system

Abstract

The system according to this embodiment aims to generate marketable text and reference prices with minimal information input. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit receives voice and product photos or videos from the seller. The analysis unit analyzes the information received by the reception unit. The generation unit generates sales text and reference prices based on the information analyzed by the analysis unit. The confirmation unit allows the seller to confirm the information generated by the generation unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the seller has to take the trouble to create a product description, and it may not lead to sales.

[0005] The system according to the embodiment aims to generate a sellable text and a reference price with minimal information input.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit receives voice and product photos or videos from the seller. The analysis unit analyzes the information received by the reception unit. The generation unit generates sales text and reference prices based on the information analyzed by the analysis unit. The confirmation unit allows the seller to confirm the information generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can generate marketable text and reference prices with minimal information input. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The listing support system according to an embodiment of the present invention is a mechanism to solve the problems of listing products being cumbersome and sales not being generated due to ineffective descriptions. The listing support system allows sellers to input voice and photos or videos of the product. Next, the listing support system's AI analyzes this information and generates compelling descriptions and reference prices. This mechanism significantly reduces the effort required for listing products, as sellers only need to input minimal information, and the AI ​​automatically inputs the listing information and reference prices. Furthermore, compelling descriptions and appropriate pricing make it easier to generate sales. For example, the seller inputs a description of the product by voice. For example, they might say, "This product is a new smartphone, it is black, and has a capacity of 128GB." They also input photos and videos of the product at the same time. This provides the AI ​​with detailed product information. Next, the listing support system's AI analyzes the input voice information and photos / videos. The AI ​​uses voice recognition technology to convert the voice information into text and extracts the product's features. It also uses image recognition technology to analyze the product's appearance and condition from the photos and videos. This allows the AI ​​to grasp detailed product information. Next, the listing support system's AI generates compelling descriptions. For example, it generates text such as, "Brand new smartphone, black, 128GB capacity. Features a high-performance camera and long-lasting battery." The AI ​​also calculates a reference price based on market data, ensuring appropriate pricing. The generated listing information and reference price are provided to the seller. The seller can review the information generated by the AI ​​and make corrections as needed. Finally, the information reviewed by the seller is listed on the flea market site. This significantly reduces the effort required for sellers, as they only need to input minimal information, and the AI ​​automatically enters the listing information and reference price. Furthermore, compelling descriptions and appropriate pricing increase the likelihood of sales. This is expected to lead to an increase in sellers and users, ultimately boosting the revenue of the flea market site. In this way, the listing support system reduces the burden on sellers and improves the success rate of sales.

[0029] The listing support system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit receives audio and product photos or videos from the seller. The reception unit can accept audio depending on the format and length of the audio file, for example. The reception unit can also accept product photos and videos depending on their resolution and format. For example, the reception unit can accept JPEG images and MP4 videos. The analysis unit analyzes the information received by the reception unit. The analysis unit converts the audio information into text using speech recognition technology and extracts product features, for example. The analysis unit can analyze audio using technologies such as deep learning and HMM (Hidden Markov Model). The analysis unit also analyzes the appearance and condition of the product from photos and videos using image recognition technology. The analysis unit can analyze images using technologies such as CNN (Convolutional Neural Network) and SIFT (Scale-Invariant Feature Transformation). The generation unit generates sales text and reference prices based on the information analyzed by the analysis unit. The generation unit generates marketable text based, for example, on criteria such as text length and word selection. The generation unit can generate text using text generation AI (e.g., LLM). The generation unit also calculates a reference price based on market data. The generation unit can calculate a price based on past sales data and pricing information of competing products. The verification unit allows the seller to verify the information generated by the generation unit. The verification unit allows the seller to verify the generated information and make corrections as needed. The verification unit can provide items that can be corrected and the procedures for making corrections. As a result, the listing support system according to this embodiment can reduce the burden on sellers and improve the success rate of sales.

[0030] The reception unit accepts audio and product photos / videos from sellers. For example, it can accept audio files according to their format and length. Specifically, it supports common audio formats such as MP3 and WAV, and can accept audio ranging from a few seconds to a few minutes in length without problems. The reception unit can also accept product photos and videos according to their resolution and format. For example, it can accept JPEG images and MP4 videos. A minimum image resolution of 800x600 pixels or higher is recommended, and a video resolution of 720p or higher is recommended. This allows the reception unit to efficiently accept diverse data formats provided by sellers. Furthermore, the reception unit performs basic error checks upon data acceptance, detecting and notifying sellers of issues such as format mismatches or insufficient resolution. For example, if an audio file is not in the specified format or the image resolution is too low, it prompts the seller to resubmit the data. This ensures high-quality data, allowing subsequent analysis and generation processes to proceed smoothly.

[0031] The analysis unit analyzes the information received by the reception unit. For example, the analysis unit converts audio information into text using speech recognition technology and extracts product features. Specifically, it can analyze audio using technologies such as deep learning and HMM (Hidden Markov Model). Speech recognition technology analyzes the waveform data of audio, identifies phonemes and words, and converts them into text. This allows for accurate transcription of product features and detailed information described by the seller via audio. The analysis unit also analyzes the appearance and condition of products from photos and videos using image recognition technology. Specifically, it can analyze images using technologies such as CNN (Convolutional Neural Network) and SIFT (Scale-Invariant Feature Transformation). CNN is suitable for extracting image features and identifying the shape, color, and texture of products. SIFT, on the other hand, is useful for detecting feature points in images and analyzing the details and condition of products in detail. This allows the analysis unit to accurately grasp the appearance and condition of products and extract the necessary data for listing information. Furthermore, the analysis unit can also integrate audio and image data to analyze the overall characteristics of the product. For example, by combining product features described via audio with the product's appearance and condition confirmed through images and videos, more detailed and accurate listing information can be generated. This allows the analysis unit to effectively analyze the diverse data provided by sellers and improve the quality of the listing information.

[0032] The generation unit generates compelling sales copy and reference prices based on information analyzed by the analysis unit. For example, the generation unit generates sales copy based on criteria such as text length and word selection. Specifically, it can generate text using text generation AI (e.g., LLM). LLM has learned from a large amount of text data and possesses the ability to generate natural-sounding text. For example, it can generate catchy slogans and descriptions that emphasize product features and benefits, stimulating purchasing intent. The generation unit also calculates reference prices based on market data. Specifically, it can calculate prices based on past sales data and competitor pricing information. The generation unit uses an algorithm that analyzes past sales history and market trends stored in a database to calculate the appropriate price for a product. This allows sellers to set appropriate prices based on market trends. Furthermore, the generation unit also has a function to customize the generated text and pricing information to suit the seller's needs. For example, if a seller wants to emphasize specific keywords or has special requests regarding pricing, the generation unit can generate listing information that reflects these requests. This reduces the burden on sellers and allows the generation unit to provide effective listing information.

[0033] The verification unit allows the seller to review the information generated by the generation unit. For example, the verification unit allows the seller to review the generated information and make corrections as needed. Specifically, the verification unit can provide editable items and correction procedures. For instance, if the seller wants to modify part of the generated text, the verification unit provides an editable text editor, making it easy for the seller to make corrections. Regarding pricing information, the verification unit also provides an interface for adjusting the price to the seller's desired level. This allows the seller to customize the generated information to their needs. Furthermore, the verification unit supports the process of the seller reviewing the information again after making corrections and finalizing it as the listing information. For example, after the seller has completed the corrections, the verification unit displays a final confirmation screen, allowing the seller to review all information and confirm that there are no problems. The verification unit also provides the option for the seller to return to the generation unit and generate new information if they are not satisfied with the corrections. This allows the verification unit to provide flexible support for sellers to create satisfactory listing information, ensuring a smooth listing process.

[0034] The analysis unit can convert audio information into text using speech recognition technology and extract product features. For example, the analysis unit can analyze audio using deep learning technology and convert it into text. The analysis unit can also analyze audio using a Hidden Markov Model (HMM) and extract product features. Furthermore, the analysis unit can apply algorithms to extract product features using speech recognition technology. For example, the analysis unit can use speech recognition technology to extract features such as the product's color, size, and condition. This improves the accuracy of listing information by converting audio information into text and extracting product features. Some or all of the above processing in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input audio data into an AI, which can then analyze the audio data, convert it into text, and extract product features.

[0035] The analysis unit can analyze the appearance and condition of products from photos and videos using image recognition technology. For example, the analysis unit can analyze images using a CNN (Convolutional Neural Network) to understand the appearance and condition of the product. The analysis unit can also analyze images using SIFT (Scale-Invariant Feature Transformation) to extract product features. Furthermore, the analysis unit can apply algorithms to analyze the appearance and condition of products using image recognition technology. For example, the analysis unit can use image recognition technology to detect the presence or absence of scratches or stains on the product. This improves the accuracy of listing information by analyzing the appearance and condition of products from photos and videos. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI. For example, the analysis unit can input image data into an AI, which can then analyze the image data to understand the appearance and condition of the product.

[0036] The generation unit can calculate a reference price based on market data. For example, the generation unit can calculate a reference price based on past sales data. The generation unit can also calculate a reference price based on price information of competing products. Furthermore, the generation unit can calculate a reference price based on market data that corresponds to the supply and demand of a product. For example, the generation unit can set a higher price for products with high demand and a lower price for products with high supply. This makes it possible to set appropriate prices by calculating a reference price based on market data. Some or all of the above processes in the generation unit may be performed using AI or not. For example, the generation unit can input market data into AI, and the AI ​​can analyze the market data to calculate a reference price.

[0037] The verification unit allows the seller to review the generated information and make corrections as needed. For example, the verification unit can display the generated information so that the seller can review it. The verification unit can also display editable items so that the seller can make corrections. Furthermore, the verification unit can provide correction procedures so that the seller can easily make corrections. For example, the verification unit can display the correction procedures step by step so that the seller can make corrections without getting lost. This improves the accuracy of the listing information by allowing the seller to review the generated information and make corrections as needed. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input the generated information into AI, and the AI ​​can suggest corrections.

[0038] The reception desk can provide an interface for sellers to input product descriptions by voice. For example, the reception desk can provide a voice input UI design to make it easy for sellers to input product descriptions by voice. The reception desk can also provide instructions on how to use voice input to ensure sellers can use voice input without confusion. Furthermore, the reception desk can provide voice input guides to ensure sellers can use voice input appropriately. For example, the reception desk can display voice input guidelines to show sellers how to use voice input. This reduces the effort required for sellers to input product descriptions by voice. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can input the voice input UI design into an AI, which can then suggest the optimal UI design.

[0039] The generation unit may include a learning data management unit that manages learning data for generating persuasive text. The generation unit may, for example, manage the method of collecting learning data and collect appropriate data. The generation unit may also, for example, manage the method of preprocessing the learning data to improve data quality. Furthermore, the generation unit may manage the method of updating the learning data to ensure that the latest data is always available. For example, the generation unit periodically updates the learning data and adds new data. This improves the accuracy of text generation by managing the learning data for generating persuasive text. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit inputs learning data into the AI, and the AI ​​preprocesses the data.

[0040] The reception desk can analyze the seller's past listing history and suggest the optimal input method. For example, the reception desk can prioritize suggesting input methods (voice, text, etc.) that the seller has frequently used in the past. The reception desk can also suggest input methods suitable for specific categories based on the seller's past listing history. Furthermore, the reception desk can analyze the seller's past successful listing history and suggest similar input methods. In this way, the optimal input method can be suggested by analyzing the seller's past listing history. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the seller's past listing history data into AI, and the AI ​​can suggest the optimal input method.

[0041] The reception system can filter voice input based on the seller's current projects and areas of interest. For example, the reception system may only accept voice input for products related to the seller's current ongoing projects. The reception system may also prioritize voice input for relevant products based on the seller's areas of interest. Furthermore, the reception system can filter voice input for relevant products by referring to the seller's past project history. This allows for the priority acquisition of highly relevant information by filtering based on the seller's current projects and areas of interest. Some or all of the above processing in the reception system may be performed using AI or not. For example, the reception system can input the seller's project data into an AI, which can then perform the filtering.

[0042] The reception unit can prioritize retrieving highly relevant information based on the seller's geographical location information when voice input is received. For example, the reception unit can prioritize retrieving region-specific product information based on the seller's current location. The reception unit can also prioritize retrieving information on products with high demand in the vicinity based on the seller's geographical location information. Furthermore, the reception unit can prioritize retrieving information on products that can be delivered, taking into account the seller's geographical location information. This improves the accuracy of the listing information by prioritizing the retrieval of highly relevant information based on the seller's geographical location information. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input geographical location information into the AI, which can then retrieve highly relevant information.

[0043] The reception desk can analyze the seller's social media activity and obtain relevant information when voice input is received. For example, the reception desk can analyze the content of the seller's social media posts and obtain information about related products. The reception desk can also obtain information about related products based on the interests of the seller's followers. Furthermore, the reception desk can obtain information about related products by referring to the seller's social media activity history. In this way, relevant information can be obtained by analyzing the seller's social media activity. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input social media data into AI, and the AI ​​can obtain relevant information.

[0044] The analysis unit can use speech recognition technology to perform text conversion that is appropriate to the seller's speaking style and accent. For example, the analysis unit can perform natural text conversion according to the seller's speaking style. The analysis unit can also perform accurate text conversion that takes into account the seller's accent. Furthermore, the analysis unit can analyze the characteristics of the seller's speaking style and perform optimal text conversion. For example, the analysis unit can perform phoneme analysis and intonation analysis to perform text conversion that is appropriate to the seller's speaking style. This improves the accuracy of text conversion by performing text conversion that is appropriate to the seller's speaking style and accent. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI. For example, the analysis unit can input the seller's voice data into AI, and the AI ​​can perform text conversion that is appropriate to the speaking style and accent.

[0045] The analysis unit can use image recognition technology to analyze the appearance and condition of a product in detail and extract its features. For example, the analysis unit can analyze the appearance of a product in detail and detect the presence or absence of scratches or stains. For example, the analysis unit can analyze the condition of a product and determine whether it is new or used. Furthermore, the analysis unit can extract the features of a product and provide information for generating a detailed description. For example, the analysis unit analyzes the appearance and condition of a product and applies an algorithm to extract its features. This improves the accuracy of the listing information by analyzing the appearance and condition of the product in detail and extracting its features.

[0046] The analysis unit can use image recognition technology to analyze the background information of a product and extract relevant information. For example, the analysis unit can analyze the background information of a product to identify the manufacturer and year of manufacture. The analysis unit can also analyze the background information of a product to identify past owners and usage history. Furthermore, the analysis unit can analyze the background information of a product and extract relevant market data. For example, the analysis unit can analyze the background information of a product and extract information about the product's manufacturer and related historical data. By analyzing the background information of a product and extracting relevant information, the accuracy of the listing information is improved. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the background information data of a product into an AI, which can then analyze the background information and extract relevant information.

[0047] The analysis unit can improve analysis accuracy by referencing the seller's past voice data using speech recognition technology. For example, the analysis unit can improve analysis accuracy by learning the seller's speaking style characteristics by referencing the seller's past voice data. The analysis unit can also make it easier to recognize specific terms or phrases based on the seller's past voice data. Furthermore, the analysis unit can improve the accuracy of speech recognition by analyzing the seller's past voice data. For example, the analysis unit optimizes the speech recognition algorithm based on past voice data. This improves analysis accuracy by referencing the seller's past voice data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input past voice data into AI, which can then improve the accuracy of speech recognition.

[0048] The generation unit can calculate a reference price based on market data, corresponding to the supply and demand of a product. For example, the generation unit can calculate a reference price based on market demand data. The generation unit can also calculate a reference price based on market supply data. Furthermore, the generation unit can calculate a reference price based on market trend data. For example, the generation unit can set a higher price for products with high demand and a lower price for products with high supply. This allows for appropriate pricing by calculating a reference price that corresponds to the supply and demand of a product. Some or all of the above-described processes in the generation unit may be performed using AI, or they may not be performed using AI. For example, the generation unit can input market data into AI, and the AI ​​can calculate a reference price that corresponds to supply and demand.

[0049] The generation unit can apply different generation algorithms depending on the product category when generating sales copy. For example, for electronics products, the generation unit can apply an algorithm that generates text including technical details. For fashion products, for example, the generation unit can apply an algorithm that generates text focusing on design and materials. Furthermore, for furniture products, the generation unit can apply an algorithm that generates text emphasizing usability and functionality. This enables the generation of optimal text tailored to the product category. Some or all of the above processing in the generation unit may be performed using AI, or not. For example, the generation unit can input product category data into the AI, and the AI ​​can apply a generation algorithm appropriate to the category.

[0050] The generation unit can calculate a reference price based on market data, taking into account the seasonality and trends of a product. For example, for highly seasonal products, the generation unit calculates a reference price according to the season. For example, for trending products, the generation unit can also calculate a reference price based on the latest market data. Furthermore, the generation unit can calculate a reference price during periods of high demand, taking into account seasonality and trends. For example, the generation unit calculates the price using seasonal sales data and trend prediction algorithms. This enables appropriate pricing that takes into account the seasonality and trends of a product. Some or all of the above processing in the generation unit may be performed using AI, or not. For example, the generation unit can input market data into AI, which can then calculate a reference price considering seasonality and trends.

[0051] The verification unit can refer to the seller's past revision history and make optimal revision suggestions. For example, the verification unit can analyze the revisions the seller has made in the past and make similar revision suggestions. For example, the verification unit can identify frequently revised sections from the seller's past revision history and make revision suggestions in advance. Furthermore, the verification unit can suggest the optimal revision method based on the seller's revision history. In this way, by referring to the seller's past revision history, it becomes possible to make optimal revision suggestions. Some or all of the above processes in the verification unit may be performed using AI or not. For example, the verification unit can input past revision history data into AI, and the AI ​​can make optimal revision suggestions.

[0052] The confirmation unit can customize the displayed content based on the seller's current situation when displaying the confirmation screen. For example, if the seller is in a hurry, the confirmation unit can display a concise confirmation screen. For example, if the seller is relaxed, the confirmation unit can also display a detailed confirmation screen. Furthermore, the confirmation unit can provide optimal display content based on the seller's current situation (time of day, location, etc.). This ensures that the optimal display content is provided based on the seller's current situation. Some or all of the above processing in the confirmation unit may be performed using AI or not. For example, the confirmation unit can input the seller's situation data into the AI, which can then customize the display content.

[0053] The verification unit can select the optimal display method when displaying the confirmation screen, taking into account the seller's device information. For example, if the seller is using a smartphone, the verification unit can provide a display method that matches the screen size. For example, if the seller is using a tablet, the verification unit can also provide a display method optimized for a larger screen. Furthermore, if the seller is using a desktop, the verification unit can provide a display method that includes detailed information. This ensures that the optimal display method is provided based on the seller's device information. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input device information into the AI, which can then select the optimal display method.

[0054] The verification unit can refer to the seller's social media activity and display relevant information when displaying the verification screen. For example, the verification unit can refer to the content of the seller's social media posts and display information about related products. For example, the verification unit can also display information about related products based on the interests of the seller's followers. Furthermore, the verification unit can refer to the seller's social media activity history and display information about related products. This provides relevant information based on the seller's social media activity. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input social media data into AI, and the AI ​​can display relevant information.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The reception desk can analyze a seller's past listing history and suggest the most suitable input method. For example, it can prioritize suggesting input methods that the seller has frequently used in the past (voice, text, etc.). It can also suggest input methods suitable for specific categories based on the seller's past listing history. Furthermore, it can analyze a seller's past successful listing history and suggest similar input methods. As a result, by analyzing a seller's past listing history, it is expected that the optimal input method can be suggested, improving the efficiency of the listing process.

[0057] The analysis unit can use speech recognition technology to perform text conversion that is tailored to the seller's speaking style and accent. For example, it can perform natural-sounding text conversion based on the seller's speaking style. It can also perform accurate text conversion by considering the seller's accent. Furthermore, it can analyze the characteristics of the seller's speaking style and perform optimal text conversion. As a result, it is expected that the accuracy of text conversion will improve by performing text conversion that is tailored to the seller's speaking style and accent.

[0058] The generation unit can apply different generation algorithms depending on the product category when generating compelling sales copy. For example, for electronics products, an algorithm that generates text including technical details can be applied. For fashion products, an algorithm that generates text focusing on design and materials can be applied. Furthermore, for furniture products, an algorithm that generates text emphasizing usability and functionality can be applied. This enables the generation of optimal text tailored to each product category, and is expected to provide more effective listing information.

[0059] The verification unit can refer to the seller's past revision history and make optimal revision suggestions. For example, it can analyze the revisions the seller has made in the past and make similar revision suggestions. It can also identify frequently revised areas from the seller's past revision history and make revision suggestions in advance. Furthermore, it can suggest the most suitable revision method based on the seller's revision history. As a result, by referring to the seller's past revision history, optimal revision suggestions become possible, and the accuracy of the listing information is expected to improve.

[0060] The reception system can prioritize retrieving highly relevant information based on the seller's geographical location when voice input is received. For example, it can prioritize retrieving region-specific product information based on the seller's current location. It can also prioritize retrieving information on products with high demand in the surrounding area based on the seller's geographical location. Furthermore, it can prioritize retrieving information on products that can be shipped, taking the seller's geographical location into consideration. As a result, it is expected that the accuracy of listing information will improve by prioritizing the retrieval of highly relevant information based on the seller's geographical location.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The reception desk receives audio and product photos / videos from the seller. For example, it can accept audio files depending on their format and length, as well as JPEG images and MP4 videos. Step 2: The analysis unit analyzes the information received by the reception unit. For example, it may use speech recognition technology to convert speech information into text and extract product features. It may also use technologies such as deep learning and HMM (Hidden Markov Model) to analyze speech, and image recognition technology to analyze the appearance and condition of products from photos and videos. It can also use technologies such as CNN (Convolutional Neural Network) and SIFT (Scale-Invariant Feature Transfer) to analyze images. Step 3: The generation unit generates marketable text and reference prices based on the information analyzed by the analysis unit. For example, it generates marketable text based on the length of the text and the selection criteria for the words used, and generates the text using text generation AI (e.g., LLM). It also calculates reference prices by referring to past sales data and price information of competing products based on market data. Step 4: The verification unit allows the seller to verify the information generated by the generation unit. For example, the seller can review the generated information and make corrections as needed. The verification unit provides the items that can be corrected and the steps for making those corrections.

[0063] (Example of form 2) The listing support system according to an embodiment of the present invention is a mechanism to solve the problems of listing products being cumbersome and sales not being generated due to ineffective descriptions. The listing support system allows sellers to input voice and photos or videos of the product. Next, the listing support system's AI analyzes this information and generates compelling descriptions and reference prices. This mechanism significantly reduces the effort required for listing products, as sellers only need to input minimal information, and the AI ​​automatically inputs the listing information and reference prices. Furthermore, compelling descriptions and appropriate pricing make it easier to generate sales. For example, the seller inputs a description of the product by voice. For example, they might say, "This product is a new smartphone, it is black, and has a capacity of 128GB." They also input photos and videos of the product at the same time. This provides the AI ​​with detailed product information. Next, the listing support system's AI analyzes the input voice information and photos / videos. The AI ​​uses voice recognition technology to convert the voice information into text and extracts the product's features. It also uses image recognition technology to analyze the product's appearance and condition from the photos and videos. This allows the AI ​​to grasp detailed product information. Next, the listing support system's AI generates compelling descriptions. For example, it generates text such as, "Brand new smartphone, black, 128GB capacity. Features a high-performance camera and long-lasting battery." The AI ​​also calculates a reference price based on market data, ensuring appropriate pricing. The generated listing information and reference price are provided to the seller. The seller can review the information generated by the AI ​​and make corrections as needed. Finally, the information reviewed by the seller is listed on the flea market site. This significantly reduces the effort required for sellers, as they only need to input minimal information, and the AI ​​automatically enters the listing information and reference price. Furthermore, compelling descriptions and appropriate pricing increase the likelihood of sales. This is expected to lead to an increase in sellers and users, ultimately boosting the revenue of the flea market site. In this way, the listing support system reduces the burden on sellers and improves the success rate of sales.

[0064] The listing support system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, and a confirmation unit. The reception unit receives audio and product photos or videos from the seller. The reception unit can accept audio depending on the format and length of the audio file, for example. The reception unit can also accept product photos and videos depending on their resolution and format. For example, the reception unit can accept JPEG images and MP4 videos. The analysis unit analyzes the information received by the reception unit. The analysis unit converts the audio information into text using speech recognition technology and extracts product features, for example. The analysis unit can analyze audio using technologies such as deep learning and HMM (Hidden Markov Model). The analysis unit also analyzes the appearance and condition of the product from photos and videos using image recognition technology. The analysis unit can analyze images using technologies such as CNN (Convolutional Neural Network) and SIFT (Scale-Invariant Feature Transformation). The generation unit generates sales text and reference prices based on the information analyzed by the analysis unit. The generation unit generates marketable text based, for example, on criteria such as text length and word selection. The generation unit can generate text using text generation AI (e.g., LLM). The generation unit also calculates a reference price based on market data. The generation unit can calculate a price based on past sales data and pricing information of competing products. The verification unit allows the seller to verify the information generated by the generation unit. The verification unit allows the seller to verify the generated information and make corrections as needed. The verification unit can provide items that can be corrected and the procedures for making corrections. As a result, the listing support system according to this embodiment can reduce the burden on sellers and improve the success rate of sales.

[0065] The reception unit accepts audio and product photos / videos from sellers. For example, it can accept audio files according to their format and length. Specifically, it supports common audio formats such as MP3 and WAV, and can accept audio ranging from a few seconds to a few minutes in length without problems. The reception unit can also accept product photos and videos according to their resolution and format. For example, it can accept JPEG images and MP4 videos. A minimum image resolution of 800x600 pixels or higher is recommended, and a video resolution of 720p or higher is recommended. This allows the reception unit to efficiently accept diverse data formats provided by sellers. Furthermore, the reception unit performs basic error checks upon data acceptance, detecting and notifying sellers of issues such as format mismatches or insufficient resolution. For example, if an audio file is not in the specified format or the image resolution is too low, it prompts the seller to resubmit the data. This ensures high-quality data, allowing subsequent analysis and generation processes to proceed smoothly.

[0066] The analysis unit analyzes the information received by the reception unit. For example, the analysis unit converts audio information into text using speech recognition technology and extracts product features. Specifically, it can analyze audio using technologies such as deep learning and HMM (Hidden Markov Model). Speech recognition technology analyzes the waveform data of audio, identifies phonemes and words, and converts them into text. This allows for accurate transcription of product features and detailed information described by the seller via audio. The analysis unit also analyzes the appearance and condition of products from photos and videos using image recognition technology. Specifically, it can analyze images using technologies such as CNN (Convolutional Neural Network) and SIFT (Scale-Invariant Feature Transformation). CNN is suitable for extracting image features and identifying the shape, color, and texture of products. SIFT, on the other hand, is useful for detecting feature points in images and analyzing the details and condition of products in detail. This allows the analysis unit to accurately grasp the appearance and condition of products and extract the necessary data for listing information. Furthermore, the analysis unit can also integrate audio and image data to analyze the overall characteristics of the product. For example, by combining product features described via audio with the product's appearance and condition confirmed through images and videos, more detailed and accurate listing information can be generated. This allows the analysis unit to effectively analyze the diverse data provided by sellers and improve the quality of the listing information.

[0067] The generation unit generates compelling sales copy and reference prices based on information analyzed by the analysis unit. For example, the generation unit generates sales copy based on criteria such as text length and word selection. Specifically, it can generate text using text generation AI (e.g., LLM). LLM has learned from a large amount of text data and possesses the ability to generate natural-sounding text. For example, it can generate catchy slogans and descriptions that emphasize product features and benefits, stimulating purchasing intent. The generation unit also calculates reference prices based on market data. Specifically, it can calculate prices based on past sales data and competitor pricing information. The generation unit uses an algorithm that analyzes past sales history and market trends stored in a database to calculate the appropriate price for a product. This allows sellers to set appropriate prices based on market trends. Furthermore, the generation unit also has a function to customize the generated text and pricing information to suit the seller's needs. For example, if a seller wants to emphasize specific keywords or has special requests regarding pricing, the generation unit can generate listing information that reflects these requests. This reduces the burden on sellers and allows the generation unit to provide effective listing information.

[0068] The verification unit allows the seller to review the information generated by the generation unit. For example, the verification unit allows the seller to review the generated information and make corrections as needed. Specifically, the verification unit can provide editable items and correction procedures. For instance, if the seller wants to modify part of the generated text, the verification unit provides an editable text editor, making it easy for the seller to make corrections. Regarding pricing information, the verification unit also provides an interface for adjusting the price to the seller's desired level. This allows the seller to customize the generated information to their needs. Furthermore, the verification unit supports the process of the seller reviewing the information again after making corrections and finalizing it as the listing information. For example, after the seller has completed the corrections, the verification unit displays a final confirmation screen, allowing the seller to review all information and confirm that there are no problems. The verification unit also provides the option for the seller to return to the generation unit and generate new information if they are not satisfied with the corrections. This allows the verification unit to provide flexible support for sellers to create satisfactory listing information, ensuring a smooth listing process.

[0069] The analysis unit can convert audio information into text using speech recognition technology and extract product features. For example, the analysis unit can analyze audio using deep learning technology and convert it into text. The analysis unit can also analyze audio using a Hidden Markov Model (HMM) and extract product features. Furthermore, the analysis unit can apply algorithms to extract product features using speech recognition technology. For example, the analysis unit can use speech recognition technology to extract features such as the product's color, size, and condition. This improves the accuracy of listing information by converting audio information into text and extracting product features. Some or all of the above processing in the analysis unit may be performed using AI, or without AI. For example, the analysis unit can input audio data into an AI, which can then analyze the audio data, convert it into text, and extract product features.

[0070] The analysis unit can analyze the appearance and condition of products from photos and videos using image recognition technology. For example, the analysis unit can analyze images using a CNN (Convolutional Neural Network) to understand the appearance and condition of the product. The analysis unit can also analyze images using SIFT (Scale-Invariant Feature Transformation) to extract product features. Furthermore, the analysis unit can apply algorithms to analyze the appearance and condition of products using image recognition technology. For example, the analysis unit can use image recognition technology to detect the presence or absence of scratches or stains on the product. This improves the accuracy of listing information by analyzing the appearance and condition of products from photos and videos. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI. For example, the analysis unit can input image data into an AI, which can then analyze the image data to understand the appearance and condition of the product.

[0071] The generation unit can calculate a reference price based on market data. For example, the generation unit can calculate a reference price based on past sales data. The generation unit can also calculate a reference price based on price information of competing products. Furthermore, the generation unit can calculate a reference price based on market data that corresponds to the supply and demand of a product. For example, the generation unit can set a higher price for products with high demand and a lower price for products with high supply. This makes it possible to set appropriate prices by calculating a reference price based on market data. Some or all of the above processes in the generation unit may be performed using AI or not. For example, the generation unit can input market data into AI, and the AI ​​can analyze the market data to calculate a reference price.

[0072] The verification unit allows the seller to review the generated information and make corrections as needed. For example, the verification unit can display the generated information so that the seller can review it. The verification unit can also display editable items so that the seller can make corrections. Furthermore, the verification unit can provide correction procedures so that the seller can easily make corrections. For example, the verification unit can display the correction procedures step by step so that the seller can make corrections without getting lost. This improves the accuracy of the listing information by allowing the seller to review the generated information and make corrections as needed. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input the generated information into AI, and the AI ​​can suggest corrections.

[0073] The reception desk can provide an interface for sellers to input product descriptions by voice. For example, the reception desk can provide a voice input UI design to make it easy for sellers to input product descriptions by voice. The reception desk can also provide instructions on how to use voice input to ensure sellers can use voice input without confusion. Furthermore, the reception desk can provide voice input guides to ensure sellers can use voice input appropriately. For example, the reception desk can display voice input guidelines to show sellers how to use voice input. This reduces the effort required for sellers to input product descriptions by voice. Some or all of the above processes in the reception desk may be performed using AI or not. For example, the reception desk can input the voice input UI design into an AI, which can then suggest the optimal UI design.

[0074] The generation unit may include a learning data management unit that manages learning data for generating persuasive text. The generation unit may, for example, manage the method of collecting learning data and collect appropriate data. The generation unit may also, for example, manage the method of preprocessing the learning data to improve data quality. Furthermore, the generation unit may manage the method of updating the learning data to ensure that the latest data is always available. For example, the generation unit periodically updates the learning data and adds new data. This improves the accuracy of text generation by managing the learning data for generating persuasive text. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit inputs learning data into the AI, and the AI ​​preprocesses the data.

[0075] The reception unit can estimate the user's emotions and adjust the timing of voice input based on the estimated emotions. For example, if the user is nervous, the reception unit can slow down the timing of voice input to help them relax. For example, if the user is in a hurry, the reception unit can shorten the timing to quickly accept voice input. Also, if the user is focused, the reception unit can prompt for voice input at the optimal time. This improves input efficiency by adjusting the timing of voice input according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input user emotion data into an AI, which can then estimate the emotions and adjust the timing.

[0076] The reception desk can analyze the seller's past listing history and suggest the optimal input method. For example, the reception desk can prioritize suggesting input methods (voice, text, etc.) that the seller has frequently used in the past. The reception desk can also suggest input methods suitable for specific categories based on the seller's past listing history. Furthermore, the reception desk can analyze the seller's past successful listing history and suggest similar input methods. In this way, the optimal input method can be suggested by analyzing the seller's past listing history. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the seller's past listing history data into AI, and the AI ​​can suggest the optimal input method.

[0077] The reception system can filter voice input based on the seller's current projects and areas of interest. For example, the reception system may only accept voice input for products related to the seller's current ongoing projects. The reception system may also prioritize voice input for relevant products based on the seller's areas of interest. Furthermore, the reception system can filter voice input for relevant products by referring to the seller's past project history. This allows for the priority acquisition of highly relevant information by filtering based on the seller's current projects and areas of interest. Some or all of the above processing in the reception system may be performed using AI or not. For example, the reception system can input the seller's project data into an AI, which can then perform the filtering.

[0078] The reception desk can estimate the user's emotions and determine the priority of products to be entered based on the estimated emotions. For example, if the user is excited, the reception desk will prioritize products that interest them. If the user is tired, the reception desk may also prioritize products that are easy to enter. If the user is relaxed, the reception desk may also prioritize products that require detailed input. This improves the efficiency of input by determining product priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input user emotion data into an AI, which can then determine the priority of products.

[0079] The reception unit can prioritize retrieving highly relevant information based on the seller's geographical location information when voice input is received. For example, the reception unit can prioritize retrieving region-specific product information based on the seller's current location. The reception unit can also prioritize retrieving information on products with high demand in the vicinity based on the seller's geographical location information. Furthermore, the reception unit can prioritize retrieving information on products that can be delivered, taking into account the seller's geographical location information. This improves the accuracy of the listing information by prioritizing the retrieval of highly relevant information based on the seller's geographical location information. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input geographical location information into the AI, which can then retrieve highly relevant information.

[0080] The reception desk can analyze the seller's social media activity and obtain relevant information when voice input is received. For example, the reception desk can analyze the content of the seller's social media posts and obtain information about related products. The reception desk can also obtain information about related products based on the interests of the seller's followers. Furthermore, the reception desk can obtain information about related products by referring to the seller's social media activity history. In this way, relevant information can be obtained by analyzing the seller's social media activity. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input social media data into AI, and the AI ​​can obtain relevant information.

[0081] The analysis unit can estimate the user's emotions and adjust the method of analyzing the audio information based on the estimated emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis and create a highly accurate text conversion. For example, if the user is in a hurry, the analysis unit can perform a rapid analysis and create a concise text conversion. Furthermore, if the user is excited, the analysis unit can create a text conversion that reflects those emotions. This improves the accuracy of the analysis by adjusting the method of analyzing the audio information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI, which can then adjust the method of analyzing the audio information.

[0082] The analysis unit can use speech recognition technology to perform text conversion that is appropriate to the seller's speaking style and accent. For example, the analysis unit can perform natural text conversion according to the seller's speaking style. The analysis unit can also perform accurate text conversion that takes into account the seller's accent. Furthermore, the analysis unit can analyze the characteristics of the seller's speaking style and perform optimal text conversion. For example, the analysis unit can perform phoneme analysis and intonation analysis to perform text conversion that is appropriate to the seller's speaking style. This improves the accuracy of text conversion by performing text conversion that is appropriate to the seller's speaking style and accent. Some or all of the above processing in the analysis unit may be performed using AI, or it may be performed without AI. For example, the analysis unit can input the seller's voice data into AI, and the AI ​​can perform text conversion that is appropriate to the speaking style and accent.

[0083] The analysis unit can use image recognition technology to analyze the appearance and condition of a product in detail and extract its features. For example, the analysis unit can analyze the appearance of a product in detail and detect the presence or absence of scratches or stains. For example, the analysis unit can analyze the condition of a product and determine whether it is new or used. Furthermore, the analysis unit can extract the features of a product and provide information for generating a detailed description. For example, the analysis unit analyzes the appearance and condition of a product and applies an algorithm to extract its features. This improves the accuracy of the listing information by analyzing the appearance and condition of the product in detail and extracting its features.

[0084] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated emotions. For example, if the user is excited, the analysis unit can prioritize displaying important analysis results. For example, if the user is relaxed, the analysis unit can prioritize displaying detailed analysis results. Furthermore, if the user is in a hurry, the analysis unit can prioritize displaying concise analysis results. In this way, by prioritizing the analysis results according to the user's emotions, important information can be displayed preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input user emotion data into an AI, and the AI ​​can determine the priority of the analysis results.

[0085] The analysis unit can use image recognition technology to analyze the background information of a product and extract relevant information. For example, the analysis unit can analyze the background information of a product to identify the manufacturer and year of manufacture. The analysis unit can also analyze the background information of a product to identify past owners and usage history. Furthermore, the analysis unit can analyze the background information of a product and extract relevant market data. For example, the analysis unit can analyze the background information of a product and extract information about the product's manufacturer and related historical data. By analyzing the background information of a product and extracting relevant information, the accuracy of the listing information is improved. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input the background information data of a product into an AI, which can then analyze the background information and extract relevant information.

[0086] The analysis unit can improve analysis accuracy by referencing the seller's past voice data using speech recognition technology. For example, the analysis unit can improve analysis accuracy by learning the seller's speaking style characteristics by referencing the seller's past voice data. The analysis unit can also make it easier to recognize specific terms or phrases based on the seller's past voice data. Furthermore, the analysis unit can improve the accuracy of speech recognition by analyzing the seller's past voice data. For example, the analysis unit optimizes the speech recognition algorithm based on past voice data. This improves analysis accuracy by referencing the seller's past voice data. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can input past voice data into AI, which can then improve the accuracy of speech recognition.

[0087] The generation unit can estimate the user's emotions and adjust the expression of the generated text based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate text using softer language. If the user is in a hurry, the generation unit can also generate concise and to-the-point text. Furthermore, if the user is excited, the generation unit can generate expressive text that reflects those emotions. By adjusting the expression of text according to the user's emotions, more effective text can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input user emotion data into the AI, and the AI ​​can adjust the expression of the text.

[0088] The generation unit can calculate a reference price based on market data, corresponding to the supply and demand of a product. For example, the generation unit can calculate a reference price based on market demand data. The generation unit can also calculate a reference price based on market supply data. Furthermore, the generation unit can calculate a reference price based on market trend data. For example, the generation unit can set a higher price for products with high demand and a lower price for products with high supply. This allows for appropriate pricing by calculating a reference price that corresponds to the supply and demand of a product. Some or all of the above-described processes in the generation unit may be performed using AI, or they may not be performed using AI. For example, the generation unit can input market data into AI, and the AI ​​can calculate a reference price that corresponds to supply and demand.

[0089] The generation unit can apply different generation algorithms depending on the product category when generating sales copy. For example, for electronics products, the generation unit can apply an algorithm that generates text including technical details. For fashion products, for example, the generation unit can apply an algorithm that generates text focusing on design and materials. Furthermore, for furniture products, the generation unit can apply an algorithm that generates text emphasizing usability and functionality. This enables the generation of optimal text tailored to the product category. Some or all of the above processing in the generation unit may be performed using AI, or not. For example, the generation unit can input product category data into the AI, and the AI ​​can apply a generation algorithm appropriate to the category.

[0090] The generation unit can estimate the user's emotions and adjust the length of the generated text based on the estimated emotions. For example, if the user is in a hurry, the generation unit can generate short, concise text. If the user is relaxed, the generation unit can also generate longer text with detailed explanations. Furthermore, if the user is excited, the generation unit can generate expressive text that reflects those emotions. By adjusting the length of the text according to the user's emotions, more effective text can be generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI or not. For example, the generation unit can input user emotion data into an AI, which can then adjust the length of the text.

[0091] The generation unit can calculate a reference price based on market data, taking into account the seasonality and trends of a product. For example, for highly seasonal products, the generation unit calculates a reference price according to the season. For example, for trending products, the generation unit can also calculate a reference price based on the latest market data. Furthermore, the generation unit can calculate a reference price during periods of high demand, taking into account seasonality and trends. For example, the generation unit calculates the price using seasonal sales data and trend prediction algorithms. This enables appropriate pricing that takes into account the seasonality and trends of a product. Some or all of the above processing in the generation unit may be performed using AI, or not. For example, the generation unit can input market data into AI, which can then calculate a reference price considering seasonality and trends.

[0092] The generation unit can adjust the order of sentences based on product relevance when generating persuasive sales copy. For example, it might list the main features of a product first, followed by detailed explanations. It can also prioritize highly relevant information to attract the buyer's attention. Furthermore, it can organize the usage instructions and benefits of a product to generate easy-to-understand text. This enables the generation of optimal text based on product relevance. Some or all of the above processes in the generation unit may be performed using AI or not. For example, the generation unit can input product-related data into the AI, which can then adjust the order of the sentences.

[0093] The confirmation unit can estimate the user's emotions and adjust the display method of the confirmation screen based on the estimated user emotions. For example, if the user is nervous, the confirmation unit can provide a simple and highly visible display method. For example, if the user is relaxed, the confirmation unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the confirmation unit can provide a display method that gets straight to the point. This makes it possible to display the optimal confirmation screen according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the confirmation unit may be performed using AI or not using AI. For example, the confirmation unit can input user emotion data into AI, and the AI ​​can adjust the display method of the confirmation screen.

[0094] The verification unit can refer to the seller's past revision history and make optimal revision suggestions. For example, the verification unit can analyze the revisions the seller has made in the past and make similar revision suggestions. For example, the verification unit can identify frequently revised sections from the seller's past revision history and make revision suggestions in advance. Furthermore, the verification unit can suggest the optimal revision method based on the seller's revision history. In this way, by referring to the seller's past revision history, it becomes possible to make optimal revision suggestions. Some or all of the above processes in the verification unit may be performed using AI or not. For example, the verification unit can input past revision history data into AI, and the AI ​​can make optimal revision suggestions.

[0095] The confirmation unit can customize the displayed content based on the seller's current situation when displaying the confirmation screen. For example, if the seller is in a hurry, the confirmation unit can display a concise confirmation screen. For example, if the seller is relaxed, the confirmation unit can also display a detailed confirmation screen. Furthermore, the confirmation unit can provide optimal display content based on the seller's current situation (time of day, location, etc.). This ensures that the optimal display content is provided based on the seller's current situation. Some or all of the above processing in the confirmation unit may be performed using AI or not. For example, the confirmation unit can input the seller's situation data into the AI, which can then customize the display content.

[0096] The confirmation unit can estimate the user's emotions and adjust the operation procedures of the confirmation screen based on the estimated emotions. For example, if the user is nervous, the confirmation unit can simplify the operation procedures to reduce stress. For example, if the user is relaxed, the confirmation unit can provide detailed operation procedures to give a sense of security. Furthermore, if the user is in a hurry, the confirmation unit can provide procedures that allow for quick operation. This ensures that the optimal operation procedures are provided according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the confirmation unit may be performed using AI or not. For example, the confirmation unit can input user emotion data into AI, and the AI ​​can adjust the operation procedures.

[0097] The verification unit can select the optimal display method when displaying the confirmation screen, taking into account the seller's device information. For example, if the seller is using a smartphone, the verification unit can provide a display method that matches the screen size. For example, if the seller is using a tablet, the verification unit can also provide a display method optimized for a larger screen. Furthermore, if the seller is using a desktop, the verification unit can provide a display method that includes detailed information. This ensures that the optimal display method is provided based on the seller's device information. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input device information into the AI, which can then select the optimal display method.

[0098] The verification unit can refer to the seller's social media activity and display relevant information when displaying the verification screen. For example, the verification unit can refer to the content of the seller's social media posts and display information about related products. For example, the verification unit can also display information about related products based on the interests of the seller's followers. Furthermore, the verification unit can refer to the seller's social media activity history and display information about related products. This provides relevant information based on the seller's social media activity. Some or all of the above processing in the verification unit may be performed using AI or not. For example, the verification unit can input social media data into AI, and the AI ​​can display relevant information.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The reception system can analyze the emotions conveyed in a seller's voice input and provide feedback tailored to their emotional state. For example, if a seller is feeling anxious, the reception system can display an encouraging message to reassure them. If a seller is excited, the reception system can provide positive feedback that shares their excitement. Furthermore, if a seller is tired, the reception system can provide concise and easy-to-understand instructions to reduce their burden. By providing feedback that matches the seller's emotions, it is expected that the seller experience will improve and the listing process will proceed more smoothly.

[0101] The analysis unit uses speech recognition technology to estimate the seller's emotions from their voice data and adjusts the accuracy of the analysis based on the estimated emotions. For example, if the seller is relaxed, the analysis unit can perform a detailed analysis and produce a highly accurate text conversion. If the seller is in a hurry, the analysis unit can perform a rapid analysis and produce a concise text conversion. Furthermore, if the seller is excited, the analysis unit can produce a text conversion that reflects those emotions. By applying an analysis method tailored to the seller's emotions, it is expected that the accuracy and efficiency of the analysis will improve.

[0102] The generation unit can estimate the seller's emotions and adjust the tone of the generated text based on those emotions. For example, if the seller is relaxed, the generation unit can generate text with a soft tone. If the seller is in a hurry, the generation unit can generate concise and to-the-point text. Furthermore, if the seller is excited, the generation unit can generate expressive text that reflects those emotions. This enables text generation that responds to the seller's emotions, and is expected to provide more effective listing information.

[0103] The confirmation unit can estimate the seller's emotions and adjust the display method of the confirmation screen based on the estimated emotions. For example, if the seller is nervous, the confirmation unit can provide a simple and highly visible display method. If the seller is relaxed, the confirmation unit can provide a display method that includes detailed information. Furthermore, if the seller is in a hurry, the confirmation unit can provide a display method that gets straight to the point. This makes it possible to display the optimal confirmation screen according to the seller's emotions, and is expected to improve the efficiency of the listing process.

[0104] The reception desk can analyze a seller's past listing history and suggest the most suitable input method. For example, it can prioritize suggesting input methods that the seller has frequently used in the past (voice, text, etc.). It can also suggest input methods suitable for specific categories based on the seller's past listing history. Furthermore, it can analyze a seller's past successful listing history and suggest similar input methods. As a result, by analyzing a seller's past listing history, it is expected that the optimal input method can be suggested, improving the efficiency of the listing process.

[0105] The analysis unit can use speech recognition technology to perform text conversion that is tailored to the seller's speaking style and accent. For example, it can perform natural-sounding text conversion based on the seller's speaking style. It can also perform accurate text conversion by considering the seller's accent. Furthermore, it can analyze the characteristics of the seller's speaking style and perform optimal text conversion. As a result, it is expected that the accuracy of text conversion will improve by performing text conversion that is tailored to the seller's speaking style and accent.

[0106] The generation unit can apply different generation algorithms depending on the product category when generating compelling sales copy. For example, for electronics products, an algorithm that generates text including technical details can be applied. For fashion products, an algorithm that generates text focusing on design and materials can be applied. Furthermore, for furniture products, an algorithm that generates text emphasizing usability and functionality can be applied. This enables the generation of optimal text tailored to each product category, and is expected to provide more effective listing information.

[0107] The verification unit can refer to the seller's past revision history and make optimal revision suggestions. For example, it can analyze the revisions the seller has made in the past and make similar revision suggestions. It can also identify frequently revised areas from the seller's past revision history and make revision suggestions in advance. Furthermore, it can suggest the most suitable revision method based on the seller's revision history. As a result, by referring to the seller's past revision history, optimal revision suggestions become possible, and the accuracy of the listing information is expected to improve.

[0108] The reception system can prioritize retrieving highly relevant information based on the seller's geographical location when voice input is received. For example, it can prioritize retrieving region-specific product information based on the seller's current location. It can also prioritize retrieving information on products with high demand in the surrounding area based on the seller's geographical location. Furthermore, it can prioritize retrieving information on products that can be shipped, taking the seller's geographical location into consideration. As a result, it is expected that the accuracy of listing information will improve by prioritizing the retrieval of highly relevant information based on the seller's geographical location.

[0109] The generation unit can estimate the user's emotions and adjust the length of the generated text based on those emotions. For example, if the user is in a hurry, it can generate short, concise sentences. If the user is relaxed, it can generate longer sentences with detailed explanations. Furthermore, if the user is excited, it can generate expressive sentences that reflect those emotions. By adjusting the length of the text according to the user's emotions, it is expected that more effective texts can be generated.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The reception desk receives audio and product photos / videos from the seller. For example, it can accept audio files depending on their format and length, as well as JPEG images and MP4 videos. Step 2: The analysis unit analyzes the information received by the reception unit. For example, it may use speech recognition technology to convert speech information into text and extract product features. It may also use technologies such as deep learning and HMM (Hidden Markov Model) to analyze speech, and image recognition technology to analyze the appearance and condition of products from photos and videos. It can also use technologies such as CNN (Convolutional Neural Network) and SIFT (Scale-Invariant Feature Transfer) to analyze images. Step 3: The generation unit generates marketable text and reference prices based on the information analyzed by the analysis unit. For example, it generates marketable text based on the length of the text and the selection criteria for the words used, and generates the text using text generation AI (e.g., LLM). It also calculates reference prices by referring to past sales data and price information of competing products based on market data. Step 4: The verification unit allows the seller to verify the information generated by the generation unit. For example, the seller can review the generated information and make corrections as needed. The verification unit provides the items that can be corrected and the steps for making those corrections.

[0112] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0114] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0115] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, and confirmation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and accepts voice and product photos and videos as input. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and converts the voice information into text and extracts the characteristics of the product. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates compelling descriptions and reference prices. The confirmation unit is implemented by the control unit 46A of the smart device 14 and allows the seller to confirm the generated information and make corrections as necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0120] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0122] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0123] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0124] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0125] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0126] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0130] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, and confirmation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and accepts voice and product photos and videos as input. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and converts the voice information into text and extracts the characteristics of the product. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates compelling descriptions and reference prices. The confirmation unit is implemented by the control unit 46A of the smart glasses 214 and allows the seller to confirm the generated information and make corrections as necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0134] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0135] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0136] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0138] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0139] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0140] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0141] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0142] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0144] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0147] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, and confirmation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and accepts voice and product photos and videos as input. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and converts the voice information into text and extracts the characteristics of the product. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates compelling descriptions and reference prices. The confirmation unit is implemented by the control unit 46A of the headset terminal 314 and allows the seller to confirm the generated information and make corrections as necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0151] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0152] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0154] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0155] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0156] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0157] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0158] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0159] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0161] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0162] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0164] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, and verification unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and accepts voice and product photos and videos as input. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and converts voice information into text and extracts product features. The generation unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and generates compelling sales text and reference prices. The verification unit is implemented by, for example, the control unit 46A of the robot 414 and allows the seller to verify the generated information and make corrections as necessary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0165] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0166] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0167] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0168] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0169] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0170] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0171] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0172] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0173] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0174] 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.

[0175] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0176] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0177] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0178] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0179] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0180] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0181] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0182] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0183] (Note 1) A reception area that receives audio and product photos / videos from sellers, An analysis unit that analyzes the information received by the reception unit, A generation unit generates sales pitches and reference prices based on the information analyzed by the aforementioned analysis unit, The system includes a verification unit for the seller to verify the information generated by the generation unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Using speech recognition technology, audio information is converted into text, and product features are extracted. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Using image recognition technology, we analyze the appearance and condition of products from photos and videos. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is A reference price is calculated based on market data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned verification unit is The seller reviews the generated information and makes corrections as needed. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is Provides an interface that allows sellers to input product descriptions using voice. The system described in Appendix 1, characterized by the features described herein. (Note 7) The generating unit is It includes a learning data management unit that manages the learning data used to generate sales-generating text. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is It estimates the user's emotions and adjusts the timing of voice input based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is We analyze the seller's past listing history and suggest the optimal input method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When using voice input, filtering is performed based on the seller's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is It estimates the user's emotions and determines the priority of products to be entered based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When using voice input, the system prioritizes retrieving highly relevant information based on the seller's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is During voice input, the system analyzes the seller's social media activity and retrieves relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the method of analyzing voice information based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, Using speech recognition technology, the system converts the seller's speech to text according to their accent and manner of speaking. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, Using image recognition technology, we analyze the appearance and condition of products in detail and extract their features. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, It estimates the user's emotions and prioritizes the analysis results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, Using image recognition technology, we analyze the background information of products and extract relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, Using speech recognition technology, we refer to the seller's past voice data to improve analysis accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is It estimates the user's emotions and adjusts the way the generated text is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is Based on market data, we calculate a reference price that corresponds to the supply and demand of the product. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is When generating compelling sales copy, different generation algorithms are applied depending on the product category. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is It estimates the user's emotions and adjusts the length of the generated text based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is Based on market data, we calculate a reference price considering the seasonality and trends of the product. The system described in Appendix 1, characterized by the features described herein. (Note 25) The generating unit is When generating sales copy, adjust the order of sentences based on the relevance of the product. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned verification unit is The system estimates the user's emotions and adjusts how the confirmation screen is displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned verification unit is We will refer to the seller's past revision history and propose the most suitable revisions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned verification unit is When the confirmation screen is displayed, customize the displayed content based on the seller's current status. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned verification unit is The system estimates the user's emotions and adjusts the operation procedure on the confirmation screen based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned verification unit is When displaying the confirmation screen, the system will select the optimal display method considering the seller's device information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned verification unit is When the confirmation screen is displayed, the seller's social media activity will be referenced and relevant information will be shown. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0184] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception area that receives audio and product photos / videos from sellers, An analysis unit that analyzes the information received by the reception unit, A generation unit generates sales pitches and reference prices based on the information analyzed by the aforementioned analysis unit, The system includes a verification unit for the seller to verify the information generated by the generation unit. A system characterized by the following features.

2. The aforementioned analysis unit, Using speech recognition technology, audio information is converted into text, and product features are extracted. The system according to feature 1.

3. The aforementioned analysis unit, Using image recognition technology, we analyze the appearance and condition of products from photos and videos. The system according to feature 1.

4. The generating unit is A reference price is calculated based on market data. The system according to feature 1.

5. The aforementioned verification unit is The seller reviews the generated information and makes corrections as needed. The system according to feature 1.

6. The aforementioned reception unit is Provides an interface that allows sellers to input product descriptions using voice. The system according to feature 1.

7. The generating unit is It includes a learning data management unit that manages the learning data used to generate sales-generating text. The system according to feature 1.

8. The aforementioned reception unit is It estimates the user's emotions and adjusts the timing of voice input based on the estimated emotions. The system according to feature 1.

Images