system

Abstract

We provide the system. [Solution] In conversations with customers, a voice input means for acquiring voice, A speech recognition means that converts the aforementioned speech into text data, A generative AI means for analyzing the aforementioned text data and generating response candidates, A display means for displaying the generated response candidates, A recording means for recording the aforementioned response candidates and using them for future dialogue, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In customer service, a problem is the decline in customer satisfaction caused by the variation in the quality of communication due to the skill difference among staff and the difficulty for new staff to provide appropriate responses. Also, the fact that a large amount of time and cost are required for training is a burden on the company and improvement is demanded. To improve this, means are needed to maintain the quality of responses of the entire staff above a certain level, reduce training costs, and improve work efficiency.

Means for Solving the Problems

[0005] This invention provides a system comprising a voice input means for acquiring audio during customer interactions and a voice recognition means for converting the audio into text data. Furthermore, it includes a generation AI means for analyzing the converted text data and generating appropriate response candidates, which are then provided to staff through a display means. A recording means saves the response history, which can be used for future interactions. This system allows staff to always receive appropriate assistance in their interactions, improving customer satisfaction while simultaneously reducing training time and costs.

[0006] "Voice input means" refers to a device or function that captures voice during a conversation between a user and a customer and acquires it as digital data.

[0007] "Speech recognition means" refers to a function that converts acquired speech digital data into text data, and is a technology that processes speech content as a string of characters.

[0008] "Generative AI means" refers to a technology or device that uses artificial intelligence to analyze speech or text data and generate appropriate response candidates according to the context.

[0009] "Display means" refers to a device or interface for visually presenting the generated response candidates to the user.

[0010] "Recording means" refers to a function or device for saving the content and history of responses in a dialogue in digital format for future reference and analysis. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention is a system for providing support in customer service and is implemented as follows.

[0033] The system includes a voice input mechanism that captures audio when the user interacts with a customer. The device's microphone captures the audio, collecting voice data in real time.

[0034] The terminal converts the acquired audio data into text data using speech recognition technology. This conversion process is performed by a speech-to-text engine, and the converted text is sent to the server.

[0035] When the server receives text data, it analyzes it using generative AI. This analysis includes understanding the context of the conversation and, if necessary, referencing customer profiles and past interaction records. Based on this information, the server generates optimal response candidates and provides them to the user.

[0036] The generated response options are presented to the user through the terminal's display. By viewing these, the user can select the appropriate response. Furthermore, the user can modify the response themselves, customizing it to suit the situation.

[0037] After the interaction is complete, the device records the conversation content and response results and saves them to the server. This information will be used to improve future conversation support through the recording system.

[0038] As a concrete example, consider a scenario where a user receives an inquiry from a customer regarding a product issue. The system uses speech recognition to analyze the user's voice report and displays common solutions. For example, it might suggest, "Check the power cable." The user can then respond based on these suggestions, enabling quick and efficient provision of necessary support. This facilitates smooth customer service and improves customer satisfaction.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] When a user begins a conversation with a customer, the device starts capturing the audio in real time. The voice input mechanism activates, and audio data is collected through the microphone.

[0042] Step 2:

[0043] The device converts the collected audio data into text data using speech recognition. A speech-to-text engine analyzes the audio and generates the corresponding string of characters.

[0044] Step 3:

[0045] The terminal sends the converted text data to the server. The text data is then sent to the server's analysis engine via the network.

[0046] Step 4:

[0047] The server analyzes the received text data using AI generation tools. It generates contextually appropriate response candidates while referencing the customer's profile and past interaction history.

[0048] Step 5:

[0049] The server sends back the generated response candidates to the terminal. The response candidates are provided to the terminal as data containing various options.

[0050] Step 6:

[0051] The terminal presents the received response candidates to the user through a display mechanism. Multiple response options are displayed on the screen in a user-friendly format.

[0052] Step 7:

[0053] The user selects the appropriate response from the options displayed on the device. The user reviews their selection, modifies the response as needed, and communicates it to the customer.

[0054] Step 8:

[0055] After the conversation ends, the terminal uses recording devices to save the conversation content and response history. This information is sent to a server and stored in a database that will be used for future conversations.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] The challenge is to improve customer satisfaction by providing smooth, efficient, and optimal responses during customer interactions. Furthermore, there is a need to provide a system that effectively utilizes past conversation history and allows users to flexibly select or customize responses.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes receiving means for acquiring an acoustic signal, recognition means for converting the acoustic signal into a string of characters, and generation model means for analyzing the string of characters and generating response candidates. This enables the rapid provision of appropriate responses in real time during customer interactions, improves the accuracy of responses by utilizing past dialogue history, and ensures flexibility in the user's response options.

[0061] An "acoustic signal" is a digital representation of sound waves transmitted by air vibrations.

[0062] "Receiving means" refers to a device or function for acquiring an acoustic signal, and usually includes a microphone.

[0063] "Recognition means" refers to a technology or device that converts acquired acoustic signals into strings of characters, and includes speech recognition software and algorithms.

[0064] A "string" is a sequence of characters, usually referring to sentences or text data.

[0065] "Generative model means" refers to an algorithm or system for generating response candidates based on input data, and includes generative AI and natural language processing models.

[0066] "Presentation means" refers to a device or method for providing the user with generated response candidates visually or audibly, and includes displays or speakers.

[0067] "Recording means" refers to a device or method for saving dialogue history and making it available for reference in subsequent dialogues, and includes databases and storage devices.

[0068] An "information processing device" refers to a machine or system that has a set of functions for inputting, processing, generating, and outputting data.

[0069] This invention relates to an information processing device for customer service support using speech recognition and generative AI models. The terminal uses a microphone to acquire acoustic signals of customer interaction. These acoustic signals are converted into text strings using speech recognition software such as Google® Cloud Speech-to-Text API. This converted text string is then sent to a server and analyzed by a generative AI model.

[0070] The server analyzes these strings using a natural language processing system such as OpenAI's ChatGPT model and generates appropriate response candidates. These response candidates are then forwarded to the terminal, which presents them to the user using its display.

[0071] The user can review the displayed response options and select or modify them as needed to respond to the customer. After the conversation ends, the terminal records the conversation history and response results and saves them to the server. This information can be used for future customer service.

[0072] For example, if a user receives an inquiry from a customer stating, "The product isn't working," the terminal converts the voice into text, and the server generates a suggested response such as, "Please check the product's power cable." This allows the user to provide quick and appropriate support.

[0073] Examples of prompt messages include the following:

[0074] "We have received an inquiry from a customer regarding a product malfunction. Please generate a proposed solution based on the following text: Customer inquiry: 'The product does not work when powered on. What should I do?'"

[0075] In this way, the invention aims to enable efficient customer service and improve customer satisfaction.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The user initiates a conversation with a customer, and the audio is input. The terminal acquires the audio signal through the microphone. The input is the raw audio from the customer, which the terminal converts into a digital audio signal. Specifically, the analog audio captured from the microphone is digitally processed and recorded as an audio signal on the terminal side.

[0079] Step 2:

[0080] The terminal converts the acquired acoustic signal into a string of text. The input is the digital acoustic signal acquired in the previous stage, and the output is the string data converted by speech recognition. This conversion process uses a speech recognition engine such as the Google Cloud Speech-to-Text API. The audio signal is processed, phonemes and words are identified based on the language model, and finally it is formatted as a sentence.

[0081] Step 3:

[0082] The server receives string data sent from the terminal and performs analysis. The input is converted string data sent to the server. The server analyzes the input data using a generative AI model and generates appropriate response candidates. Specifically, it uses OpenAI's ChatGPT model to understand and analyze the context of the conversation. During this process, the user's past conversation history is referenced, and responses are generated based on this contextual understanding.

[0083] Step 4:

[0084] The server sends the generated response candidates to the terminal. The input is the response candidates generated in the previous step, and the output is data transfer to the terminal. The response candidates contain specific content that should be suggested to the user and are formatted in a way that allows them to be displayed on the terminal.

[0085] Step 5:

[0086] The terminal displays the received response candidates to the user. The input is the response candidates sent from the server, and the output is visual information presented to the user. The terminal uses its display to show the response candidates in a format that the user can review and select. For example, multiple candidates may be displayed in a list format, from which the user can select the most suitable response.

[0087] Step 6:

[0088] The user responds to the customer based on the suggested responses, modifying them as needed. Input is the information displayed on the device, and output is the final voice or text response to the customer. The user can refer to response suggestions and make real-time modifications based on the specific situation.

[0089] Step 7:

[0090] After the interaction ends, the terminal records the conversation content and response results. Input consists of data generated throughout the entire interaction process, while output includes data transmission to the server and storage in the database. The recording is performed to improve future interactions and is used as user feedback and empirical data.

[0091] (Application Example 1)

[0092] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Improving the efficiency and accuracy of customer communication is a crucial challenge in today's business environment. In particular, in brick-and-mortar stores, customer interaction directly impacts revenue, requiring prompt and accurate responses. However, in reality, the quality of service varies depending on the experience and knowledge of the person handling the interaction. Therefore, there is a need for techniques to respond quickly and accurately to customer requests.

[0094] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0095] In this invention, the server includes speech recognition means for converting speech into text data, generation AI means for analyzing the text data and generating response candidates, and a display device for presenting the generated response candidates to an information processing device in real time. This makes it possible to suggest appropriate responses in real time when dealing with customers.

[0096] A "voice input means" is a device used to acquire voice during conversations with customers.

[0097] "Speech recognition means" refers to technology for converting acquired speech into text data.

[0098] "Generative AI means" refers to artificial intelligence technology that analyzes converted text data and generates response candidates.

[0099] A "display device" is an output device that presents the generated response candidates to the user.

[0100] A "recording means" is a system for recording generated response candidates and dialogue content, and for using them in subsequent dialogues.

[0101] An "information processing device" is a device that installs programs and performs information processing such as speech recognition and response generation.

[0102] "Real-time" refers to presenting processing results immediately during a conversation with the customer.

[0103] The system for realizing this invention efficiently processes voice during customer interactions and provides accurate responses. The server acquires voice data through a microphone installed in an information processing device as a voice input means. The Google Cloud Speech-to-Text API is used for speech recognition, accurately and quickly converting the acquired voice into text data.

[0104] The converted text data is sent to a server and analyzed using the OpenAI API, a generative AI tool. Here, response candidates are generated, referencing past dialogue history. These generated response candidates are displayed in real time on the information processing device's display. For example, smart glasses are used as the display, serving to visually present information to the user.

[0105] As a concrete example, if a customer asks about shoe size in a store, the employee's voice is instantly captured, and an appropriate response regarding the size is displayed on the glasses' display. This allows the employee to respond to the customer quickly. An example of a prompt is, "The customer is asking for details about the product. Please provide the most helpful information based on past conversation data." This prompt enables the generating AI to suggest an efficient and accurate response.

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The terminal uses voice input to capture the conversation between the user and the customer as audio data. Specifically, the microphone captures the signal, which is then input to the terminal as digital audio data.

[0109] Step 2:

[0110] The device uses speech recognition to convert the acquired audio data into text data. Here, the Google Cloud Speech-to-Text API is used to analyze the audio signal in real time and generate data in text format.

[0111] Step 3:

[0112] The server receives text data sent from the terminal and analyzes it using a generative AI. This involves processing the text according to its context using the OpenAI API and calculating the optimal response candidate. The input data is the content of the conversation with the customer, and the output is the response candidate.

[0113] Step 4:

[0114] The server sends back the generated response candidates to the terminal in real time. The terminal uses a display device installed in the information processing unit to visually present the response candidates to the user. For example, the message may be displayed on smart glasses.

[0115] Step 5:

[0116] Users review the displayed response options and customize them as needed to respond to customers. This allows users to respond quickly and efficiently to their target audience.

[0117] Step 6:

[0118] The terminal records the final response and dialogue log and saves it to the server. This information will serve as reference data for future interactions and contribute to improving customer service. This record includes the date and time, response content, and customer information.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] The present invention is a system comprising voice input means, voice recognition means, generation AI means, display means, recording means, and emotion engine to provide support in customer interactions.

[0121] The system collects customer speech via voice input when the user initiates a conversation with a customer. The terminal captures this voice data in real time and converts it into text data. This speech recognition process enables speech-to-text conversion.

[0122] After the audio is converted to text, the server receives this data. The server uses generative AI to analyze the text and generate response candidates suitable for customer interaction. The analysis takes into account the customer's past conversation history and current emotional state.

[0123] The emotion engine analyzes the customer's emotional state based on their voice tone and speech content. For example, it identifies emotions such as anger or anxiety and provides the results to the AI ​​generation system. Based on this analysis, response candidates are generated in a way that adapts to the customer's emotions.

[0124] The generated response options are provided to the user through the terminal's display mechanism. The user can view the options, select or modify the most appropriate response for the situation, and communicate it to the customer. This allows the user to take appropriate action that takes the other party's feelings into consideration, thereby improving customer satisfaction.

[0125] For example, if a user receives a product complaint from a customer, the emotion engine analyzes the customer's voice and detects anger. The server uses this information to generate response options that take the customer's emotions into consideration, displaying suggestions such as, "I'm sorry to hear you're upset. How can I help?" The user can then use these suggestions to respond in a way that is considerate of the customer's situation.

[0126] This system allows users to provide consistent service that takes customer emotions into account, thereby increasing customer satisfaction and improving operational efficiency.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] When a user begins a conversation with a customer, the device uses voice input to capture the customer's voice in real time. The collected voice data is temporarily stored on the device.

[0130] Step 2:

[0131] The device uses speech recognition to collect speech data and converts it into text data. Speech-to-text technology is used to transcribe the speech into text.

[0132] Step 3:

[0133] The terminal sends the converted text data to the server. This data is delivered to the server as the customer's spoken content.

[0134] Step 4:

[0135] When the server receives text data, it uses an emotion engine to analyze the information extracted from the voice and identify the customer's emotional state. Based on the voice tone and content, it categorizes the customer's emotions into categories such as "anger," "anxiety," and "happiness."

[0136] Step 5:

[0137] The AI ​​generation system is activated, and the server combines customer text data with information about the customer's emotional state to generate response candidates. The optimal response, tailored to the customer's emotions, is determined while also referencing past conversation history.

[0138] Step 6:

[0139] The server sends the generated response candidates to the terminal. The response data is then transferred to the terminal so that the user can view it.

[0140] Step 7:

[0141] The terminal uses a display mechanism to show the user the received response options. The user can select the most appropriate response from these options and confirm it on the screen.

[0142] Step 8:

[0143] The user communicates selected or adjusted responses to the customer, taking into account the customer's current emotions. The flow of the conversation is managed in a way that is emotionally adaptive.

[0144] Step 9:

[0145] After the interaction is complete, the device saves the conversation content and response history using a recording device and sends it to the server. This data is then retained and can be used for future interactions.

[0146] (Example 2)

[0147] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0148] Conventional dialogue systems have faced challenges in accurately understanding customer utterances and responding in a way that takes their emotional state into account. In particular, in situations where responses that consider customer emotions are required, simply relying on responses based on past dialogue history may be insufficient, potentially leading to decreased customer satisfaction.

[0149] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0150] In this invention, the server includes an input means, a recognition means, a generation means, a coordination means, a presentation means, a storage means, and an emotion analysis means. This enables the generation of appropriate responses according to the customer's emotional state.

[0151] "Input means" refers to a device or method for acquiring voice from a customer.

[0152] "Recognition means" refers to a device or method that converts acquired audio into textual information.

[0153] "Generation means" refers to an apparatus or method that analyzes character information and generates response candidates.

[0154] "Presentation means" refers to a device or method for displaying generated response candidates to the user.

[0155] A "memory device" is a device or method for recording generated response candidates and using them for future dialogue.

[0156] "Emotional analysis means" refers to a device or method that analyzes a customer's voice or text data to identify their emotional state.

[0157] "Adjustment means" refers to a device or method for appropriately adjusting response candidates based on a specified emotional state.

[0158] This system is designed to support customer interaction. Specifically, it acquires customer voices and analyzes them appropriately to provide users with emotionally sensitive responses. A specific embodiment is shown below.

[0159] Speech acquisition and conversion

[0160] The device uses a microphone to capture the customer's voice. This voice data is converted into text using speech recognition software. For example, services such as the Google Cloud Speech-to-Text API are used for speech recognition.

[0161] Text analysis and response generation

[0162] The server receives the converted text information and performs analysis using a generative AI model. The generative AI model used here is, for example, a general-purpose natural language processing model. During the analysis process, the server considers the customer's past conversation history and current emotional state to generate the most suitable response candidates.

[0163] Emotional analysis and response adjustment

[0164] The server identifies the customer's emotions through an emotion analysis engine and adjusts the generated response based on the information obtained. This enables appropriate responses tailored to the customer's situation.

[0165] Presentation and selection of responses

[0166] The generated response options are displayed on the device, and the user can select the most appropriate response through the on-screen interface.

[0167] Specific example

[0168] For example, if a user makes a complaint about a product, the emotion analysis engine can detect anger from the customer's tone of voice. The server can then use this information to generate an emotionally sensitive response using a generative AI model, displaying suggestions such as, "I'm sorry to hear you're upset. How can I help?"

[0169] Example of a prompt

[0170] "The customer is dissatisfied with the product and their tone of voice is angry. Refer to similar cases from past customer history and generate a response that includes an appropriate apology and proposed next steps."

[0171] This system enables users to respond in a way that appropriately considers customer emotions, leading to improved customer satisfaction and increased operational efficiency.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The device acquires the customer's voice through the microphone. The input is real-time voice data. This voice data is temporarily buffered on the device and prepared for the speech recognition process. The final output is the voice data itself.

[0175] Step 2:

[0176] The terminal uses speech recognition software to convert speech data into text information. The input data is the speech data acquired in step 1. This conversion involves, for example, using a speech recognition service to process the speech signal. The output is text data that reflects what the customer says.

[0177] Step 3:

[0178] The terminal sends the converted text data to the server. The input here is the text data generated in step 2. The terminal sends the data using a secure communication protocol. This is supplied to the server as input for subsequent analysis.

[0179] Step 4:

[0180] The server analyzes the received text data using a generating AI model. The input is the text data sent in step 3. The server performs contextual analysis and references past history to identify the customer's intent. The output is a list of candidate responses to send back to the customer.

[0181] Step 5:

[0182] The server uses an emotion analysis engine to identify the customer's emotional state. The input is the text information and voice tone from step 2. The analysis evaluates the voice pitch and word choices to assess the emotion. The output is the identified customer's emotional state.

[0183] Step 6:

[0184] The server adjusts the generated response based on the emotional state. The inputs are the candidate response from step 4 and the emotional state from step 5. The server modifies or strengthens the response to make it the most appropriate form. The output of this adjustment process is the final adjusted response.

[0185] Step 7:

[0186] The terminal displays the response received from the server to the user. The input is the adjusted response from step 6. The user looks at the displayed response and decides what to tell the customer. The output is the response selected by the user and is delivered to the customer.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0189] Traditional customer service systems struggled to analyze customers' emotions in real time during conversations and provide appropriate responses. As a result, customer service was inconsistent, making it difficult to improve customer satisfaction. Furthermore, there was insufficient support for service providers to grasp the customer's emotional state at that moment and respond accordingly.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes a voice input means for acquiring voice, a voice recognition means for converting voice into text data, and means capable of being fitted with a visual device for visually displaying the generated response candidates. This makes it possible to analyze the emotional state of a customer from their voice in real time, provide the responder with emotionally sensitive response candidates on the spot, and improve customer satisfaction.

[0192] "Voice input means" refers to a device or group of devices that acquires voice signals from a customer.

[0193] "Speech recognition means" refers to a technology that analyzes acquired speech signals and converts them into corresponding text data.

[0194] "Generating information processing means" refers to information processing technology for generating appropriate response candidates based on text data.

[0195] "Problem display means" refers to a device or method that visually displays and makes operable the generated response candidates.

[0196] "Recording means" refers to technology for saving generated response candidates and dialogue history to prepare for future reference.

[0197] "Emotional analysis means" refers to technology that analyzes and identifies a customer's emotional state from their voice or text.

[0198] "Means for attaching a visual device" refers to a technology or method that enables a user to attach a device for visually displaying response candidates or other information.

[0199] The system that realizes this invention mainly consists of a server, a terminal, and a visual device. The server includes voice input means, voice recognition means, generated information processing means, emotion analysis means, and recording means. The terminal and visual device provide response candidates in real time through task display means.

[0200] The server acquires customer voice using voice input and converts it into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text). The converted text data is analyzed by a generative AI model (e.g., OpenAI GPT) to generate appropriate response candidates. During this process, the server uses sentiment analysis tools and NLP tools (e.g., Microsoft® Azure® Text Analytics) to determine the customer's emotional state. This information is fed back to the generative AI model, which then presents an optimized response.

[0201] The terminal or visual device displays generated response options via a task display mechanism. The user reviews the provided response options through smart glasses or another visual display and selects or modifies them as needed. This system enables flexible responses that respond to customer emotions.

[0202] As a concrete example, when a customer asks a question about a product at a store counter, the server analyzes the customer's relaxed tone and uses a generative AI model to generate response options such as, "This product is the latest model and has these features in particular." These options are then displayed on smart glasses.

[0203] An example of a prompt message is: "Customer's question: 'Tell me more about this product.', Customer's emotional state: 'Relaxed', Suggest an appropriate response:"

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server acquires audio from the customer via a voice input device. The audio data is sent in real time to a speech recognition API, which converts the audio into text data. In this step, the input is the customer's voice, and the output is the corresponding text data.

[0207] Step 2:

[0208] The server inputs text data into a generated AI model, which then analyzes the customer's utterances. During the analysis, the model references the customer's past conversation history and related information to generate appropriate response candidates. The input consists of text data and past conversation history, while the output is a set of response candidates.

[0209] Step 3:

[0210] The server uses sentiment analysis tools to determine the customer's emotional state from their text data. A specific sentiment analysis algorithm is used to analyze voice tone and text content to identify the customer's emotional state. The input is text data, and the output is the estimated emotional state.

[0211] Step 4:

[0212] The server incorporates the results of sentiment analysis into the generated response candidates and selects the optimized response. The generative AI model fine-tunes multiple response candidates according to the emotional state and selects the most appropriate one. The input is the response candidates and the emotional state, and the output is the adjusted response.

[0213] Step 5:

[0214] The terminal displays the adjusted response to the user through a visual device. The user can review the displayed response and select or modify it as needed. The input is the adjusted response, and the output is the information reviewed by the user.

[0215] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0216] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0217] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0218] [Second Embodiment]

[0219] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0220] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0221] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0222] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0223] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0224] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0225] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0226] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0227] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0228] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0229] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0230] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0231] This invention is a system for providing support in customer service and is implemented as follows.

[0232] The system includes a voice input mechanism that captures audio when the user interacts with a customer. The device's microphone captures the audio, collecting voice data in real time.

[0233] The terminal converts the acquired audio data into text data using speech recognition technology. This conversion process is performed by a speech-to-text engine, and the converted text is sent to the server.

[0234] When the server receives text data, it analyzes it using generative AI. This analysis includes understanding the context of the conversation and, if necessary, referencing customer profiles and past interaction records. Based on this information, the server generates optimal response candidates and provides them to the user.

[0235] The generated response options are presented to the user through the terminal's display. By viewing these, the user can select the appropriate response. Furthermore, the user can modify the response themselves, customizing it to suit the situation.

[0236] After the interaction is complete, the device records the conversation content and response results and saves them to the server. This information will be used to improve future conversation support through the recording system.

[0237] As a concrete example, consider a scenario where a user receives an inquiry from a customer regarding a product issue. The system uses speech recognition to analyze the user's voice report and displays common solutions. For example, it might suggest, "Check the power cable." The user can then respond based on these suggestions, enabling quick and efficient provision of necessary support. This facilitates smooth customer service and improves customer satisfaction.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] When a user begins a conversation with a customer, the device starts capturing the audio in real time. The voice input mechanism activates, and audio data is collected through the microphone.

[0241] Step 2:

[0242] The device converts the collected audio data into text data using speech recognition. A speech-to-text engine analyzes the audio and generates the corresponding string of characters.

[0243] Step 3:

[0244] The terminal sends the converted text data to the server. The text data is then sent to the server's analysis engine via the network.

[0245] Step 4:

[0246] The server analyzes the received text data using AI generation tools. It generates contextually appropriate response candidates while referencing the customer's profile and past interaction history.

[0247] Step 5:

[0248] The server sends back the generated response candidates to the terminal. The response candidates are provided to the terminal as data containing various options.

[0249] Step 6:

[0250] The terminal presents the received response candidates to the user through a display mechanism. Multiple response options are displayed on the screen in a user-friendly format.

[0251] Step 7:

[0252] The user selects the appropriate response from the options displayed on the device. The user reviews their selection, modifies the response as needed, and communicates it to the customer.

[0253] Step 8:

[0254] After the conversation ends, the terminal uses recording devices to save the conversation content and response history. This information is sent to a server and stored in a database that will be used for future conversations.

[0255] (Example 1)

[0256] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0257] The challenge is to improve customer satisfaction by providing smooth, efficient, and optimal responses during customer interactions. Furthermore, there is a need to provide a system that effectively utilizes past conversation history and allows users to flexibly select or customize responses.

[0258] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0259] In this invention, the server includes receiving means for acquiring an acoustic signal, recognition means for converting the acoustic signal into a string of characters, and generation model means for analyzing the string of characters and generating response candidates. This enables the rapid provision of appropriate responses in real time during customer interactions, improves the accuracy of responses by utilizing past dialogue history, and ensures flexibility in the user's response options.

[0260] An "acoustic signal" is a digital representation of sound waves transmitted by air vibrations.

[0261] "Receiving means" refers to a device or function for acquiring an acoustic signal, and usually includes a microphone.

[0262] "Recognition means" refers to a technology or device that converts acquired acoustic signals into strings of characters, and includes speech recognition software and algorithms.

[0263] A "string" is a sequence of characters, usually referring to sentences or text data.

[0264] "Generative model means" refers to an algorithm or system for generating response candidates based on input data, and includes generative AI and natural language processing models.

[0265] "Presentation means" refers to a device or method for providing the user with generated response candidates visually or audibly, and includes displays or speakers.

[0266] "Recording means" refers to a device or method for saving dialogue history and making it available for reference in subsequent dialogues, and includes databases and storage devices.

[0267] An "information processing device" refers to a machine or system that has a set of functions for inputting, processing, generating, and outputting data.

[0268] This invention relates to an information processing device for customer service support using speech recognition and generative AI models. The terminal uses a microphone to acquire acoustic signals of customer interaction. These acoustic signals are converted into text strings using speech recognition software such as the Google Cloud Speech-to-Text API. This converted text string is then sent to a server and analyzed by a generative AI model.

[0269] The server analyzes these strings using a natural language processing system such as OpenAI's ChatGPT model and generates appropriate response candidates. These response candidates are then sent to the terminal, which presents them to the user using its display.

[0270] The user can review the displayed response options and select or modify them as needed to respond to the customer. After the conversation ends, the terminal records the conversation history and response results and saves them to the server. This information can be used for future customer service.

[0271] For example, if a user receives an inquiry from a customer stating, "The product isn't working," the terminal converts the voice into text, and the server generates a suggested response such as, "Please check the product's power cable." This allows the user to provide quick and appropriate support.

[0272] Examples of prompt messages include the following:

[0273] "We have received an inquiry from a customer regarding a product malfunction. Please generate a proposed solution based on the following text: Customer inquiry: 'The product does not work when powered on. What should I do?'"

[0274] In this way, the invention aims to enable efficient customer service and improve customer satisfaction.

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The user initiates a conversation with a customer, and the audio is input. The terminal acquires the audio signal through the microphone. The input is the raw audio from the customer, which the terminal converts into a digital audio signal. Specifically, the analog audio captured from the microphone is digitally processed and recorded as an audio signal on the terminal side.

[0278] Step 2:

[0279] The terminal converts the acquired acoustic signal into a string of text. The input is the digital acoustic signal acquired in the previous stage, and the output is the string data converted by speech recognition. This conversion process uses a speech recognition engine such as the Google Cloud Speech-to-Text API. The audio signal is processed, phonemes and words are identified based on the language model, and finally it is formatted as a sentence.

[0280] Step 3:

[0281] The server receives the string data sent from the terminal and performs analysis. As input, the converted string data is sent to the server. The server analyzes the input data using a generative AI model and generates appropriate response candidates. Specifically, the ChatGPT model of OpenAI is used to understand the context of the conversation and perform the analysis. In this process, the user's past conversation history is referred to, and a response is generated based on the context understanding.

[0282] Step 4:

[0283] The server sends the generated response candidates to the terminal. The input is the response candidates generated in the previous step, and the output is the data transfer to the terminal. The response candidates include the specific content to be proposed to the user and are formatted into a form for display on the terminal.

[0284] Step 5:

[0285] The terminal displays the received response candidates to the user. The input is the response candidates sent from the server, and the output is the visual information presented to the user. The terminal uses a display to display the response candidates in a form that the user can confirm and select. As a specific example, multiple candidates are displayed in a list form, and the user can select the optimal response from them.

[0286] Step 6:

[0287] The user replies to the customer based on the presented response and modifies the response as needed. The input is the display information on the terminal, and the output is the final voice or text response to the customer. The user can make real-time modifications according to the specific situation while referring to the response candidates.

[0288] Step 7:

[0289] After the interaction ends, the terminal records the conversation content and response results. Input consists of data generated throughout the entire interaction process, while output includes data transmission to the server and storage in the database. The recording is performed to improve future interactions and is used as user feedback and empirical data.

[0290] (Application Example 1)

[0291] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0292] Improving the efficiency and accuracy of customer communication is a crucial challenge in today's business environment. In particular, in brick-and-mortar stores, customer interaction directly impacts revenue, requiring prompt and accurate responses. However, in reality, the quality of service varies depending on the experience and knowledge of the person handling the interaction. Therefore, there is a need for techniques to respond quickly and accurately to customer requests.

[0293] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0294] In this invention, the server includes speech recognition means for converting speech into text data, generation AI means for analyzing the text data and generating response candidates, and a display device for presenting the generated response candidates to an information processing device in real time. This makes it possible to suggest appropriate responses in real time when dealing with customers.

[0295] A "voice input means" is a device used to acquire voice during conversations with customers.

[0296] "Speech recognition means" refers to technology for converting acquired speech into text data.

[0297] "Generative AI means" refers to artificial intelligence technology that analyzes converted text data and generates response candidates.

[0298] A "display device" is an output device that presents the generated response candidates to the user.

[0299] A "recording means" is a system for recording generated response candidates and dialogue content, and for using them in subsequent dialogues.

[0300] An "information processing device" is a device that installs programs and performs information processing such as speech recognition and response generation.

[0301] "Real-time" refers to presenting processing results immediately during a conversation with the customer.

[0302] The system for realizing this invention efficiently processes voice during customer interactions and provides accurate responses. The server acquires voice data through a microphone installed in an information processing device as a voice input means. The Google Cloud Speech-to-Text API is used for speech recognition, accurately and quickly converting the acquired voice into text data.

[0303] The converted text data is sent to a server and analyzed using the OpenAI API, a generative AI tool. Here, response candidates are generated, referencing past dialogue history. These generated response candidates are displayed in real time on the information processing device's display. For example, smart glasses are used as the display, serving to visually present information to the user.

[0304] As a concrete example, if a customer asks about shoe size in a store, the employee's voice is instantly captured, and an appropriate response regarding the size is displayed on the glasses' display. This allows the employee to respond to the customer quickly. An example of a prompt is, "The customer is asking for details about the product. Please provide the most helpful information based on past conversation data." This prompt enables the generating AI to suggest an efficient and accurate response.

[0305] The flow of the specific process in Application Example 1 will be described with reference to FIG. 12.

[0306] Step 1:

[0307] The terminal uses the voice input means to acquire the conversation between the user and the customer as voice data. Specifically, the microphone captures the signal and inputs it into the terminal as digital voice data.

[0308] Step 2:

[0309] The terminal uses voice recognition means to convert the acquired voice data into text data. Here, the Google Cloud Speech-to-Text API is utilized to analyze the voice signal in real time and generate data in text format.

[0310] Step 3:

[0311] The server receives the text data transmitted from the terminal and analyzes it by means of the generation AI. This includes the process of using the OpenAI API to process the text according to the context and calculate the optimal response candidates. The input data is the content of the conversation with the customer, and response candidates are generated as output.

[0312] Step 4:

[0313] The server sends the generated response candidates back to the terminal in real time. The terminal uses the display device installed in the information processing device to visually present the response candidates to the user. As an example, a message is displayed on smart glasses.

[0314] Step 5:

[0315] The user checks the displayed response candidates and, if necessary, customizes them to respond to the customer. Thereby, the user can quickly and efficiently take appropriate actions according to the target.

[0316] Step 6:

[0317] The terminal records the final response and dialogue log and saves it to the server. This information will serve as reference data for future interactions and contribute to improving customer service. This record includes the date and time, response content, and customer information.

[0318] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0319] The present invention is a system comprising voice input means, voice recognition means, generation AI means, display means, recording means, and emotion engine to provide support in customer interactions.

[0320] The system collects customer speech via voice input when the user initiates a conversation with a customer. The terminal captures this voice data in real time and converts it into text data. This speech recognition process enables speech-to-text conversion.

[0321] After the audio is converted to text, the server receives this data. The server uses generative AI to analyze the text and generate response candidates suitable for customer interaction. The analysis takes into account the customer's past conversation history and current emotional state.

[0322] The emotion engine analyzes the customer's emotional state based on their voice tone and speech content. For example, it identifies emotions such as anger or anxiety and provides the results to the AI ​​generation system. Based on this analysis, response candidates are generated in a way that adapts to the customer's emotions.

[0323] The generated response options are provided to the user through the terminal's display mechanism. The user can view the options, select or modify the most appropriate response for the situation, and communicate it to the customer. This allows the user to take appropriate action that takes the other party's feelings into consideration, thereby improving customer satisfaction.

[0324] For example, if a user receives a product complaint from a customer, the emotion engine analyzes the customer's voice and detects anger. The server uses this information to generate response options that take the customer's emotions into consideration, displaying suggestions such as, "I'm sorry to hear you're upset. How can I help?" The user can then use these suggestions to respond in a way that is considerate of the customer's situation.

[0325] This system allows users to provide consistent service that takes customer emotions into account, thereby increasing customer satisfaction and improving operational efficiency.

[0326] The following describes the processing flow.

[0327] Step 1:

[0328] When a user begins a conversation with a customer, the device uses voice input to capture the customer's voice in real time. The collected voice data is temporarily stored on the device.

[0329] Step 2:

[0330] The device uses speech recognition to collect speech data and converts it into text data. Speech-to-text technology is used to transcribe the speech into text.

[0331] Step 3:

[0332] The terminal sends the converted text data to the server. This data is delivered to the server as the customer's spoken content.

[0333] Step 4:

[0334] When the server receives text data, it uses an emotion engine to analyze the information extracted from the voice and identify the customer's emotional state. Based on the voice tone and content, it categorizes the customer's emotions into categories such as "anger," "anxiety," and "happiness."

[0335] Step 5:

[0336] The AI ​​generation system is activated, and the server combines customer text data with information about the customer's emotional state to generate response candidates. The optimal response, tailored to the customer's emotions, is determined while also referencing past conversation history.

[0337] Step 6:

[0338] The server sends the generated response candidates to the terminal. The response data is then transferred to the terminal so that the user can view it.

[0339] Step 7:

[0340] The terminal uses a display mechanism to show the user the received response options. The user can select the most appropriate response from these options and confirm it on the screen.

[0341] Step 8:

[0342] The user communicates selected or adjusted responses to the customer, taking into account the customer's current emotions. The flow of the conversation is managed in a way that is emotionally adaptive.

[0343] Step 9:

[0344] After the interaction is complete, the device saves the conversation content and response history using a recording device and sends it to the server. This data is then retained and can be used for future interactions.

[0345] (Example 2)

[0346] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0347] Conventional dialogue systems have faced challenges in accurately understanding customer utterances and responding in a way that takes their emotional state into account. In particular, in situations where responses that consider customer emotions are required, simply relying on responses based on past dialogue history may be insufficient, potentially leading to decreased customer satisfaction.

[0348] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0349] In this invention, the server includes an input means, a recognition means, a generation means, a coordination means, a presentation means, a storage means, and an emotion analysis means. This enables the generation of appropriate responses according to the customer's emotional state.

[0350] "Input means" refers to a device or method for acquiring voice from a customer.

[0351] "Recognition means" refers to a device or method that converts acquired audio into textual information.

[0352] "Generation means" refers to an apparatus or method that analyzes character information and generates response candidates.

[0353] "Presentation means" refers to a device or method for displaying generated response candidates to the user.

[0354] A "memory device" is a device or method for recording generated response candidates and using them for future dialogue.

[0355] "Emotional analysis means" refers to a device or method that analyzes a customer's voice or text data to identify their emotional state.

[0356] "Adjustment means" refers to a device or method for appropriately adjusting response candidates based on a specified emotional state.

[0357] This system is designed to support customer interaction. Specifically, it acquires customer voices and analyzes them appropriately to provide users with emotionally sensitive responses. A specific embodiment is shown below.

[0358] Speech acquisition and conversion

[0359] The device uses a microphone to capture the customer's voice. This voice data is converted into text using speech recognition software. For example, services such as the Google Cloud Speech-to-Text API are used for speech recognition.

[0360] Text analysis and response generation

[0361] The server receives the converted text information and performs analysis using a generative AI model. The generative AI model used here is, for example, a general-purpose natural language processing model. During the analysis process, the server considers the customer's past conversation history and current emotional state to generate the most suitable response candidates.

[0362] Emotional analysis and response adjustment

[0363] The server identifies the customer's emotions through an emotion analysis engine and adjusts the generated response based on the information obtained. This enables appropriate responses tailored to the customer's situation.

[0364] Presentation and selection of responses

[0365] The generated response options are displayed on the device, and the user can select the most appropriate response through the on-screen interface.

[0366] Specific example

[0367] For example, if a user makes a complaint about a product, the emotion analysis engine can detect anger from the customer's tone of voice. The server can then use this information to generate an emotionally sensitive response using a generative AI model, displaying suggestions such as, "I'm sorry to hear you're upset. How can I help?"

[0368] Example of a prompt

[0369] "The customer is dissatisfied with the product and their tone of voice is angry. Refer to similar cases from past customer history and generate a response that includes an appropriate apology and proposed next steps."

[0370] This system enables users to respond in a way that appropriately considers customer emotions, leading to improved customer satisfaction and increased operational efficiency.

[0371] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0372] Step 1:

[0373] The device acquires the customer's voice through the microphone. The input is real-time voice data. This voice data is temporarily buffered on the device and prepared for the speech recognition process. The final output is the voice data itself.

[0374] Step 2:

[0375] The terminal uses speech recognition software to convert speech data into text information. The input data is the speech data acquired in step 1. This conversion involves, for example, using a speech recognition service to process the speech signal. The output is text data that reflects what the customer says.

[0376] Step 3:

[0377] The terminal sends the converted text data to the server. The input here is the text data generated in step 2. The terminal sends the data using a secure communication protocol. This is supplied to the server as input for subsequent analysis.

[0378] Step 4:

[0379] The server analyzes the received text data using a generating AI model. The input is the text data sent in step 3. The server performs contextual analysis and references past history to identify the customer's intent. The output is a list of candidate responses to send back to the customer.

[0380] Step 5:

[0381] The server uses an emotion analysis engine to identify the customer's emotional state. The input is the text information and voice tone from step 2. The analysis evaluates the voice pitch and word choices to assess the emotion. The output is the identified customer's emotional state.

[0382] Step 6:

[0383] The server adjusts the generated response based on the emotional state. The inputs are the candidate response from step 4 and the emotional state from step 5. The server modifies or strengthens the response to make it the most appropriate form. The output of this adjustment process is the final adjusted response.

[0384] Step 7:

[0385] The terminal displays the response received from the server to the user. The input is the adjusted response from step 6. The user looks at the displayed response and decides what to tell the customer. The output is the response selected by the user and is delivered to the customer.

[0386] (Application Example 2)

[0387] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0388] Traditional customer service systems struggled to analyze customers' emotions in real time during conversations and provide appropriate responses. As a result, customer service was inconsistent, making it difficult to improve customer satisfaction. Furthermore, there was insufficient support for service providers to grasp the customer's emotional state at that moment and respond accordingly.

[0389] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0390] In this invention, the server includes a voice input means for acquiring voice, a voice recognition means for converting voice into text data, and means capable of being fitted with a visual device for visually displaying the generated response candidates. This makes it possible to analyze the emotional state of a customer from their voice in real time, provide the responder with emotionally sensitive response candidates on the spot, and improve customer satisfaction.

[0391] "Voice input means" refers to a device or group of devices that acquires voice signals from a customer.

[0392] "Speech recognition means" refers to a technology that analyzes acquired speech signals and converts them into corresponding text data.

[0393] "Generating information processing means" refers to information processing technology for generating appropriate response candidates based on text data.

[0394] "Problem display means" refers to a device or method that visually displays and makes operable the generated response candidates.

[0395] "Recording means" refers to technology for saving generated response candidates and dialogue history to prepare for future reference.

[0396] "Emotional analysis means" refers to technology that analyzes and identifies a customer's emotional state from their voice or text.

[0397] "Means for attaching a visual device" refers to a technology or method that enables a user to attach a device for visually displaying response candidates or other information.

[0398] The system that realizes this invention mainly consists of a server, a terminal, and a visual device. The server includes voice input means, voice recognition means, generated information processing means, emotion analysis means, and recording means. The terminal and visual device provide response candidates in real time through task display means.

[0399] The server acquires customer voice using voice input and converts it into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text). The converted text data is analyzed by a generative AI model (e.g., OpenAI GPT) to generate appropriate response candidates. During this process, the server uses sentiment analysis tools and NLP tools (e.g., Microsoft Azure Text Analytics) to determine the customer's emotional state. This information is fed back to the generative AI model, which then presents an optimized response.

[0400] The terminal or visual device displays generated response options via a task display mechanism. The user reviews the provided response options through smart glasses or another visual display and selects or modifies them as needed. This system enables flexible responses that respond to customer emotions.

[0401] As a concrete example, when a customer asks a question about a product at a store counter, the server analyzes the customer's relaxed tone and uses a generative AI model to generate response options such as, "This product is the latest model and has these features in particular." These options are then displayed on smart glasses.

[0402] An example of a prompt message is: "Customer's question: 'Tell me more about this product.', Customer's emotional state: 'Relaxed', Suggest an appropriate response:"

[0403] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0404] Step 1:

[0405] The server acquires audio from the customer via a voice input device. The audio data is sent in real time to a speech recognition API, which converts the audio into text data. In this step, the input is the customer's voice, and the output is the corresponding text data.

[0406] Step 2:

[0407] The server inputs text data into a generated AI model, which then analyzes the customer's utterances. During the analysis, the model references the customer's past conversation history and related information to generate appropriate response candidates. The input consists of text data and past conversation history, while the output is a set of response candidates.

[0408] Step 3:

[0409] The server uses sentiment analysis tools to determine the customer's emotional state from their text data. A specific sentiment analysis algorithm is used to analyze voice tone and text content to identify the customer's emotional state. The input is text data, and the output is the estimated emotional state.

[0410] Step 4:

[0411] The server incorporates the results of sentiment analysis into the generated response candidates and selects the optimized response. The generative AI model fine-tunes multiple response candidates according to the emotional state and selects the most appropriate one. The input is the response candidates and the emotional state, and the output is the adjusted response.

[0412] Step 5:

[0413] The terminal displays the adjusted response to the user through a visual device. The user can review the displayed response and select or modify it as needed. The input is the adjusted response, and the output is the information reviewed by the user.

[0414] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0415] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0416] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0417] [Third Embodiment]

[0418] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0419] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0420] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0421] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0422] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0423] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0424] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0425] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0426] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0427] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0428] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0429] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0430] This invention is a system for providing support in customer service and is implemented as follows.

[0431] The system includes a voice input mechanism that captures audio when the user interacts with a customer. The device's microphone captures the audio, collecting voice data in real time.

[0432] The terminal converts the acquired audio data into text data using speech recognition technology. This conversion process is performed by a speech-to-text engine, and the converted text is sent to the server.

[0433] When the server receives text data, it analyzes it using generative AI. This analysis includes understanding the context of the conversation and, if necessary, referencing customer profiles and past interaction records. Based on this information, the server generates optimal response candidates and provides them to the user.

[0434] The generated response options are presented to the user through the terminal's display. By viewing these, the user can select the appropriate response. Furthermore, the user can modify the response themselves, customizing it to suit the situation.

[0435] After the interaction is complete, the device records the conversation content and response results and saves them to the server. This information will be used to improve future conversation support through the recording system.

[0436] As a concrete example, consider a scenario where a user receives an inquiry from a customer regarding a product issue. The system uses speech recognition to analyze the user's voice report and displays common solutions. For example, it might suggest, "Check the power cable." The user can then respond based on these suggestions, enabling quick and efficient provision of necessary support. This facilitates smooth customer service and improves customer satisfaction.

[0437] The following describes the processing flow.

[0438] Step 1:

[0439] When a user begins a conversation with a customer, the device starts capturing the audio in real time. The voice input mechanism activates, and audio data is collected through the microphone.

[0440] Step 2:

[0441] The device converts the collected audio data into text data using speech recognition. A speech-to-text engine analyzes the audio and generates the corresponding string of characters.

[0442] Step 3:

[0443] The terminal sends the converted text data to the server. The text data is then sent to the server's analysis engine via the network.

[0444] Step 4:

[0445] The server analyzes the received text data using AI generation tools. It generates contextually appropriate response candidates while referencing the customer's profile and past interaction history.

[0446] Step 5:

[0447] The server sends back the generated response candidates to the terminal. The response candidates are provided to the terminal as data containing various options.

[0448] Step 6:

[0449] The terminal presents the received response candidates to the user through a display mechanism. Multiple response options are displayed on the screen in a user-friendly format.

[0450] Step 7:

[0451] The user selects the appropriate response from the options displayed on the device. The user reviews their selection, modifies the response as needed, and communicates it to the customer.

[0452] Step 8:

[0453] After the conversation ends, the terminal uses recording devices to save the conversation content and response history. This information is sent to a server and stored in a database that will be used for future conversations.

[0454] (Example 1)

[0455] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0456] The challenge is to improve customer satisfaction by providing smooth, efficient, and optimal responses during customer interactions. Furthermore, there is a need to provide a system that effectively utilizes past conversation history and allows users to flexibly select or customize responses.

[0457] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0458] In this invention, the server includes receiving means for acquiring an acoustic signal, recognition means for converting the acoustic signal into a string of characters, and generation model means for analyzing the string of characters and generating response candidates. This enables the rapid provision of appropriate responses in real time during customer interactions, improves the accuracy of responses by utilizing past dialogue history, and ensures flexibility in the user's response options.

[0459] An "acoustic signal" is a digital representation of sound waves transmitted by air vibrations.

[0460] "Receiving means" refers to a device or function for acquiring an acoustic signal, and usually includes a microphone.

[0461] "Recognition means" refers to a technology or device that converts acquired acoustic signals into strings of characters, and includes speech recognition software and algorithms.

[0462] A "string" is a sequence of characters, usually referring to sentences or text data.

[0463] "Generative model means" refers to an algorithm or system for generating response candidates based on input data, and includes generative AI and natural language processing models.

[0464] "Presentation means" refers to a device or method for providing the user with generated response candidates visually or audibly, and includes displays or speakers.

[0465] "Recording means" refers to a device or method for saving dialogue history and making it available for reference in subsequent dialogues, and includes databases and storage devices.

[0466] An "information processing device" refers to a machine or system that has a set of functions for inputting, processing, generating, and outputting data.

[0467] This invention relates to an information processing device for customer service support using speech recognition and generative AI models. The terminal uses a microphone to acquire acoustic signals of customer interaction. These acoustic signals are converted into text strings using speech recognition software such as the Google Cloud Speech-to-Text API. This converted text string is then sent to a server and analyzed by a generative AI model.

[0468] The server analyzes these strings using a natural language processing system such as OpenAI's ChatGPT model and generates appropriate response candidates. These response candidates are then sent to the terminal, which presents them to the user using its display.

[0469] The user can review the displayed response options and select or modify them as needed to respond to the customer. After the conversation ends, the terminal records the conversation history and response results and saves them to the server. This information can be used for future customer service.

[0470] For example, if a user receives an inquiry from a customer stating, "The product isn't working," the terminal converts the voice into text, and the server generates a suggested response such as, "Please check the product's power cable." This allows the user to provide quick and appropriate support.

[0471] Examples of prompt messages include the following:

[0472] "We have received an inquiry from a customer regarding a product malfunction. Please generate a proposed solution based on the following text: Customer inquiry: 'The product does not work when powered on. What should I do?'"

[0473] In this way, the invention aims to enable efficient customer service and improve customer satisfaction.

[0474] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0475] Step 1:

[0476] The user initiates a conversation with a customer, and the audio is input. The terminal acquires the audio signal through the microphone. The input is the raw audio from the customer, which the terminal converts into a digital audio signal. Specifically, the analog audio captured from the microphone is digitally processed and recorded as an audio signal on the terminal side.

[0477] Step 2:

[0478] The terminal converts the acquired acoustic signal into a string of text. The input is the digital acoustic signal acquired in the previous stage, and the output is the string data converted by speech recognition. This conversion process uses a speech recognition engine such as the Google Cloud Speech-to-Text API. The audio signal is processed, phonemes and words are identified based on the language model, and finally it is formatted as a sentence.

[0479] Step 3:

[0480] The server receives string data sent from the terminal and performs analysis. The input is converted string data sent to the server. The server analyzes the input data using a generative AI model and generates appropriate response candidates. Specifically, it uses OpenAI's ChatGPT model to understand and analyze the context of the conversation. During this process, the user's past conversation history is referenced, and responses are generated based on this contextual understanding.

[0481] Step 4:

[0482] The server sends the generated response candidates to the terminal. The input is the response candidates generated in the previous step, and the output is data transfer to the terminal. The response candidates contain specific content that should be suggested to the user and are formatted in a way that allows them to be displayed on the terminal.

[0483] Step 5:

[0484] The terminal displays the received response candidates to the user. The input is the response candidates sent from the server, and the output is visual information presented to the user. The terminal uses its display to show the response candidates in a format that the user can review and select. For example, multiple candidates may be displayed in a list format, from which the user can select the most suitable response.

[0485] Step 6:

[0486] The user responds to the customer based on the suggested responses, modifying them as needed. Input is the information displayed on the device, and output is the final voice or text response to the customer. The user can refer to response suggestions and make real-time modifications based on the specific situation.

[0487] Step 7:

[0488] After the interaction ends, the terminal records the conversation content and response results. Input consists of data generated throughout the entire interaction process, while output includes data transmission to the server and storage in the database. The recording is performed to improve future interactions and is used as user feedback and empirical data.

[0489] (Application Example 1)

[0490] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0491] Improving the efficiency and accuracy of customer communication is a crucial challenge in today's business environment. In particular, in brick-and-mortar stores, customer interaction directly impacts revenue, requiring prompt and accurate responses. However, in reality, the quality of service varies depending on the experience and knowledge of the person handling the interaction. Therefore, there is a need for techniques to respond quickly and accurately to customer requests.

[0492] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0493] In this invention, the server includes speech recognition means for converting speech into text data, generation AI means for analyzing the text data and generating response candidates, and a display device for presenting the generated response candidates to an information processing device in real time. This makes it possible to suggest appropriate responses in real time when dealing with customers.

[0494] A "voice input means" is a device used to acquire voice during conversations with customers.

[0495] "Speech recognition means" refers to technology for converting acquired speech into text data.

[0496] "Generative AI means" refers to artificial intelligence technology that analyzes converted text data and generates response candidates.

[0497] A "display device" is an output device that presents the generated response candidates to the user.

[0498] A "recording means" is a system for recording generated response candidates and dialogue content, and for using them in subsequent dialogues.

[0499] An "information processing device" is a device that installs programs and performs information processing such as speech recognition and response generation.

[0500] "Real-time" refers to presenting processing results immediately during a conversation with the customer.

[0501] The system for realizing this invention efficiently processes voice during customer interactions and provides accurate responses. The server acquires voice data through a microphone installed in an information processing device as a voice input means. The Google Cloud Speech-to-Text API is used for speech recognition, accurately and quickly converting the acquired voice into text data.

[0502] The converted text data is sent to a server and analyzed using the OpenAI API, a generative AI tool. Here, response candidates are generated, referencing past dialogue history. These generated response candidates are displayed in real time on the information processing device's display. For example, smart glasses are used as the display, serving to visually present information to the user.

[0503] As a concrete example, if a customer asks about shoe size in a store, the employee's voice is instantly captured, and an appropriate response regarding the size is displayed on the glasses' display. This allows the employee to respond to the customer quickly. An example of a prompt is, "The customer is asking for details about the product. Please provide the most helpful information based on past conversation data." This prompt enables the generating AI to suggest an efficient and accurate response.

[0504] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0505] Step 1:

[0506] The terminal uses voice input to capture the conversation between the user and the customer as audio data. Specifically, the microphone captures the signal, which is then input to the terminal as digital audio data.

[0507] Step 2:

[0508] The device uses speech recognition to convert the acquired audio data into text data. Here, the Google Cloud Speech-to-Text API is used to analyze the audio signal in real time and generate data in text format.

[0509] Step 3:

[0510] The server receives text data sent from the terminal and analyzes it using a generative AI. This involves processing the text according to its context using the OpenAI API and calculating the optimal response candidate. The input data is the content of the conversation with the customer, and the output is the response candidate.

[0511] Step 4:

[0512] The server sends back the generated response candidates to the terminal in real time. The terminal uses a display device installed in the information processing unit to visually present the response candidates to the user. For example, the message may be displayed on smart glasses.

[0513] Step 5:

[0514] Users review the displayed response options and customize them as needed to respond to customers. This allows users to respond quickly and efficiently to their target audience.

[0515] Step 6:

[0516] The terminal records the final response and dialogue log and saves it to the server. This information will serve as reference data for future interactions and contribute to improving customer service. This record includes the date and time, response content, and customer information.

[0517] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0518] The present invention is a system comprising voice input means, voice recognition means, generation AI means, display means, recording means, and emotion engine to provide support in customer interactions.

[0519] The system collects customer speech via voice input when the user initiates a conversation with a customer. The terminal captures this voice data in real time and converts it into text data. This speech recognition process enables speech-to-text conversion.

[0520] After the audio is converted to text, the server receives this data. The server uses generative AI to analyze the text and generate response candidates suitable for customer interaction. The analysis takes into account the customer's past conversation history and current emotional state.

[0521] The emotion engine analyzes the customer's emotional state based on their voice tone and speech content. For example, it identifies emotions such as anger or anxiety and provides the results to the AI ​​generation system. Based on this analysis, response candidates are generated in a way that adapts to the customer's emotions.

[0522] The generated response options are provided to the user through the terminal's display mechanism. The user can view the options, select or modify the most appropriate response for the situation, and communicate it to the customer. This allows the user to take appropriate action that takes the other party's feelings into consideration, thereby improving customer satisfaction.

[0523] For example, if a user receives a product complaint from a customer, the emotion engine analyzes the customer's voice and detects anger. The server uses this information to generate response options that take the customer's emotions into consideration, displaying suggestions such as, "I'm sorry to hear you're upset. How can I help?" The user can then use these suggestions to respond in a way that is considerate of the customer's situation.

[0524] This system allows users to provide consistent service that takes customer emotions into account, thereby increasing customer satisfaction and improving operational efficiency.

[0525] The following describes the processing flow.

[0526] Step 1:

[0527] When a user begins a conversation with a customer, the device uses voice input to capture the customer's voice in real time. The collected voice data is temporarily stored on the device.

[0528] Step 2:

[0529] The device uses speech recognition to collect speech data and converts it into text data. Speech-to-text technology is used to transcribe the speech into text.

[0530] Step 3:

[0531] The terminal sends the converted text data to the server. This data is delivered to the server as the customer's spoken content.

[0532] Step 4:

[0533] When the server receives text data, it uses an emotion engine to analyze the information extracted from the voice and identify the customer's emotional state. Based on the voice tone and content, it categorizes the customer's emotions into categories such as "anger," "anxiety," and "happiness."

[0534] Step 5:

[0535] The AI ​​generation system is activated, and the server combines customer text data with information about the customer's emotional state to generate response candidates. The optimal response, tailored to the customer's emotions, is determined while also referencing past conversation history.

[0536] Step 6:

[0537] The server sends the generated response candidates to the terminal. The response data is then transferred to the terminal so that the user can view it.

[0538] Step 7:

[0539] The terminal uses a display mechanism to show the user the received response options. The user can select the most appropriate response from these options and confirm it on the screen.

[0540] Step 8:

[0541] The user communicates selected or adjusted responses to the customer, taking into account the customer's current emotions. The flow of the conversation is managed in a way that is emotionally adaptive.

[0542] Step 9:

[0543] After the interaction is complete, the device saves the conversation content and response history using a recording device and sends it to the server. This data is then retained and can be used for future interactions.

[0544] (Example 2)

[0545] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0546] Conventional dialogue systems have faced challenges in accurately understanding customer utterances and responding in a way that takes their emotional state into account. In particular, in situations where responses that consider customer emotions are required, simply relying on responses based on past dialogue history may be insufficient, potentially leading to decreased customer satisfaction.

[0547] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0548] In this invention, the server includes an input means, a recognition means, a generation means, a coordination means, a presentation means, a storage means, and an emotion analysis means. This enables the generation of appropriate responses according to the customer's emotional state.

[0549] "Input means" refers to a device or method for acquiring voice from a customer.

[0550] "Recognition means" refers to a device or method that converts acquired audio into textual information.

[0551] "Generation means" refers to an apparatus or method that analyzes character information and generates response candidates.

[0552] "Presentation means" refers to a device or method for displaying generated response candidates to the user.

[0553] A "memory device" is a device or method for recording generated response candidates and using them for future dialogue.

[0554] "Emotional analysis means" refers to a device or method that analyzes a customer's voice or text data to identify their emotional state.

[0555] "Adjustment means" refers to a device or method for appropriately adjusting response candidates based on a specified emotional state.

[0556] This system is designed to support customer interaction. Specifically, it acquires customer voices and analyzes them appropriately to provide users with emotionally sensitive responses. A specific embodiment is shown below.

[0557] Speech acquisition and conversion

[0558] The device uses a microphone to capture the customer's voice. This voice data is converted into text using speech recognition software. For example, services such as the Google Cloud Speech-to-Text API are used for speech recognition.

[0559] Text analysis and response generation

[0560] The server receives the converted text information and performs analysis using a generative AI model. The generative AI model used here is, for example, a general-purpose natural language processing model. During the analysis process, the server considers the customer's past conversation history and current emotional state to generate the most suitable response candidates.

[0561] Emotional analysis and response adjustment

[0562] The server identifies the customer's emotions through an emotion analysis engine and adjusts the generated response based on the information obtained. This enables appropriate responses tailored to the customer's situation.

[0563] Presentation and selection of responses

[0564] The generated response options are displayed on the device, and the user can select the most appropriate response through the on-screen interface.

[0565] Specific example

[0566] For example, if a user makes a complaint about a product, the emotion analysis engine can detect anger from the customer's tone of voice. The server can then use this information to generate an emotionally sensitive response using a generative AI model, displaying suggestions such as, "I'm sorry to hear you're upset. How can I help?"

[0567] Example of a prompt

[0568] "The customer is dissatisfied with the product and their tone of voice is angry. Refer to similar cases from past customer history and generate a response that includes an appropriate apology and proposed next steps."

[0569] This system enables users to respond in a way that appropriately considers customer emotions, leading to improved customer satisfaction and increased operational efficiency.

[0570] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0571] Step 1:

[0572] The device acquires the customer's voice through the microphone. The input is real-time voice data. This voice data is temporarily buffered on the device and prepared for the speech recognition process. The final output is the voice data itself.

[0573] Step 2:

[0574] The terminal uses speech recognition software to convert speech data into text information. The input data is the speech data acquired in step 1. This conversion involves, for example, using a speech recognition service to process the speech signal. The output is text data that reflects what the customer says.

[0575] Step 3:

[0576] The terminal sends the converted text data to the server. The input here is the text data generated in step 2. The terminal sends the data using a secure communication protocol. This is supplied to the server as input for subsequent analysis.

[0577] Step 4:

[0578] The server analyzes the received text data using a generating AI model. The input is the text data sent in step 3. The server performs contextual analysis and references past history to identify the customer's intent. The output is a list of candidate responses to send back to the customer.

[0579] Step 5:

[0580] The server uses an emotion analysis engine to identify the customer's emotional state. The input is the text information and voice tone from step 2. The analysis evaluates the voice pitch and word choices to assess the emotion. The output is the identified customer's emotional state.

[0581] Step 6:

[0582] The server adjusts the generated response based on the emotional state. The inputs are the candidate response from step 4 and the emotional state from step 5. The server modifies or strengthens the response to make it the most appropriate form. The output of this adjustment process is the final adjusted response.

[0583] Step 7:

[0584] The terminal displays the response received from the server to the user. The input is the adjusted response from step 6. The user looks at the displayed response and decides what to tell the customer. The output is the response selected by the user and is delivered to the customer.

[0585] (Application Example 2)

[0586] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0587] Traditional customer service systems struggled to analyze customers' emotions in real time during conversations and provide appropriate responses. As a result, customer service was inconsistent, making it difficult to improve customer satisfaction. Furthermore, there was insufficient support for service providers to grasp the customer's emotional state at that moment and respond accordingly.

[0588] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0589] In this invention, the server includes a voice input means for acquiring voice, a voice recognition means for converting voice into text data, and means capable of being fitted with a visual device for visually displaying the generated response candidates. This makes it possible to analyze the emotional state of a customer from their voice in real time, provide the responder with emotionally sensitive response candidates on the spot, and improve customer satisfaction.

[0590] "Voice input means" refers to a device or group of devices that acquires voice signals from a customer.

[0591] "Speech recognition means" refers to a technology that analyzes acquired speech signals and converts them into corresponding text data.

[0592] "Generating information processing means" refers to information processing technology for generating appropriate response candidates based on text data.

[0593] "Problem display means" refers to a device or method that visually displays and makes operable the generated response candidates.

[0594] "Recording means" refers to technology for saving generated response candidates and dialogue history to prepare for future reference.

[0595] "Emotional analysis means" refers to technology that analyzes and identifies a customer's emotional state from their voice or text.

[0596] "Means for attaching a visual device" refers to a technology or method that enables a user to attach a device for visually displaying response candidates or other information.

[0597] The system that realizes this invention mainly consists of a server, a terminal, and a visual device. The server includes voice input means, voice recognition means, generated information processing means, emotion analysis means, and recording means. The terminal and visual device provide response candidates in real time through task display means.

[0598] The server acquires customer voice using voice input and converts it into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text). The converted text data is analyzed by a generative AI model (e.g., OpenAI GPT) to generate appropriate response candidates. During this process, the server uses sentiment analysis tools and NLP tools (e.g., Microsoft Azure Text Analytics) to determine the customer's emotional state. This information is fed back to the generative AI model, which then presents an optimized response.

[0599] The terminal or visual device displays generated response options via a task display mechanism. The user reviews the provided response options through smart glasses or another visual display and selects or modifies them as needed. This system enables flexible responses that respond to customer emotions.

[0600] As a concrete example, when a customer asks a question about a product at a store counter, the server analyzes the customer's relaxed tone and uses a generative AI model to generate response options such as, "This product is the latest model and has these features in particular." These options are then displayed on smart glasses.

[0601] An example of a prompt message is: "Customer's question: 'Tell me more about this product.', Customer's emotional state: 'Relaxed', Suggest an appropriate response:"

[0602] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0603] Step 1:

[0604] The server acquires audio from the customer via a voice input device. The audio data is sent in real time to a speech recognition API, which converts the audio into text data. In this step, the input is the customer's voice, and the output is the corresponding text data.

[0605] Step 2:

[0606] The server inputs text data into a generated AI model, which then analyzes the customer's utterances. During the analysis, the model references the customer's past conversation history and related information to generate appropriate response candidates. The input consists of text data and past conversation history, while the output is a set of response candidates.

[0607] Step 3:

[0608] The server uses sentiment analysis tools to determine the customer's emotional state from their text data. A specific sentiment analysis algorithm is used to analyze voice tone and text content to identify the customer's emotional state. The input is text data, and the output is the estimated emotional state.

[0609] Step 4:

[0610] The server incorporates the results of sentiment analysis into the generated response candidates and selects the optimized response. The generative AI model fine-tunes multiple response candidates according to the emotional state and selects the most appropriate one. The input is the response candidates and the emotional state, and the output is the adjusted response.

[0611] Step 5:

[0612] The terminal displays the adjusted response to the user through a visual device. The user can review the displayed response and select or modify it as needed. The input is the adjusted response, and the output is the information reviewed by the user.

[0613] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0614] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0615] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0616] [Fourth Embodiment]

[0617] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0618] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0619] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0620] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0621] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0622] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0623] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0624] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0625] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0626] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0627] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0628] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0629] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0630] This invention is a system for providing support in customer service and is implemented as follows.

[0631] The system includes a voice input mechanism that captures audio when the user interacts with a customer. The device's microphone captures the audio, collecting voice data in real time.

[0632] The terminal converts the acquired audio data into text data using speech recognition technology. This conversion process is performed by a speech-to-text engine, and the converted text is sent to the server.

[0633] When the server receives text data, it analyzes it using generative AI. This analysis includes understanding the context of the conversation and, if necessary, referencing customer profiles and past interaction records. Based on this information, the server generates optimal response candidates and provides them to the user.

[0634] The generated response options are presented to the user through the terminal's display. By viewing these, the user can select the appropriate response. Furthermore, the user can modify the response themselves, customizing it to suit the situation.

[0635] After the interaction is complete, the device records the conversation content and response results and saves them to the server. This information will be used to improve future conversation support through the recording system.

[0636] As a concrete example, consider a scenario where a user receives an inquiry from a customer regarding a product issue. The system uses speech recognition to analyze the user's voice report and displays common solutions. For example, it might suggest, "Check the power cable." The user can then respond based on these suggestions, enabling quick and efficient provision of necessary support. This facilitates smooth customer service and improves customer satisfaction.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] When a user begins a conversation with a customer, the device starts capturing the audio in real time. The voice input mechanism activates, and audio data is collected through the microphone.

[0640] Step 2:

[0641] The device converts the collected audio data into text data using speech recognition. A speech-to-text engine analyzes the audio and generates the corresponding string of characters.

[0642] Step 3:

[0643] The terminal sends the converted text data to the server. The text data is then sent to the server's analysis engine via the network.

[0644] Step 4:

[0645] The server analyzes the received text data using AI generation tools. It generates contextually appropriate response candidates while referencing the customer's profile and past interaction history.

[0646] Step 5:

[0647] The server sends back the generated response candidates to the terminal. The response candidates are provided to the terminal as data containing various options.

[0648] Step 6:

[0649] The terminal presents the received response candidates to the user through a display mechanism. Multiple response options are displayed on the screen in a user-friendly format.

[0650] Step 7:

[0651] The user selects the appropriate response from the options displayed on the device. The user reviews their selection, modifies the response as needed, and communicates it to the customer.

[0652] Step 8:

[0653] After the conversation ends, the terminal uses recording devices to save the conversation content and response history. This information is sent to a server and stored in a database that will be used for future conversations.

[0654] (Example 1)

[0655] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0656] The challenge is to improve customer satisfaction by providing smooth, efficient, and optimal responses during customer interactions. Furthermore, there is a need to provide a system that effectively utilizes past conversation history and allows users to flexibly select or customize responses.

[0657] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0658] In this invention, the server includes receiving means for acquiring an acoustic signal, recognition means for converting the acoustic signal into a string of characters, and generation model means for analyzing the string of characters and generating response candidates. This enables the rapid provision of appropriate responses in real time during customer interactions, improves the accuracy of responses by utilizing past dialogue history, and ensures flexibility in the user's response options.

[0659] An "acoustic signal" is a digital representation of sound waves transmitted by air vibrations.

[0660] "Receiving means" refers to a device or function for acquiring an acoustic signal, and usually includes a microphone.

[0661] "Recognition means" refers to a technology or device that converts acquired acoustic signals into strings of characters, and includes speech recognition software and algorithms.

[0662] A "string" is a sequence of characters, usually referring to sentences or text data.

[0663] "Generative model means" refers to an algorithm or system for generating response candidates based on input data, and includes generative AI and natural language processing models.

[0664] "Presentation means" refers to a device or method for providing the user with generated response candidates visually or audibly, and includes displays or speakers.

[0665] "Recording means" refers to a device or method for saving dialogue history and making it available for reference in subsequent dialogues, and includes databases and storage devices.

[0666] An "information processing device" refers to a machine or system that has a set of functions for inputting, processing, generating, and outputting data.

[0667] This invention relates to an information processing device for customer service support using speech recognition and generative AI models. The terminal uses a microphone to acquire acoustic signals of customer interaction. These acoustic signals are converted into text strings using speech recognition software such as the Google Cloud Speech-to-Text API. This converted text string is then sent to a server and analyzed by a generative AI model.

[0668] The server analyzes these strings using a natural language processing system such as OpenAI's ChatGPT model and generates appropriate response candidates. These response candidates are then sent to the terminal, which presents them to the user using its display.

[0669] The user can review the displayed response options and select or modify them as needed to respond to the customer. After the conversation ends, the terminal records the conversation history and response results and saves them to the server. This information can be used for future customer service.

[0670] For example, if a user receives an inquiry from a customer stating, "The product isn't working," the terminal converts the voice into text, and the server generates a suggested response such as, "Please check the product's power cable." This allows the user to provide quick and appropriate support.

[0671] Examples of prompt messages include the following:

[0672] "We have received an inquiry from a customer regarding a product malfunction. Please generate a proposed solution based on the following text: Customer inquiry: 'The product does not work when powered on. What should I do?'"

[0673] In this way, the invention aims to enable efficient customer service and improve customer satisfaction.

[0674] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0675] Step 1:

[0676] The user initiates a conversation with a customer, and the audio is input. The terminal acquires the audio signal through the microphone. The input is the raw audio from the customer, which the terminal converts into a digital audio signal. Specifically, the analog audio captured from the microphone is digitally processed and recorded as an audio signal on the terminal side.

[0677] Step 2:

[0678] The terminal converts the acquired acoustic signal into a string of text. The input is the digital acoustic signal acquired in the previous stage, and the output is the string data converted by speech recognition. This conversion process uses a speech recognition engine such as the Google Cloud Speech-to-Text API. The audio signal is processed, phonemes and words are identified based on the language model, and finally it is formatted as a sentence.

[0679] Step 3:

[0680] The server receives string data sent from the terminal and performs analysis. The input is converted string data sent to the server. The server analyzes the input data using a generative AI model and generates appropriate response candidates. Specifically, it uses OpenAI's ChatGPT model to understand and analyze the context of the conversation. During this process, the user's past conversation history is referenced, and responses are generated based on this contextual understanding.

[0681] Step 4:

[0682] The server sends the generated response candidates to the terminal. The input is the response candidates generated in the previous step, and the output is data transfer to the terminal. The response candidates contain specific content that should be suggested to the user and are formatted in a way that allows them to be displayed on the terminal.

[0683] Step 5:

[0684] The terminal displays the received response candidates to the user. The input is the response candidates sent from the server, and the output is visual information presented to the user. The terminal uses its display to show the response candidates in a format that the user can review and select. For example, multiple candidates may be displayed in a list format, from which the user can select the most suitable response.

[0685] Step 6:

[0686] The user responds to the customer based on the suggested responses, modifying them as needed. Input is the information displayed on the device, and output is the final voice or text response to the customer. The user can refer to response suggestions and make real-time modifications based on the specific situation.

[0687] Step 7:

[0688] After the interaction ends, the terminal records the conversation content and response results. Input consists of data generated throughout the entire interaction process, while output includes data transmission to the server and storage in the database. The recording is performed to improve future interactions and is used as user feedback and empirical data.

[0689] (Application Example 1)

[0690] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0691] Improving the efficiency and accuracy of customer communication is a crucial challenge in today's business environment. In particular, in brick-and-mortar stores, customer interaction directly impacts revenue, requiring prompt and accurate responses. However, in reality, the quality of service varies depending on the experience and knowledge of the person handling the interaction. Therefore, there is a need for techniques to respond quickly and accurately to customer requests.

[0692] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0693] In this invention, the server includes speech recognition means for converting speech into text data, generation AI means for analyzing the text data and generating response candidates, and a display device for presenting the generated response candidates to an information processing device in real time. This makes it possible to suggest appropriate responses in real time when dealing with customers.

[0694] A "voice input means" is a device used to acquire voice during conversations with customers.

[0695] "Speech recognition means" refers to technology for converting acquired speech into text data.

[0696] "Generative AI means" refers to artificial intelligence technology that analyzes converted text data and generates response candidates.

[0697] A "display device" is an output device that presents the generated response candidates to the user.

[0698] A "recording means" is a system for recording generated response candidates and dialogue content, and for using them in subsequent dialogues.

[0699] An "information processing device" is a device that installs programs and performs information processing such as speech recognition and response generation.

[0700] "Real-time" refers to presenting processing results immediately during a conversation with the customer.

[0701] The system for realizing this invention efficiently processes voice during customer interactions and provides accurate responses. The server acquires voice data through a microphone installed in an information processing device as a voice input means. The Google Cloud Speech-to-Text API is used for speech recognition, accurately and quickly converting the acquired voice into text data.

[0702] The converted text data is sent to a server and analyzed using the OpenAI API, a generative AI tool. Here, response candidates are generated, referencing past dialogue history. These generated response candidates are displayed in real time on the information processing device's display. For example, smart glasses are used as the display, serving to visually present information to the user.

[0703] As a concrete example, if a customer asks about shoe size in a store, the employee's voice is instantly captured, and an appropriate response regarding the size is displayed on the glasses' display. This allows the employee to respond to the customer quickly. An example of a prompt is, "The customer is asking for details about the product. Please provide the most helpful information based on past conversation data." This prompt enables the generating AI to suggest an efficient and accurate response.

[0704] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0705] Step 1:

[0706] The terminal uses voice input to capture the conversation between the user and the customer as audio data. Specifically, the microphone captures the signal, which is then input to the terminal as digital audio data.

[0707] Step 2:

[0708] The device uses speech recognition to convert the acquired audio data into text data. Here, the Google Cloud Speech-to-Text API is used to analyze the audio signal in real time and generate data in text format.

[0709] Step 3:

[0710] The server receives text data sent from the terminal and analyzes it using a generative AI. This involves processing the text according to its context using the OpenAI API and calculating the optimal response candidate. The input data is the content of the conversation with the customer, and the output is the response candidate.

[0711] Step 4:

[0712] The server sends back the generated response candidates to the terminal in real time. The terminal uses a display device installed in the information processing unit to visually present the response candidates to the user. For example, the message may be displayed on smart glasses.

[0713] Step 5:

[0714] Users review the displayed response options and customize them as needed to respond to customers. This allows users to respond quickly and efficiently to their target audience.

[0715] Step 6:

[0716] The terminal records the final response and dialogue log and saves it to the server. This information will serve as reference data for future interactions and contribute to improving customer service. This record includes the date and time, response content, and customer information.

[0717] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0718] The present invention is a system comprising voice input means, voice recognition means, generation AI means, display means, recording means, and emotion engine to provide support in customer interactions.

[0719] The system collects customer speech via voice input when the user initiates a conversation with a customer. The terminal captures this voice data in real time and converts it into text data. This speech recognition process enables speech-to-text conversion.

[0720] After the audio is converted to text, the server receives this data. The server uses generative AI to analyze the text and generate response candidates suitable for customer interaction. The analysis takes into account the customer's past conversation history and current emotional state.

[0721] The emotion engine analyzes the customer's emotional state based on their voice tone and speech content. For example, it identifies emotions such as anger or anxiety and provides the results to the AI ​​generation system. Based on this analysis, response candidates are generated in a way that adapts to the customer's emotions.

[0722] The generated response options are provided to the user through the terminal's display mechanism. The user can view the options, select or modify the most appropriate response for the situation, and communicate it to the customer. This allows the user to take appropriate action that takes the other party's feelings into consideration, thereby improving customer satisfaction.

[0723] For example, if a user receives a product complaint from a customer, the emotion engine analyzes the customer's voice and detects anger. The server uses this information to generate response options that take the customer's emotions into consideration, displaying suggestions such as, "I'm sorry to hear you're upset. How can I help?" The user can then use these suggestions to respond in a way that is considerate of the customer's situation.

[0724] This system allows users to provide consistent service that takes customer emotions into account, thereby increasing customer satisfaction and improving operational efficiency.

[0725] The following describes the processing flow.

[0726] Step 1:

[0727] When a user begins a conversation with a customer, the device uses voice input to capture the customer's voice in real time. The collected voice data is temporarily stored on the device.

[0728] Step 2:

[0729] The device uses speech recognition to collect speech data and converts it into text data. Speech-to-text technology is used to transcribe the speech into text.

[0730] Step 3:

[0731] The terminal sends the converted text data to the server. This data is delivered to the server as the customer's spoken content.

[0732] Step 4:

[0733] When the server receives text data, it uses an emotion engine to analyze the information extracted from the voice and identify the customer's emotional state. Based on the voice tone and content, it categorizes the customer's emotions into categories such as "anger," "anxiety," and "happiness."

[0734] Step 5:

[0735] The AI ​​generation system is activated, and the server combines customer text data with information about the customer's emotional state to generate response candidates. The optimal response, tailored to the customer's emotions, is determined while also referencing past conversation history.

[0736] Step 6:

[0737] The server sends the generated response candidates to the terminal. The response data is then transferred to the terminal so that the user can view it.

[0738] Step 7:

[0739] The terminal uses a display mechanism to show the user the received response options. The user can select the most appropriate response from these options and confirm it on the screen.

[0740] Step 8:

[0741] The user communicates selected or adjusted responses to the customer, taking into account the customer's current emotions. The flow of the conversation is managed in a way that is emotionally adaptive.

[0742] Step 9:

[0743] After the interaction is complete, the device saves the conversation content and response history using a recording device and sends it to the server. This data is then retained and can be used for future interactions.

[0744] (Example 2)

[0745] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0746] Conventional dialogue systems have faced challenges in accurately understanding customer utterances and responding in a way that takes their emotional state into account. In particular, in situations where responses that consider customer emotions are required, simply relying on responses based on past dialogue history may be insufficient, potentially leading to decreased customer satisfaction.

[0747] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0748] In this invention, the server includes an input means, a recognition means, a generation means, a coordination means, a presentation means, a storage means, and an emotion analysis means. This enables the generation of appropriate responses according to the customer's emotional state.

[0749] "Input means" refers to a device or method for acquiring voice from a customer.

[0750] "Recognition means" refers to a device or method that converts acquired audio into textual information.

[0751] "Generation means" refers to an apparatus or method that analyzes character information and generates response candidates.

[0752] "Presentation means" refers to a device or method for displaying generated response candidates to the user.

[0753] A "memory device" is a device or method for recording generated response candidates and using them for future dialogue.

[0754] "Emotional analysis means" refers to a device or method that analyzes a customer's voice or text data to identify their emotional state.

[0755] "Adjustment means" refers to a device or method for appropriately adjusting response candidates based on a specified emotional state.

[0756] This system is designed to support customer interaction. Specifically, it acquires customer voices and analyzes them appropriately to provide users with emotionally sensitive responses. A specific embodiment is shown below.

[0757] Speech acquisition and conversion

[0758] The device uses a microphone to capture the customer's voice. This voice data is converted into text using speech recognition software. For example, services such as the Google Cloud Speech-to-Text API are used for speech recognition.

[0759] Text analysis and response generation

[0760] The server receives the converted text information and performs analysis using a generative AI model. The generative AI model used here is, for example, a general-purpose natural language processing model. During the analysis process, the server considers the customer's past conversation history and current emotional state to generate the most suitable response candidates.

[0761] Emotional analysis and response adjustment

[0762] The server identifies the customer's emotions through an emotion analysis engine and adjusts the generated response based on the information obtained. This enables appropriate responses tailored to the customer's situation.

[0763] Presentation and selection of responses

[0764] The generated response options are displayed on the device, and the user can select the most appropriate response through the on-screen interface.

[0765] Specific example

[0766] For example, if a user makes a complaint about a product, the emotion analysis engine can detect anger from the customer's tone of voice. The server can then use this information to generate an emotionally sensitive response using a generative AI model, displaying suggestions such as, "I'm sorry to hear you're upset. How can I help?"

[0767] Example of a prompt

[0768] "The customer is dissatisfied with the product and their tone of voice is angry. Refer to similar cases from past customer history and generate a response that includes an appropriate apology and proposed next steps."

[0769] This system enables users to respond in a way that appropriately considers customer emotions, leading to improved customer satisfaction and increased operational efficiency.

[0770] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0771] Step 1:

[0772] The device acquires the customer's voice through the microphone. The input is real-time voice data. This voice data is temporarily buffered on the device and prepared for the speech recognition process. The final output is the voice data itself.

[0773] Step 2:

[0774] The terminal uses speech recognition software to convert speech data into text information. The input data is the speech data acquired in step 1. This conversion involves, for example, using a speech recognition service to process the speech signal. The output is text data that reflects what the customer says.

[0775] Step 3:

[0776] The terminal sends the converted text data to the server. The input here is the text data generated in step 2. The terminal sends the data using a secure communication protocol. This is supplied to the server as input for subsequent analysis.

[0777] Step 4:

[0778] The server analyzes the received text data using a generating AI model. The input is the text data sent in step 3. The server performs contextual analysis and references past history to identify the customer's intent. The output is a list of candidate responses to send back to the customer.

[0779] Step 5:

[0780] The server uses an emotion analysis engine to identify the customer's emotional state. The input is the text information and voice tone from step 2. The analysis evaluates the voice pitch and word choices to assess the emotion. The output is the identified customer's emotional state.

[0781] Step 6:

[0782] The server adjusts the generated response based on the emotional state. The inputs are the candidate response from step 4 and the emotional state from step 5. The server modifies or strengthens the response to make it the most appropriate form. The output of this adjustment process is the final adjusted response.

[0783] Step 7:

[0784] The terminal displays the response received from the server to the user. The input is the adjusted response from step 6. The user looks at the displayed response and decides what to tell the customer. The output is the response selected by the user and is delivered to the customer.

[0785] (Application Example 2)

[0786] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0787] Traditional customer service systems struggled to analyze customers' emotions in real time during conversations and provide appropriate responses. As a result, customer service was inconsistent, making it difficult to improve customer satisfaction. Furthermore, there was insufficient support for service providers to grasp the customer's emotional state at that moment and respond accordingly.

[0788] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0789] In this invention, the server includes a voice input means for acquiring voice, a voice recognition means for converting voice into text data, and means capable of being fitted with a visual device for visually displaying the generated response candidates. This makes it possible to analyze the emotional state of a customer from their voice in real time, provide the responder with emotionally sensitive response candidates on the spot, and improve customer satisfaction.

[0790] "Voice input means" refers to a device or group of devices that acquires voice signals from a customer.

[0791] "Speech recognition means" refers to a technology that analyzes acquired speech signals and converts them into corresponding text data.

[0792] "Generating information processing means" refers to information processing technology for generating appropriate response candidates based on text data.

[0793] "Problem display means" refers to a device or method that visually displays and makes operable the generated response candidates.

[0794] "Recording means" refers to technology for saving generated response candidates and dialogue history to prepare for future reference.

[0795] "Emotional analysis means" refers to technology that analyzes and identifies a customer's emotional state from their voice or text.

[0796] "Means for attaching a visual device" refers to a technology or method that enables a user to attach a device for visually displaying response candidates or other information.

[0797] The system that realizes this invention mainly consists of a server, a terminal, and a visual device. The server includes voice input means, voice recognition means, generated information processing means, emotion analysis means, and recording means. The terminal and visual device provide response candidates in real time through task display means.

[0798] The server acquires customer voice using voice input and converts it into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text). The converted text data is analyzed by a generative AI model (e.g., OpenAI GPT) to generate appropriate response candidates. During this process, the server uses sentiment analysis tools and NLP tools (e.g., Microsoft Azure Text Analytics) to determine the customer's emotional state. This information is fed back to the generative AI model, which then presents an optimized response.

[0799] The terminal or visual device displays generated response options via a task display mechanism. The user reviews the provided response options through smart glasses or another visual display and selects or modifies them as needed. This system enables flexible responses that respond to customer emotions.

[0800] As a concrete example, when a customer asks a question about a product at a store counter, the server analyzes the customer's relaxed tone and uses a generative AI model to generate response options such as, "This product is the latest model and has these features in particular." These options are then displayed on smart glasses.

[0801] An example of a prompt message is: "Customer's question: 'Tell me more about this product.', Customer's emotional state: 'Relaxed', Suggest an appropriate response:"

[0802] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0803] Step 1:

[0804] The server acquires audio from the customer via a voice input device. The audio data is sent in real time to a speech recognition API, which converts the audio into text data. In this step, the input is the customer's voice, and the output is the corresponding text data.

[0805] Step 2:

[0806] The server inputs text data into a generated AI model, which then analyzes the customer's utterances. During the analysis, the model references the customer's past conversation history and related information to generate appropriate response candidates. The input consists of text data and past conversation history, while the output is a set of response candidates.

[0807] Step 3:

[0808] The server uses sentiment analysis tools to determine the customer's emotional state from their text data. A specific sentiment analysis algorithm is used to analyze voice tone and text content to identify the customer's emotional state. The input is text data, and the output is the estimated emotional state.

[0809] Step 4:

[0810] The server incorporates the results of sentiment analysis into the generated response candidates and selects the optimized response. The generative AI model fine-tunes multiple response candidates according to the emotional state and selects the most appropriate one. The input is the response candidates and the emotional state, and the output is the adjusted response.

[0811] Step 5:

[0812] The terminal displays the adjusted response to the user through a visual device. The user can review the displayed response and select or modify it as needed. The input is the adjusted response, and the output is the information reviewed by the user.

[0813] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0814] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0815] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0816] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0817] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0818] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0819] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0820] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0821] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0822] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0823] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0824] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0825] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0826] 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.

[0827] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0828] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0829] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0830] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0831] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0832] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0833] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0834] The following is further disclosed regarding the embodiments described above.

[0835] (Claim 1)

[0836] In conversations with customers, a voice input means for acquiring voice,

[0837] A speech recognition means that converts the aforementioned speech into text data,

[0838] A generative AI means for analyzing the aforementioned text data and generating response candidates,

[0839] A display means for displaying the generated response candidates,

[0840] A recording means for recording the aforementioned response candidates and using them for future dialogue,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, characterized in that the generating AI means refers to the customer's past conversation history.

[0844] (Claim 3)

[0845] The system according to claim 1, characterized in that the display means presents a plurality of responses that the user can select.

[0846] "Example 1"

[0847] (Claim 1)

[0848] A receiving means for acquiring an acoustic signal,

[0849] Recognition means for converting the aforementioned acoustic signal into a string of characters,

[0850] A generative model means that analyzes the aforementioned string and generates response candidates,

[0851] A presentation means for presenting generated response candidates,

[0852] A recording means for recording the aforementioned response candidates and dialogue history and utilizing them in subsequent dialogues,

[0853] Information processing device including

[0854] (Claim 2)

[0855] The information processing apparatus according to claim 1, characterized in that the generation model means refers to the user's past dialogue records.

[0856] (Claim 3)

[0857] The information processing apparatus according to claim 1, characterized in that the presentation means displays a plurality of responses that the user can select.

[0858] "Application Example 1"

[0859] (Claim 1)

[0860] In conversations with customers, a voice input means for acquiring voice,

[0861] A speech recognition means that converts the aforementioned speech into text data,

[0862] A generative AI means for analyzing the aforementioned text data and generating response candidates,

[0863] A display device that shows the generated response candidates,

[0864] A recording means for recording the aforementioned response candidates and using them for future dialogue,

[0865] A program installed on an information processing device that presents generated response candidates on a display device in real time,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, characterized in that the generating AI means refers to the customer's past dialogue history and presents the generated response candidates through the display device of the information processing device.

[0869] (Claim 3)

[0870] The system according to claim 1, characterized in that the display device presents a plurality of responses that the user can select, and further allows the user to customize the response based on these.

[0871] "Example 2 of combining an emotion engine"

[0872] (Claim 1)

[0873] An input means for acquiring sound,

[0874] Recognition means for converting the aforementioned sound into text information,

[0875] A generation means for analyzing the aforementioned character information and generating response candidates,

[0876] A presentation means for displaying the generated response candidates,

[0877] A memory means for recording the aforementioned response candidates and using them for future dialogue,

[0878] A means of analyzing the emotional state of customers,

[0879] An adjustment means for adjusting response candidates based on the aforementioned emotional state,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, characterized in that the generation means refers to the customer's past dialogue history and emotional state.

[0883] (Claim 3)

[0884] The system according to claim 1, characterized in that the presentation means displays a plurality of responses that the user can select.

[0885] "Application example 2 when combining with an emotional engine"

[0886] (Claim 1)

[0887] In conversations with customers, a voice input means for acquiring voice,

[0888] A speech recognition means that converts the aforementioned speech into text data,

[0889] A generating information processing means that analyzes the aforementioned text data and generates response candidates,

[0890] A task display means that displays the generated response candidates,

[0891] A recording means for recording the aforementioned response candidates and using them for future dialogue,

[0892] A means of analyzing emotional states,

[0893] A means to which a visual device that presents actions can be worn,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, characterized in that the generated information processing means refers to the user's past contact history and takes into account the user's current emotional state.

[0897] (Claim 3)

[0898] The system according to claim 1, characterized in that the problem display means presents a plurality of proposals that the operator can select. [Explanation of Symbols]

[0899] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. In conversations with customers, a voice input means for acquiring voice, A speech recognition means that converts the aforementioned speech into text data, A generative AI means for analyzing the aforementioned text data and generating response candidates, A display means for displaying the generated response candidates, A recording means for recording the aforementioned response candidates and using them for future dialogue, A system that includes this.

2. The system according to claim 1, characterized in that the generating AI means refers to the customer's past conversation history.

3. The system according to claim 1, characterized in that the display means presents a plurality of responses that the user can select.

Images