System

Abstract

An object of a system according to an embodiment is to utilize a talk of an excellent crew and to level customer service to visitors with a high skill.SOLUTION: A system includes a collection unit, an analysis unit, a generation unit, and an output unit. The collection unit collects learning data. The analysis unit analyzes the data collected by the collection unit. The generation unit generates a voice based on the data analyzed by the analysis unit. The output unit outputs the voice generated by the generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it is difficult to standardize the high skills of excellent staff while utilizing their talk when serving customers, and there is room for improvement.

[0005] The system of the embodiment aims to utilize the talk of excellent crew members to standardize customer service to high skill levels. [Means for solving the problem]

[0006] A system according to an embodiment includes a collection unit, an analysis unit, a generation unit, and an output unit. The collection unit collects training data. The analysis unit analyzes the data collected by the collection unit. The generation unit generates speech based on the data analyzed by the analysis unit. The output unit outputs the speech generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment utilizes the talk of excellent crew members to standardize customer service to high skill levels. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The customer service system according to an embodiment of the present invention uses an improved robot incorporating a generative AI to serve customers. The customer service system uses the generative AI to provide voice-to-voice interaction and, if necessary, can accept image and text input and generate voice based on that. Training data includes information on various services, devices, campaign specifications, and other information, and also utilizes Function Calling and RAG. For sales pitches in particular, the generative AI generates voice responses based on speech extracted from excellent speech data. For example, the customer service system responds to customer questions with voice. For example, if a customer asks, "What are the features of this smartphone?", the customer service system responds based on the training data with, "This smartphone has a high-resolution camera and good battery life." Regarding campaign information, if a customer asks, "What are the current campaigns?", the customer service system responds with, "Currently, if you purchase a smartphone, you will receive a free case." This allows the customer service system to provide quick and accurate service to customers. This allows the customer service system to provide quick and accurate service to customers using the generative AI. For example, customer satisfaction can be improved, which is expected to lead to an increase in the number of contracts. Furthermore, reskilling robots will enable them to respond to new services and campaigns, broadening the scope of their use.

[0029] The customer service system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and an output unit. The collection unit collects training data. The training data may include, but is not limited to, voice data, text data, and image data. The collection unit may collect information on various services, terminals, campaign specifications, and the like. The analysis unit analyzes the data collected by the collection unit. The analysis may be performed, for example, based on data preprocessing, feature extraction, and algorithm application, but is not limited to these examples. The analysis unit may also refine the analysis results using function calling or RAG. The generation unit generates speech based on the data analyzed by the analysis unit. The speech may be generated, for example, based on speech synthesis technology or an algorithm, but is not limited to these examples. The generation unit may also generate speech based on speech extracted from excellent speech data. The output unit outputs the speech generated by the generation unit. The output may be performed, for example, by audio output through a speaker or text output, but is not limited to these examples. This allows the customer service system according to the embodiment to perform a consistent process from training data collection to analysis, speech generation, and output. For example, the customer service system responds by voice to questions posed by customers. For example, if a customer asks, "What are the features of this smartphone?", the customer service system will respond based on the learning data with, "This smartphone has a high-resolution camera and a long battery life." Similarly, if a customer asks about campaign information, "What are the current campaigns?", the customer service system will respond with, "Currently, if you purchase a smartphone, you will receive a case for free." This allows the customer service system to respond to customers quickly and accurately.

[0030] The collection unit can collect information on various services, devices, and campaign specifications. The collection unit can, for example, collect information on online services and offline services. The collection unit can also collect device information such as smartphones, tablets, and PCs. Furthermore, the collection unit can collect information on campaign specifications such as promotion content, period, and target users. By collecting a variety of information, more accurate analysis is possible. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input information on various services, devices, and campaign specifications into a generation AI and cause the generation AI to collect information.

[0031] The analysis unit can refine the analysis results using function calling or RAG. The analysis unit can perform function calling using, for example, an API call. The analysis unit can also refine the analysis results using a retrieval augmented generation (RAG) technique. This improves the accuracy of the analysis results by utilizing function calling or RAG. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input function calling or RAG techniques into a generation AI and have the generation AI refine the analysis results.

[0032] The generation unit can generate speech based on talk extracted from excellent talk data. The generation unit can generate speech using, for example, excellent talk data selected based on evaluation criteria. The generation unit can also generate speech based on talk data extracted through a selection process. This enables high-quality service by generating speech based on excellent talk data. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the generation unit can input excellent talk data into a generation AI and have the generation AI generate speech.

[0033] The output unit can provide the generated voice to the customer. The output unit can provide the generated voice to the customer through a speaker, for example. The output unit can also display the content of the generated voice using text output. This allows for quick and accurate response by providing the generated voice to the customer. Some or all of the above-mentioned processing in the output unit can be performed using, for example, AI, or can be performed without using AI. For example, the output unit can input the generated voice to a generation AI and have the generation AI provide the voice.

[0034] The generation unit can generate an appropriate response to a customer's question. The generation unit can generate an appropriate response based on, for example, the content of the customer's question. The generation unit can also generate a response to the customer's question based on learning data. This generates an appropriate response to the customer's question, thereby improving customer satisfaction. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the content of the customer's question into the generation AI and cause the generation AI to generate an appropriate response.

[0035] During collection, the collection unit can analyze the user's past interaction history and select an appropriate data collection method. For example, the collection unit can prioritize collection of product information in which the user has shown interest in the past. The collection unit can also re-collect information on campaigns in which the user has previously participated. Furthermore, the collection unit can collect related data based on the content of inquiries made by the user in the past. This makes it possible to select an optimal data collection method by analyzing the past interaction history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past interaction history into a generation AI and have the generation AI select a data collection method.

[0036] The collection unit can perform filtering based on the user's current areas of interest and purchase history when collecting data. For example, the collection unit can prioritize collecting information related to products recently purchased by the user. The collection unit can also collect new product information in categories in which the user is interested. Furthermore, the collection unit can collect related accessory information from the user's purchase history. This allows for filtering based on the user's areas of interest and purchase history to collect more relevant data. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's areas of interest and purchase history into a generation AI and have the generation AI perform filtering.

[0037] The collection unit can select an appropriate collection means depending on the user's input method during collection. For example, if the user is using voice input, the collection unit can prioritize collecting voice data. Furthermore, if the user is using text input, the collection unit can also prioritize collecting text data. Furthermore, if the user is using image input, the collection unit can also prioritize collecting image data. This enables efficient data collection by selecting the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's input method to the generation AI and have the generation AI select the collection means.

[0038] During collection, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, the collection unit can prioritize collecting campaign information for the store where the user is currently located. The collection unit can also collect sale information for nearby stores based on the user's location information. Furthermore, the collection unit can also collect region-specific product information based on the user's location information. In this way, highly relevant data can be collected preferentially by taking the user's geographical location information into account. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to collect highly relevant data.

[0039] During collection, the collection unit can analyze the user's social media activities and collect related data. For example, the collection unit can collect product information shared by the user on social media. The collection unit can also analyze the content of the user's social media posts and collect related campaign information. Furthermore, the collection unit can collect related data by referring to the activities of the user's friends on social media. In this way, related data can be collected by analyzing the user's social media activities. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's social media activities into the generation AI and cause the generation AI to collect related data.

[0040] The collection unit can adjust the collection method by reflecting the user's past feedback when collecting data. The collection unit can, for example, adjust the type of data to collect based on feedback provided by the user in the past. The collection unit can also change the priority of data to collect by reflecting the user's feedback. Furthermore, the collection unit can optimize the collection method based on the user's feedback. In this way, the collection method can be optimized by reflecting the user's past feedback. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's past feedback into the generation AI and cause the generation AI to adjust the collection method.

[0041] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit can perform a detailed analysis on important campaign information. The analysis unit can also perform a standard analysis on general product information. Furthermore, the analysis unit can also perform a simplified analysis on information with low urgency. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of the data to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit can apply an analysis algorithm specialized for product characteristics to product information. The analysis unit can also apply an analysis algorithm specialized for marketing to campaign information. Furthermore, the analysis unit can apply an analysis algorithm specialized for service quality to service information. By applying different analysis algorithms depending on the data category, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data category to the generation AI and cause the generation AI to apply the analysis algorithm.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit can, for example, adjust the analysis algorithm based on feedback provided by the user in the past. The analysis unit can also improve the accuracy of the analysis by referring to the user's past analysis results. Furthermore, the analysis unit can determine the priority of the analysis based on the user's past analysis results. This improves the accuracy of the analysis by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0044] During analysis, the analysis unit can determine the priority of analysis based on the time of data submission. The analysis unit can, for example, prioritize analysis of the most recent data. The analysis unit can also postpone data that was submitted earlier. Furthermore, the analysis unit can prioritize analysis of data with high urgency. In this way, by determining the priority of analysis based on the time of data submission, the most recent data can be analyzed preferentially. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time of data submission to the generation AI and have the generation AI determine the priority of analysis.

[0045] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit can prioritize analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. Furthermore, the analysis unit can optimize the order of analysis based on the relevance of the data. This enables efficient analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of the data to the generation AI and have the generation AI adjust the order of analysis.

[0046] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has specialized knowledge, the analysis unit can use a lot of technical terms. Furthermore, if the user only has general knowledge, the analysis unit can avoid technical terms. Furthermore, the analysis unit can adjust the expression of the analysis results according to the user's level of expertise. By adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise into the generation AI and have the generation AI use technical terms.

[0047] The generation unit can adjust the level of detail of the generated voice based on the importance of the data during generation. For example, the generation unit can generate detailed voice for important campaign information. The generation unit can also generate standard voice for general product information. Furthermore, the generation unit can generate simple voice for information with low urgency. This enables efficient voice generation by adjusting the level of detail of the voice based on the importance of the data. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the voice.

[0048] The generation unit can apply different generation algorithms depending on the data category during generation. For example, the generation unit can apply a generation algorithm specialized for product characteristics to product information. The generation unit can also apply a generation algorithm specialized for marketing to campaign information. The generation unit can also apply a generation algorithm specialized for service quality to service information. By applying different generation algorithms depending on the data category, the accuracy of voice generation is improved. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the data category to the generation AI and cause the generation AI to apply the generation algorithm.

[0049] During generation, the generation unit can improve the accuracy of generation by referring to the user's past generation results. The generation unit can, for example, adjust the generation algorithm based on feedback provided by the user in the past. The generation unit can also improve the accuracy of generation by referring to the user's past generation results. Furthermore, the generation unit can determine the priority of generation based on the user's past generation results. In this way, the accuracy of generation is improved by referring to the user's past generation results. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's past generation results into the generation AI and cause the generation AI to improve the accuracy of generation.

[0050] At the time of generation, the generation unit can determine the priority of the voice to be generated based on the time of data submission. The generation unit can, for example, generate voice based on the latest data. The generation unit can also postpone data that was submitted earlier. Furthermore, the generation unit can also prioritize generating voice for data with high urgency. In this way, by determining the priority of voice based on the time of data submission, voice can be generated with priority for the latest data. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the time of data submission to the generation AI and have the generation AI determine the priority of the voice.

[0051] The generation unit can adjust the order of the voices to be generated based on the relevance of the data during generation. For example, the generation unit can prioritize generating voice from highly relevant data. The generation unit can also postpone generating voice from less relevant data. Furthermore, the generation unit can optimize the order of voice generation based on the relevance of the data. This enables efficient voice generation by adjusting the order of voices based on the relevance of the data. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input the relevance of the data to the generation AI and cause the generation AI to adjust the order of voice generation.

[0052] During generation, the generation unit can adjust the use of technical terms in the generated speech according to the user's level of expertise. For example, if the user has specialized knowledge, the generation unit can generate speech that uses a lot of technical terms. Furthermore, if the user only has general knowledge, the generation unit can generate speech that avoids technical terms. Furthermore, the generation unit can adjust the expression of the speech according to the user's level of expertise. This allows for a more understandable speech response by adjusting the use of technical terms in the speech according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's level of expertise into the generation AI and have the generation AI execute the use of technical terms.

[0053] At the time of output, the output unit can select the optimal output method by referring to the user's past interaction history. For example, the output unit can output based on the user's preferred voice tone in the past. The output unit can also select the optimal output method by referring to the user's past interaction history. Furthermore, the output unit can adjust the output method based on the user's past feedback. In this way, the optimal output method can be selected by referring to the user's past interaction history. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's past interaction history into a generation AI and have the generation AI select the output method.

[0054] The output unit can customize the output content based on the user's current areas of interest and purchasing history at the time of output. The output unit can, for example, output information related to products recently purchased by the user. The output unit can also output information about new products in a category in which the user is interested. Furthermore, the output unit can output related accessory information based on the user's purchasing history. This allows the output content to be customized based on the user's areas of interest and purchasing history, thereby providing more relevant information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's areas of interest and purchasing history into a generation AI and have the generation AI customize the output content.

[0055] The output unit can improve the output method by reflecting user feedback at the time of output. The output unit can adjust the output method, for example, based on feedback provided by the user in the past. The output unit can also customize the output content by reflecting user feedback. Furthermore, the output unit can determine output priorities based on user feedback. In this way, the output method can be optimized by reflecting user feedback. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input user feedback into a generation AI and cause the generation AI to improve the output method.

[0056] The output unit can select the optimal output method at the time of output, taking into account the user's geographical location information. For example, the output unit can prioritize output of campaign information for the store where the user is currently located. The output unit can also output sale information for nearby stores based on the user's location information. Furthermore, the output unit can output regionally-limited product information based on the user's location information. This makes it possible to provide highly relevant information by taking the user's geographical location information into consideration. Some or all of the above-described processing in the output unit can be performed using, for example, AI, or can be performed without using AI. For example, the output unit can input the user's geographical location information to a generation AI and cause the generation AI to select the optimal output method.

[0057] At the time of output, the output unit can analyze the user's social media activity and provide related information. The output unit can, for example, output product information shared by the user on social media. The output unit can also analyze the content of the user's social media posts and output related campaign information. Furthermore, the output unit can output related information by referring to the activity of the user's friends on social media. In this way, highly relevant information can be provided by analyzing the user's social media activity. Some or all of the above-described processing in the output unit can be performed, for example, using AI or without AI. For example, the output unit can input the user's social media activity into a generation AI and cause the generation AI to provide related information.

[0058] The output unit can customize the output method by reflecting the user's past feedback at the time of output. The output unit can adjust the output method based on, for example, feedback provided by the user in the past. The output unit can also customize the output content by reflecting the user's feedback. Furthermore, the output unit can determine output priorities based on the user's feedback. This allows the output method to be optimized by reflecting the user's past feedback. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's feedback to a generation AI and have the generation AI customize the output method.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The analysis unit can analyze the user's past purchase history and suggest similar products and services. For example, it can analyze information about smartphone accessories the user has previously purchased and provide information about related new products. It can also prioritize analysis of similar campaign information based on the history of campaigns the user has previously participated in. It can also analyze information about related products and services by referring to inquiries the user has made in the past. This makes it possible to make more personalized suggestions by utilizing the user's past purchase history.

[0061] The collection unit can analyze the user's social media activities and collect related data. For example, it can collect product information shared by the user on social media. It can also analyze the content posted by the user on social media and collect related campaign information. It can also collect related data by referring to the activities of the user's friends on social media. In this way, it is possible to collect related data by analyzing the user's social media activities.

[0062] The output unit can prioritize output of highly relevant data taking into account the user's geographical location information. For example, it can prioritize output of campaign information for the store where the user is currently located. It can also output sale information for nearby stores based on the user's location information. It can also output regionally-limited product information based on the user's location information. In this way, it is possible to provide highly relevant information by taking into account the user's geographical location information.

[0063] The collection unit can adjust the collection method by reflecting the user's past feedback. For example, the type of data to be collected can be adjusted based on feedback provided by the user in the past. The collection unit can also change the priority of the data to be collected by reflecting the user's feedback. Furthermore, the collection unit can optimize the collection method based on the user's feedback. In this way, the collection method can be optimized by reflecting the user's past feedback.

[0064] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, an analysis algorithm specialized for product characteristics can be applied to product information. The analysis unit can also apply an analysis algorithm specialized for marketing to campaign information. Furthermore, the analysis unit can apply an analysis algorithm specialized for service quality to service information. In this way, applying different analysis algorithms depending on the data category improves the accuracy of analysis.

[0065] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, it can prioritize collecting campaign information for the store where the user is currently located. The collection unit can also collect sale information for nearby stores based on the user's location information. Furthermore, the collection unit can also collect regionally-limited product information based on the user's location information. In this way, it is possible to prioritize collecting highly relevant data by taking into account the user's geographical location information.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The collection unit collects training data. The training data includes, but is not limited to, voice data, text data, and image data. The collection unit can collect information such as various services, terminals, and campaign specifications. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis is performed based on, for example, data preprocessing, feature extraction, algorithm application, etc., but is not limited to these examples. The analysis unit can also refine the analysis results using function calling or RAG. Step 3: The generator generates speech based on the data analyzed by the analyzer. The speech generation is performed, for example, based on speech synthesis technology or an algorithm used, but is not limited to such examples. The generator can also generate speech based on speech extracted from excellent speech data. Step 4: The output unit outputs the voice generated by the generation unit. The output is performed by a method such as, but not limited to, voice output through a speaker or text output.

[0068] (Example 2) The customer service system according to an embodiment of the present invention uses an improved robot incorporating a generative AI to serve customers. The customer service system uses the generative AI to provide voice-to-voice interaction and, if necessary, can accept image and text input and generate voice based on that. Training data includes information on various services, devices, campaign specifications, and other information, and also utilizes Function Calling and RAG. For sales pitches in particular, the generative AI generates voice responses based on speech extracted from excellent speech data. For example, the customer service system responds to customer questions with voice. For example, if a customer asks, "What are the features of this smartphone?", the customer service system responds based on the training data with, "This smartphone has a high-resolution camera and good battery life." Regarding campaign information, if a customer asks, "What are the current campaigns?", the customer service system responds with, "Currently, if you purchase a smartphone, you will receive a free case." This allows the customer service system to provide quick and accurate service to customers. This allows the customer service system to provide quick and accurate service to customers using the generative AI. For example, customer satisfaction can be improved, which is expected to lead to an increase in the number of contracts. Furthermore, reskilling robots will enable them to respond to new services and campaigns, broadening the scope of their use.

[0069] The customer service system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and an output unit. The collection unit collects training data. The training data may include, but is not limited to, voice data, text data, and image data. The collection unit may collect information on various services, terminals, campaign specifications, and the like. The analysis unit analyzes the data collected by the collection unit. The analysis may be performed, for example, based on data preprocessing, feature extraction, and algorithm application, but is not limited to these examples. The analysis unit may also refine the analysis results using function calling or RAG. The generation unit generates speech based on the data analyzed by the analysis unit. The speech may be generated, for example, based on speech synthesis technology or an algorithm, but is not limited to these examples. The generation unit may also generate speech based on speech extracted from excellent speech data. The output unit outputs the speech generated by the generation unit. The output may be performed, for example, by audio output through a speaker or text output, but is not limited to these examples. This allows the customer service system according to the embodiment to perform a consistent process from training data collection to analysis, speech generation, and output. For example, the customer service system responds by voice to questions posed by customers. For example, if a customer asks, "What are the features of this smartphone?", the customer service system will respond based on the learning data with, "This smartphone has a high-resolution camera and a long battery life." Similarly, if a customer asks about campaign information, "What are the current campaigns?", the customer service system will respond with, "Currently, if you purchase a smartphone, you will receive a case for free." This allows the customer service system to respond to customers quickly and accurately.

[0070] The collection unit can collect information on various services, devices, and campaign specifications. The collection unit can, for example, collect information on online services and offline services. The collection unit can also collect device information such as smartphones, tablets, and PCs. Furthermore, the collection unit can collect information on campaign specifications such as promotion content, period, and target users. By collecting a variety of information, more accurate analysis is possible. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input information on various services, devices, and campaign specifications into a generation AI and cause the generation AI to collect information.

[0071] The analysis unit can refine the analysis results using function calling or RAG. The analysis unit can perform function calling using, for example, an API call. The analysis unit can also refine the analysis results using a retrieval augmented generation (RAG) technique. This improves the accuracy of the analysis results by utilizing function calling or RAG. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input function calling or RAG techniques into a generation AI and have the generation AI refine the analysis results.

[0072] The generation unit can generate speech based on talk extracted from excellent talk data. The generation unit can generate speech using, for example, excellent talk data selected based on evaluation criteria. The generation unit can also generate speech based on talk data extracted through a selection process. This enables high-quality service by generating speech based on excellent talk data. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the generation unit can input excellent talk data into a generation AI and have the generation AI generate speech.

[0073] The output unit can provide the generated voice to the customer. The output unit can provide the generated voice to the customer through a speaker, for example. The output unit can also display the content of the generated voice using text output. This allows for quick and accurate response by providing the generated voice to the customer. Some or all of the above-mentioned processing in the output unit can be performed using, for example, AI, or can be performed without using AI. For example, the output unit can input the generated voice to a generation AI and have the generation AI provide the voice.

[0074] The generation unit can generate an appropriate response to a customer's question. The generation unit can generate an appropriate response based on, for example, the content of the customer's question. The generation unit can also generate a response to the customer's question based on learning data. This generates an appropriate response to the customer's question, thereby improving customer satisfaction. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the content of the customer's question into the generation AI and cause the generation AI to generate an appropriate response.

[0075] The collection unit can estimate the user's emotions and prioritize the data to be collected based on the estimated user emotions. For example, if the user is excited, the collection unit can prioritize collecting the latest campaign information. Furthermore, if the user is relaxed, the collection unit can prioritize collecting detailed product information. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting concise sales points. This enables more appropriate data collection by prioritizing data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI determine the data priorities.

[0076] During collection, the collection unit can analyze the user's past interaction history and select an appropriate data collection method. For example, the collection unit can prioritize collection of product information in which the user has shown interest in the past. The collection unit can also re-collect information on campaigns in which the user has previously participated. Furthermore, the collection unit can collect related data based on the content of inquiries made by the user in the past. This makes it possible to select an optimal data collection method by analyzing the past interaction history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past interaction history into a generation AI and have the generation AI select a data collection method.

[0077] The collection unit can perform filtering based on the user's current areas of interest and purchase history when collecting data. For example, the collection unit can prioritize collecting information related to products recently purchased by the user. The collection unit can also collect new product information in categories in which the user is interested. Furthermore, the collection unit can collect related accessory information from the user's purchase history. This allows for filtering based on the user's areas of interest and purchase history to collect more relevant data. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's areas of interest and purchase history into a generation AI and have the generation AI perform filtering.

[0078] The collection unit can select an appropriate collection means depending on the user's input method during collection. For example, if the user is using voice input, the collection unit can prioritize collecting voice data. Furthermore, if the user is using text input, the collection unit can also prioritize collecting text data. Furthermore, if the user is using image input, the collection unit can also prioritize collecting image data. This enables efficient data collection by selecting the optimal collection means depending on the user's input method. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's input method to the generation AI and have the generation AI select the collection means.

[0079] The collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated user emotions. For example, if the user is excited, the collection unit can collect the latest information in real time. Furthermore, if the user is relaxed, the collection unit can collect information at a slow pace. Furthermore, if the user is in a hurry, the collection unit can quickly collect necessary information. By adjusting the timing of data collection based on the user's emotions, data can be collected at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI adjust the timing of data collection.

[0080] During collection, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, the collection unit can prioritize collecting campaign information for the store where the user is currently located. The collection unit can also collect sale information for nearby stores based on the user's location information. Furthermore, the collection unit can also collect region-specific product information based on the user's location information. In this way, highly relevant data can be collected preferentially by taking the user's geographical location information into account. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to collect highly relevant data.

[0081] During collection, the collection unit can analyze the user's social media activities and collect related data. For example, the collection unit can collect product information shared by the user on social media. The collection unit can also analyze the content of the user's social media posts and collect related campaign information. Furthermore, the collection unit can collect related data by referring to the activities of the user's friends on social media. In this way, related data can be collected by analyzing the user's social media activities. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's social media activities into the generation AI and cause the generation AI to collect related data.

[0082] The collection unit can adjust the collection method by reflecting the user's past feedback when collecting data. The collection unit can, for example, adjust the type of data to collect based on feedback provided by the user in the past. The collection unit can also change the priority of data to collect by reflecting the user's feedback. Furthermore, the collection unit can optimize the collection method based on the user's feedback. In this way, the collection method can be optimized by reflecting the user's past feedback. Some or all of the above-described processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input the user's past feedback into the generation AI and cause the generation AI to adjust the collection method.

[0083] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated user emotions. For example, if the user is excited, the analysis unit can perform a detailed analysis to improve accuracy. The analysis unit can also perform a standard analysis when the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit can quickly perform an analysis and provide results. This enables more appropriate analysis by adjusting the accuracy of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the analysis accuracy.

[0084] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit can perform a detailed analysis on important campaign information. The analysis unit can also perform a standard analysis on general product information. Furthermore, the analysis unit can also perform a simplified analysis on information with low urgency. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of the data to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0085] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, the analysis unit can apply an analysis algorithm specialized for product characteristics to product information. The analysis unit can also apply an analysis algorithm specialized for marketing to campaign information. Furthermore, the analysis unit can apply an analysis algorithm specialized for service quality to service information. By applying different analysis algorithms depending on the data category, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data category to the generation AI and cause the generation AI to apply the analysis algorithm.

[0086] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit can, for example, adjust the analysis algorithm based on feedback provided by the user in the past. The analysis unit can also improve the accuracy of the analysis by referring to the user's past analysis results. Furthermore, the analysis unit can determine the priority of the analysis based on the user's past analysis results. This improves the accuracy of the analysis by referring to the user's past analysis results. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0087] The analysis unit can estimate the user's emotions and determine analysis priorities based on the estimated user emotions. For example, if the user is excited, the analysis unit can prioritize analyzing important information. Furthermore, if the user is relaxed, the analysis unit can prioritize analyzing standard information. Furthermore, if the user is in a hurry, the analysis unit can prioritize analyzing information that requires quick analysis. Thus, by determining analysis priorities based on the user's emotions, more important data can be analyzed preferentially. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI determine the analysis priorities.

[0088] During analysis, the analysis unit can determine the priority of analysis based on the time of data submission. The analysis unit can, for example, prioritize analysis of the most recent data. The analysis unit can also postpone data that was submitted earlier. Furthermore, the analysis unit can prioritize analysis of data with high urgency. In this way, by determining the priority of analysis based on the time of data submission, the most recent data can be analyzed preferentially. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time of data submission to the generation AI and have the generation AI determine the priority of analysis.

[0089] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. For example, the analysis unit can prioritize analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. Furthermore, the analysis unit can optimize the order of analysis based on the relevance of the data. This enables efficient analysis by adjusting the order of analysis based on the relevance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of the data to the generation AI and have the generation AI adjust the order of analysis.

[0090] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has specialized knowledge, the analysis unit can use a lot of technical terms. Furthermore, if the user only has general knowledge, the analysis unit can avoid technical terms. Furthermore, the analysis unit can adjust the expression of the analysis results according to the user's level of expertise. By adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise into the generation AI and have the generation AI use technical terms.

[0091] The generation unit can estimate the user's emotions and adjust the expression method of the generated voice based on the estimated user's emotions. For example, if the user is excited, the generation unit can generate a bright and cheerful voice. Furthermore, if the user is relaxed, the generation unit can generate a calm voice. Furthermore, if the user is in a hurry, the generation unit can generate a quick and concise voice. This enables more appropriate voice responses by adjusting the expression method of the voice based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the expression method of the voice.

[0092] The generation unit can adjust the level of detail of the generated voice based on the importance of the data during generation. For example, the generation unit can generate detailed voice for important campaign information. The generation unit can also generate standard voice for general product information. Furthermore, the generation unit can generate simple voice for information with low urgency. This enables efficient voice generation by adjusting the level of detail of the voice based on the importance of the data. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the importance of the data to the generation AI and cause the generation AI to adjust the level of detail of the voice.

[0093] The generation unit can apply different generation algorithms depending on the data category during generation. For example, the generation unit can apply a generation algorithm specialized for product characteristics to product information. The generation unit can also apply a generation algorithm specialized for marketing to campaign information. The generation unit can also apply a generation algorithm specialized for service quality to service information. By applying different generation algorithms depending on the data category, the accuracy of voice generation is improved. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the data category to the generation AI and cause the generation AI to apply the generation algorithm.

[0094] During generation, the generation unit can improve the accuracy of generation by referring to the user's past generation results. The generation unit can, for example, adjust the generation algorithm based on feedback provided by the user in the past. The generation unit can also improve the accuracy of generation by referring to the user's past generation results. Furthermore, the generation unit can determine the priority of generation based on the user's past generation results. In this way, the accuracy of generation is improved by referring to the user's past generation results. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's past generation results into the generation AI and cause the generation AI to improve the accuracy of generation.

[0095] The generation unit can estimate the user's emotions and adjust the length of the generated audio based on the estimated user emotions. For example, if the user is in a hurry, the generation unit can generate short, to-the-point audio. Furthermore, if the user is relaxed, the generation unit can generate longer audio with detailed explanations. Furthermore, if the user is excited, the generation unit can generate audio with visually stimulating effects. This enables more appropriate audio responses by adjusting the length of the audio based on the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the audio.

[0096] At the time of generation, the generation unit can determine the priority of the voice to be generated based on the time of data submission. The generation unit can, for example, generate voice based on the latest data. The generation unit can also postpone data that was submitted earlier. Furthermore, the generation unit can also prioritize generating voice for data with high urgency. In this way, by determining the priority of voice based on the time of data submission, voice can be generated with priority for the latest data. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the time of data submission to the generation AI and have the generation AI determine the priority of the voice.

[0097] The generation unit can adjust the order of the voices to be generated based on the relevance of the data during generation. For example, the generation unit can prioritize generating voice from highly relevant data. The generation unit can also postpone generating voice from less relevant data. Furthermore, the generation unit can optimize the order of voice generation based on the relevance of the data. This enables efficient voice generation by adjusting the order of voices based on the relevance of the data. Some or all of the above-described processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can input the relevance of the data to the generation AI and cause the generation AI to adjust the order of voice generation.

[0098] During generation, the generation unit can adjust the use of technical terms in the generated speech according to the user's level of expertise. For example, if the user has specialized knowledge, the generation unit can generate speech that uses a lot of technical terms. Furthermore, if the user only has general knowledge, the generation unit can generate speech that avoids technical terms. Furthermore, the generation unit can adjust the expression of the speech according to the user's level of expertise. This allows for a more understandable speech response by adjusting the use of technical terms in the speech according to the user's level of expertise. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the user's level of expertise into the generation AI and have the generation AI execute the use of technical terms.

[0099] The output unit can estimate the user's emotion and adjust the voice expression method to be output based on the estimated user's emotion. For example, if the user is excited, the output unit can output a bright and cheerful voice. Furthermore, if the user is relaxed, the output unit can output a calm voice. Furthermore, if the user is in a hurry, the output unit can output a quick and concise voice. This enables more appropriate voice response by adjusting the voice expression method based on the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the output unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the output unit can input the user's emotion data to the generation AI and have the generation AI adjust the voice expression method.

[0100] At the time of output, the output unit can select the optimal output method by referring to the user's past interaction history. For example, the output unit can output based on the user's preferred voice tone in the past. The output unit can also select the optimal output method by referring to the user's past interaction history. Furthermore, the output unit can adjust the output method based on the user's past feedback. In this way, the optimal output method can be selected by referring to the user's past interaction history. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's past interaction history into a generation AI and have the generation AI select the output method.

[0101] The output unit can customize the output content based on the user's current areas of interest and purchasing history at the time of output. The output unit can, for example, output information related to products recently purchased by the user. The output unit can also output information about new products in a category in which the user is interested. Furthermore, the output unit can output related accessory information based on the user's purchasing history. This allows the output content to be customized based on the user's areas of interest and purchasing history, thereby providing more relevant information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's areas of interest and purchasing history into a generation AI and have the generation AI customize the output content.

[0102] The output unit can improve the output method by reflecting user feedback at the time of output. The output unit can adjust the output method, for example, based on feedback provided by the user in the past. The output unit can also customize the output content by reflecting user feedback. Furthermore, the output unit can determine output priorities based on user feedback. In this way, the output method can be optimized by reflecting user feedback. Some or all of the above-mentioned processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input user feedback into a generation AI and cause the generation AI to improve the output method.

[0103] The output unit can estimate the user's emotions and determine the priority of audio to be output based on the estimated user's emotions. For example, when the user is excited, the output unit can prioritize output of important information. Furthermore, when the user is relaxed, the output unit can prioritize output of standard information. Furthermore, when the user is in a hurry, the output unit can prioritize output of information that needs to be output quickly. Thus, by determining the priority of audio based on the user's emotions, more important information can be provided preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the output unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the output unit can input the user's emotion data to the generation AI and have the generation AI determine the priority of audio.

[0104] The output unit can select the optimal output method at the time of output, taking into account the user's geographical location information. For example, the output unit can prioritize output of campaign information for the store where the user is currently located. The output unit can also output sale information for nearby stores based on the user's location information. Furthermore, the output unit can output regionally-limited product information based on the user's location information. This makes it possible to provide highly relevant information by taking the user's geographical location information into consideration. Some or all of the above-described processing in the output unit can be performed using, for example, AI, or can be performed without using AI. For example, the output unit can input the user's geographical location information to a generation AI and cause the generation AI to select the optimal output method.

[0105] At the time of output, the output unit can analyze the user's social media activity and provide related information. The output unit can, for example, output product information shared by the user on social media. The output unit can also analyze the content of the user's social media posts and output related campaign information. Furthermore, the output unit can output related information by referring to the activity of the user's friends on social media. In this way, highly relevant information can be provided by analyzing the user's social media activity. Some or all of the above-described processing in the output unit can be performed, for example, using AI or without AI. For example, the output unit can input the user's social media activity into a generation AI and cause the generation AI to provide related information.

[0106] The output unit can customize the output method by reflecting the user's past feedback at the time of output. The output unit can adjust the output method based on, for example, feedback provided by the user in the past. The output unit can also customize the output content by reflecting the user's feedback. Furthermore, the output unit can determine output priorities based on the user's feedback. This allows the output method to be optimized by reflecting the user's past feedback. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's feedback to a generation AI and have the generation AI customize the output method. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and output unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit can collect voice data and image data using the camera 42 and microphone 38B of the smart device 14, and collect information such as various services, terminals, and campaign specifications using the specific processing unit 290 of the data processing device 12. The analysis unit, for example, analyzes the data collected by the specific processing unit 290 of the data processing device 12 and refines the analysis results using Function Calling or RAG. For example, the generation unit can generate voice based on the data analyzed by the specific processing unit 290 of the data processing device 12, and can also generate voice based on talk extracted from excellent talk data. The output unit, for example, outputs the generated voice through the speaker 40B of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and output unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect voice data and image data using the camera 42 and microphone 238 of the smart glasses 214, and collect information such as various services, terminals, and campaign specifications via the specific processing unit 290 of the data processing device 12. The analysis unit, for example, analyzes the data collected by the specific processing unit 290 of the data processing device 12 and refines the analysis results using Function Calling or RAG. For example, the generation unit can generate voice based on the data analyzed by the specific processing unit 290 of the data processing device 12, and can also generate voice based on talk extracted from excellent talk data. The output unit, for example, outputs the generated voice through the speaker 240 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and output unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit can collect voice data and image data using the camera 42 and microphone 238 of the headset-type terminal 314, and collect information such as various services, terminals, and campaign specifications using the specific processing unit 290 of the data processing device 12. The analysis unit, for example, analyzes the data collected by the specific processing unit 290 of the data processing device 12 and refines the analysis results using Function Calling or RAG. For example, the generation unit can generate voice based on the data analyzed by the specific processing unit 290 of the data processing device 12, and can also generate voice based on talk extracted from excellent talk data. The output unit, for example, outputs the generated voice through the speaker 240 of the headset-type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and output unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect voice data and image data using the camera 42 and microphone 238 of the robot 414, and collect information such as various services, terminals, and campaign specifications via the specific processing unit 290 of the data processing device 12. The analysis unit, for example, analyzes the data collected by the specific processing unit 290 of the data processing device 12 and refines the analysis results using Function Calling or RAG. For example, the generation unit can generate voice based on the data analyzed by the specific processing unit 290 of the data processing device 12, and can also generate voice based on talk extracted from excellent talk data. The output unit, for example, outputs the generated voice through the speaker 240 of the robot 414.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] The analysis unit can analyze the user's past purchase history and suggest similar products and services. For example, it can analyze information about smartphone accessories the user has previously purchased and provide information about related new products. It can also prioritize analysis of similar campaign information based on the history of campaigns the user has previously participated in. It can also analyze information about related products and services by referring to inquiries the user has made in the past. This makes it possible to make more personalized suggestions by utilizing the user's past purchase history.

[0109] The collection unit can analyze the user's social media activities and collect related data. For example, it can collect product information shared by the user on social media. It can also analyze the content posted by the user on social media and collect related campaign information. It can also collect related data by referring to the activities of the user's friends on social media. In this way, it is possible to collect related data by analyzing the user's social media activities.

[0110] The generation unit can estimate the user's emotions and adjust the tone of the generated voice based on the estimated user emotions. For example, if the user is excited, the voice can be generated in a bright and cheerful tone. If the user is relaxed, the voice can be generated in a calm tone. Furthermore, if the user is in a hurry, the voice can be generated in a quick and concise tone. This allows for more appropriate voice responses by adjusting the voice tone based on the user's emotions.

[0111] The output unit can prioritize output of highly relevant data taking into account the user's geographical location information. For example, it can prioritize output of campaign information for the store where the user is currently located. It can also output sale information for nearby stores based on the user's location information. It can also output regionally-limited product information based on the user's location information. In this way, it is possible to provide highly relevant information by taking into account the user's geographical location information.

[0112] The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user's emotions. For example, if the user is excited, important information can be analyzed with priority. Also, if the user is relaxed, standard information can be analyzed with priority. Furthermore, if the user is in a hurry, information that requires quick analysis can be analyzed with priority. In this way, by determining the analysis priority based on the user's emotions, more important data can be analyzed with priority.

[0113] The collection unit can adjust the collection method by reflecting the user's past feedback. For example, the type of data to be collected can be adjusted based on feedback provided by the user in the past. The collection unit can also change the priority of the data to be collected by reflecting the user's feedback. Furthermore, the collection unit can optimize the collection method based on the user's feedback. In this way, the collection method can be optimized by reflecting the user's past feedback.

[0114] The generation unit can estimate the user's emotions and adjust the length of the generated voice based on the estimated user emotions. For example, if the user is in a hurry, a short voice that gets to the point can be generated. If the user is relaxed, a longer voice that includes detailed explanations can be generated. Furthermore, if the user is excited, a voice that adds visually stimulating effects can be generated. This allows for more appropriate voice responses by adjusting the length of the voice based on the user's emotions.

[0115] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. For example, an analysis algorithm specialized for product characteristics can be applied to product information. The analysis unit can also apply an analysis algorithm specialized for marketing to campaign information. Furthermore, the analysis unit can apply an analysis algorithm specialized for service quality to service information. In this way, applying different analysis algorithms depending on the data category improves the accuracy of analysis.

[0116] The output unit can estimate the user's emotions and adjust the way the voice is expressed to be output based on the estimated user's emotions. For example, if the user is excited, a bright and cheerful voice can be output. If the user is relaxed, a calm voice can be output. Furthermore, if the user is in a hurry, a quick and concise voice can be output. This allows for more appropriate voice responses by adjusting the way the voice is expressed based on the user's emotions.

[0117] When collecting data, the collection unit can prioritize collecting highly relevant data by taking into account the user's geographical location information. For example, it can prioritize collecting campaign information for the store where the user is currently located. The collection unit can also collect sale information for nearby stores based on the user's location information. Furthermore, the collection unit can also collect regionally-limited product information based on the user's location information. In this way, it is possible to prioritize collecting highly relevant data by taking into account the user's geographical location information.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The collection unit collects training data. The training data includes, but is not limited to, voice data, text data, and image data. The collection unit can collect information such as various services, terminals, and campaign specifications. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis is performed based on, for example, data preprocessing, feature extraction, algorithm application, etc., but is not limited to these examples. The analysis unit can also refine the analysis results using function calling or RAG. Step 3: The generator generates speech based on the data analyzed by the analyzer. The speech generation is performed, for example, based on speech synthesis technology or an algorithm used, but is not limited to such examples. The generator can also generate speech based on speech extracted from excellent speech data. Step 4: The output unit outputs the voice generated by the generation unit. The output is performed by a method such as, but not limited to, voice output through a speaker or text output.

[0120] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0121] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0123] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0126] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0127] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0128] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0129] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0130] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0131] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0132] 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.

[0133] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0134] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0135] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0136] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0138] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0142] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0143] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0144] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0145] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0146] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0147] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0148] 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.

[0149] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0150] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0151] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0152] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0154] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0158] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0159] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0160] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0161] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0162] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0163] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0164] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0165] 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.

[0166] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0167] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0169] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0171] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0174] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0175] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0176] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0177] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0178] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0179] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0180] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0181] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0182] 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.

[0183] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0184] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0185] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0186] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0187] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0188] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0189] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0190] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0191] [Explanation of symbols]

[0192] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects learning data; an analysis unit that analyzes the data collected by the collection unit; a generation unit that generates a voice based on the data analyzed by the analysis unit; an output unit that outputs the sound generated by the generation unit; Equipped with A system characterized by:

2. The collecting unit Collect information on various services, devices, and campaign specifications 2. The system of claim 1.

3. The analysis unit Refine your analysis results using Function Calling or RAG 2. The system of claim 1.

4. The generation unit Generate speech based on speech extracted from high-quality speech data 2. The system of claim 1.

5. The output unit Providing the generated audio to customers 2. The system of claim 1.

6. The generation unit Generate appropriate responses to customer questions 2. The system of claim 1.

7. The collecting unit Estimate user emotions and prioritize data collection based on the estimated user emotions 2. The system of claim 1.

8. The collecting unit At the time of collection, analyze the user's past interaction history and select the appropriate data collection method.

2. The system of claim 1.

Images