screen.

[1287] The terminal analyzes the received data and displays it in a visually easy-to-understand format for the crew and customer. The crew can then explain the features of the model that best suits the customer based on the displayed list.

[1288] In this way, the system of the present invention analyzes the customer's voice and emotions, and quickly and accurately recommends the most suitable smartphone. It also enables support that is tailored to the customer's emotional state.

[1289] Example 2

[1290] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1291] Conventional smartphone recommendation systems have difficulty accurately understanding customer needs and recommending the most suitable model. They also lack the ability to take into account the customer's emotional state, resulting in lower customer satisfaction. Furthermore, there was a risk of running out of stock due to insufficient means for checking inventory information in real time.

[1292] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1293] In this invention, the server includes a means for converting voice data into text data, a means for preprocessing the text data, a means for analyzing the customer's interests and requests, a means for using an emotion engine for analyzing the customer's emotional state, and a means for adjusting a list of optimal model candidates based on the customer's emotional state. This makes it possible to accurately understand the customer's emotions and requests and to propose the optimal smartphone based on them.

[1294] "Voice input" refers to capturing conversations between crew members and customers in real time using a microphone and obtaining them as voice data.

[1295] "Voice Data" means audio information captured and stored in digital form during conversations between Crew Members and Customers.

[1296] The "server" is a central processing unit that receives, converts, analyzes, and selects the most suitable smartphone for voice data.

[1297] "Text data" is voice data converted into character information, and is data to be analyzed.

[1298] "Preprocessing" refers to data processing carried out to remove unnecessary spaces and line breaks from text data and improve the accuracy of analysis.

[1299] "Natural language processing" is a technology used to analyze customer preferences and requirements from text data, and is a process that includes machine learning algorithms.

[1300] An "emotion engine" is a technology for analyzing a customer's emotional state from voice data, and is an engine that identifies and analyzes emotions.

[1301] A "candidate list" is a list of optimal smartphones generated based on the analyzed customer's tastes, requirements, and emotional state.

[1302] "Stock information" refers to the current stock status of the selected model and stock information for each store.

[1303] A "terminal" is a device that captures conversations between crew members and customers and displays a list of candidates.

[1304] This system proposes the optimal smartphone for a customer by acquiring voice input from a conversation between a crew member and a customer, analyzing and converting the voice data. This system is composed of multiple components including voice input, voice data transmission, text data conversion and preprocessing, analysis of the customer's hobbies and requests, analysis of the customer's emotional state, selection of the optimal model, confirmation of inventory information, and generation and display of a candidate list.

[1305] First, the terminal receives the conversation between the crew and the customer as voice input. The terminal's microphone captures the voice data in real time and saves it digitally in WAV or MP3 format. This voice data is stored in the terminal's temporary memory.

[1306] The device then sends the captured audio data to the server via an HTTPS request, using a secure communications protocol to upload the audio file to the server's speech recognition processing endpoint.

[1307] The server converts the received voice data into text data using speech recognition technology such as the Google Cloud Speech-to-Text API, which is then returned to the server for further analysis.

[1308] The server preprocesses the text data, removing spaces and line breaks, normalizing the text, and so on, to improve the quality of the data.

[1309] The server then uses a natural language processing (NLP) model to analyze customer preferences and requirements from the preprocessed text data. Specifically, machine learning algorithms are used to extract keywords such as "camera performance" and "battery life."

[1310] In addition, the server uses an emotion engine to analyze the customer's emotional state from the voice data. For example, if the customer speaks with an excited voice, it will interpret this as positive interest and adjust the list accordingly.

[1311] The server selects the most suitable smartphone from a database based on the analyzed hobbies, needs, and emotional state, and then connects the selected model to an inventory management system to check the inventory information of each store.

[1312] Finally, the server generates a list of the best models, including each model's recommended features, such as specific suggestions like "a smartphone with a high-performance camera and night mode."

[1313] The generated candidate list is sent to the terminal, which displays the results in a visually easy-to-understand format. Based on this display, the crew, who are the users, can propose the most suitable model to the customer.

[1314] For example, if a customer enjoys traveling and prioritizes camera performance, the device captures the conversation and the server converts the speech into text. Keywords like "travel" and "camera performance" are extracted using an NLP model, and an emotion engine analyzes the customer's excited voice to select a model with high camera performance and check whether it is in stock. Finally, a list of recommended models, such as "iPhone 14 Pro - High-Performance Camera and Night Mode," is generated and displayed on the device.

[1315] By utilizing a generative AI model, these steps can be executed efficiently and accurately. An example of a useful prompt would be, "Design a system that analyzes voice data and recommends smartphones based on customer needs."

[1316] In this way, by combining voice input and emotion analysis, the system of the present invention can recommend the smartphone that best suits the customer's needs and increase customer satisfaction.

[1317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] The terminal receives the conversation between the crew and the customer as audio input. Specifically, it captures the audio in real time through the terminal's microphone and digitally stores it in high-quality WAV or MP3 format. The input is an audio signal, and the output is a digital audio file.

[1320] Step 2:

[1321] The device stores the captured voice data in temporary memory and sends it to the server via an HTTPS request. Specifically, the audio file is uploaded to the server's voice recognition processing endpoint using the HTTPS protocol. The input is the digital audio file, and the output is the upload status to the server via the HTTPS request.

[1322] Step 3:

[1323] The server converts the received audio data into text data using the Google Cloud Speech-to-Text API. Specifically, the audio file is sent to the API, and a machine learning algorithm converts the audio into text. The input is an audio file, and the output is text data.

[1324] Step 4:

[1325] The server preprocesses the text data it receives. Specifically, it removes spaces and line breaks, normalizes the text, etc. The input is unprocessed text data, and the output is preprocessed text data.

[1326] Step 5:

[1327] The server analyzes the preprocessed text data using a natural language processing (NLP) model. Specifically, it uses a machine learning algorithm to extract keywords such as "camera performance" and "battery life." The input is the preprocessed text data, and the output is the extracted keywords.

[1328] Step 6:

[1329] The server selects the optimal model from the database based on the analysis results. Specifically, it queries the database using the extracted keywords and generates a list of related smartphones. The input is the extracted keywords, and the output is a list of candidate smartphones.

[1330] Step 7:

[1331] The server checks the stock information of the selected model. Specifically, it sends a request to the inventory management system's API to collect the current stock status. The input is a list of candidate smartphones, and the output is stock information.

[1332] Step 8:

[1333] The server uses an emotion engine to analyze the customer's emotional state from the voice data. Specifically, the voice data is input into the emotion engine, and the emotion engine analyzes the customer's emotions, such as excitement, interest, and anxiety. The input is the voice data, and the output is the emotion analysis result.

[1334] Step 9:

[1335] The server adjusts the candidate list of optimal models based on the customer's emotional state. Specifically, based on the results of emotion analysis, models that the customer is particularly interested in are placed at the top of the list. The input is the emotion analysis results and inventory information, and the output is the adjusted candidate list.

[1336] Step 10:

[1337] The server generates a candidate list of optimal models, including the recommended points for each model. Specifically, it lists the recommended points that explain the features of each model along with the collected inventory information. The input is the adjusted candidate list and inventory information, and the output is the final candidate list.

[1338] Step 11:

[1339] The terminal displays the generated candidate list in a visually easy-to-understand format. Specifically, it provides an interface that allows the crew (user) to refer to the list and displays it to the customer. The input is the final candidate list, and the output is display information that can be visually confirmed by the crew and customer.

[1340] (Application example 2)

[1341] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1342] While conventional systems can suggest the appropriate smartphone based on customer needs, they are unable to take customer emotions into consideration when making suggestions, which means they are unable to sufficiently improve customer satisfaction. Furthermore, there is a lack of an effective means for analyzing conversations in real time and quickly providing a list of optimal models.

[1343] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1344] In this invention, the server includes means for acquiring a conversation between a crew member and a customer as voice input, means for transmitting the acquired voice data to the server, means for converting the voice data into text data on the server, means for analyzing the customer's preferences and requests from the text data, means for selecting an optimal model based on the analysis results, means for checking inventory information for the selected model, means for generating a candidate list of optimal models, means for displaying the candidate list on a terminal, means for analyzing the customer's emotions and adjusting the candidate list of optimal models based on the emotions, and means for analyzing the conversation in real time and visually presenting the results. This makes it possible to recommend the optimal smartphone in real time while taking the customer's emotions into consideration, thereby increasing customer satisfaction.

[1345] "Means for acquiring conversations between staff and customers as audio input" refers to a device or method for recording conversations between staff and customers using an audio input device such as a microphone and acquiring the audio data.

[1346] The "means for transmitting acquired voice data to a server" refers to a communication means or protocol for transferring voice data acquired by a voice input device to a remote server via the Internet or a local network.

[1347] "Means for converting voice data into text data on a server" refers to the process and device that converts transmitted voice data into text format using voice recognition software or an API.

[1348] "Means for analyzing customer interests and needs from text data" refers to algorithms and software that analyze text data using natural language processing (NLP) to identify customer interests and needs.

[1349] The "means for selecting the optimal model based on the analysis results" refers to a database query and selection algorithm for selecting the optimal smartphone model based on customer requirements extracted by text data analysis.

[1350] The "means for checking stock information for the selected model" refers to an API or protocol that works with an inventory management system to check the stock status of the selected smartphone model.

[1351] The "means for generating a candidate list of optimal models" is software for generating a candidate list including the features and recommended points of smartphone models that have been selected and stock confirmed.

[1352] The "means for displaying the candidate list on the terminal" refers to a display screen or application for visually presenting the generated smartphone model candidate list to the user.

[1353] "Means for analyzing customer sentiment and adjusting a candidate list of optimal models based on the sentiment" refers to algorithms and software that analyze sentiment from customer voice data and dynamically sort or filter the candidate list according to the sentiment.

[1354] "Means for analyzing conversations in real time and providing the results visually" refers to technology and applications for analyzing conversations between crew members and customers in real time and displaying the results on a screen in a timely manner.

[1355] This invention is a system that acquires voice input from conversations between crew members and customers, combines it with emotion analysis, and proposes the most suitable smartphone. This system is mainly built by combining a voice input device, a server, a terminal, and various APIs.

[1356] First, the conversation between the crew and the customer is captured using a voice input device, i.e., a smartphone microphone. High-quality audio data (e.g., WAV or MP3 format) is captured in real time and sent to a server via HTTPS protocol. This process is performed using a data communication method.

[1357] The server uses speech recognition software such as the Google Cloud Speech-to-Text API to convert the received voice data into text data. This converted text data is preprocessed on the server to remove spaces and line breaks and normalize the sentences. The preprocessed text data is then input into a natural language processing (NLP) model to extract customer preferences and requirements (e.g., "camera performance," "battery life," etc.).

[1358] Furthermore, the server uses an emotion recognition engine to analyze the customer's emotional state from the text data. The text data is used to identify emotional situations such as "the customer is interested" or "the customer is anxious." Based on the results of this emotion analysis, the candidate list of optimal models is adjusted.

[1359] The server then executes a database query based on the extracted keywords and the results of sentiment analysis to generate a list of smartphones that meet the customer's needs. After generating the list, it connects with an inventory management system to check stock information and confirm the availability of the most suitable models. Finally, a list of recommended models that meet criteria such as "high-performance camera" or "high battery capacity" is generated and displayed on the device.

[1360] The device presents the user with a list of smartphones in a visually easy-to-understand format. The crew then uses the list to explain the features of suitable smartphones to the customer and helps them make a purchasing decision. The crew can also dynamically update the recommended smartphone models based on the customer's real-time conversation analysis and emotional feedback.

[1361] As a specific example, for a customer who enjoys traveling and places importance on camera performance, the system will capture the customer's conversation through the smartphone's microphone, analyze their emotions, and then recommend the most suitable smartphone, such as the ``iPhone 14 Pro - High-Performance Camera and Night Mode.''

[1362] Here are some examples of prompts to input to the generative AI model:

[1363] "For a customer who enjoys traveling and prioritizes camera performance, capture their conversation through the smartphone's microphone, analyze their emotions, and then recommend the best smartphone for them."

[1364] By implementing this system, it will be possible to take into account customer emotions and make optimal smartphone recommendations in real time, thereby improving customer satisfaction.

[1365] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1366] Step 1:

[1367] Capture conversations between crew and customers as voice input.

[1368] (Specific actions)

[1369] The device (smartphone) uses a microphone to record conversations in real time.

[1370] (input)

[1371] Audio data

[1372] (output)

[1373] Recorded audio files (high quality formats, e.g. WAV, MP3)

[1374] Step 2:

[1375] The acquired voice data is sent to the server.

[1376] (Specific actions)

[1377] The device stores the audio file in temporary memory and uploads it to the server's speech recognition processing endpoint using the HTTPS protocol.

[1378] (input)

[1379] Audio files

[1380] (output)

[1381] Uploading audio files to the server

[1382] Step 3:

[1383] The voice data is converted into text data on the server.

[1384] (Specific actions)

[1385] The server sends the received audio file to the Google Cloud Speech-to-Text API, which automatically converts it into text data.

[1386] (input)

[1387] Audio files

[1388] (output)

[1389] Converted text data

[1390] Step 4:

[1391] Preprocess text data.

[1392] (Specific actions)

[1393] The server performs preprocessing on the text data, such as removing spaces and line breaks and normalizing the text.

[1394] (input)

[1395] Converted text data

[1396] (output)

[1397] Preprocessed text data

[1398] Step 5:

[1399] Analyze customer interests and requests from text data.

[1400] (Specific actions)

[1401] The server inputs the preprocessed text data into an NLP model, which uses machine learning algorithms to extract keywords (e.g., "camera performance," "battery life," etc.).

[1402] (input)

[1403] Preprocessed text data

[1404] (output)

[1405] Extracted keywords

[1406] Step 6:

[1407] Analyze customer sentiment.

[1408] (Specific actions)

[1409] The server inputs the converted text data into an emotion analysis engine, which identifies the customer's emotional state based on the voice data.

[1410] (input)

[1411] Preprocessed text data

[1412] (output)

[1413] Customer sentiment data

[1414] Step 7:

[1415] The optimal model is selected based on the analysis results.

[1416] (Specific actions)

[1417] The server runs a database query based on the extracted keywords and emotion data to generate a list of smartphones that meet the user's needs.

[1418] (input)

[1419] Extracted keywords and sentiment data

[1420] (output)

[1421] A list of the best models

[1422] Step 8:

[1423] Check the stock information for the selected model.

[1424] (Specific actions)

[1425] The server sends a request to the inventory management system API to check the stock status of the selected model.

[1426] (input)

[1427] A list of the best models

[1428] (output)

[1429] Suggestion list with stock information

[1430] Step 9:

[1431] Generate a list of optimal models.

[1432] (Specific actions)

[1433] The server creates a final candidate list that includes inventory and feature information.

[1434] (input)

[1435] Suggestion list with stock information

[1436] (output)

[1437] Final candidate list

[1438] Step 10:

[1439] Display the candidate list on the terminal.

[1440] (Specific actions)

[1441] The device visually displays the generated candidate list, allowing the crew to suggest the best smartphone for the customer.

[1442] (input)

[1443] Final candidate list

[1444] (output)

[1445] Candidate list displayed on device

[1446] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1447] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1448] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1449] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1450] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1451] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1452] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1453] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1454] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1455] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1456] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1457] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1458] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1459] 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.

[1460] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1461] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1462] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1463] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1464] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1465] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1466] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1467] The following is further disclosed regarding the above embodiment.

[1468] (Claim 1)

[1469] a means for capturing a conversation between the crew and the customer as voice input;

[1470] means for transmitting the acquired voice data to a server;

[1471] A means for converting voice data into text data on a server;

[1472] A means of analyzing customer interests and requests from text data,

[1473] A means for selecting the optimal model based on the analysis results;

[1474] A means for checking stock information for the selected model;

[1475] A means for generating a candidate list of optimal models;

[1476] The system includes means for displaying the candidate list on a terminal.

[1477] (Claim 2)

[1478] 10. The system of claim 1, wherein natural language processing is used to analyze customer preferences and requirements.

[1479] (Claim 3)

[1480] 10. The system of claim 1, which interfaces with an inventory management system to verify inventory information.

[1481] "Example 1"

[1482] (Claim 1)

[1483] a means for capturing a conversation between the crew and the customer as voice input;

[1484] means for transmitting the captured audio data in a request;

[1485] A means for converting voice data into text data on a server;

[1486] A means of analyzing customer interests and requests from text data,

[1487] means for selecting an optimal mobile communication terminal based on the analysis results;

[1488] means for checking inventory information for the selected mobile communication terminal;

[1489] means for generating a candidate list of optimal mobile communication terminals;

[1490] The system includes means for displaying the candidate list on a terminal.

[1491] (Claim 2)

[1492] 10. The system of claim 1, wherein natural language processing is used to analyze customer preferences and requirements.

[1493] (Claim 3)

[1494] 10. The system of claim 1, which interfaces with a management system to verify inventory information.

[1495] "Application Example 1"

[1496] (Claim 1)

[1497] a means for capturing a conversation between the crew and the customer as voice input;

[1498] means for transmitting the acquired voice data to a server via a communication network;

[1499] A means for converting voice data into text data on a server;

[1500] A means for using natural language processing to analyze customer preferences and requirements from text data;

[1501] A means for selecting the optimal equipment based on the analysis results;

[1502] means for interfacing with an inventory management system to check inventory information for the selected equipment;

[1503] a means for generating a candidate list of optimal devices;

[1504] The system includes means for displaying the candidate list on an information display device.

[1505] (Claim 2)

[1506] 10. The system of claim 1, wherein the system uses a generative AI model to analyze customer preferences and requirements.

[1507] (Claim 3)

[1508] 2. The system of claim 1, wherein a prompt sentence is generated to display the characteristics of the devices included in the candidate list in a visually easy-to-understand format.

[1509] "Example 2: Combining Emotion Engines"

[1510] (Claim 1)

[1511] a means for capturing a conversation between the crew and the customer as voice input;

[1512] means for transmitting the acquired voice data to a server;

[1513] A means for converting voice data into text data on a server;

[1514] means for preprocessing text data;

[1515] A means of analyzing customer interests and requests from text data,

[1516] A means for selecting the optimal model based on the analysis results;

[1517] A means for checking stock information for the selected model;

[1518] a means for using an emotion engine to analyze the emotional state of the customer;

[1519] A means for adjusting a shortlist of optimal models based on the emotional state of the customer;

[1520] A means for generating a candidate list of optimal models;

[1521] The system includes means for displaying the candidate list on a terminal.

[1522] (Claim 2)

[1523] 10. The system of claim 1, wherein natural language processing is used to analyze customer preferences and requirements.

[1524] (Claim 3)

[1525] 10. The system of claim 1, which interfaces with an inventory management system to verify inventory information.

[1526] "Application example 2 when combining emotion engines"

[1527] (Claim 1)

[1528] a means for capturing a conversation between the crew and the customer as voice input;

[1529] means for transmitting the acquired voice data to a server;

[1530] A means for converting voice data into text data on a server;

[1531] A means of analyzing customer interests and requests from text data,

[1532] A means for selecting the optimal model based on the analysis results;

[1533] A means for checking stock information for the selected model;

[1534] A means for generating a candidate list of optimal models;

[1535] a means for displaying the candidate list on a terminal;

[1536] A means of analyzing customer sentiment and adjusting the best model shortlist based on that sentiment;

[1537] A means of analyzing conversations in real time and providing visual results,

[1538] A system including:

[1539] (Claim 2)

[1540] 10. The system of claim 1, wherein natural language processing is used to analyze customer preferences and requirements.

[1541] (Claim 3)

[1542] 10. The system of claim 1, which interfaces with an inventory management system to verify inventory information. [Explanation of symbols]

[1543] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for capturing a conversation between the crew and the customer as voice input; means for transmitting the acquired voice data to a server; A means for converting voice data into text data on a server; A means of analyzing customer interests and requests from text data, A means for selecting the optimal model based on the analysis results; A means for checking stock information for the selected model; A means for generating a candidate list of optimal models; The system includes means for displaying the candidate list on a terminal.

2. 10. The system of claim 1, wherein natural language processing is used to analyze customer preferences and requirements.

3. 10. The system of claim 1, which interfaces with an inventory management system to verify inventory information.

Images