System

Abstract

An object of a system according to an embodiment is to automatically associate attributes of a customer and create and distribute an optimal document.SOLUTION: A system according to an embodiment includes a customer attribute definition unit, an exchange analysis unit, an attribute association unit, a delivery content generation unit, and a message delivery unit. A customer attribute definition part defines customer attributes and tags. The exchange analysis unit analyzes an exchange such as a conversation with a customer or an action history on a site. The attribute association unit automatically associates the customer with the attribute based on the data analyzed by the exchange analysis unit. A distribution content generation part customizes the distribution content based on the attribute of the customer, and prepares an optimal document. The message delivery unit delivers the document generated by the delivery content generation unit to the customer.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 requires customers to manually set their attributes, making it difficult to deliver segments efficiently.

[0005] The system according to the embodiment aims to automatically associate customer attributes and create and distribute optimal documents. [Means for solving the problem]

[0006] The system according to the embodiment includes a customer attribute definition unit, an interaction analysis unit, an attribute linking unit, a delivery content generation unit, and a message delivery unit. The customer attribute definition unit defines customer attributes and tags. The interaction analysis unit analyzes interactions such as conversations with customers and action histories on the site. The attribute linking unit automatically links customers with attributes based on data analyzed by the interaction analysis unit. The delivery content generation unit customizes delivery content based on customer attributes and creates optimal documents. The message delivery unit delivers the documents generated by the delivery content generation unit to customers. [Effects of the Invention]

[0007] The system according to the embodiment can automatically associate customer attributes and create and distribute optimal documents. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The segment delivery system according to an embodiment of the present invention is a system that uses generation AI to automatically link customer attributes and deliver messages customized at the individual level. This enables the segment delivery system to provide optimal information for each customer and achieve effective segment delivery.

[0029] The segment delivery system according to the embodiment includes a customer attribute definition unit, an interaction analysis unit, an attribute linking unit, a delivery content generation unit, and a message delivery unit. The customer attribute definition unit defines customer attributes and tags. For example, attributes such as age, gender, interests, and purchasing history are set. The interaction analysis unit analyzes interactions with customers, such as conversations with customers and their on-site action history. For example, it collects data such as which pages customers viewed on the site, which products they purchased, and what questions they asked in chat. The attribute linking unit automatically links customers to attributes based on the data analyzed by the interaction analysis unit. For example, a customer who frequently views a specific product is assigned an attribute such as "Interest: Product A." The delivery content generation unit customizes delivery content based on customer attributes and creates optimal documents. For example, for a customer interested in a specific product, it creates a message containing information and promotions related to that product. The message delivery unit delivers the documents generated by the delivery content generation unit to customers. For example, messages can be sent to customers at optimal times using means such as email, SMS, or in-app notifications. As a result, the segment distribution system according to the embodiment can provide optimal information for each customer and achieve effective segment distribution.

[0030] The customer attribute definition unit can analyze purchase data and social media posts and dynamically update attributes. The customer attribute definition unit, for example, analyzes past purchase data to identify customer purchasing patterns. For example, a customer who frequently purchases a particular product is assigned the attribute "repeat customer," which is dynamically updated. The unit also analyzes social media posts to identify customer interests. For example, a customer who frequently mentions a particular brand is assigned the attribute "brand enthusiast," which is dynamically updated. The unit also analyzes purchase data and social media posts in an integrated manner to identify customer lifestyles. For example, a customer who frequently purchases outdoor products and posts about outdoor activities is assigned the attribute "outdoor enthusiast," which is dynamically updated. In this way, dynamically updating customer attributes enables more accurate segment delivery.

[0031] The customer attribute definition unit can detect life events and automatically change attributes based on them. For example, the customer attribute definition unit analyzes a customer's purchase history and social media posts to detect signs of marriage. For example, a customer who purchases wedding-related products or posts wedding photos can be assigned the attribute "newlywed." It also analyzes data related to childbirth to detect signs of childbirth. For example, a customer who purchases baby products or posts about childbirth can be assigned the attribute "new mom / dad." It also analyzes data related to moving to detect signs of moving. For example, a customer who changes to a new address or posts about moving can be assigned the attribute "new home." This allows for more personalized delivery by changing attributes based on customer life events.

[0032] The interaction analysis unit can analyze the customer's voice data and video data and set attributes based on the tone of voice and facial expression. The interaction analysis unit, for example, analyzes the customer's voice data and infers the customer's emotional state from the tone of voice. For example, a customer with a calm voice is assigned the attribute "calm." The interaction analysis unit also analyzes the video data and infers the customer's emotional state from the customer's facial expression. For example, a customer who smiles a lot is assigned the attribute "positive." The interaction analysis unit also analyzes the voice data and video data in an integrated manner to comprehensively determine the customer's emotional state. For example, if the tone of voice and facial expression match, the attribute "emotion match" is assigned. This makes it possible to set more detailed attributes by analyzing the customer's voice data and video data.

[0033] The interaction analysis unit can set attributes from a global perspective, taking into account the characteristics of different cultural spheres and regions. The interaction analysis unit, for example, analyzes data from different cultural spheres and sets culture-specific attributes. For example, Japanese customers are assigned the attribute "Japanese food lover," and American customers are assigned the attribute "fast food lover." It also analyzes purchasing data by region and sets region-specific attributes. For example, customers in cold climates are assigned the attribute "cold weather gear user," and customers in warm climates are assigned the attribute "summer goods user." It also analyzes customer interests from a global perspective and sets common attributes. For example, customers who are highly interested in environmental issues are assigned the attribute "highly eco-conscious." This makes it possible to set attributes from a global perspective by taking into account the characteristics of different cultural spheres and regions.

[0034] The interaction analysis unit analyzes specific keywords and phrases used in interactions with customers, and can identify customer needs based on the results. The interaction analysis unit, for example, analyzes the content of chats with customers to extract frequently used keywords. For example, if keywords such as "discount" and "sale" are frequently used, it determines that the customer is price-sensitive. It also analyzes the content of emails to extract specific phrases. For example, if phrases such as "easy to use" and "convenient" are frequently used, it determines that the customer places importance on convenience. It also analyzes customer reviews and feedback to extract specific keywords. For example, if keywords such as "quality" and "durability" are frequently used, it determines that the customer places importance on product quality. This allows for more appropriate delivery by identifying customer needs.

[0035] The interaction analysis unit can analyze customer behavior patterns and understand behavioral trends by time of day and day of the week. For example, the interaction analysis unit analyzes a customer's site visit history to understand trends by visit time of day and day of the week. For example, customers who visit frequently on weekday evenings can be assigned the attribute "night owl." The interaction analysis unit also analyzes purchase history to understand trends by purchase time of day and day of the week. For example, customers who make many purchases on weekends can be assigned the attribute "weekend shopper." The interaction analysis unit also analyzes chat and email interactions to understand trends by contact time of day and day of the week. For example, customers who contact frequently during the daytime on weekdays can be assigned the attribute "prefers daytime contact." This allows for understanding customer behavioral trends, enabling more appropriate delivery.

[0036] The interaction analysis unit can analyze the customer's voice data and video data and identify their needs from their tone of voice and facial expressions. For example, the interaction analysis unit analyzes the customer's voice data and identifies their needs from their tone of voice. For example, a customer who sounds excited can be provided with information about a new product. The interaction analysis unit can also analyze the video data and identify their needs from their facial expressions. For example, a customer who smiles a lot can be provided with a positive message. The interaction analysis unit can also analyze the voice data and video data in an integrated manner to comprehensively determine the customer's needs. For example, if the tone of voice and facial expressions match, a specific product or service can be suggested. This makes it possible to identify more detailed needs by analyzing the customer's voice data and video data.

[0037] The interaction analysis unit can perform an integrated analysis of interactions with customers across different platforms. For example, the interaction analysis unit analyzes the content of posts on social media to identify customer interests. For example, customers who frequently mention a particular brand can be assigned the attribute of "brand enthusiast." It can also analyze the content of emails to identify customer needs. For example, if phrases such as "easy to use" or "convenient" are frequently used, it can be determined that the customer places importance on convenience. It can also analyze the content of chats to identify customer questions and requests. For example, if the keywords "discount" or "sale" are frequently used, it can be determined that the customer is price-sensitive. This integrated analysis of interactions across different platforms enables a more detailed understanding of customers.

[0038] The attribute linking unit can analyze a customer's purchase history and browsing history and dynamically update attributes. For example, the attribute linking unit analyzes a customer's purchase history and sets attributes based on the products they frequently purchase. For example, a customer who frequently purchases a specific product is assigned the attribute "repeat customer." The attribute linking unit also analyzes a customer's browsing history and sets attributes based on the pages they frequently view. For example, a customer who frequently views a specific product page is assigned the attribute "Interest: Product A." The purchase history and browsing history are also analyzed in an integrated manner to comprehensively determine the customer's interests. For example, a customer who frequently purchases a specific product and frequently views that product page is assigned the attribute "Product A enthusiast." This enables more accurate segment delivery by dynamically updating attributes based on the customer's purchase history and browsing history.

[0039] The attribute linking unit can analyze the content of a customer's social media posts and automatically determine their interests. For example, the attribute linking unit analyzes the content of social media posts and extracts specific keywords and hashtags. For example, a customer who frequently uses the hashtags "#travel" and "#gourmet" is assigned the attributes "travel lover" and "food lover." The unit also analyzes the content of customer posts to identify frequently mentioned brands and products. For example, a customer who frequently mentions a specific brand is assigned the attribute "brand lover." The unit also analyzes the content of social media posts to identify the customer's lifestyle. For example, a customer who frequently posts about outdoor activities is assigned the attribute "outdoor enthusiast." This enables more appropriate delivery by automatically determining the customer's interests based on the content of their social media posts.

[0040] The attribute linking unit can analyze the customer's voice data and video data and set attributes based on the tone of voice and facial expression. The attribute linking unit, for example, analyzes the customer's voice data and infers the emotional state from the tone of voice. For example, a customer with a calm voice is assigned the attribute "calm." The attribute linking unit also analyzes the video data and infers the emotional state from the customer's facial expression. For example, a customer who smiles a lot is assigned the attribute "positive." The attribute linking unit also analyzes the voice data and video data in an integrated manner to comprehensively determine the customer's emotional state. For example, if the tone of voice and facial expression match, the attribute "emotion match" is assigned. This makes it possible to set more detailed attributes by analyzing the customer's voice data and video data.

[0041] The attribute linking unit can set attributes from a global perspective, taking into account the characteristics of different cultural spheres and regions. The attribute linking unit, for example, analyzes data from different cultural spheres and sets culture-specific attributes. For example, it assigns the attribute "Japanese food lover" to Japanese customers and "fast food lover" to American customers. It also analyzes purchasing data by region and sets region-specific attributes. For example, it assigns the attribute "cold weather gear user" to customers in cold climates and "summer goods user" to customers in warm climates. It also analyzes customer interests from a global perspective and sets common attributes. For example, it assigns the attribute "highly eco-conscious" to customers who are highly interested in environmental issues. This makes it possible to set attributes from a global perspective by taking into account the characteristics of different cultural spheres and regions.

[0042] The delivery content generation unit can analyze past customer response data and identify the most effective message format. The delivery content generation unit, for example, analyzes a customer's past email open rate and click rate to identify the most effective message format. For example, for a customer for whom messages that use a lot of images are effective, a message that includes many images is created. The unit also analyzes a customer's past purchase history to identify whether a particular message format is likely to lead to a purchase. For example, for a customer for whom short text messages are effective, a concise message is created. The unit also analyzes a customer's past feedback to identify the message format that will elicit the most positive response. For example, for a customer for whom storytelling-style messages are effective, a narrative message is created. In this way, more effective delivery is possible by identifying the optimal message format based on the customer's past response data.

[0043] The distribution content generation unit can automatically extract highly relevant information based on a customer's purchase history and browsing history. The distribution content generation unit, for example, analyzes a customer's purchase history to identify highly relevant products and services. For example, for a customer who has purchased a specific product, accessories and options related to that product are suggested. The distribution content generation unit also analyzes a customer's browsing history to identify products and services in which the customer is interested. For example, for a customer who frequently views a specific product page, information related to that product is provided. The purchase history and browsing history are also analyzed in an integrated manner to comprehensively determine the customer's interests. For example, for a customer who frequently purchases a specific product and frequently views that product page, promotions related to that product are provided. This enables more appropriate distribution by extracting highly relevant information based on a customer's purchase history and browsing history.

[0044] The delivery content generation unit can analyze the customer's voice data and video data and generate optimal message content based on the tone of voice and facial expression. The delivery content generation unit, for example, analyzes the customer's voice data, infers the customer's emotional state from the tone of voice, and generates optimal message content based on that. For example, for a customer with a calm voice, it creates a message with a calm tone. It also analyzes video data, infers the customer's emotional state from the customer's facial expression, and generates optimal message content based on that. For example, it creates a positive message for a customer who smiles a lot. It also analyzes the voice data and video data in an integrated manner, comprehensively judges the customer's emotional state, and generates optimal message content based on that. For example, if the tone of voice and facial expression match, it creates a message that matches the emotion. This enables more appropriate delivery by generating optimal message content based on the customer's voice data and video data.

[0045] The distribution content generation unit can comprehensively customize distribution content across different platforms. The distribution content generation unit, for example, analyzes the content posted on social media and generates customized messages based on the customer's interests. For example, if a customer frequently mentions a particular brand, it provides information related to that brand. It also analyzes the content of emails and generates customized messages based on the customer's needs. For example, if phrases such as "easy to use" and "convenient" are frequently used, it creates a message that emphasizes convenience. It also analyzes the content of chats and generates customized messages based on the customer's questions and requests. For example, if the keywords "discount" and "sale" are frequently used, it provides promotions for price-sensitive customers. This makes it possible to comprehensively customize distribution content across different platforms, enabling more appropriate distribution.

[0046] The message delivery unit can analyze past customer response data and identify the optimal delivery timing. The message delivery unit, for example, analyzes a customer's past email open rate and click rate to identify the optimal delivery timing. For example, for customers with a high open rate during a specific time period, the message is delivered during that time period. The unit also analyzes a customer's past purchase history to identify whether purchases are more common during specific time periods or on specific days of the week. For example, for customers who make more purchases on weekends, a promotional message is delivered on the weekend. The unit also analyzes a customer's past feedback to identify the delivery timing that will elicit the most positive response. For example, for customers who receive a lot of positive feedback during a specific time period, a message is delivered during that time period. This enables more effective delivery by identifying the optimal delivery timing based on the customer's past response data.

[0047] The message delivery unit can analyze customer behavior patterns and determine the optimal delivery timing for each time period and day of the week. The message delivery unit, for example, analyzes a customer's site visit history to determine trends by visit time period and day of the week. For example, for customers who visit frequently on weekday evenings, a message is delivered during that time period. The unit also analyzes purchase history to determine trends by purchase time period and day of the week. For example, for customers who make many purchases on weekends, a promotional message is delivered on the weekend. The unit also analyzes chat and email exchanges to determine trends by contact time period and day of the week. For example, for customers who contact frequently during the daytime on weekdays, a message is delivered during that time period. This allows for more effective delivery by determining the optimal delivery timing based on the customer's behavior patterns.

[0048] The message delivery unit can analyze the customer's voice data and video data and identify the optimal delivery timing based on the tone of voice and facial expression. The message delivery unit, for example, analyzes the customer's voice data, estimates the customer's emotional state from the tone of voice, and identifies the optimal delivery timing based on that. For example, for a customer with a calm voice, it creates a calm-toned message. It also analyzes video data, estimates the customer's emotional state from the customer's facial expression, and identifies the optimal delivery timing based on that. For example, it creates a positive message for a customer who smiles a lot. It also analyzes the voice data and video data in an integrated manner to comprehensively determine the customer's emotional state and identify the optimal delivery timing based on that. For example, if the tone of voice and facial expression match, it creates a message that matches the emotion. This enables more appropriate delivery by identifying the optimal delivery timing based on the customer's voice data and video data.

[0049] The message delivery unit can adjust the timing of delivery across different platforms in an integrated manner. The message delivery unit, for example, analyzes the content of posts on social media and generates customized messages based on the customer's interests. For example, if a customer frequently mentions a particular brand, it provides information related to that brand. It also analyzes the content of emails and generates customized messages based on the customer's needs. For example, if phrases such as "easy to use" and "convenient" are frequently used, it creates a message that emphasizes convenience. It also analyzes the content of chats and generates customized messages based on the customer's questions and requests. For example, if the keywords "discount" and "sale" are frequently used, it provides promotions for price-sensitive customers. This makes it possible to deliver more appropriate messages by adjusting the timing of delivery across different platforms in an integrated manner.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The segment delivery system can also analyze customer health data and set attributes based on their health status. For example, data obtained from fitness trackers and smartwatches can be analyzed to identify exercise habits and sleep patterns. Customers who exercise regularly can be assigned the attribute "active," while customers who consistently suffer from lack of sleep can be assigned the attribute "fatigued." Data from health apps can also be analyzed to identify dietary trends. For example, customers who follow a health-conscious diet can be assigned the attribute "health-conscious." This allows for more personalized delivery by setting attributes based on the customer's health status.

[0052] The segment delivery system can also set attributes based on customer hobbies and preferences. For example, by analyzing data on the events and hobbies that customers participate in, customers with specific hobbies can be assigned attributes such as "Hobbies: Music" or "Hobbies: Sports." The system can also analyze the content of magazines and newsletters that customers subscribe to to identify areas of interest. For example, a customer who frequently subscribes to technology-related news can be assigned the attribute "Technology Enthusiast." The system can also analyze the influencers and brands that customers follow to identify their interests. For example, a customer who follows a specific fashion brand can be assigned the attribute "Fashion Enthusiast." By setting attributes based on customers' hobbies and preferences, more appropriate delivery is possible.

[0053] The segment delivery system can also analyze customer location information and set geographic attributes. For example, by analyzing data on a customer's place of residence and visited destinations, customers living in urban areas can be assigned the attribute "urban resident," and customers living in suburban or rural areas can be assigned the attributes "suburban resident" or "countryside resident." It can also analyze the places a customer frequently visits and set attributes related to specific regions. For example, customers who frequently visit a specific shopping mall can be assigned the attribute "shopping mall regular." It can also analyze data on travel destinations and assign the attribute "travel enthusiast" to customers who love to travel. By setting attributes based on a customer's location information, more personalized delivery becomes possible.

[0054] The segment delivery system can also estimate a customer's purchasing intent and set attributes based on that intent. For example, it can analyze a customer's past purchase history and browsing history, and assign an attribute of "high purchasing intent" to customers with a high purchasing intent. It can also analyze the items added to a customer's cart and the contents of their wish list to estimate purchasing intent. For example, it can assign an attribute of "currently intending to purchase" to customers who have many items in their cart. It can also analyze a customer's time on the site and the number of pages viewed to estimate purchasing intent. For example, it can assign an attribute of "high purchasing intent" to customers who stay on the site for a long time and view many pages. In this way, setting attributes based on a customer's purchasing intent enables more effective delivery.

[0055] The segment delivery system can also set attributes based on a customer's life stage. For example, by analyzing a customer's age and family structure, attributes such as "student," "newlywed," or "raising children" can be assigned to customers in a particular life stage. It can also analyze a customer's occupation and income data to identify their life stage. For example, a customer in the early stages of their career could be assigned the attribute "young employee," and a customer who has reached retirement age could be assigned the attribute "retirement." Attributes can also be set based on a customer's life events. For example, customers who have reached life events such as marriage, childbirth, or moving could be assigned the attributes "newlywed," "new mom / dad," or "new home." Setting attributes based on a customer's life stage enables more personalized delivery.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The customer attribute definition section defines customer attributes and tags, such as age, gender, interests, and purchasing history. Step 2: The interaction analysis unit analyzes interactions, such as conversations with customers and their actions on the site. For example, it collects data such as which pages customers viewed on the site, which products they purchased, and what questions they asked in chat. Step 3: The attribute linking unit automatically links customers to attributes based on the data analyzed by the interaction analysis unit. For example, a customer who frequently views a specific product is assigned the attribute "Interest: Product A." Step 4: The content generator customizes the content based on customer attributes and creates the most appropriate document. For example, for customers interested in a particular product, it creates a message containing information and promotions related to that product. Step 5: The message delivery unit delivers the document generated by the delivery content generation unit to the customer. For example, the message is sent to the customer at the optimal time using means such as email, SMS, or in-app notifications.

[0058] (Example 2) The segment delivery system according to an embodiment of the present invention is a system that uses generation AI to automatically link customer attributes and deliver messages customized at the individual level. This enables the segment delivery system to provide optimal information for each customer and achieve effective segment delivery.

[0059] The segment delivery system according to the embodiment includes a customer attribute definition unit, an interaction analysis unit, an attribute linking unit, a delivery content generation unit, and a message delivery unit. The customer attribute definition unit defines customer attributes and tags. For example, attributes such as age, gender, interests, and purchasing history are set. The interaction analysis unit analyzes interactions with customers, such as conversations with customers and their on-site action history. For example, it collects data such as which pages customers viewed on the site, which products they purchased, and what questions they asked in chat. The attribute linking unit automatically links customers to attributes based on the data analyzed by the interaction analysis unit. For example, a customer who frequently views a specific product is assigned an attribute such as "Interest: Product A." The delivery content generation unit customizes delivery content based on customer attributes and creates optimal documents. For example, for a customer interested in a specific product, it creates a message containing information and promotions related to that product. The message delivery unit delivers the documents generated by the delivery content generation unit to customers. For example, messages can be sent to customers at optimal times using means such as email, SMS, or in-app notifications. As a result, the segment distribution system according to the embodiment can provide optimal information for each customer and achieve effective segment distribution.

[0060] The customer attribute definition unit can analyze purchase data and social media posts and dynamically update attributes. The customer attribute definition unit, for example, analyzes past purchase data to identify customer purchasing patterns. For example, a customer who frequently purchases a particular product is assigned the attribute "repeat customer," which is dynamically updated. The unit also analyzes social media posts to identify customer interests. For example, a customer who frequently mentions a particular brand is assigned the attribute "brand enthusiast," which is dynamically updated. The unit also analyzes purchase data and social media posts in an integrated manner to identify customer lifestyles. For example, a customer who frequently purchases outdoor products and posts about outdoor activities is assigned the attribute "outdoor enthusiast," which is dynamically updated. In this way, dynamically updating customer attributes enables more accurate segment delivery.

[0061] The customer attribute definition unit can detect life events and automatically change attributes based on them. For example, the customer attribute definition unit analyzes a customer's purchase history and social media posts to detect signs of marriage. For example, a customer who purchases wedding-related products or posts wedding photos can be assigned the attribute "newlywed." It also analyzes data related to childbirth to detect signs of childbirth. For example, a customer who purchases baby products or posts about childbirth can be assigned the attribute "new mom / dad." It also analyzes data related to moving to detect signs of moving. For example, a customer who changes to a new address or posts about moving can be assigned the attribute "new home." This allows for more personalized delivery by changing attributes based on customer life events.

[0062] The customer attribute definition unit can use the emotion estimation function to analyze the emotional state of a customer in real time and dynamically set attributes based on that emotion. The customer attribute definition unit, for example, analyzes the content of a customer's chat or email to estimate the emotional state in real time. For example, a customer with strong positive emotions is assigned an attribute of "high satisfaction." The customer attribute definition unit also analyzes the content of social media posts to estimate the customer's emotional state in real time. For example, a customer with many negative posts is assigned an attribute of "dissatisfied." The customer's voice data is also analyzed to estimate the emotional state in real time from the tone of voice. For example, a customer with an excited voice is assigned an attribute of "excited." This allows for dynamic setting of attributes based on the customer's emotional state, enabling more appropriate delivery.

[0063] The interaction analysis unit can analyze the customer's voice data and video data and set attributes based on the tone of voice and facial expression. The interaction analysis unit, for example, analyzes the customer's voice data and infers the customer's emotional state from the tone of voice. For example, a customer with a calm voice is assigned the attribute "calm." The interaction analysis unit also analyzes the video data and infers the customer's emotional state from the customer's facial expression. For example, a customer who smiles a lot is assigned the attribute "positive." The interaction analysis unit also analyzes the voice data and video data in an integrated manner to comprehensively determine the customer's emotional state. For example, if the tone of voice and facial expression match, the attribute "emotion match" is assigned. This makes it possible to set more detailed attributes by analyzing the customer's voice data and video data.

[0064] The interaction analysis unit can set attributes from a global perspective, taking into account the characteristics of different cultural spheres and regions. The interaction analysis unit, for example, analyzes data from different cultural spheres and sets culture-specific attributes. For example, Japanese customers are assigned the attribute "Japanese food lover," and American customers are assigned the attribute "fast food lover." It also analyzes purchasing data by region and sets region-specific attributes. For example, customers in cold climates are assigned the attribute "cold weather gear user," and customers in warm climates are assigned the attribute "summer goods user." It also analyzes customer interests from a global perspective and sets common attributes. For example, customers who are highly interested in environmental issues are assigned the attribute "highly eco-conscious." This makes it possible to set attributes from a global perspective by taking into account the characteristics of different cultural spheres and regions.

[0065] The interaction analysis unit can use the emotion estimation function to analyze the emotions customers have toward a specific product or service, and set attributes based on those emotions. The interaction analysis unit, for example, analyzes customer reviews and feedback to estimate emotions toward a specific product. For example, customers with many positive reviews can be assigned an attribute of "high product satisfaction." The interaction analysis unit also analyzes the content of social media posts to estimate emotions toward a specific service. For example, customers with many negative posts can be assigned an attribute of "dissatisfied with service." The interaction analysis unit also analyzes the content of customer chats and emails to estimate emotions toward a specific product or service. For example, customers with many excited messages can be assigned an attribute of "high product excitement." In this way, setting attributes based on customer emotions enables more personalized delivery.

[0066] The interaction analysis unit analyzes specific keywords and phrases used in interactions with customers, and can identify customer needs based on the results. The interaction analysis unit, for example, analyzes the content of chats with customers to extract frequently used keywords. For example, if keywords such as "discount" and "sale" are frequently used, it determines that the customer is price-sensitive. It also analyzes the content of emails to extract specific phrases. For example, if phrases such as "easy to use" and "convenient" are frequently used, it determines that the customer places importance on convenience. It also analyzes customer reviews and feedback to extract specific keywords. For example, if keywords such as "quality" and "durability" are frequently used, it determines that the customer places importance on product quality. This allows for more appropriate delivery by identifying customer needs.

[0067] The interaction analysis unit can analyze customer behavior patterns and understand behavioral trends by time of day and day of the week. For example, the interaction analysis unit analyzes a customer's site visit history to understand trends by visit time of day and day of the week. For example, customers who visit frequently on weekday evenings can be assigned the attribute "night owl." The interaction analysis unit also analyzes purchase history to understand trends by purchase time of day and day of the week. For example, customers who make many purchases on weekends can be assigned the attribute "weekend shopper." The interaction analysis unit also analyzes chat and email interactions to understand trends by contact time of day and day of the week. For example, customers who contact frequently during the daytime on weekdays can be assigned the attribute "prefers daytime contact." This allows for understanding customer behavioral trends, enabling more appropriate delivery.

[0068] The interaction analysis unit uses the emotion estimation function to analyze changes in a customer's emotions in real time during interactions with the customer, and can adjust responses based on those emotions. The interaction analysis unit, for example, analyzes chat content in real time to estimate changes in a customer's emotions. For example, if negative emotions become stronger, a prompt response is made. It also analyzes email content in real time to estimate changes in a customer's emotions. For example, if positive emotions become stronger, an additional promotion is suggested. It also analyzes customer voice data in real time to estimate changes in emotions from the tone of voice. For example, a customer who sounds excited can be provided with interesting information. This makes it possible to adjust responses based on changes in the customer's emotions, enabling more appropriate responses.

[0069] The interaction analysis unit can analyze the customer's voice data and video data and identify their needs from their tone of voice and facial expressions. For example, the interaction analysis unit analyzes the customer's voice data and identifies their needs from their tone of voice. For example, a customer who sounds excited can be provided with information about a new product. The interaction analysis unit can also analyze the video data and identify their needs from their facial expressions. For example, a customer who smiles a lot can be provided with a positive message. The interaction analysis unit can also analyze the voice data and video data in an integrated manner to comprehensively determine the customer's needs. For example, if the tone of voice and facial expressions match, a specific product or service can be suggested. This makes it possible to identify more detailed needs by analyzing the customer's voice data and video data.

[0070] The interaction analysis unit can perform an integrated analysis of interactions with customers across different platforms. For example, the interaction analysis unit analyzes the content of posts on social media to identify customer interests. For example, customers who frequently mention a particular brand can be assigned the attribute of "brand enthusiast." It can also analyze the content of emails to identify customer needs. For example, if phrases such as "easy to use" or "convenient" are frequently used, it can be determined that the customer places importance on convenience. It can also analyze the content of chats to identify customer questions and requests. For example, if the keywords "discount" or "sale" are frequently used, it can be determined that the customer is price-sensitive. This integrated analysis of interactions across different platforms enables a more detailed understanding of customers.

[0071] The interaction analysis unit can use the emotion estimation function to analyze the emotions customers have toward a specific product or service, and adjust the content of the interaction based on those emotions. The interaction analysis unit, for example, analyzes customer reviews and feedback to estimate emotions toward a specific product. For example, customers with many positive reviews are assigned an attribute of "high product satisfaction." The interaction analysis unit also analyzes the content of social media posts to estimate emotions toward a specific service. For example, customers with many negative posts are assigned an attribute of "dissatisfied with service." The interaction analysis unit also analyzes the content of customer chats and emails to estimate emotions toward a specific product or service. For example, customers with many excited messages are assigned an attribute of "high product excitement." This makes it possible to adjust the content of the interaction based on the customer's emotions, thereby enabling more appropriate responses.

[0072] The attribute linking unit can analyze a customer's purchase history and browsing history and dynamically update attributes. For example, the attribute linking unit analyzes a customer's purchase history and sets attributes based on the products they frequently purchase. For example, a customer who frequently purchases a specific product is assigned the attribute "repeat customer." The attribute linking unit also analyzes a customer's browsing history and sets attributes based on the pages they frequently view. For example, a customer who frequently views a specific product page is assigned the attribute "Interest: Product A." The purchase history and browsing history are also analyzed in an integrated manner to comprehensively determine the customer's interests. For example, a customer who frequently purchases a specific product and frequently views that product page is assigned the attribute "Product A enthusiast." This enables more accurate segment delivery by dynamically updating attributes based on the customer's purchase history and browsing history.

[0073] The attribute linking unit can analyze the content of a customer's social media posts and automatically determine their interests. For example, the attribute linking unit analyzes the content of social media posts and extracts specific keywords and hashtags. For example, a customer who frequently uses the hashtags "#travel" and "#gourmet" is assigned the attributes "travel lover" and "food lover." The unit also analyzes the content of customer posts to identify frequently mentioned brands and products. For example, a customer who frequently mentions a specific brand is assigned the attribute "brand lover." The unit also analyzes the content of social media posts to identify the customer's lifestyle. For example, a customer who frequently posts about outdoor activities is assigned the attribute "outdoor enthusiast." This enables more appropriate delivery by automatically determining the customer's interests based on the content of their social media posts.

[0074] The attribute linking unit can use the emotion estimation function to analyze the emotional state of a customer in real time and dynamically set attributes based on that emotion. The attribute linking unit, for example, analyzes the content of a customer's chat or email to estimate the emotional state in real time. For example, a customer with strong positive emotions is assigned an attribute of "high satisfaction." The attribute linking unit also analyzes the content of social media posts to estimate the emotional state of a customer in real time. For example, a customer with many negative posts is assigned an attribute of "dissatisfied." The attribute linking unit also analyzes the customer's voice data to estimate the emotional state in real time from the tone of voice. For example, a customer with an excited voice is assigned an attribute of "excited." This allows for more appropriate delivery by dynamically setting attributes based on the customer's emotional state.

[0075] The attribute linking unit can analyze the customer's voice data and video data and set attributes based on the tone of voice and facial expression. The attribute linking unit, for example, analyzes the customer's voice data and infers the emotional state from the tone of voice. For example, a customer with a calm voice is assigned the attribute "calm." The attribute linking unit also analyzes the video data and infers the emotional state from the customer's facial expression. For example, a customer who smiles a lot is assigned the attribute "positive." The attribute linking unit also analyzes the voice data and video data in an integrated manner to comprehensively determine the customer's emotional state. For example, if the tone of voice and facial expression match, the attribute "emotion match" is assigned. This makes it possible to set more detailed attributes by analyzing the customer's voice data and video data.

[0076] The attribute linking unit can set attributes from a global perspective, taking into account the characteristics of different cultural spheres and regions. The attribute linking unit, for example, analyzes data from different cultural spheres and sets culture-specific attributes. For example, it assigns the attribute "Japanese food lover" to Japanese customers and "fast food lover" to American customers. It also analyzes purchasing data by region and sets region-specific attributes. For example, it assigns the attribute "cold weather gear user" to customers in cold climates and "summer goods user" to customers in warm climates. It also analyzes customer interests from a global perspective and sets common attributes. For example, it assigns the attribute "highly eco-conscious" to customers who are highly interested in environmental issues. This makes it possible to set attributes from a global perspective by taking into account the characteristics of different cultural spheres and regions.

[0077] The attribute linking unit can use the emotion estimation function to analyze the emotions customers have toward a specific product or service, and set attributes based on those emotions. The attribute linking unit, for example, analyzes customer reviews and feedback to estimate emotions toward a specific product. For example, a customer with many positive reviews is assigned an attribute of "high product satisfaction." The attribute linking unit also analyzes the content of social media posts to estimate emotions toward a specific service. For example, a customer with many negative posts is assigned an attribute of "dissatisfied with service." The attribute linking unit also analyzes the content of customer chats and emails to estimate emotions toward a specific product or service. For example, a customer with many excited messages is assigned an attribute of "high product excitement." In this way, setting attributes based on customer emotions enables more personalized delivery.

[0078] The delivery content generation unit can analyze past customer response data and identify the most effective message format. The delivery content generation unit, for example, analyzes a customer's past email open rate and click rate to identify the most effective message format. For example, for a customer for whom messages that use a lot of images are effective, a message that includes many images is created. The unit also analyzes a customer's past purchase history to identify whether a particular message format is likely to lead to a purchase. For example, for a customer for whom short text messages are effective, a concise message is created. The unit also analyzes a customer's past feedback to identify the message format that will elicit the most positive response. For example, for a customer for whom storytelling-style messages are effective, a narrative message is created. In this way, more effective delivery is possible by identifying the optimal message format based on the customer's past response data.

[0079] The distribution content generation unit can automatically extract highly relevant information based on a customer's purchase history and browsing history. The distribution content generation unit, for example, analyzes a customer's purchase history to identify highly relevant products and services. For example, for a customer who has purchased a specific product, accessories and options related to that product are suggested. The distribution content generation unit also analyzes a customer's browsing history to identify products and services in which the customer is interested. For example, for a customer who frequently views a specific product page, information related to that product is provided. The purchase history and browsing history are also analyzed in an integrated manner to comprehensively determine the customer's interests. For example, for a customer who frequently purchases a specific product and frequently views that product page, promotions related to that product are provided. This enables more appropriate distribution by extracting highly relevant information based on a customer's purchase history and browsing history.

[0080] The delivery content generation unit can analyze the customer's voice data and video data and generate optimal message content based on the tone of voice and facial expression. The delivery content generation unit, for example, analyzes the customer's voice data, infers the customer's emotional state from the tone of voice, and generates optimal message content based on that. For example, for a customer with a calm voice, it creates a message with a calm tone. It also analyzes video data, infers the customer's emotional state from the customer's facial expression, and generates optimal message content based on that. For example, it creates a positive message for a customer who smiles a lot. It also analyzes the voice data and video data in an integrated manner, comprehensively judges the customer's emotional state, and generates optimal message content based on that. For example, if the tone of voice and facial expression match, it creates a message that matches the emotion. This enables more appropriate delivery by generating optimal message content based on the customer's voice data and video data.

[0081] The distribution content generation unit can comprehensively customize distribution content across different platforms. The distribution content generation unit, for example, analyzes the content posted on social media and generates customized messages based on the customer's interests. For example, if a customer frequently mentions a particular brand, it provides information related to that brand. It also analyzes the content of emails and generates customized messages based on the customer's needs. For example, if phrases such as "easy to use" and "convenient" are frequently used, it creates a message that emphasizes convenience. It also analyzes the content of chats and generates customized messages based on the customer's questions and requests. For example, if the keywords "discount" and "sale" are frequently used, it provides promotions for price-sensitive customers. This makes it possible to comprehensively customize distribution content across different platforms, enabling more appropriate distribution.

[0082] The delivery content generation unit can use the emotion estimation function to analyze the emotions customers have toward a specific product or service and adjust the message content based on those emotions. The delivery content generation unit, for example, analyzes customer reviews and feedback to estimate emotions toward a specific product and adjusts the message content based on that. For example, for customers with many positive reviews, it provides additional information about the product. It can also analyze social media posts to estimate emotions toward a specific service and adjust the message content based on that. For example, for customers with many negative posts, it provides information about service improvements. It can also analyze the content of customer chats and emails to estimate emotions toward a specific product or service and adjust the message content based on that. For example, for customers with many excited messages, it introduces new features of the product. In this way, adjusting the message content based on customer emotions enables more appropriate delivery.

[0083] The message delivery unit can analyze past customer response data and identify the optimal delivery timing. The message delivery unit, for example, analyzes a customer's past email open rate and click rate to identify the optimal delivery timing. For example, for customers with a high open rate during a specific time period, the message is delivered during that time period. The unit also analyzes a customer's past purchase history to identify whether purchases are more common during specific time periods or on specific days of the week. For example, for customers who make more purchases on weekends, a promotional message is delivered on the weekend. The unit also analyzes a customer's past feedback to identify the delivery timing that will elicit the most positive response. For example, for customers who receive a lot of positive feedback during a specific time period, a message is delivered during that time period. This enables more effective delivery by identifying the optimal delivery timing based on the customer's past response data.

[0084] The message delivery unit can analyze customer behavior patterns and determine the optimal delivery timing for each time period and day of the week. The message delivery unit, for example, analyzes a customer's site visit history to determine trends by visit time period and day of the week. For example, for customers who visit frequently on weekday evenings, a message is delivered during that time period. The unit also analyzes purchase history to determine trends by purchase time period and day of the week. For example, for customers who make many purchases on weekends, a promotional message is delivered on the weekend. The unit also analyzes chat and email exchanges to determine trends by contact time period and day of the week. For example, for customers who contact frequently during the daytime on weekdays, a message is delivered during that time period. This allows for more effective delivery by determining the optimal delivery timing based on the customer's behavior patterns.

[0085] The message delivery unit can use the emotion estimation function to analyze the emotional state of a customer in real time and dynamically adjust the timing of delivery based on that emotion. The message delivery unit, for example, analyzes chat content in real time, estimates changes in the customer's emotions, and adjusts the optimal timing of delivery. For example, if negative emotions become stronger, it responds quickly. It also analyzes email content in real time, estimates changes in the customer's emotions, and adjusts the optimal timing of delivery. For example, if positive emotions become stronger, it suggests additional promotions. It also analyzes customer voice data in real time, estimates changes in emotions from the tone of voice, and adjusts the timing of delivery based on that. For example, it provides interesting information to a customer who sounds excited. This allows for more appropriate delivery by dynamically adjusting the timing of delivery based on the customer's emotional state.

[0086] The message delivery unit can analyze the customer's voice data and video data and identify the optimal delivery timing based on the tone of voice and facial expression. The message delivery unit, for example, analyzes the customer's voice data, estimates the customer's emotional state from the tone of voice, and identifies the optimal delivery timing based on that. For example, for a customer with a calm voice, it creates a calm-toned message. It also analyzes video data, estimates the customer's emotional state from the customer's facial expression, and identifies the optimal delivery timing based on that. For example, it creates a positive message for a customer who smiles a lot. It also analyzes the voice data and video data in an integrated manner to comprehensively determine the customer's emotional state and identify the optimal delivery timing based on that. For example, if the tone of voice and facial expression match, it creates a message that matches the emotion. This enables more appropriate delivery by identifying the optimal delivery timing based on the customer's voice data and video data.

[0087] The message delivery unit can adjust the timing of delivery across different platforms in an integrated manner. The message delivery unit, for example, analyzes the content of posts on social media and generates customized messages based on the customer's interests. For example, if a customer frequently mentions a particular brand, it provides information related to that brand. It also analyzes the content of emails and generates customized messages based on the customer's needs. For example, if phrases such as "easy to use" and "convenient" are frequently used, it creates a message that emphasizes convenience. It also analyzes the content of chats and generates customized messages based on the customer's questions and requests. For example, if the keywords "discount" and "sale" are frequently used, it provides promotions for price-sensitive customers. This makes it possible to deliver more appropriate messages by adjusting the timing of delivery across different platforms in an integrated manner.

[0088] The message delivery unit can use the emotion estimation function to analyze the emotions customers have toward a specific product or service and adjust the timing of delivery based on those emotions. The message delivery unit, for example, analyzes customer reviews and feedback to estimate emotions toward a specific product and adjusts the timing of delivery based on that. For example, for customers with many positive reviews, it provides additional information about the product. It also analyzes the content of social media posts to estimate emotions toward a specific service and adjusts the timing of delivery based on that. For example, for customers with many negative posts, it provides information about service improvements. It also analyzes the content of customer chats and emails to estimate emotions toward a specific product or service and adjust the timing of delivery based on that. For example, for customers with many excited messages, it introduces new features of the product. This allows for more appropriate delivery by adjusting the timing of delivery based on customer emotions.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The segment delivery system can also analyze customer health data and set attributes based on their health status. For example, data obtained from fitness trackers and smartwatches can be analyzed to identify exercise habits and sleep patterns. Customers who exercise regularly can be assigned the attribute "active," while customers who consistently suffer from lack of sleep can be assigned the attribute "fatigued." Data from health apps can also be analyzed to identify dietary trends. For example, customers who follow a health-conscious diet can be assigned the attribute "health-conscious." This allows for more personalized delivery by setting attributes based on the customer's health status.

[0091] The segment delivery system can also set attributes based on customer hobbies and preferences. For example, by analyzing data on the events and hobbies that customers participate in, customers with specific hobbies can be assigned attributes such as "Hobbies: Music" or "Hobbies: Sports." The system can also analyze the content of magazines and newsletters that customers subscribe to to identify areas of interest. For example, a customer who frequently subscribes to technology-related news can be assigned the attribute "Technology Enthusiast." The system can also analyze the influencers and brands that customers follow to identify their interests. For example, a customer who follows a specific fashion brand can be assigned the attribute "Fashion Enthusiast." By setting attributes based on customers' hobbies and preferences, more appropriate delivery is possible.

[0092] The segment delivery system can also analyze customer location information and set geographic attributes. For example, by analyzing data on a customer's place of residence and visited destinations, customers living in urban areas can be assigned the attribute "urban resident," and customers living in suburban or rural areas can be assigned the attributes "suburban resident" or "countryside resident." It can also analyze the places a customer frequently visits and set attributes related to specific regions. For example, customers who frequently visit a specific shopping mall can be assigned the attribute "shopping mall regular." It can also analyze data on travel destinations and assign the attribute "travel enthusiast" to customers who love to travel. By setting attributes based on a customer's location information, more personalized delivery becomes possible.

[0093] The segment delivery system can also estimate a customer's purchasing intent and set attributes based on that intent. For example, it can analyze a customer's past purchase history and browsing history, and assign an attribute of "high purchasing intent" to customers with a high purchasing intent. It can also analyze the items added to a customer's cart and the contents of their wish list to estimate purchasing intent. For example, it can assign an attribute of "currently intending to purchase" to customers who have many items in their cart. It can also analyze a customer's time on the site and the number of pages viewed to estimate purchasing intent. For example, it can assign an attribute of "high purchasing intent" to customers who stay on the site for a long time and view many pages. In this way, setting attributes based on a customer's purchasing intent enables more effective delivery.

[0094] The segment delivery system can also set attributes based on a customer's life stage. For example, by analyzing a customer's age and family structure, attributes such as "student," "newlywed," or "raising children" can be assigned to customers in a particular life stage. It can also analyze a customer's occupation and income data to identify their life stage. For example, a customer in the early stages of their career could be assigned the attribute "young employee," and a customer who has reached retirement age could be assigned the attribute "retirement." Attributes can also be set based on a customer's life events. For example, customers who have reached life events such as marriage, childbirth, or moving could be assigned the attributes "newlywed," "new mom / dad," or "new home." Setting attributes based on a customer's life stage enables more personalized delivery.

[0095] The segment delivery system can also use a customer emotion estimation function to analyze a customer's stress level and set attributes based on that stress level. For example, the content of a customer's chats and emails can be analyzed to estimate their stress level. Customers with high stress levels can be assigned the attribute "high stress." The system can also analyze the content of social media posts to estimate their stress level. Customers with many negative posts can be assigned the attribute "moderate stress." The system can also analyze a customer's voice data to estimate their stress level from their tone of voice. For example, a customer who sounds tense can be assigned the attribute "high stress." This allows for more appropriate delivery by setting attributes based on the customer's stress level.

[0096] The segment delivery system can also use a customer emotion estimation function to analyze a customer's happiness level and set attributes based on that happiness level. For example, the content of a customer's chats and emails can be analyzed to estimate their happiness level. Customers with a high level of happiness can be assigned the attribute "high happiness." The system can also analyze the content of social media posts to estimate their happiness level. Customers with many positive posts can be assigned the attribute "medium happiness." The system can also analyze a customer's voice data to estimate their happiness level from their tone of voice. For example, a customer with a cheerful voice can be assigned the attribute "high happiness." This allows for more appropriate delivery by setting attributes based on the customer's happiness level.

[0097] The segment delivery system can also use a customer emotion estimation function to analyze a customer's excitement level and set attributes based on that excitement level. For example, the content of a customer's chats and emails can be analyzed to estimate the excitement level. Customers with a high level of excitement can be assigned the attribute "high excitement level." The system can also analyze the content of social media posts to estimate the excitement level. Customers with many positive posts can be assigned the attribute "medium excitement level." The system can also analyze a customer's voice data to estimate the excitement level from the tone of their voice. For example, a customer who sounds excited can be assigned the attribute "high excitement level." This allows for more appropriate delivery by setting attributes based on the customer's excitement level.

[0098] The segment delivery system can also use a customer emotion estimation function to analyze customer satisfaction and set attributes based on that satisfaction. For example, the content of customer chats and emails can be analyzed to estimate satisfaction. Customers with high satisfaction can be assigned the attribute "high satisfaction." The content of social media posts can also be analyzed to estimate satisfaction. Customers with many positive posts can be assigned the attribute "medium satisfaction." Customer voice data can also be analyzed to estimate satisfaction from the tone of voice. For example, a customer with a calm voice can be assigned the attribute "high satisfaction." This allows for more appropriate delivery by setting attributes based on customer satisfaction.

[0099] The segment delivery system can also use a customer emotion estimation function to analyze the customer's level of dissatisfaction and set attributes based on that level of dissatisfaction. For example, the content of customer chats and emails can be analyzed to estimate the level of dissatisfaction. Customers with a high level of dissatisfaction can be assigned the attribute "highly dissatisfied." The system can also analyze the content of social media posts to estimate the level of dissatisfaction. Customers with many negative posts can be assigned the attribute "medium dissatisfied." The system can also analyze customer voice data to estimate the level of dissatisfaction from the tone of voice. For example, customers who sound angry can be assigned the attribute "highly dissatisfied." This allows for more appropriate delivery by setting attributes based on the customer's level of dissatisfaction.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The customer attribute definition section defines customer attributes and tags, such as age, gender, interests, and purchasing history. Step 2: The interaction analysis unit analyzes interactions, such as conversations with customers and their actions on the site. For example, it collects data such as which pages customers viewed on the site, which products they purchased, and what questions they asked in chat. Step 3: The attribute linking unit automatically links customers to attributes based on the data analyzed by the interaction analysis unit. For example, a customer who frequently views a specific product is assigned the attribute "Interest: Product A." Step 4: The content generator customizes the content based on customer attributes and creates the most appropriate document. For example, for customers interested in a particular product, it creates a message containing information and promotions related to that product. Step 5: The message delivery unit delivers the document generated by the delivery content generation unit to the customer. For example, the message is sent to the customer at the optimal time using means such as email, SMS, or in-app notifications.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0115] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0116] 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.

[0117] 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.

[0118] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] 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.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0130] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0131] 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.

[0132] 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.

[0133] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0134] 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.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0146] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] 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.

[0148] 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.

[0149] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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."

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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]

[0169] 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 customer attribute definition section for defining customer attributes and tags; An interaction analysis section that analyzes interactions such as conversations with customers and action history on the site, and an attribute linking unit that automatically links a customer with an attribute based on the data analyzed by the transaction analysis unit; a distribution content generation unit that customizes distribution content based on the attributes of the customer and creates an optimal document; a message delivery unit that delivers the document generated by the delivery content generation unit to a customer. A system characterized by:

2. The customer attribute definition unit Analyze purchasing data and social media posts to dynamically update the attributes 2. The system of claim 1.

3. The customer attribute definition unit Detecting customer life events and automatically modifying said attributes based on those events 2. The system of claim 1.

4. The customer attribute definition unit Analyzing the emotional state of the customer in real time and dynamically setting the attributes based on the emotional state.

2. The system of claim 1.

5. The interaction analysis unit Analyzing the voice data and video data of the customer and setting the attributes based on the tone of voice and facial expression 2. The system of claim 1.

6. The interaction analysis unit Considering the characteristics of different cultures and regions, set the above attributes from a global perspective 2. The system of claim 1.

Images