system

Abstract

An object of a system according to an embodiment is to automatically order a necessary item based on a user's daily notes.SOLUTION: A system includes a tweet collection part, an analysis part, an order part, and a notification part. The tweet collector is configured to collect a user's daily tweet in a natural language. The analysis section analyzes the tweets collected by the tweet collection section and determines a necessary tweet. The ordering unit automatically places an order on the EC site based on what is necessary as determined by the analysis unit. The notification unit notifies the user of the content of the order placed by the ordering unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem of being inconvenient because it cannot automatically order what a user needs based on their daily tweets.

[0005] The system according to the embodiment aims to automatically order necessary items based on the user's daily tweets. [Means for solving the problem]

[0006] The system according to the embodiment includes a tweet collection unit, an analysis unit, an ordering unit, and a notification unit. The tweet collection unit collects everyday tweets written in natural language by the user. The analysis unit analyzes the tweets collected by the tweet collection unit and determines what is needed. The ordering unit automatically places an order on the EC site based on the what is needed determined by the analysis unit. The notification unit notifies the user of the order content placed by the ordering unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically order necessary items based on the user's daily tweets. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The errand system according to an embodiment of the present invention analyzes the natural language tweets that users make on a daily basis, determines what they need from the content of those tweets, and automatically places an order. This saves users the trouble of daily shopping and allows them to obtain what they need in a timely manner.

[0029] The errand system according to the embodiment includes a tweet collection unit, an analysis unit, an ordering unit, and a notification unit. The tweet collection unit collects a user's everyday tweets in natural language. For example, the tweet collection unit collects tweets such as "I'm running out of milk" via a smartphone or smart speaker. The tweet collection unit also has a function of converting voice data into text data. For example, it converts the user's voice into text using voice recognition technology. The analysis unit analyzes the tweets collected by the tweet collection unit and determines what the user needs. For example, a generation AI analyzes a tweet such as "I'm running out of milk" and determines that the user needs milk. The generation AI analyzes the content of the tweets using a text generation AI (e.g., LLM) or a multimodal generation AI. The order unit automatically places an order on an e-commerce website based on the needs determined by the analysis unit. For example, if the generation AI determines that "milk" is needed, it searches for milk on the e-commerce website, selects an appropriate product, and completes the order. The notification unit notifies the user of the order content placed by the order unit. For example, a notification such as "Milk has been ordered" is sent via a smartphone or smart speaker. In this way, the errand running system according to the embodiment can automatically order and notify users of necessary items based on their daily tweets, thereby reducing the effort required for shopping.

[0030] The tweet collection unit can collect tweets at appropriate times based on a user's lifestyle patterns to ensure that important tweets are not missed. The tweet collection unit, for example, learns a user's lifestyle patterns and strengthens collection during times when there are many tweets, such as breakfast time or after returning home. For example, if a user often tweets "There's no bread" during breakfast, the tweet collection unit will focus on collecting tweets during those times. The tweet collection unit also uses smartphone location information to strengthen collection when the user is at home or in a specific location. For example, if a user often tweets "There's no milk" while in the kitchen, the tweet collection unit will strengthen collection at that location. The tweet collection unit also analyzes the user's past tweet data and, if there are many important tweets on specific days or times, strengthen collection at those times. For example, if a user often creates shopping lists on weekends, strengthen collection at those times. In this way, by collecting tweets based on the user's lifestyle patterns, important tweets are not missed.

[0031] The tweet collection unit collects tweets from multiple devices in the home, enabling more diversified information to be obtained. For example, the tweet collection unit uses a microphone installed in a smart refrigerator to collect tweets made when a user opens the refrigerator. For example, if a user utters, "There's no milk," the moment the refrigerator is opened, the tweet collection unit collects this information. The tweet collection unit also uses a microphone and camera installed in a smart mirror to collect tweets made by a user in front of the mirror. For example, if a user utters, "I'm running out of shampoo," while getting ready in the morning, the tweet collection unit collects this information. The tweet collection unit also simultaneously collects voice data from multiple devices in the home, such as smart speakers and smart TVs, and performs integrated analysis. For example, if a user utters, "There's no tea," in the living room, the tweet collection unit collects this information. By collecting tweets from multiple devices in the home, more diversified information can be obtained.

[0032] The tweet collection unit can also collect tweets in different languages ​​and analyze them using a multilingual generation AI. The tweet collection unit collects tweets in different languages, such as English and Japanese, and analyzes them using a multilingual generation AI. For example, if a user tweets, "I need milk," the tweet collection unit analyzes the content. Furthermore, if the smart speaker supports multiple languages, the tweet collection unit automatically translates and analyzes tweets from users in different languages. For example, if a user tweets, "There's no milk," in Japanese, the tweet collection unit translates the content into English and analyzes it. Furthermore, if multiple devices in the home support different languages, the tweet collection unit translates and collects tweets from users in real time. For example, if a user tweets, "There's no milk," on a smartphone, the tweet collection unit translates the content into English and analyzes it. In this way, by collecting tweets in different languages ​​and analyzing them using a multilingual generation AI, it is possible to meet the needs of a wider variety of users.

[0033] The analysis unit can make more personalized decisions based on purchase history and user preferences. For example, the generation AI in the analysis unit refers to the user's past purchase history and analyzes the content of tweets. For example, if a user tweets, "I'm running low on milk," the analysis unit will take into account the brands and types of milk purchased in the past. The analysis unit also allows the generation AI to learn the user's preferences and analyze the content of tweets. For example, if a user tweets, "I'm running low on milk," the analysis unit will prioritize low-fat milk, which the user prefers. The analysis unit also allows the generation AI to learn the user's purchasing patterns and analyze the content of tweets. For example, if a user tweets, "I'm running low on milk," the analysis unit will prioritize products that the user purchases regularly. This allows for more personalized decisions by taking into account past purchase history and user preferences.

[0034] The analysis unit can use news and trend information as a basis for understanding the context when analyzing tweets. For example, when the generation AI analyzes a tweet, the analysis unit refers to related news and trend information. For example, if a tweet says, "I'm running out of milk," the analysis unit will take into account recent milk price fluctuations and supply conditions when making a decision. The analysis unit also refers to related trend information when the generation AI analyzes a tweet. For example, if a tweet says, "I'm running out of milk," the analysis unit will take into account recent health trends and diet information when making a decision. The analysis unit also refers to related news when the generation AI analyzes a tweet. For example, if a tweet says, "I'm running out of milk," the analysis unit will take into account recent food safety information and recall information when making a decision. This enables more accurate analysis by referring to related news and trend information to understand the context.

[0035] The analysis unit also takes into account the tweets of other members in the household and can grasp the overall needs. For example, the generation AI collects the tweets of other members in the household and grasps the overall needs. For example, if all family members tweet, "There's no milk," that need will be given priority in determining the needs. The analysis unit also analyzes the tweets of other members in the household and grasps the overall needs. For example, if a child tweets, "I want some sweets," that need will be taken into consideration in determining the needs. The analysis unit also collects the tweets of other members in the household and grasps the overall needs. For example, if multiple members tweet, "There's no milk," that need will be given priority in determining the needs. In this way, the analysis unit can grasp the overall needs by taking into account the tweets of other members in the household.

[0036] The analysis unit can feed back the results of the tweet analysis to the user and provide an interface that allows the user to confirm and modify what they need. For example, the analysis unit may feed back the results of the tweet analysis by the generation AI to the user and provide an interface that allows the user to confirm and modify what they need. For example, the analysis unit may ask, "Do you need milk?" The analysis unit may also feed back the results of the tweet analysis by the generation AI to the user and provide an interface that allows the user to confirm and modify what they need. For example, the analysis unit may ask, "Do you want to order milk?" The analysis unit may also feed back the results of the tweet analysis by the generation AI to the user and provide an interface that allows the user to confirm and modify what they need. For example, the analysis unit may ask, "Please select the type of milk." In this way, the tweet analysis results are fed back to the user, allowing the user to confirm and modify what they need.

[0037] The ordering unit can compare multiple e-commerce sites and select the optimal price and delivery terms. In the ordering unit, for example, the generation AI compares multiple e-commerce sites and selects the optimal price and delivery terms. For example, when ordering milk, the site with the lowest price and shortest delivery time is selected. In addition, the ordering unit can compare multiple e-commerce sites and select the optimal price and delivery terms. For example, when ordering milk, the generation AI prioritizes the selection of sites with free shipping. In addition, the ordering unit can compare multiple e-commerce sites and select the optimal price and delivery terms. For example, when ordering milk, the generation AI selects a reliable site taking into account the user's past purchase history. This makes it possible to select the optimal price and delivery terms by comparing multiple e-commerce sites.

[0038] The ordering unit can select highly reliable products by referring to the user's past ratings and reviews. In the ordering unit, for example, the generation AI refers to the user's past ratings and reviews and selects highly reliable products. For example, when ordering milk, products that have received high ratings in the past are preferentially selected. In addition, the ordering unit can select highly reliable products by referring to the user's past ratings and reviews. For example, when ordering milk, products with a large number of reviews and high ratings are selected. In addition, the ordering unit can select highly reliable products by referring to the user's past ratings and reviews. For example, when ordering milk, products of the same brand as products that the user has purchased in the past are selected. In this way, highly reliable products can be selected by referring to the user's past ratings and reviews.

[0039] The ordering unit can select an appropriate product by taking into account the user's health condition and allergy information. In the ordering unit, for example, the generation AI takes into account the user's health condition and allergy information and selects an appropriate product. For example, when ordering milk, if the user is lactose intolerant, lactose-free milk is selected. In addition, the ordering unit can select an appropriate product by taking into account the user's health condition and allergy information. For example, when ordering milk, if the user is on a diet, low-fat milk is selected. In addition, the ordering unit can select an appropriate product by taking into account the user's health condition and allergy information. For example, when ordering milk, if the user prefers organic food, organic milk is selected. In this way, an appropriate product can be selected by taking into account the user's health condition and allergy information.

[0040] The ordering unit can suggest related and complementary products based on the user's purchasing history. For example, the generation AI in the ordering unit suggests related and complementary products based on the user's purchasing history. For example, when ordering milk, it suggests cereal that the user has previously purchased. Also, the generation AI in the ordering unit suggests related and complementary products based on the user's purchasing history. For example, when ordering milk, it suggests coffee that the user has previously purchased. Also, the generation AI in the ordering unit suggests related and complementary products based on the user's purchasing history. For example, when ordering milk, it suggests bread that the user has previously purchased. This makes it possible to provide a more convenient shopping experience by suggesting related and complementary products based on the user's purchasing history.

[0041] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0042] The tweet collection unit can collect not only user tweets but also environmental sounds within the home and use them for analysis. For example, it collects sounds such as the opening and closing of a refrigerator and the sound of running water, and infers user behavior patterns from these sounds. The tweet collection unit can also collect environmental data such as temperature and humidity within the home and use them for analysis. For example, if the room temperature is high, it can be determined that there is an increased demand for cold drinks. The tweet collection unit can also collect information such as the on / off status of lights in the home and television viewing status, and can grasp the user's lifestyle rhythm. This allows for more accurate judgments to be made by using not only user tweets but also environmental data within the home for analysis.

[0043] The analysis unit can determine what a user needs based on their health data. For example, it can analyze heart rate and sleep data obtained from the user's smartwatch and suggest products that match their health condition. The analysis unit can also suggest products that take nutritional balance into consideration based on data obtained from the user's food recording app. For example, it can suggest foods that will supplement nutrients that have been lacking in recent meals. The analysis unit can also suggest products that are suitable for post-exercise recovery based on data obtained from the user's exercise recording app. For example, it can suggest protein or energy bars that are needed after exercise. This makes it possible to suggest more personalized products based on the user's health data.

[0044] The analysis unit can analyze the content of a user's social media posts to determine what they need. For example, if a user posts on social media that they want new running shoes, the analysis unit can suggest running shoes based on that information. The analysis unit can also analyze the content of the user's "likes" and comments on social media to suggest products that the user is interested in. For example, the analysis unit can suggest a new gadget that the user has "liked" on a friend's post. The analysis unit can also analyze the content of the accounts the user follows on social media to suggest products in areas of interest. For example, if the user follows many cooking accounts, the analysis unit can suggest cooking-related products. This makes it possible to make more personalized product suggestions by analyzing the content of a user's social media posts.

[0045] The analysis unit can suggest products according to seasons and events based on the user's past purchasing history. For example, based on products purchased during the Christmas season in the past, products suitable for this year's Christmas can be suggested. The analysis unit can also suggest products related to specific events based on the user's past purchasing history. For example, if the user has purchased barbecue equipment in the past, products related to the summer barbecue season can be suggested. The analysis unit can also suggest products according to seasonal demand based on the user's past purchasing history. For example, if a heating appliance was purchased in winter, products related to the following winter can be suggested. This makes it possible to suggest products according to seasons and events based on the user's past purchasing history.

[0046] The analysis unit can suggest related products based on the user's hobbies and interests. For example, if the user's hobby is music, the analysis unit can suggest the latest music equipment and sheet music. If the user's hobby is reading, the analysis unit can suggest recent bestsellers or books that suit the user's preferences. For example, if the user likes mystery novels, the analysis unit can suggest the latest mystery novels. If the user's hobby is outdoor activities, the analysis unit can suggest camping equipment and hiking gear. For example, if the user is planning to camp, the analysis unit can suggest the necessary camping equipment. This makes it possible to suggest related products based on the user's hobbies and interests.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The tweet collection unit collects users' everyday tweets in natural language. For example, it collects tweets such as "I'm running out of milk" from users via smartphones or smart speakers. The tweet collection unit also has the function of converting voice data into text data. For example, it uses voice recognition technology to convert the user's voice into text. Step 2: The analysis unit analyzes the tweets collected by the tweet collection unit and determines what is needed. For example, the generation AI analyzes the tweet "I'm running out of milk" and determines that the user needs milk. The generation AI uses text generation AI (e.g., LLM) or multimodal generation AI to analyze the content of the tweet. Step 3: The ordering unit automatically places an order on the e-commerce site based on the items determined by the analysis unit. For example, if the generation AI determines that "milk" is needed, it searches for milk on the e-commerce site, selects the appropriate product, and completes the order. Step 4: The notification unit notifies the user of the order made by the ordering unit. For example, the notification is sent via a smartphone or smart speaker in the form of "Milk has been ordered."

[0049] (Example 2) The errand system according to an embodiment of the present invention analyzes the natural language tweets that users make on a daily basis, determines what they need from the content of those tweets, and automatically places an order. This saves users the trouble of daily shopping and allows them to obtain what they need in a timely manner.

[0050] The errand system according to the embodiment includes a tweet collection unit, an analysis unit, an ordering unit, and a notification unit. The tweet collection unit collects a user's everyday tweets in natural language. For example, the tweet collection unit collects tweets such as "I'm running out of milk" via a smartphone or smart speaker. The tweet collection unit also has a function of converting voice data into text data. For example, it converts the user's voice into text using voice recognition technology. The analysis unit analyzes the tweets collected by the tweet collection unit and determines what the user needs. For example, a generation AI analyzes a tweet such as "I'm running out of milk" and determines that the user needs milk. The generation AI analyzes the content of the tweets using a text generation AI (e.g., LLM) or a multimodal generation AI. The order unit automatically places an order on an e-commerce website based on the needs determined by the analysis unit. For example, if the generation AI determines that "milk" is needed, it searches for milk on the e-commerce website, selects an appropriate product, and completes the order. The notification unit notifies the user of the order content placed by the order unit. For example, a notification such as "Milk has been ordered" is sent via a smartphone or smart speaker. In this way, the errand running system according to the embodiment can automatically order and notify users of necessary items based on their daily tweets, thereby reducing the effort required for shopping.

[0051] The tweet collection unit simultaneously analyzes not only voice but also facial expressions and gestures, enabling a more accurate understanding of the user's intentions. For example, when a user tweets, "I'm almost out of milk," the tweet collection unit simultaneously collects not only voice data but also the user's facial expressions and hand movements. This allows a more accurate understanding of the user's intentions. The tweet collection unit also uses the smartphone's camera to analyze the user's facial expressions in real time when tweeting to understand their emotional state. For example, if the user has a troubled expression, it determines that there is a high level of urgency. The tweet collection unit also links the camera and microphone installed in the smart speaker to analyze the user's gestures simultaneously with the user's tweets. For example, it analyzes pointing gestures and determines that the user is pointing at a specific object. This allows a more accurate understanding of the user's intentions by analyzing not only voice but also facial expressions and gestures.

[0052] The tweet collection unit can collect tweets at appropriate times based on a user's lifestyle patterns to ensure that important tweets are not missed. The tweet collection unit, for example, learns a user's lifestyle patterns and strengthens collection during times when there are many tweets, such as breakfast time or after returning home. For example, if a user often tweets "There's no bread" during breakfast, the tweet collection unit will focus on collecting tweets during those times. The tweet collection unit also uses smartphone location information to strengthen collection when the user is at home or in a specific location. For example, if a user often tweets "There's no milk" while in the kitchen, the tweet collection unit will strengthen collection at that location. The tweet collection unit also analyzes the user's past tweet data and, if there are many important tweets on specific days or times, strengthen collection at those times. For example, if a user often creates shopping lists on weekends, strengthen collection at those times. In this way, by collecting tweets based on the user's lifestyle patterns, important tweets are not missed.

[0053] The tweet collection unit can analyze the user's emotional state using the emotion estimation function and prioritize collecting tweets at moments when emotions are heightened. For example, when a user emotionally utters, "We're out of milk!", the tweet collection unit uses the emotion estimation function to detect this heightened emotion and prioritize collecting the tweets. For example, it detects moments when emotions such as anger or impatience are heightened. The tweet collection unit also analyzes the tone and volume of the user's voice using a smart speaker to identify moments when emotions are heightened. For example, it prioritizes collecting tweets when the user's voice gets louder or the tone changes. The tweet collection unit also analyzes the user's facial expressions using a camera to detect moments when emotions are heightened. For example, it detects expressions such as furrowing the brow or widening the eyes and prioritizes collecting tweets with these expressions. This prioritizes collecting tweets at moments when emotions are heightened, ensuring that important tweets are not missed.

[0054] The tweet collection unit collects tweets from multiple devices in the home, enabling more diversified information to be obtained. For example, the tweet collection unit uses a microphone installed in a smart refrigerator to collect tweets made when a user opens the refrigerator. For example, if a user utters, "There's no milk," the moment the refrigerator is opened, the tweet collection unit collects this information. The tweet collection unit also uses a microphone and camera installed in a smart mirror to collect tweets made by a user in front of the mirror. For example, if a user utters, "I'm running out of shampoo," while getting ready in the morning, the tweet collection unit collects this information. The tweet collection unit also simultaneously collects voice data from multiple devices in the home, such as smart speakers and smart TVs, and performs integrated analysis. For example, if a user utters, "There's no tea," in the living room, the tweet collection unit collects this information. By collecting tweets from multiple devices in the home, more diversified information can be obtained.

[0055] The tweet collection unit can also collect tweets in different languages ​​and analyze them using a multilingual generation AI. The tweet collection unit collects tweets in different languages, such as English and Japanese, and analyzes them using a multilingual generation AI. For example, if a user tweets, "I need milk," the tweet collection unit analyzes the content. Furthermore, if the smart speaker supports multiple languages, the tweet collection unit automatically translates and analyzes tweets from users in different languages. For example, if a user tweets, "There's no milk," in Japanese, the tweet collection unit translates the content into English and analyzes it. Furthermore, if multiple devices in the home support different languages, the tweet collection unit translates and collects tweets from users in real time. For example, if a user tweets, "There's no milk," on a smartphone, the tweet collection unit translates the content into English and analyzes it. In this way, by collecting tweets in different languages ​​and analyzing them using a multilingual generation AI, it is possible to meet the needs of a wider variety of users.

[0056] The tweet collection unit can monitor a user's emotional state in real time using a wearable device equipped with an emotion estimation function and collect tweets in response to changes in emotion. The tweet collection unit, for example, uses a smartwatch equipped with an emotion estimation function to monitor a user's heart rate and electrodermal response to detect changes in emotion. For example, if a user tweets "There's no milk" when their heart rate increases, the tweet collection unit collects this information. The tweet collection unit also uses smart glasses equipped with an emotion estimation function to analyze a user's gaze and facial expression to detect changes in emotion. For example, if a user tweets "There's no milk" when their gaze is focused on a specific object, the tweet collection unit collects this information. The tweet collection unit also uses smart earphones equipped with an emotion estimation function to analyze the user's tone and volume of voice to detect changes in emotion. For example, if a user tweets "There's no milk" when their voice gets louder, the tweet collection unit collects this information. In this way, by using a wearable device equipped with an emotion estimation function, a user's emotional state can be monitored in real time and tweets can be collected in response to changes in emotion.

[0057] The analysis unit can make more personalized decisions based on purchase history and user preferences. For example, the generation AI in the analysis unit refers to the user's past purchase history and analyzes the content of tweets. For example, if a user tweets, "I'm running low on milk," the analysis unit will take into account the brands and types of milk purchased in the past. The analysis unit also allows the generation AI to learn the user's preferences and analyze the content of tweets. For example, if a user tweets, "I'm running low on milk," the analysis unit will prioritize low-fat milk, which the user prefers. The analysis unit also allows the generation AI to learn the user's purchasing patterns and analyze the content of tweets. For example, if a user tweets, "I'm running low on milk," the analysis unit will prioritize products that the user purchases regularly. This allows for more personalized decisions by taking into account past purchase history and user preferences.

[0058] The analysis unit can use news and trend information as a basis for understanding the context when analyzing tweets. For example, when the generation AI analyzes a tweet, the analysis unit refers to related news and trend information. For example, if a tweet says, "I'm running out of milk," the analysis unit will take into account recent milk price fluctuations and supply conditions when making a decision. The analysis unit also refers to related trend information when the generation AI analyzes a tweet. For example, if a tweet says, "I'm running out of milk," the analysis unit will take into account recent health trends and diet information when making a decision. The analysis unit also refers to related news when the generation AI analyzes a tweet. For example, if a tweet says, "I'm running out of milk," the analysis unit will take into account recent food safety information and recall information when making a decision. This enables more accurate analysis by referring to related news and trend information to understand the context.

[0059] The analysis unit uses the emotion estimation function to analyze the emotional nuances of tweets and can make judgments based on the emotions. For example, when the generation AI analyzes tweets, the analysis unit uses the emotion estimation function to analyze the emotional nuances. For example, it analyzes the emotion when a tweet such as "I'm running out of milk" and determines the urgency. In addition, the analysis unit uses the emotion estimation function to analyze the emotional nuances when the generation AI analyzes tweets. For example, it analyzes the emotion when a tweet such as "I'm running out of milk" and determines the user's stress level. In addition, the analysis unit uses the emotion estimation function to analyze the emotional nuances when the generation AI analyzes tweets. For example, it analyzes the emotion when a tweet such as "I'm running out of milk" and determines the user's satisfaction level. In this way, by using the emotion estimation function, it is possible to analyze the emotional nuances of tweets and make judgments based on emotions.

[0060] The analysis unit also takes into account the tweets of other members in the household and can grasp the overall needs. For example, the generation AI collects the tweets of other members in the household and grasps the overall needs. For example, if all family members tweet, "There's no milk," that need will be given priority in determining the needs. The analysis unit also analyzes the tweets of other members in the household and grasps the overall needs. For example, if a child tweets, "I want some sweets," that need will be taken into consideration in determining the needs. The analysis unit also collects the tweets of other members in the household and grasps the overall needs. For example, if multiple members tweet, "There's no milk," that need will be given priority in determining the needs. In this way, the analysis unit can grasp the overall needs by taking into account the tweets of other members in the household.

[0061] The analysis unit can feed back the results of the tweet analysis to the user and provide an interface that allows the user to confirm and modify what they need. For example, the analysis unit may feed back the results of the tweet analysis by the generation AI to the user and provide an interface that allows the user to confirm and modify what they need. For example, the analysis unit may ask, "Do you need milk?" The analysis unit may also feed back the results of the tweet analysis by the generation AI to the user and provide an interface that allows the user to confirm and modify what they need. For example, the analysis unit may ask, "Do you want to order milk?" The analysis unit may also feed back the results of the tweet analysis by the generation AI to the user and provide an interface that allows the user to confirm and modify what they need. For example, the analysis unit may ask, "Please select the type of milk." In this way, the tweet analysis results are fed back to the user, allowing the user to confirm and modify what they need.

[0062] The analysis unit uses the emotion estimation function to analyze the emotional trends of tweets and make product suggestions according to changes in emotion. For example, the generation AI in the analysis unit analyzes the emotional trends of tweets and makes product suggestions according to changes in emotion. For example, if the user is feeling stressed, it suggests products with a relaxing effect. The analysis unit also analyzes the emotional trends of tweets and makes product suggestions according to changes in emotion. For example, if the user is feeling positive, it suggests luxury products. The analysis unit also analyzes the emotional trends of tweets and makes product suggestions according to changes in emotion. For example, if the user is tired, it suggests products that are suitable for replenishing energy. As a result, by using the emotion estimation function, it is possible to analyze the emotional trends of tweets and make product suggestions according to changes in emotion.

[0063] The ordering unit can compare multiple e-commerce sites and select the optimal price and delivery terms. In the ordering unit, for example, the generation AI compares multiple e-commerce sites and selects the optimal price and delivery terms. For example, when ordering milk, the site with the lowest price and shortest delivery time is selected. In addition, the ordering unit can compare multiple e-commerce sites and select the optimal price and delivery terms. For example, when ordering milk, the generation AI prioritizes the selection of sites with free shipping. In addition, the ordering unit can compare multiple e-commerce sites and select the optimal price and delivery terms. For example, when ordering milk, the generation AI selects a reliable site taking into account the user's past purchase history. This makes it possible to select the optimal price and delivery terms by comparing multiple e-commerce sites.

[0064] The ordering unit can select highly reliable products by referring to the user's past ratings and reviews. In the ordering unit, for example, the generation AI refers to the user's past ratings and reviews and selects highly reliable products. For example, when ordering milk, products that have received high ratings in the past are preferentially selected. In addition, the ordering unit can select highly reliable products by referring to the user's past ratings and reviews. For example, when ordering milk, products with a large number of reviews and high ratings are selected. In addition, the ordering unit can select highly reliable products by referring to the user's past ratings and reviews. For example, when ordering milk, products of the same brand as products that the user has purchased in the past are selected. In this way, highly reliable products can be selected by referring to the user's past ratings and reviews.

[0065] The ordering unit can use the emotion estimation function to preferentially select products that the user feels most positive about. In the ordering unit, for example, the generation AI uses the emotion estimation function to preferentially select products that the user feels most positive about. For example, when ordering milk, a product that the user has previously felt positive about is selected. In addition, the ordering unit can use the emotion estimation function to preferentially select products that the user feels most positive about. For example, when ordering milk, a product that the user has given high ratings to in reviews is selected. In addition, the ordering unit can use the emotion estimation function to preferentially select products that the user feels most positive about. For example, when ordering milk, a product that the user has previously purchased and was satisfied with is selected. In this way, by using the emotion estimation function, the ordering unit can preferentially select products that the user feels most positive about.

[0066] The ordering unit can select an appropriate product by taking into account the user's health condition and allergy information. In the ordering unit, for example, the generation AI takes into account the user's health condition and allergy information and selects an appropriate product. For example, when ordering milk, if the user is lactose intolerant, lactose-free milk is selected. In addition, the ordering unit can select an appropriate product by taking into account the user's health condition and allergy information. For example, when ordering milk, if the user is on a diet, low-fat milk is selected. In addition, the ordering unit can select an appropriate product by taking into account the user's health condition and allergy information. For example, when ordering milk, if the user prefers organic food, organic milk is selected. In this way, an appropriate product can be selected by taking into account the user's health condition and allergy information.

[0067] The ordering unit can suggest related and complementary products based on the user's purchasing history. For example, the generation AI in the ordering unit suggests related and complementary products based on the user's purchasing history. For example, when ordering milk, it suggests cereal that the user has previously purchased. Also, the generation AI in the ordering unit suggests related and complementary products based on the user's purchasing history. For example, when ordering milk, it suggests coffee that the user has previously purchased. Also, the generation AI in the ordering unit suggests related and complementary products based on the user's purchasing history. For example, when ordering milk, it suggests bread that the user has previously purchased. This makes it possible to provide a more convenient shopping experience by suggesting related and complementary products based on the user's purchasing history.

[0068] The ordering unit can use the emotion estimation function to monitor the user's emotional response after placing an order and reflect it in the next order. In the ordering unit, for example, the generation AI can use the emotion estimation function to monitor the user's emotional response after placing an order and reflect it in the next order. For example, if the user is satisfied after ordering milk, the information can be reflected in the next order. In addition, the ordering unit can use the emotion estimation function to monitor the user's emotional response after placing an order and reflect it in the next order. For example, if the user expresses dissatisfaction after ordering milk, the information can be reflected in the next order. In addition, the ordering unit can use the emotion estimation function to monitor the user's emotional response after placing an order and reflect it in the next order. For example, if the user expresses positive emotions after ordering milk, the information can be reflected in the next order. In this way, by using the emotion estimation function, the user's emotional response after placing an order can be monitored and reflected in the next order.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The tweet collection unit can collect not only user tweets but also environmental sounds within the home and use them for analysis. For example, it collects sounds such as the opening and closing of a refrigerator and the sound of running water, and infers user behavior patterns from these sounds. The tweet collection unit can also collect environmental data such as temperature and humidity within the home and use them for analysis. For example, if the room temperature is high, it can be determined that there is an increased demand for cold drinks. The tweet collection unit can also collect information such as the on / off status of lights in the home and television viewing status, and can grasp the user's lifestyle rhythm. This allows for more accurate judgments to be made by using not only user tweets but also environmental data within the home for analysis.

[0071] The analysis unit can determine what a user needs based on their health data. For example, it can analyze heart rate and sleep data obtained from the user's smartwatch and suggest products that match their health condition. The analysis unit can also suggest products that take nutritional balance into consideration based on data obtained from the user's food recording app. For example, it can suggest foods that will supplement nutrients that have been lacking in recent meals. The analysis unit can also suggest products that are suitable for post-exercise recovery based on data obtained from the user's exercise recording app. For example, it can suggest protein or energy bars that are needed after exercise. This makes it possible to suggest more personalized products based on the user's health data.

[0072] The analysis unit can analyze the content of a user's social media posts to determine what they need. For example, if a user posts on social media that they want new running shoes, the analysis unit can suggest running shoes based on that information. The analysis unit can also analyze the content of the user's "likes" and comments on social media to suggest products that the user is interested in. For example, the analysis unit can suggest a new gadget that the user has "liked" on a friend's post. The analysis unit can also analyze the content of the accounts the user follows on social media to suggest products in areas of interest. For example, if the user follows many cooking accounts, the analysis unit can suggest cooking-related products. This makes it possible to make more personalized product suggestions by analyzing the content of a user's social media posts.

[0073] The analysis unit can suggest products according to seasons and events based on the user's past purchasing history. For example, based on products purchased during the Christmas season in the past, products suitable for this year's Christmas can be suggested. The analysis unit can also suggest products related to specific events based on the user's past purchasing history. For example, if the user has purchased barbecue equipment in the past, products related to the summer barbecue season can be suggested. The analysis unit can also suggest products according to seasonal demand based on the user's past purchasing history. For example, if a heating appliance was purchased in winter, products related to the following winter can be suggested. This makes it possible to suggest products according to seasons and events based on the user's past purchasing history.

[0074] The analysis unit can suggest related products based on the user's hobbies and interests. For example, if the user's hobby is music, the analysis unit can suggest the latest music equipment and sheet music. If the user's hobby is reading, the analysis unit can suggest recent bestsellers or books that suit the user's preferences. For example, if the user likes mystery novels, the analysis unit can suggest the latest mystery novels. If the user's hobby is outdoor activities, the analysis unit can suggest camping equipment and hiking gear. For example, if the user is planning to camp, the analysis unit can suggest the necessary camping equipment. This makes it possible to suggest related products based on the user's hobbies and interests.

[0075] The analysis unit can estimate the user's emotions and make product suggestions based on the emotions. For example, if the user is feeling stressed, it can suggest products with a relaxing effect, such as an aroma diffuser or relaxation music. If the user is feeling positive, the analysis unit can suggest luxury products, such as high-quality chocolates or spa experiences. If the user is tired, it can suggest products suitable for replenishing energy, such as energy drinks or nutritional supplements. This makes it possible to estimate the user's emotions and make product suggestions based on emotions.

[0076] The analysis unit can estimate the user's emotions and provide notifications based on those emotions. For example, if the user is feeling anxious, the analysis unit can send a notification that gives the user a sense of security. For example, it can send a notification such as "Your order has been successfully completed." If the user is feeling happy, the analysis unit can send a notification that further enhances that emotion. For example, it can send a notification such as "We will give you a special discount coupon." If the user is tired, the analysis unit can send a notification that encourages relaxation. For example, it can send a notification such as "Enjoy some relaxing music." This makes it possible to estimate the user's emotions and provide notifications based on those emotions.

[0077] The analysis unit can estimate the user's emotions and provide feedback based on the emotions. For example, if the user is feeling dissatisfied, the analysis unit can identify the cause and suggest improvements. For example, the analysis unit can provide feedback such as, "If your product delivery is delayed, we will offer priority delivery for your next order." If the user is satisfied, the analysis unit can provide feedback that further enhances the user's emotions. For example, the analysis unit can provide feedback such as, "Thank you for your order. We will give you a discount coupon that you can use for your next order." If the user is feeling stressed, the analysis unit can provide feedback that alleviates the user's emotions. For example, the analysis unit can provide feedback such as, "We will suggest products that will help you relax." This makes it possible to estimate the user's emotions and provide feedback based on emotions.

[0078] The analysis unit can estimate the user's emotions and provide emotion-based reminders. For example, if the user feels busy, the analysis unit can send an important reminder, such as a reminder saying, "Your milk is running low." If the user feels relaxed, the analysis unit can send a reminder to maintain that emotion, such as a reminder saying, "Take some time to relax." If the user feels tired, the analysis unit can send a reminder to encourage rest, such as a reminder saying, "Take a short break." This makes it possible to estimate the user's emotions and provide emotion-based reminders.

[0079] The analysis unit can estimate the user's emotions and provide alerts based on the emotions. For example, if the user feels urgent, the analysis unit sends an alert urging a quick response. For example, it sends an alert such as "You're completely out of milk." If the user feels relieved, the analysis unit can send an alert that maintains that emotion. For example, it sends an alert such as "Your order has been completed successfully." If the user feels anxious, the analysis unit can send an alert that eases that emotion. For example, it sends an alert such as "Your product delivery is delayed, but will arrive soon." This makes it possible to estimate the user's emotions and provide alerts based on emotions.

[0080] The processing flow of the second embodiment will be briefly explained below.

[0081] Step 1: The tweet collection unit collects users' everyday tweets in natural language. For example, it collects tweets such as "I'm running out of milk" from users via smartphones or smart speakers. The tweet collection unit also has the function of converting voice data into text data. For example, it uses voice recognition technology to convert the user's voice into text. Step 2: The analysis unit analyzes the tweets collected by the tweet collection unit and determines what is needed. For example, the generation AI analyzes the tweet "I'm running out of milk" and determines that the user needs milk. The generation AI uses text generation AI (e.g., LLM) or multimodal generation AI to analyze the content of the tweet. Step 3: The ordering unit automatically places an order on the e-commerce site based on the items determined by the analysis unit. For example, if the generation AI determines that "milk" is needed, it searches for milk on the e-commerce site, selects the appropriate product, and completes the order. Step 4: The notification unit notifies the user of the order made by the ordering unit. For example, the notification is sent via a smartphone or smart speaker in the form of "Milk has been ordered."

[0082] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0083] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0084] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0085] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0086] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0087] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0088] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0089] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0090] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0091] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0092] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0093] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0094] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0095] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0096] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0097] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0098] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0099] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0100] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0101] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0102] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0103] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0104] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0105] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0106] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0107] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0108] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0110] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0111] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0112] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0114] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0115] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0116] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0122] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0123] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0126] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0132] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0133] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0134] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0135] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0136] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0137] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0138] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0139] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0140] 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.

[0141] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0142] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0143] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0144] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0145] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0146] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0147] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0148] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0149] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a tweet collection unit that collects daily tweets in natural language from users; an analysis unit that analyzes the tweets collected by the tweet collection unit and determines what is necessary; an order unit that automatically places an order on an EC site based on the necessary items determined by the analysis unit; a notification unit that notifies the user of the order content placed by the ordering unit. A system characterized by:

2. The tweet collection unit Analyzes not only voice but also facial expressions and gestures to understand intent more accurately 2. The system of claim 1.

3. The tweet collection unit The tweets in different languages ​​will also be collected and analyzed using multilingual generative AI.

2. The system of claim 1.

4. The analysis unit Make more personalized decisions based on the user's purchasing history and preferences 2. The system of claim 1.

5. The ordering unit Compare multiple e-commerce sites and choose the best price and delivery terms 2. The system of claim 1.

6. The tweet collection unit Analyze emotional states and prioritize collecting tweets at moments of heightened emotion 2. The system of claim 1.

7. The analysis unit Analyze the emotional nuances of the tweets and make emotion-based decisions 2. The system of claim 1.

8. The ordering unit Monitor the user's emotional response after placing the order and reflect it in the next order.

2. The system of claim 1.

Images