system

Abstract

The system according to this embodiment aims to improve customer satisfaction by automatically generating and sending follow-up emails based on customer purchase history and behavioral data. [Solution] The system according to the embodiment comprises a collection unit, a generation unit, a transmission unit, and an analysis unit. The collection unit collects customer purchase history and behavioral data. The generation unit generates the content of follow-up emails based on the data collected by the collection unit. The transmission unit sends the emails generated by the generation unit at an appropriate time. The analysis unit analyzes the effectiveness of the emails sent by the transmission unit and optimizes the content and timing of the next email.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, follow-up after a customer's purchase is not sufficiently carried out, and there is room for improvement in improving customer satisfaction and promoting repeat purchases.

[0005] The system according to the embodiment aims to automatically generate and send follow-up emails based on a customer's purchase history and behavioral data, and improve customer satisfaction.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a generation unit, a transmission unit, and an analysis unit. The collection unit collects customer purchase history and behavioral data. The generation unit generates the content of follow-up emails based on the data collected by the collection unit. The transmission unit sends the emails generated by the generation unit at an appropriate time. The analysis unit analyzes the effectiveness of the emails sent by the transmission unit and optimizes the content and timing of the next email. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate and send follow-up emails based on customer purchase history and behavioral data, thereby improving customer satisfaction. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The automated follow-up email generation and distribution system according to an embodiment of the present invention is a system in which a generating AI automatically generates and distributes personalized follow-up emails at the optimal timing based on the customer's purchase history and behavioral data. The automated follow-up email generation and distribution system can alleviate customers' anxieties and questions after purchase and provide information on how to use the product and after-care. Furthermore, the automated follow-up email generation and distribution system has the effect of improving customer satisfaction and promoting repeat purchases for store operators. For example, when a customer purchases a product, the automated follow-up email generation and distribution system automatically sends a purchase confirmation email. Next, a notification email is sent when the product arrives, and thereafter, usage surveys, reminder emails, and promotional emails are sent at appropriate times. These emails are automatically generated by the generating AI, which estimates the optimal content and timing based on the customer's purchase history and behavioral data. For example, when a customer purchases a specific product, an email containing information on how to use that product and after-care information is sent. In addition, a usage survey is sent after a certain period to collect customer feedback. Furthermore, promotional emails are sent to encourage repeat purchases, providing customers with information on benefits and discounts. This system allows customers to receive post-purchase support and use products with peace of mind. Furthermore, store operators can improve customer satisfaction and encourage repeat purchases. By utilizing AI generation, the content and timing of emails are optimized, enabling effective follow-up. As a result, the automated follow-up email generation and distribution system provides post-purchase support to customers and improves customer satisfaction.

[0029] The automated follow-up email generation and distribution system according to this embodiment comprises a collection unit, a generation unit, a sending unit, and an analysis unit. The collection unit collects customer purchase history and behavioral data. For example, the collection unit can collect data such as information on products purchased by the customer, purchase date and time, purchase frequency, and browsing history. The collection unit can also use AI to analyze customer behavior patterns and collect data. The generation unit generates the content of follow-up emails based on the data collected by the collection unit. The generation unit uses generation AI to analyze customer purchase history and behavioral data and generates emails with optimal content. For example, the generation unit can generate emails that include instructions on how to use the products purchased by the customer and after-care information. The generation unit can also adjust the content of the next email based on customer feedback. The sending unit sends the emails generated by the generation unit at an appropriate time. The sending unit uses AI to analyze customer behavioral data and estimate the optimal sending timing. For example, the sending unit sends a purchase confirmation email immediately after the customer purchases a product and a notification email when the product arrives. Furthermore, the sending unit can also send usage surveys, reminder emails, and promotional emails after a certain period of time. The analysis unit analyzes the effectiveness of emails sent by the sending unit and optimizes the content and timing of the next email. The analysis unit uses AI to analyze data such as email open rates, click-through rates, and conversion rates and evaluate their effectiveness. For example, the analysis unit analyzes whether customers opened the email and clicked on links within the email, and adjusts the content and timing of the next email accordingly. As a result, the automated follow-up email generation and distribution system according to this embodiment can automatically generate and distribute personalized follow-up emails based on customer purchase history and behavioral data, thereby improving customer satisfaction and promoting repeat purchases.

[0030] The data collection unit collects customer purchase history and behavioral data. Specifically, it can collect data such as information on products purchased by customers, purchase dates and times, purchase frequency, and browsing history. For example, this includes detailed information on products purchased from online stores, payment methods used at the time of purchase, and shipping address information. Furthermore, it also collects information on products that customers have viewed on the website and products that were added to their cart but not purchased. The data collection unit centrally manages this data and creates a profile for each customer. It can also use AI to analyze customer behavior patterns and collect data. For example, AI can analyze a customer's past purchase and browsing history to predict the products they are most likely to purchase next. It can also intensify data collection during times when customers tend to visit the website at specific times. This allows the data collection unit to understand customer behavior in detail and efficiently collect data tailored to individual needs. In addition, the data collection unit can integrate data from social media and third-party data providers to gain a more accurate overall picture of customers. This allows the data collection unit to analyze customer purchasing behavior and interests from multiple perspectives and provide more accurate data.

[0031] The generation unit generates follow-up email content based on data collected by the collection unit. Using generation AI, the generation unit analyzes customer purchase history and behavioral data to generate emails with optimal content. Specifically, the generation AI uses natural language processing technology to automatically create emails containing information beneficial to the customer. For example, it can generate emails containing instructions on how to use products purchased by the customer and after-care information. Furthermore, the generation unit can adjust the content of subsequent emails based on past customer feedback and evaluations. For example, if a customer gave a positive evaluation to the information provided in the previous email, it can resend an email with similar content. The generation unit can also generate emails suggesting related or recommended products based on the customer's purchase history. This allows the generation unit to efficiently generate personalized emails tailored to customer needs, improving customer satisfaction. Additionally, the generation unit can automatically optimize email templates and designs, creating visually appealing emails. This allows the generation unit to provide customers with a consistent brand image and maximize the effectiveness of emails.

[0032] The sending unit sends emails generated by the generating unit at the appropriate time. The sending unit uses AI to analyze customer behavior data and estimate the optimal sending time. Specifically, the AI ​​analyzes the customer's past email open history and website visit history to identify the times when customers are most likely to open emails. For example, the sending unit can send a purchase confirmation email immediately after a customer makes a purchase and a notification email when the product arrives. The sending unit can also send usage surveys, reminder emails, and promotional emails after a certain period of time. This allows the sending unit to send emails to customers at the right time, improving email open rates and click-through rates. Furthermore, the sending unit can customize the frequency and content of emails for each customer. For example, it can send promotional emails regularly to customers who make frequent purchases and reminder emails to customers who make infrequent purchases. The sending unit can also monitor email sending status in real time and automatically detect and address sending errors and bounced emails. This streamlines the email sending process and ensures that information is reliably delivered to customers.

[0033] The analytics department analyzes the effectiveness of emails sent by the sending department and optimizes the content and timing of future emails. Using AI, the analytics department analyzes data such as email open rates, click-through rates, and conversion rates to evaluate effectiveness. Specifically, the AI ​​analyzes details such as email open time, link clicks, and purchase rates to identify which elements were effective. For example, the analytics department analyzes whether customers opened the email and clicked on links within the email to adjust the content and timing of future emails. Furthermore, the analytics department can conduct different analyses for each customer segment and develop optimal email strategies for specific segments. For example, they can send visually-oriented emails to younger customers and detailed emails to senior customers, taking a target-based approach. The analytics department can also conduct A / B testing to compare the effectiveness of different email content and timing. This allows the analytics department to identify the most effective email strategy and incorporate it into future email campaigns. Additionally, the analytics department can analyze long-term trends and patterns to improve future email strategies. This allows the analytics department to continuously improve the effectiveness of email marketing and increase customer satisfaction and repeat purchase rates.

[0034] The data collection unit can analyze a customer's past purchase history and select the optimal data collection method. For example, the data collection unit can analyze the product categories that a customer has frequently purchased in the past and select a data collection method specific to those categories. The data collection unit can also prioritize the collection of data related to specific seasons or events from the customer's past purchase history. Furthermore, based on the customer's past purchase history, the data collection unit can focus on collecting data for specific brands or products. This enables effective data collection by selecting the optimal data collection method based on past purchase history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the customer's past purchase history data into a generating AI and have the generating AI select the optimal data collection method.

[0035] The data collection unit can filter purchase history and behavioral data based on the customer's current lifestyle and areas of interest. For example, if a customer has specific needs in their current lifestyle, the data collection unit will prioritize collecting data related to those needs. The data collection unit can also filter and collect data on relevant products based on the customer's areas of interest. Furthermore, the data collection unit can exclude unnecessary data and collect only the necessary data, depending on the customer's lifestyle and areas of interest. This enables data collection tailored to the customer's lifestyle and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input customer lifestyle data into a generating AI and have the generating AI perform the filtering.

[0036] The data collection unit can prioritize the collection of highly relevant data by considering the customer's geographical location when collecting purchase history and behavioral data. For example, if a customer lives in a specific region, the data collection unit will prioritize the collection of data related to products in that region. The data collection unit can also collect region-specific promotional data based on the customer's geographical location. Furthermore, the data collection unit can collect data on regional trends and popular products by considering the customer's geographical location. This enables data collection based on the customer's geographical location. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the customer's geographical location data into a generating AI and have the generating AI perform the collection of highly relevant data.

[0037] The data collection unit can analyze customers' social media activity and collect relevant data when collecting purchase history and behavioral data. For example, if a customer mentions a specific product on social media, the data collection unit will collect data related to that product. The data collection unit can also prioritize the collection of data on products of interest based on the customer's social media activity. Furthermore, the data collection unit can analyze customers' social media activity and collect data on trends and popular products. This enables data collection based on the customer's social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input customer social media data into a generating AI and have the generating AI perform the collection of relevant data.

[0038] The generation unit can adjust the level of detail in follow-up emails based on the importance of the product. For example, for expensive products, the generation unit's AI can generate emails containing detailed usage instructions and after-sales care information. For everyday products, the generation unit's AI can also generate emails containing concise usage instructions. Furthermore, for products related to specific events or seasons, the generation unit's AI can generate emails containing detailed information tailored to that time of year. This allows for the generation of detailed follow-up emails according to the importance of the product, thereby improving customer satisfaction. Some or all of the above processing in the generation unit may be performed using the generation AI, or it may be performed without the generation AI. For example, the generation unit can input product importance data into the generation AI and have the generation AI adjust the level of detail in the emails.

[0039] The generation unit can apply different generation algorithms depending on the product category when generating follow-up emails. For example, in the case of electronic devices, the generation unit's AI can apply a generation algorithm that includes technical details. Similarly, in the case of fashion items, the generation unit's AI can apply a generation algorithm that includes styling suggestions. Furthermore, in the case of food products, the generation unit's AI can apply a generation algorithm that includes recipes and storage instructions. This allows for the generation of appropriate follow-up emails tailored to the product category, thereby improving customer satisfaction. Some or all of the above-described processes in the generation unit may be performed using the generation AI, or they may be performed without the generation AI. For example, the generation unit can input product category data into the generation AI and have the generation AI execute the application of the generation algorithm.

[0040] The generation unit can determine the priority of follow-up emails based on the purchase date of the product. For example, if a product has been recently purchased, the generation unit's AI can immediately generate a follow-up email. The generation unit can also generate a reminder email if a certain period of time has passed since the purchase of the product. Furthermore, for seasonal or event-related products, the generation unit's AI can generate follow-up emails tailored to the time of year. This enables effective communication by generating follow-up emails according to the purchase date of the product. Some or all of the above processing in the generation unit may be performed using the generation AI, or it may be performed without using the generation AI. For example, the generation unit can input product purchase date data into the generation AI and have the generation AI determine the priority of emails.

[0041] The generation unit can adjust the order of follow-up emails based on the relevance of the products. For example, if a customer purchases multiple products, the generation unit's AI will generate follow-up emails in order of relevance, starting with the most relevant products. Furthermore, if a customer purchases products from a specific category, the generation unit's AI can prioritize generating emails containing information related to that category. Additionally, the generation unit's AI can generate emails containing information on how to use the purchased products and after-care information, in order of relevance. This enables effective communication by generating follow-up emails tailored to the relevance of the products. Some or all of the above processing in the generation unit may be performed using the generation AI, or without it. For example, the generation unit can input product relevance data into the generation AI and have the generation AI adjust the order of the emails.

[0042] The sending unit can analyze a customer's past email open history to select the optimal sending method when sending an email. For example, the sending unit can analyze the time periods when a customer has opened emails in the past and send emails at those times. It can also analyze the content of emails a customer has opened in the past and send emails containing similar content. Furthermore, the sending unit can select the optimal sending method (text, HTML, etc.) based on the customer's past email open history. This enables effective follow-up by selecting the optimal sending method based on the customer's past email open history. Some or all of the above processing in the sending unit may be performed using AI or not. For example, the sending unit can input customer email open history data into a generating AI and have the generating AI select the optimal sending method.

[0043] The sending unit can customize the timing of email transmissions based on the customer's current lifestyle. For example, it can send emails during times when the customer is relaxed, avoiding busy periods. It can also select the optimal sending time to match the customer's daily rhythm. Furthermore, it can send emails containing important information at the appropriate time, taking into account the customer's current lifestyle. This allows for effective follow-up by customizing the sending timing according to the customer's lifestyle. Some or all of the above processes in the sending unit may be performed using AI or not. For example, the sending unit can input customer lifestyle data into a generating AI and have the generating AI perform the customization of the sending timing.

[0044] The sending unit can select the optimal sending timing when sending emails, taking into account the customer's geographical location. For example, if a customer lives in a specific region, the sending unit will send the email according to the time zone of that region. The sending unit can also send region-specific promotional emails based on the customer's geographical location. Furthermore, the sending unit can select the optimal sending timing, taking into account the customer's geographical location. This enables effective follow-up by selecting the optimal sending timing based on the customer's geographical location. Some or all of the above processing in the sending unit may be performed using AI or not. For example, the sending unit can input the customer's geographical location data into a generating AI and have the generating AI perform the selection of the sending timing.

[0045] The sending unit can analyze the customer's social media activity and adjust the sending timing when sending emails. For example, if the sending unit sees a customer mentioning a specific product on social media, it will send an email at that time. The sending unit can also send emails about products of interest based on the customer's social media activity. Furthermore, the sending unit can analyze the customer's social media activity and select the optimal sending timing. This allows for effective follow-up by adjusting the sending timing based on the customer's social media activity. Some or all of the above processing in the sending unit may be performed using AI or not. For example, the sending unit can input customer social media data into a generating AI and have the generating AI perform the adjustment of the sending timing.

[0046] The analysis department can optimize its analysis algorithm by referring to past analysis data when analyzing the effectiveness of emails. For example, the analysis department can select the optimal analysis algorithm based on past email effectiveness data. The analysis department can also refer to past analysis data to identify specific patterns and optimize the analysis algorithm. Furthermore, the analysis department can utilize past email effectiveness data to construct an analysis algorithm for effective follow-up emails. This enables effective email analysis by selecting the optimal analysis algorithm based on past analysis data. Some or all of the above processes in the analysis department may be performed using AI or not. For example, the analysis department can input past analysis data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0047] The analysis department can customize its analysis methods based on customer attribute information when analyzing the effectiveness of emails. For example, the analysis department can customize effective email analysis methods based on the customer's age and gender. It can also analyze the effectiveness of emails for specific product categories based on the customer's purchase history. Furthermore, the analysis department can apply analysis methods tailored to individual attribute information based on customer behavior data. This allows for effective email analysis by customizing analysis methods according to customer attribute information. Some or all of the above processes in the analysis department may be performed using AI or not. For example, the analysis department can input customer attribute information data into a generating AI and have the generating AI perform the customization of the analysis methods.

[0048] The analysis department can weight the analysis data based on customer purchase history when analyzing the effectiveness of emails. For example, if a customer purchases an expensive product, the analysis department will give more weight to the email effectiveness of that product. The analysis department can also weight the email effectiveness for product categories that customers frequently purchase. Furthermore, the analysis department can focus its analysis on the email effectiveness of specific products based on customer purchase history. This enables effective email analysis by weighting the analysis data based on customer purchase history. Some or all of the above processes in the analysis department may be performed using AI or not. For example, the analysis department can input customer purchase history data into a generating AI and have the generating AI perform the weighting of the analysis data.

[0049] The analytics department can improve the accuracy of its email effectiveness analysis by referencing customers' social media activity. For example, if a customer mentions a specific product on social media, the analytics department can utilize that information in its analysis. Furthermore, the analytics department can improve the accuracy of email effectiveness analysis based on customers' social media activity. In addition, the analytics department can analyze email effectiveness related to trends and popular products by referencing customers' social media activity. This improves the accuracy of analysis based on customers' social media activity, enabling more effective email analysis. Some or all of the above processes in the analytics department may be performed using AI or not. For example, the analytics department can input customer social media data into a generating AI and have the generating AI perform the analysis to improve accuracy.

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

[0051] The automated follow-up email generation and distribution system can further predict customer life events based on their purchase history and behavioral data, and provide relevant information at the appropriate time. For example, if a customer purchases a new home, the system can generate emails providing information on products and services related to moving. Similarly, if a customer is planning to get married, it can generate emails providing information on wedding-related products and services. Furthermore, if a customer is planning to have children, it can generate emails providing information on childcare-related products and services. This enables personalized follow-up tailored to each customer's life event, thereby improving customer satisfaction.

[0052] The automated follow-up email generation and distribution system can estimate a customer's health status based on their purchase history and behavioral data, and provide health-related information at the appropriate time. For example, if a customer frequently purchases health foods, the system can generate emails providing health advice and information on new health foods. Similarly, if a customer purchases fitness-related products, the system can generate emails providing fitness training methods and information on new fitness products. Furthermore, if a customer purchases pharmaceuticals, the system can generate emails providing health management information and information on new medications. This enables personalized follow-up tailored to each customer's health status, thereby improving customer satisfaction.

[0053] The automated follow-up email generation and distribution system can estimate customer hobbies and preferences based on their purchase history and behavioral data, and provide relevant information at the appropriate time. For example, if a customer frequently purchases outdoor equipment, the system can generate emails offering advice on outdoor activities and information on new outdoor products. Similarly, if a customer purchases cooking-related products, it can generate emails offering recipes and information on new cooking products. Furthermore, if a customer purchases music-related products, it can generate emails offering information on music-related events and new music products. This enables personalized follow-up tailored to customer hobbies and preferences, thereby improving customer satisfaction.

[0054] The automated follow-up email generation and distribution system can estimate customers' environmental awareness based on their purchase history and behavioral data, and provide information on environmentally friendly products and services at the appropriate time. For example, if a customer frequently purchases eco-friendly products, the system can generate emails providing information on environmentally friendly products and eco-activities. Similarly, if a customer purchases recycling-related products, the system can generate emails providing recycling advice and information on new recycling products. Furthermore, if a customer purchases energy-saving products, the system can generate emails providing energy-saving information and information on new energy-saving products. This enables personalized follow-up tailored to each customer's environmental awareness, thereby improving customer satisfaction.

[0055] The automated follow-up email generation and distribution system can estimate a customer's travel plans based on their purchase history and behavioral data, and provide travel-related information at the appropriate time. For example, if a customer frequently purchases travel goods, the system can generate emails offering travel advice and information on new travel products. If a customer is interested in a particular region, the system can generate emails providing tourist information and event information related to that region. Furthermore, if a customer has purchased travel insurance, the system can generate emails offering information on travel safety and new travel insurance options. This enables personalized follow-up tailored to the customer's travel plans, thereby improving customer satisfaction.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The data collection unit collects customer purchase history and behavioral data. For example, it can collect data such as information on products purchased by customers, purchase date and time, purchase frequency, and browsing history. The data collection unit can also use AI to analyze customer behavior patterns and collect data. Step 2: The generation unit generates the content of the follow-up email based on the data collected by the collection unit. The generation unit uses generation AI to analyze the customer's purchase history and behavioral data and generate the most suitable email content. For example, it can generate an email that includes instructions on how to use the product the customer purchased and after-care information. The generation unit can also adjust the content of the next email based on customer feedback. Step 3: The sending unit sends the emails generated by the generating unit at the appropriate time. The sending unit uses AI to analyze customer behavior data and estimate the optimal sending timing. For example, it can send a purchase confirmation email immediately after a customer makes a purchase and a notification email when the product arrives. It can also send usage surveys, reminder emails, and promotional emails after a certain period of time. Step 4: The analysis department analyzes the effectiveness of emails sent by the sending department and optimizes the content and timing of future emails. The analysis department uses AI to analyze data such as email open rates, click-through rates, and conversion rates to evaluate effectiveness. For example, it analyzes whether customers opened the email and clicked on links within the email, and adjusts the content and timing of future emails accordingly.

[0058] (Example of form 2) The automated follow-up email generation and distribution system according to an embodiment of the present invention is a system in which a generating AI automatically generates and distributes personalized follow-up emails at the optimal timing based on the customer's purchase history and behavioral data. The automated follow-up email generation and distribution system can alleviate customers' anxieties and questions after purchase and provide information on how to use the product and after-care. Furthermore, the automated follow-up email generation and distribution system has the effect of improving customer satisfaction and promoting repeat purchases for store operators. For example, when a customer purchases a product, the automated follow-up email generation and distribution system automatically sends a purchase confirmation email. Next, a notification email is sent when the product arrives, and thereafter, usage surveys, reminder emails, and promotional emails are sent at appropriate times. These emails are automatically generated by the generating AI, which estimates the optimal content and timing based on the customer's purchase history and behavioral data. For example, when a customer purchases a specific product, an email containing information on how to use that product and after-care information is sent. In addition, a usage survey is sent after a certain period to collect customer feedback. Furthermore, promotional emails are sent to encourage repeat purchases, providing customers with information on benefits and discounts. This system allows customers to receive post-purchase support and use products with peace of mind. Furthermore, store operators can improve customer satisfaction and encourage repeat purchases. By utilizing AI generation, the content and timing of emails are optimized, enabling effective follow-up. As a result, the automated follow-up email generation and distribution system provides post-purchase support to customers and improves customer satisfaction.

[0059] The automated follow-up email generation and distribution system according to this embodiment comprises a collection unit, a generation unit, a sending unit, and an analysis unit. The collection unit collects customer purchase history and behavioral data. For example, the collection unit can collect data such as information on products purchased by the customer, purchase date and time, purchase frequency, and browsing history. The collection unit can also use AI to analyze customer behavior patterns and collect data. The generation unit generates the content of follow-up emails based on the data collected by the collection unit. The generation unit uses generation AI to analyze customer purchase history and behavioral data and generates emails with optimal content. For example, the generation unit can generate emails that include instructions on how to use the products purchased by the customer and after-care information. The generation unit can also adjust the content of the next email based on customer feedback. The sending unit sends the emails generated by the generation unit at an appropriate time. The sending unit uses AI to analyze customer behavioral data and estimate the optimal sending timing. For example, the sending unit sends a purchase confirmation email immediately after the customer purchases a product and a notification email when the product arrives. Furthermore, the sending unit can also send usage surveys, reminder emails, and promotional emails after a certain period of time. The analysis unit analyzes the effectiveness of emails sent by the sending unit and optimizes the content and timing of the next email. The analysis unit uses AI to analyze data such as email open rates, click-through rates, and conversion rates and evaluate their effectiveness. For example, the analysis unit analyzes whether customers opened the email and clicked on links within the email, and adjusts the content and timing of the next email accordingly. As a result, the automated follow-up email generation and distribution system according to this embodiment can automatically generate and distribute personalized follow-up emails based on customer purchase history and behavioral data, thereby improving customer satisfaction and promoting repeat purchases.

[0060] The data collection unit collects customer purchase history and behavioral data. Specifically, it can collect data such as information on products purchased by customers, purchase dates and times, purchase frequency, and browsing history. For example, this includes detailed information on products purchased from online stores, payment methods used at the time of purchase, and shipping address information. Furthermore, it also collects information on products that customers have viewed on the website and products that were added to their cart but not purchased. The data collection unit centrally manages this data and creates a profile for each customer. It can also use AI to analyze customer behavior patterns and collect data. For example, AI can analyze a customer's past purchase and browsing history to predict the products they are most likely to purchase next. It can also intensify data collection during times when customers tend to visit the website at specific times. This allows the data collection unit to understand customer behavior in detail and efficiently collect data tailored to individual needs. In addition, the data collection unit can integrate data from social media and third-party data providers to gain a more accurate overall picture of customers. This allows the data collection unit to analyze customer purchasing behavior and interests from multiple perspectives and provide more accurate data.

[0061] The generation unit generates follow-up email content based on data collected by the collection unit. Using generation AI, the generation unit analyzes customer purchase history and behavioral data to generate emails with optimal content. Specifically, the generation AI uses natural language processing technology to automatically create emails containing information beneficial to the customer. For example, it can generate emails containing instructions on how to use products purchased by the customer and after-care information. Furthermore, the generation unit can adjust the content of subsequent emails based on past customer feedback and evaluations. For example, if a customer gave a positive evaluation to the information provided in the previous email, it can resend an email with similar content. The generation unit can also generate emails suggesting related or recommended products based on the customer's purchase history. This allows the generation unit to efficiently generate personalized emails tailored to customer needs, improving customer satisfaction. Additionally, the generation unit can automatically optimize email templates and designs, creating visually appealing emails. This allows the generation unit to provide customers with a consistent brand image and maximize the effectiveness of emails.

[0062] The sending unit sends emails generated by the generating unit at the appropriate time. The sending unit uses AI to analyze customer behavior data and estimate the optimal sending time. Specifically, the AI ​​analyzes the customer's past email open history and website visit history to identify the times when customers are most likely to open emails. For example, the sending unit can send a purchase confirmation email immediately after a customer makes a purchase and a notification email when the product arrives. The sending unit can also send usage surveys, reminder emails, and promotional emails after a certain period of time. This allows the sending unit to send emails to customers at the right time, improving email open rates and click-through rates. Furthermore, the sending unit can customize the frequency and content of emails for each customer. For example, it can send promotional emails regularly to customers who make frequent purchases and reminder emails to customers who make infrequent purchases. The sending unit can also monitor email sending status in real time and automatically detect and address sending errors and bounced emails. This streamlines the email sending process and ensures that information is reliably delivered to customers.

[0063] The analytics department analyzes the effectiveness of emails sent by the sending department and optimizes the content and timing of future emails. Using AI, the analytics department analyzes data such as email open rates, click-through rates, and conversion rates to evaluate effectiveness. Specifically, the AI ​​analyzes details such as email open time, link clicks, and purchase rates to identify which elements were effective. For example, the analytics department analyzes whether customers opened the email and clicked on links within the email to adjust the content and timing of future emails. Furthermore, the analytics department can conduct different analyses for each customer segment and develop optimal email strategies for specific segments. For example, they can send visually-oriented emails to younger customers and detailed emails to senior customers, taking a target-based approach. The analytics department can also conduct A / B testing to compare the effectiveness of different email content and timing. This allows the analytics department to identify the most effective email strategy and incorporate it into future email campaigns. Additionally, the analytics department can analyze long-term trends and patterns to improve future email strategies. This allows the analytics department to continuously improve the effectiveness of email marketing and increase customer satisfaction and repeat purchase rates.

[0064] The data collection unit can estimate customer emotions and adjust the timing of collecting purchase history and behavioral data based on the estimated emotions. For example, if a customer feels anxious after a purchase, the data collection unit can immediately collect purchase history and behavioral data to provide prompt follow-up. Furthermore, if the customer is satisfied, the data collection unit can collect purchase history and behavioral data after a certain period to use for future promotions. Additionally, if a customer has questions, the data collection unit can collect purchase history and behavioral data in real time and respond immediately. This allows for more appropriate follow-up by adjusting the data collection timing according to customer emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the data collection unit may be performed using AI or not. For example, the data collection unit can input customer facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0065] The data collection unit can analyze a customer's past purchase history and select the optimal data collection method. For example, the data collection unit can analyze the product categories that a customer has frequently purchased in the past and select a data collection method specific to those categories. The data collection unit can also prioritize the collection of data related to specific seasons or events from the customer's past purchase history. Furthermore, based on the customer's past purchase history, the data collection unit can focus on collecting data for specific brands or products. This enables effective data collection by selecting the optimal data collection method based on past purchase history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the customer's past purchase history data into a generating AI and have the generating AI select the optimal data collection method.

[0066] The data collection unit can filter purchase history and behavioral data based on the customer's current lifestyle and areas of interest. For example, if a customer has specific needs in their current lifestyle, the data collection unit will prioritize collecting data related to those needs. The data collection unit can also filter and collect data on relevant products based on the customer's areas of interest. Furthermore, the data collection unit can exclude unnecessary data and collect only the necessary data, depending on the customer's lifestyle and areas of interest. This enables data collection tailored to the customer's lifestyle and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input customer lifestyle data into a generating AI and have the generating AI perform the filtering.

[0067] The data collection unit can estimate customer emotions and prioritize the data to be collected based on the estimated emotions. For example, if a customer is feeling anxious, the data collection unit can prioritize collecting data to immediately alleviate that anxiety. If a customer is satisfied, the data collection unit can also prioritize collecting data to encourage future purchases. Furthermore, if a customer has questions, the data collection unit can prioritize collecting data to address those questions. This enables effective data collection by prioritizing data according to customer emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input customer voice data into a generative AI and have the generative AI perform emotion estimation.

[0068] The data collection unit can prioritize the collection of highly relevant data by considering the customer's geographical location when collecting purchase history and behavioral data. For example, if a customer lives in a specific region, the data collection unit will prioritize the collection of data related to products in that region. The data collection unit can also collect region-specific promotional data based on the customer's geographical location. Furthermore, the data collection unit can collect data on regional trends and popular products by considering the customer's geographical location. This enables data collection based on the customer's geographical location. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the customer's geographical location data into a generating AI and have the generating AI perform the collection of highly relevant data.

[0069] The data collection unit can analyze customers' social media activity and collect relevant data when collecting purchase history and behavioral data. For example, if a customer mentions a specific product on social media, the data collection unit will collect data related to that product. The data collection unit can also prioritize the collection of data on products of interest based on the customer's social media activity. Furthermore, the data collection unit can analyze customers' social media activity and collect data on trends and popular products. This enables data collection based on the customer's social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input customer social media data into a generating AI and have the generating AI perform the collection of relevant data.

[0070] The generation unit can estimate the customer's emotions and adjust the wording of the follow-up email based on the estimated emotions. For example, if the customer is feeling anxious, the generation AI can select a way of expressing reassurance. Similarly, if the customer is satisfied, the generation AI can select a way of expressing gratitude. Furthermore, if the customer has questions, the generation AI can select a way of expressing clear and specific answers. This enables effective communication by generating follow-up emails with wording that matches the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input customer text data into the generation AI and have the generation AI adjust the wording.

[0071] The generation unit can adjust the level of detail in follow-up emails based on the importance of the product. For example, for expensive products, the generation unit's AI can generate emails containing detailed usage instructions and after-sales care information. For everyday products, the generation unit's AI can also generate emails containing concise usage instructions. Furthermore, for products related to specific events or seasons, the generation unit's AI can generate emails containing detailed information tailored to that time of year. This allows for the generation of detailed follow-up emails according to the importance of the product, thereby improving customer satisfaction. Some or all of the above processing in the generation unit may be performed using the generation AI, or it may be performed without the generation AI. For example, the generation unit can input product importance data into the generation AI and have the generation AI adjust the level of detail in the emails.

[0072] The generation unit can apply different generation algorithms depending on the product category when generating follow-up emails. For example, in the case of electronic devices, the generation unit's AI can apply a generation algorithm that includes technical details. Similarly, in the case of fashion items, the generation unit's AI can apply a generation algorithm that includes styling suggestions. Furthermore, in the case of food products, the generation unit's AI can apply a generation algorithm that includes recipes and storage instructions. This allows for the generation of appropriate follow-up emails tailored to the product category, thereby improving customer satisfaction. Some or all of the above-described processes in the generation unit may be performed using the generation AI, or they may be performed without the generation AI. For example, the generation unit can input product category data into the generation AI and have the generation AI execute the application of the generation algorithm.

[0073] The generation unit can estimate the customer's emotions and adjust the length of follow-up emails based on the estimated emotions. For example, if the customer is in a hurry, the generation unit's AI can generate a short, concise email. If the customer is relaxed, the generation unit's AI can generate a longer email with detailed explanations. Furthermore, if the customer is excited, the generation unit's AI can generate an email with visually stimulating effects. This allows for effective communication by adjusting the length of follow-up emails according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using or without a generation AI. For example, the generation unit can input customer emotion data into a generation AI and have the generation AI adjust the length of the email.

[0074] The generation unit can determine the priority of follow-up emails based on the purchase date of the product. For example, if a product has been recently purchased, the generation unit's AI can immediately generate a follow-up email. The generation unit can also generate a reminder email if a certain period of time has passed since the purchase of the product. Furthermore, for seasonal or event-related products, the generation unit's AI can generate follow-up emails tailored to the time of year. This enables effective communication by generating follow-up emails according to the purchase date of the product. Some or all of the above processing in the generation unit may be performed using the generation AI, or it may be performed without using the generation AI. For example, the generation unit can input product purchase date data into the generation AI and have the generation AI determine the priority of emails.

[0075] The generation unit can adjust the order of follow-up emails based on the relevance of the products. For example, if a customer purchases multiple products, the generation unit's AI will generate follow-up emails in order of relevance, starting with the most relevant products. Furthermore, if a customer purchases products from a specific category, the generation unit's AI can prioritize generating emails containing information related to that category. Additionally, the generation unit's AI can generate emails containing information on how to use the purchased products and after-care information, in order of relevance. This enables effective communication by generating follow-up emails tailored to the relevance of the products. Some or all of the above processing in the generation unit may be performed using the generation AI, or without it. For example, the generation unit can input product relevance data into the generation AI and have the generation AI adjust the order of the emails.

[0076] The sending unit can estimate the customer's emotions and adjust the timing of email delivery based on the estimated emotions. For example, if the customer is feeling anxious, the sending unit can immediately send a follow-up email. It can also send a promotional email after a certain period if the customer is satisfied. Furthermore, if the customer has questions, the sending unit can quickly send an email containing answers. This allows for effective follow-up by adjusting the timing of email delivery according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sending unit may be performed using AI or not. For example, the sending unit can input customer emotion data into a generative AI and have the generative AI adjust the timing of delivery.

[0077] The sending unit can analyze a customer's past email open history to select the optimal sending method when sending an email. For example, the sending unit can analyze the time periods when a customer has opened emails in the past and send emails at those times. It can also analyze the content of emails a customer has opened in the past and send emails containing similar content. Furthermore, the sending unit can select the optimal sending method (text, HTML, etc.) based on the customer's past email open history. This enables effective follow-up by selecting the optimal sending method based on the customer's past email open history. Some or all of the above processing in the sending unit may be performed using AI or not. For example, the sending unit can input customer email open history data into a generating AI and have the generating AI select the optimal sending method.

[0078] The sending unit can customize the timing of email transmissions based on the customer's current lifestyle. For example, it can send emails during times when the customer is relaxed, avoiding busy periods. It can also select the optimal sending time to match the customer's daily rhythm. Furthermore, it can send emails containing important information at the appropriate time, taking into account the customer's current lifestyle. This allows for effective follow-up by customizing the sending timing according to the customer's lifestyle. Some or all of the above processes in the sending unit may be performed using AI or not. For example, the sending unit can input customer lifestyle data into a generating AI and have the generating AI perform the customization of the sending timing.

[0079] The sending unit can estimate customer emotions and prioritize emails based on those emotions. For example, if a customer is feeling anxious, the sending unit can immediately prioritize sending follow-up emails. It can also prioritize sending promotional emails if the customer is satisfied. Furthermore, if a customer has questions, the sending unit can quickly prioritize sending emails containing answers. This enables effective follow-up by prioritizing emails according to customer emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the sending unit may be performed using AI or not. For example, the sending unit can input customer emotion data into a generative AI and have the generative AI determine email prioritization.

[0080] The sending unit can select the optimal sending timing when sending emails, taking into account the customer's geographical location. For example, if a customer lives in a specific region, the sending unit will send the email according to the time zone of that region. The sending unit can also send region-specific promotional emails based on the customer's geographical location. Furthermore, the sending unit can select the optimal sending timing, taking into account the customer's geographical location. This enables effective follow-up by selecting the optimal sending timing based on the customer's geographical location. Some or all of the above processing in the sending unit may be performed using AI or not. For example, the sending unit can input the customer's geographical location data into a generating AI and have the generating AI perform the selection of the sending timing.

[0081] The sending unit can analyze the customer's social media activity and adjust the sending timing when sending emails. For example, if the sending unit sees a customer mentioning a specific product on social media, it will send an email at that time. The sending unit can also send emails about products of interest based on the customer's social media activity. Furthermore, the sending unit can analyze the customer's social media activity and select the optimal sending timing. This allows for effective follow-up by adjusting the sending timing based on the customer's social media activity. Some or all of the above processing in the sending unit may be performed using AI or not. For example, the sending unit can input customer social media data into a generating AI and have the generating AI perform the adjustment of the sending timing.

[0082] The analysis department can estimate customer emotions and adjust the email effectiveness analysis method based on the estimated customer emotions. For example, if a customer is feeling anxious, the analysis department will focus on analyzing the effectiveness of emails that provide reassurance. If a customer is satisfied, the analysis department can also analyze the effectiveness of emails that express gratitude. Furthermore, if a customer has questions, the analysis department can analyze the effectiveness of emails that provide clear answers. This allows for effective email analysis by adjusting the effectiveness analysis method according to customer emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis department may be performed using AI or not. For example, the analysis department can input customer emotion data into a generative AI and have the generative AI adjust the effectiveness analysis method.

[0083] The analysis department can optimize its analysis algorithm by referring to past analysis data when analyzing the effectiveness of emails. For example, the analysis department can select the optimal analysis algorithm based on past email effectiveness data. The analysis department can also refer to past analysis data to identify specific patterns and optimize the analysis algorithm. Furthermore, the analysis department can utilize past email effectiveness data to construct an analysis algorithm for effective follow-up emails. This enables effective email analysis by selecting the optimal analysis algorithm based on past analysis data. Some or all of the above processes in the analysis department may be performed using AI or not. For example, the analysis department can input past analysis data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0084] The analysis department can customize its analysis methods based on customer attribute information when analyzing the effectiveness of emails. For example, the analysis department can customize effective email analysis methods based on the customer's age and gender. It can also analyze the effectiveness of emails for specific product categories based on the customer's purchase history. Furthermore, the analysis department can apply analysis methods tailored to individual attribute information based on customer behavior data. This allows for effective email analysis by customizing analysis methods according to customer attribute information. Some or all of the above processes in the analysis department may be performed using AI or not. For example, the analysis department can input customer attribute information data into a generating AI and have the generating AI perform the customization of the analysis methods.

[0085] The analysis department can estimate customer emotions and optimize the content and timing of future emails based on those estimated emotions. For example, if a customer is feeling anxious, the analysis department can send a reassuring email next time. If a customer is satisfied, the analysis department can also send an email expressing gratitude next time. Furthermore, if a customer has questions, the analysis department can send an email containing clear answers next time. This enables effective follow-up by optimizing the content and timing of future emails according to customer emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis department may be performed using AI or not. For example, the analysis department can input customer emotion data into a generative AI and have the generative AI optimize the content and timing of future emails.

[0086] The analysis department can weight the analysis data based on customer purchase history when analyzing the effectiveness of emails. For example, if a customer purchases an expensive product, the analysis department will give more weight to the email effectiveness of that product. The analysis department can also weight the email effectiveness for product categories that customers frequently purchase. Furthermore, the analysis department can focus its analysis on the email effectiveness of specific products based on customer purchase history. This enables effective email analysis by weighting the analysis data based on customer purchase history. Some or all of the above processes in the analysis department may be performed using AI or not. For example, the analysis department can input customer purchase history data into a generating AI and have the generating AI perform the weighting of the analysis data.

[0087] The analytics department can improve the accuracy of its email effectiveness analysis by referencing customers' social media activity. For example, if a customer mentions a specific product on social media, the analytics department can utilize that information in its analysis. Furthermore, the analytics department can improve the accuracy of email effectiveness analysis based on customers' social media activity. In addition, the analytics department can analyze email effectiveness related to trends and popular products by referencing customers' social media activity. This improves the accuracy of analysis based on customers' social media activity, enabling more effective email analysis. Some or all of the above processes in the analytics department may be performed using AI or not. For example, the analytics department can input customer social media data into a generating AI and have the generating AI perform the analysis to improve accuracy.

[0088] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0089] The automated follow-up email generation and distribution system can further predict customer life events based on their purchase history and behavioral data, and provide relevant information at the appropriate time. For example, if a customer purchases a new home, the system can generate emails providing information on products and services related to moving. Similarly, if a customer is planning to get married, it can generate emails providing information on wedding-related products and services. Furthermore, if a customer is planning to have children, it can generate emails providing information on childcare-related products and services. This enables personalized follow-up tailored to each customer's life event, thereby improving customer satisfaction.

[0090] An automated follow-up email generation and distribution system can estimate customer emotions and, based on those emotions, provide information on new products and services that are likely to interest the customer. For example, if a customer is excited, it can generate emails providing information on new product announcements or limited-time sales. If a customer is relaxed, it can generate emails providing information on relaxing products and services. Furthermore, if a customer is feeling anxious, it can generate emails providing support information to alleviate their anxiety or information on products and services that provide reassurance. This makes it possible to provide information on new products and services that are tailored to the customer's emotions, thereby improving customer satisfaction.

[0091] The automated follow-up email generation and distribution system can estimate a customer's health status based on their purchase history and behavioral data, and provide health-related information at the appropriate time. For example, if a customer frequently purchases health foods, the system can generate emails providing health advice and information on new health foods. Similarly, if a customer purchases fitness-related products, the system can generate emails providing fitness training methods and information on new fitness products. Furthermore, if a customer purchases pharmaceuticals, the system can generate emails providing health management information and information on new medications. This enables personalized follow-up tailored to each customer's health status, thereby improving customer satisfaction.

[0092] An automated follow-up email generation and distribution system can estimate customer emotions and, based on those emotions, provide information about events and campaigns that are likely to interest the customer. For example, if a customer is excited, it can generate an email with information about a special event or campaign. If a customer is relaxed, it can generate an email with information about relaxing events or campaigns. Furthermore, if a customer is feeling anxious, it can generate an email with support information to alleviate that anxiety or information about events or campaigns that provide reassurance. This makes it possible to provide event and campaign information tailored to the customer's emotions, thereby improving customer satisfaction.

[0093] The automated follow-up email generation and distribution system can estimate customer hobbies and preferences based on their purchase history and behavioral data, and provide relevant information at the appropriate time. For example, if a customer frequently purchases outdoor equipment, the system can generate emails offering advice on outdoor activities and information on new outdoor products. Similarly, if a customer purchases cooking-related products, it can generate emails offering recipes and information on new cooking products. Furthermore, if a customer purchases music-related products, it can generate emails offering information on music-related events and new music products. This enables personalized follow-up tailored to customer hobbies and preferences, thereby improving customer satisfaction.

[0094] An automated follow-up email generation and distribution system can estimate customer emotions and, based on those emotions, provide content that is likely to interest the customer. For example, if a customer is excited, it can generate emails with content related to entertainment or activities. If a customer is relaxed, it can generate emails with relaxing content or information on relaxation. Furthermore, if a customer is feeling anxious, it can generate emails with support information to alleviate anxiety or content that provides reassurance. This enables the delivery of content tailored to the customer's emotions, thereby improving customer satisfaction.

[0095] The automated follow-up email generation and distribution system can estimate customers' environmental awareness based on their purchase history and behavioral data, and provide information on environmentally friendly products and services at the appropriate time. For example, if a customer frequently purchases eco-friendly products, the system can generate emails providing information on environmentally friendly products and eco-activities. Similarly, if a customer purchases recycling-related products, the system can generate emails providing recycling advice and information on new recycling products. Furthermore, if a customer purchases energy-saving products, the system can generate emails providing energy-saving information and information on new energy-saving products. This enables personalized follow-up tailored to each customer's environmental awareness, thereby improving customer satisfaction.

[0096] An automated follow-up email generation and distribution system can estimate customer emotions and, based on those emotions, provide information on education and learning that might interest the customer. For example, if a customer is excited, it can generate emails providing information on new learning programs or educational events. If a customer is relaxed, it can generate emails providing content and learning methods that allow for relaxed learning. Furthermore, if a customer is feeling anxious, it can generate emails providing support information to alleviate anxiety or information on education and learning that provides reassurance. This enables the provision of education and learning information tailored to the customer's emotions, thereby improving customer satisfaction.

[0097] The automated follow-up email generation and distribution system can estimate a customer's travel plans based on their purchase history and behavioral data, and provide travel-related information at the appropriate time. For example, if a customer frequently purchases travel goods, the system can generate emails offering travel advice and information on new travel products. If a customer is interested in a particular region, the system can generate emails providing tourist information and event information related to that region. Furthermore, if a customer has purchased travel insurance, the system can generate emails offering information on travel safety and new travel insurance options. This enables personalized follow-up tailored to the customer's travel plans, thereby improving customer satisfaction.

[0098] The automated follow-up email generation and distribution system can estimate customer emotions and, based on those emotions, request feedback or reviews that are likely to interest the customer. For example, if a customer is excited, it can generate an email requesting positive feedback or a review. If a customer is relaxed, it can generate an email that encourages them to provide feedback in a relaxed manner. Furthermore, if a customer is feeling anxious, it can generate an email requesting feedback or a review while providing support information to alleviate their anxiety. This allows for feedback and review requests tailored to the customer's emotions, thereby improving customer satisfaction.

[0099] The following briefly describes the processing flow for example form 2.

[0100] Step 1: The data collection unit collects customer purchase history and behavioral data. For example, it can collect data such as information on products purchased by customers, purchase date and time, purchase frequency, and browsing history. The data collection unit can also use AI to analyze customer behavior patterns and collect data. Step 2: The generation unit generates the content of the follow-up email based on the data collected by the collection unit. The generation unit uses generation AI to analyze the customer's purchase history and behavioral data and generate the most suitable email content. For example, it can generate an email that includes instructions on how to use the product the customer purchased and after-care information. The generation unit can also adjust the content of the next email based on customer feedback. Step 3: The sending unit sends the emails generated by the generating unit at the appropriate time. The sending unit uses AI to analyze customer behavior data and estimate the optimal sending timing. For example, it can send a purchase confirmation email immediately after a customer makes a purchase and a notification email when the product arrives. It can also send usage surveys, reminder emails, and promotional emails after a certain period of time. Step 4: The analysis department analyzes the effectiveness of emails sent by the sending department and optimizes the content and timing of future emails. The analysis department uses AI to analyze data such as email open rates, click-through rates, and conversion rates to evaluate effectiveness. For example, it analyzes whether customers opened the email and clicked on links within the email, and adjusts the content and timing of future emails accordingly.

[0101] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0102] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0103] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0104] Each of the multiple elements described above, including the collection unit, generation unit, transmission unit, and analysis unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects customer purchase history and behavioral data using the camera 42 and microphone 38B of the smart device 14, and the control unit 46A analyzes the data. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and generates the content of a follow-up email based on the collected data. The transmission unit is implemented in the specific processing unit 46A of the smart device 14, for example, and sends the generated email at an appropriate time. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the effect of the sent email to optimize the content and timing of the next email. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

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

[0106] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0107] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0108] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0109] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0110] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0111] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0112] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0113] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

[0116] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

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

[0120] Each of the multiple elements described above, including the collection unit, generation unit, transmission unit, and analysis unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects customer purchase history and behavioral data using the camera 42 and microphone 238 of the smart glasses 214, and the control unit 46A analyzes the data. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and generates the content of a follow-up email based on the collected data. The transmission unit is implemented in the specific processing unit 46A of the smart glasses 214, for example, and sends the generated email at an appropriate time. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the effect of the sent email to optimize the content and timing of the next email. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0121] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0122] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0124] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0125] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0127] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0128] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0129] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0130] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0131] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements described above, including the collection unit, generation unit, transmission unit, and analysis unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects customer purchase history and behavioral data using the camera 42 and microphone 238 of the headset terminal 314, and the control unit 46A analyzes the data. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and generates the content of a follow-up email based on the collected data. The transmission unit is implemented in the specific processing unit 46A of the headset terminal 314, for example, and transmits the generated email at an appropriate time. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the effect of the transmitted email to optimize the content and transmission timing of the next email. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0137] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0138] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0145] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0146] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0147] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0148] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0150] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0153] Each of the multiple elements described above, including the collection unit, generation unit, transmission unit, and analysis unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects customer purchase history and behavioral data using the camera 42 and microphone 238 of the robot 414, and the control unit 46A analyzes the data. The generation unit is implemented in, for example, the specific processing unit 290 of the data processing unit 12, and generates the content of a follow-up email based on the collected data. The transmission unit is implemented in, for example, the control unit 46A of the robot 414, and sends the generated email at an appropriate time. The analysis unit is implemented in, for example, the specific processing unit 290 of the data processing unit 12, and analyzes the effect of the sent email and optimizes the content and timing of the next email. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0154] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0155] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0156] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0157] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0158] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0159] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0160] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0161] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0162] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0163] 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.

[0164] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0165] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0166] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0167] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0168] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0169] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0170] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0171] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0172] (Note 1) The collection unit collects customer purchase history and behavioral data, A generation unit generates the content of a follow-up email based on the data collected by the collection unit, A sending unit that sends the email generated by the generation unit at an appropriate time, The system includes an analysis unit that analyzes the effectiveness of emails sent by the aforementioned sending unit and optimizes the content and timing of future emails. A system characterized by the following features. (Note 2) The aforementioned collection unit is We estimate customer emotions and adjust the timing of collecting purchase history and behavioral data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Analyze the customer's past purchase history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is When collecting purchase history and behavioral data, filtering is performed based on the customer's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is We estimate customer emotions and prioritize the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is When collecting purchase history and behavioral data, the system prioritizes collecting highly relevant data by considering the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting purchase history and behavioral data, analyze customers' social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 8) The generating unit is We estimate the customer's emotions and adjust the wording of follow-up emails based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The generating unit is When generating follow-up emails, adjust the level of detail in the email based on the importance of the product. The system described in Appendix 1, characterized by the features described herein. (Note 10) The generating unit is When generating follow-up emails, different generation algorithms are applied depending on the product category. The system described in Appendix 1, characterized by the features described herein. (Note 11) The generating unit is Estimate the customer's emotions and adjust the length of follow-up emails based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is When generating follow-up emails, prioritize emails based on when the product was purchased. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is When generating follow-up emails, the order of emails is adjusted based on the relevance of the products. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned transmitting unit We estimate customer emotions and adjust the timing of email sending based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned transmitting unit When sending emails, the system analyzes the customer's past email open history to select the optimal sending method. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned transmitting unit When sending emails, customize the timing of sending based on the customer's current life situation. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned transmitting unit It estimates customer sentiment and prioritizes emails to send based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned transmitting unit When sending emails, the system selects the optimal sending timing by considering the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned transmitting unit When sending emails, we analyze the customer's social media activity and adjust the timing of the email delivery. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit is We estimate customer emotions and adjust email effectiveness analysis methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit is When analyzing the effectiveness of emails, we optimize the analysis algorithm by referring to past analysis data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit is When analyzing the effectiveness of emails, customize the analysis method based on customer attribute information. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit is It estimates customer emotions and optimizes the content and timing of future emails based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit is When analyzing the effectiveness of emails, the analysis data is weighted based on the customer's purchase history. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit is When analyzing the effectiveness of email marketing, referencing customers' social media activity improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0173] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection unit collects customer purchase history and behavioral data, A generation unit generates the content of a follow-up email based on the data collected by the collection unit, A sending unit that sends the email generated by the generation unit at an appropriate time, The system includes an analysis unit that analyzes the effectiveness of emails sent by the aforementioned sending unit and optimizes the content and timing of future emails. A system characterized by the following features.

2. The aforementioned collection unit is We estimate customer emotions and adjust the timing of collecting purchase history and behavioral data based on those estimated emotions. The system according to feature 1.

3. The aforementioned collection unit is Analyze the customer's past purchase history and select the optimal data collection method. The system according to feature 1.

4. The aforementioned collection unit is When collecting purchase history and behavioral data, filtering is performed based on the customer's current lifestyle and areas of interest. The system according to feature 1.

5. The aforementioned collection unit is We estimate customer emotions and prioritize the data to collect based on those estimated emotions. The system according to feature 1.

6. The aforementioned collection unit is When collecting purchase history and behavioral data, the system prioritizes collecting highly relevant data by considering the customer's geographical location. The system according to feature 1.

7. The aforementioned collection unit is When collecting purchase history and behavioral data, analyze customers' social media activity and collect relevant data. The system according to feature 1.

8. The generating unit is We estimate the customer's emotions and adjust the wording of follow-up emails based on those estimated emotions. The system according to feature 1.

9. The generating unit is When generating follow-up emails, adjust the level of detail in the email based on the importance of the product. The system according to feature 1.

10. The generating unit is When generating follow-up emails, different generation algorithms are applied depending on the product category. The system according to feature 1.

Images