system

Abstract

The system according to this embodiment aims to detect customer problems and respond proactively. [Solution] The system according to the embodiment comprises an acquisition unit, a reference unit, a determination unit, an execution unit, and a notification unit. The acquisition unit acquires customer actions. The reference unit refers to an error pattern database based on the actions acquired by the acquisition unit. The determination unit determines the possibility of querying based on the error patterns referred to by the reference unit. The execution unit performs a customer service response if the determination unit determines that a query is possible. The notification unit notifies the customer of the results of the customer service response performed by the execution unit.

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, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 prior art, detecting the occurrence of customer problems and taking proactive measures have not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to detect the occurrence of customer problems and take proactive measures.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, a reference unit, a determination unit, an execution unit, and a notification unit. The acquisition unit acquires customer actions. The reference unit refers to an error pattern database based on the actions acquired by the acquisition unit. The determination unit determines the possibility of querying based on the error patterns referred to by the reference unit. The execution unit performs a customer service response if the determination unit determines that a query is possible. The notification unit notifies the customer of the results of the customer service response performed by the execution unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect when a customer's problem occurs and respond proactively. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The customer support system according to an embodiment of the present invention is a system that uses an AI agent to proactively detect customer issues and prevent inquiries. This customer support system can prevent inquiries by acquiring customer actions, referring to an error pattern database, determining the likelihood of an inquiry, executing a customer support response, and notifying the customer of the result. For example, if an error occurs when a customer tries to register as a member, the system will respond in the following steps: An error occurs when the customer tries to register as a member, and an activity log is sent. The proactive customer support system makes a preliminary determination as to whether the activity is likely to result in an inquiry and refers to a pre-registered error pattern database. If it is determined that there is a possibility of an inquiry, the system proceeds to the next step. The AI ​​agent acquires the information necessary for the determination and makes a secondary determination of the likelihood of an inquiry. The error pattern database is referred to again, and if it is determined that there is a possibility of an inquiry, the system proceeds to the next step. The AI ​​agent executes the customer support response and notifies the customer of the solution via a dedicated app. The error pattern database is updated when a customer support representative performs a customer support response. The AI ​​agent can also update it automatically. This mechanism allows for the prediction of signs of an inquiry from the user's actions and status, and enables the implementation of an appropriate approach before the situation escalates into an inquiry. This reduces customer pain points, decreases customer support complaints, and reduces the company's customer support costs. This allows customers, customer support, and the company to build a win-win-win relationship. As a result, the customer support system can proactively detect customer issues and prevent inquiries.

[0029] The customer support system according to this embodiment comprises an acquisition unit, a reference unit, a determination unit, an execution unit, and a notification unit. The acquisition unit acquires customer actions. Customer actions include, but are not limited to, purchase actions, inquiry actions, and website browsing actions. For example, the acquisition unit acquires actions when a customer browses products on the website. The acquisition unit can also acquire actions when a customer adds products to their cart. Furthermore, the acquisition unit can acquire the content entered by the customer in an inquiry form. For example, the acquisition unit acquires actions when a customer browses products on the website in real time. It records actions when a customer adds products to their cart as a log. It saves the content entered by the customer in an inquiry form in a database. The reference unit refers to an error pattern database based on the actions acquired by the acquisition unit. The error pattern database includes, but is not limited to, past error patterns and how to deal with them. For example, the reference unit searches the error pattern database and identifies the relevant error pattern. The reference unit can also periodically update the error pattern database. Furthermore, the reference unit can also automatically update the error pattern database. For example, the reference unit searches the error pattern database and identifies the relevant error pattern. The error pattern database is updated periodically. The error pattern database is updated automatically. The decision unit determines queryability based on the error pattern referenced by the reference unit. Queryability is determined based on, for example, the degree of error pattern matching or the customer's past query history, but is not limited to these examples. The decision unit calculates the degree of error pattern matching and determines queryability. The decision unit can also refer to the customer's past query history and determine queryability. Furthermore, the decision unit can combine the degree of error pattern matching and the customer's past query history to determine queryability. For example, the decision unit calculates the degree of error pattern matching and determines queryability. The customer's past query history is referred to and determines queryability.The likelihood of an inquiry is determined by combining the degree of matching of error patterns with the customer's past inquiry history. The execution unit performs customer service (CS) support if the decision unit determines that an inquiry is likely. CS support includes, but is not limited to, telephone support, email support, and chat support. For example, the execution unit may call the customer to provide support. The execution unit may also send an email to the customer. Furthermore, the execution unit may also chat with the customer. For example, the execution unit may call the customer to provide support. Send an email to the customer to provide support. Chat with the customer. The notification unit notifies the customer of the results of the CS support performed by the execution unit. Notifications include, but are not limited to, email, SMS, and app notifications. For example, the notification unit may notify the customer of the results by email. The notification unit may also notify the customer of the results by SMS. Furthermore, the notification unit may also notify the customer of the results by app notification. For example, the notification unit may notify the customer of the results by email. Notify the customer of the results by SMS. Notify the customer of the results by app notification. As a result, the customer support system according to this embodiment can proactively detect when a customer's problem arises and prevent inquiries.

[0030] The data acquisition unit acquires customer actions. These actions include, but are not limited to, purchase behavior, inquiry behavior, and website browsing behavior. For example, the unit acquires customer behavior when browsing products on a website. It can also acquire customer behavior when adding items to a shopping cart. Furthermore, it can acquire the content entered by customers in inquiry forms. For example, the data acquisition unit acquires customer behavior in real time when browsing products on a website. It logs customer behavior when adding items to a shopping cart. It saves the content entered by customers in inquiry forms to a database. The data acquisition unit uses website tracking codes and sensors to collect this data. Tracking codes record customer behavior in detail and transmit it to the database in real time. For example, it collects detailed behavioral data such as the time a customer spends viewing a specific product page, scrolling behavior within the page, and links clicked. This allows the data acquisition unit to understand customer behavior patterns in detail and analyze customer interests and preferences. The data acquisition unit also integrates with the shopping cart system to record customer behavior when adding items to a cart. The shopping cart system provides the data acquisition unit with information such as the items and quantities added by customers to their cart, as well as the date and time of addition. This allows the data acquisition unit to understand customers' purchasing intent and behavior, and provide support at the appropriate time. Furthermore, the data acquisition unit captures form submission data to obtain the information entered by customers in inquiry forms. Inquiry forms contain information such as the customer's name, email address, and inquiry content, and this data is stored in a database. The data acquisition unit analyzes this data to provide information that enables quick responses to customer problems and questions. In this way, the data acquisition unit can comprehensively collect customer behavior data and accurately understand customer needs and problems.

[0031] The reference unit refers to the error pattern database based on actions acquired by the acquisition unit. The error pattern database includes, but is not limited to, past error patterns and their corresponding solutions. For example, the reference unit searches the error pattern database and identifies the relevant error pattern. The reference unit can also periodically update the error pattern database. Furthermore, the reference unit can automatically update the error pattern database. For example, the reference unit searches the error pattern database and identifies the relevant error pattern. It periodically updates the error pattern database. It automatically updates the error pattern database. The reference unit analyzes customer behavior data provided by the acquisition unit and compares it with the error pattern database. For example, if a customer views a specific product page but leaves without adding it to their cart, the reference unit compares this behavior with the error pattern database and refers to data of customers who have taken similar actions in the past. This allows the reference unit to identify potential problems or obstacles the customer may be facing. To periodically update the error pattern database, the reference unit adds past support history and newly occurring error patterns to the database. This allows the reference unit to quickly identify customer problems based on the latest information and provide appropriate solutions. Furthermore, the reference unit uses machine learning algorithms to automatically update the error pattern database. These algorithms analyze historical data and automatically detect new error patterns and trends. This allows the reference unit to always identify customer problems based on the latest information and provide quick and accurate responses.

[0032] The decision unit determines the likelihood of a query based on the error patterns referenced by the reference unit. Query likelihood is determined, for example, based on the degree of error pattern matching or the customer's past query history. The decision unit may, for example, calculate the degree of error pattern matching and determine the likelihood of a query. It may also refer to the customer's past query history and determine the likelihood of a query. Furthermore, the decision unit may combine the degree of error pattern matching and the customer's past query history to determine the likelihood of a query. For example, the decision unit may calculate the degree of error pattern matching and determine the likelihood of a query. It may refer to the customer's past query history and determine the likelihood of a query. It may combine the degree of error pattern matching and the customer's past query history to determine the likelihood of a query. To calculate the degree of error pattern matching, the decision unit compares customer behavior data provided by the acquisition unit with error pattern data provided by the reference unit. For example, if a customer views a specific product page but leaves without adding it to their cart, the decision unit matches this behavior with the error pattern database and calculates the degree of matching. If the degree of error pattern matching is high, the decision unit determines that the customer is likely to have a problem. The decision unit may also refer to the customer's past query history and determine the likelihood of a query. For example, if a customer has previously inquired about a similar problem, the decision-making unit will determine that the customer is likely to inquire again. Furthermore, the decision-making unit combines the degree of similarity of the error pattern with the customer's past inquiry history to determine the likelihood of another inquiry. This allows the decision-making unit to accurately identify the customer's problem and provide appropriate solutions quickly.

[0033] The execution unit performs customer service (CS) responses when the decision-making unit determines that there is a possibility of an inquiry. CS responses include, but are not limited to, telephone support, email support, and chat support. For example, the execution unit may call the customer to provide support. Alternatively, the execution unit may send an email to the customer. Furthermore, the execution unit may chat with the customer. The execution unit selects the most appropriate CS response method based on the inquiry possibility information provided by the decision-making unit. For example, if the customer has previously preferred telephone support, the execution unit will call the customer. If the customer prefers email support, the execution unit will send an email. Furthermore, if the customer prefers chat support, the execution unit will chat with the customer. The execution unit selects the most appropriate response method based on the content of the customer inquiry and the urgency of the problem, providing a quick and appropriate response. This allows the execution unit to quickly resolve customer problems and improve customer satisfaction.

[0034] The notification unit notifies the customer of the results of the CS response performed by the execution unit. Notifications include, but are not limited to, email, SMS, and app notifications. For example, the notification unit may notify the customer of the results via email. The notification unit may also notify the customer of the results via SMS. Furthermore, the notification unit may also notify the customer of the results via app notification. For example, the notification unit may notify the customer of the results via email. The notification unit may notify the customer of the results via SMS. The notification unit may notify the customer of the results via app notification. Based on the results of the CS response provided by the execution unit, the notification unit provides appropriate notifications to the customer. For example, if a customer makes an inquiry, the notification unit will notify the customer of the results via email. Also, if a customer receives telephone support, the notification unit may notify the customer of the results via SMS. Furthermore, if a customer receives chat support, the notification unit may notify the customer of the results via app notification. The notification unit selects the most suitable notification method according to the customer's notification settings and preferences, and provides notifications quickly and accurately. This allows the notification unit to provide customers with quick and accurate information and improve customer satisfaction.

[0035] The reference unit can automatically update the error pattern database. For example, the reference unit can periodically update the error pattern database. The reference unit can also update the error pattern database in real time. The reference unit can use AI to automatically update the error pattern database. For example, the reference unit can periodically update the error pattern database. The reference unit can update the error pattern database in real time. The reference unit uses AI to automatically update the error pattern database. This allows for responses based on the latest error patterns by automatically updating the error pattern database.

[0036] The acquisition unit can analyze the customer's past action history and select the optimal acquisition method. For example, the acquisition unit prioritizes acquiring actions that the customer has frequently performed in the past. The acquisition unit can also find specific patterns from the customer's past action history and acquire actions based on those patterns. The acquisition unit can also analyze the customer's past action history and select the most efficient acquisition method. For example, the acquisition unit prioritizes acquiring actions that the customer has frequently performed in the past. The acquisition unit finds specific patterns from the customer's past action history and acquires actions based on those patterns. The acquisition unit analyzes the customer's past action history and selects the most efficient acquisition method. This allows the optimal acquisition method to be selected by analyzing the customer's past action history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI.

[0037] The acquisition unit can filter actions based on the customer's current situation and areas of interest. For example, the acquisition unit prioritizes acquiring information related to actions the customer is currently taking. The acquisition unit can also acquire highly relevant actions based on the customer's areas of interest. The acquisition unit can also acquire the most suitable actions based on the customer's current situation (e.g., time of day and location). For example, the acquisition unit prioritizes acquiring information related to actions the customer is currently taking. The acquisition unit acquires highly relevant actions based on the customer's areas of interest. The acquisition unit acquires the most suitable actions based on the customer's current situation (e.g., time of day and location). This allows for the acquisition of highly relevant actions by filtering based on the customer's current situation and areas of interest. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI.

[0038] The acquisition unit can prioritize the acquisition of highly relevant actions by considering the customer's geographical location information when acquiring actions. For example, if the customer is in a specific region, the acquisition unit will prioritize the acquisition of actions related to that region. The acquisition unit can also prioritize the acquisition of actions that occurred near the customer's current location. The acquisition unit can also acquire the most relevant actions based on the customer's geographical location information. For example, if the acquisition unit is in a specific region, the acquisition unit will prioritize the acquisition of actions related to that region. The acquisition unit will prioritize the acquisition of actions that occurred near the customer's current location. The acquisition unit will acquire the most relevant actions based on the customer's geographical location information. In this way, by considering the customer's geographical location information, highly relevant actions can be prioritized. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI.

[0039] The acquisition unit can analyze the customer's social media activity and acquire relevant actions when acquiring actions. For example, the acquisition unit can acquire relevant actions based on what the customer has mentioned on social media. The acquisition unit can also acquire actions related to topics of interest from the customer's social media activity. The acquisition unit can also analyze the customer's social media activity history and acquire the most relevant actions. For example, the acquisition unit can acquire relevant actions based on what the customer has mentioned on social media. The acquisition unit can acquire actions related to topics of interest from the customer's social media activity. The acquisition unit can analyze the customer's social media activity history and acquire the most relevant actions. In this way, relevant actions can be acquired by analyzing the customer's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI.

[0040] The reference unit can select the optimal reference method by referring to past error pattern data when referencing the error pattern database. For example, the reference unit can select the optimal reference method based on past error patterns. The reference unit can also analyze the customer's past error pattern data and select the most efficient reference method. The reference unit can also select the most relevant reference method by referring to past error pattern data. For example, the reference unit can select the optimal reference method based on past error patterns. The reference unit can analyze the customer's past error pattern data and select the most efficient reference method. The reference unit can select the most relevant reference method by referring to past error pattern data. In this way, the optimal reference method can be selected by referring to past error pattern data. Some or all of the above processing in the reference unit may be performed using AI, for example, or without using AI.

[0041] The reference unit can apply different reference algorithms depending on the customer's action category when referencing the error pattern database. For example, the reference unit applies the optimal reference algorithm based on the customer's action category. The reference unit can also set different reference algorithms for each customer's action category and reference in the most optimal way. The reference unit can also apply the most efficient reference algorithm depending on the customer's action category. For example, the reference unit applies the optimal reference algorithm based on the customer's action category. The reference unit sets different reference algorithms for each customer's action category and references in the most optimal way. The reference unit applies the most efficient reference algorithm depending on the customer's action category. This makes optimal referencing possible by applying different reference algorithms depending on the customer's action category. Some or all of the above processing in the reference unit may be performed using AI, for example, or without using AI.

[0042] The reference unit can determine the priority of references to the error pattern database based on when the customer's actions were submitted. For example, the reference unit will prioritize referencing the error pattern database if the customer's actions were recently submitted. The reference unit can also determine the optimal priority of references based on when the customer's actions were submitted. If the customer's actions are older, the reference unit can also refer to the error pattern database with normal priority. For example, the reference unit will prioritize referencing the error pattern database if the customer's actions were recently submitted. The reference unit will determine the optimal priority of references based on when the customer's actions were submitted. If the customer's actions are older, the reference unit will refer to the error pattern database with normal priority. This enables quick and appropriate referencing by determining the priority of references based on when the customer's actions were submitted. Some or all of the above processing in the reference unit may be performed using AI, for example, or not using AI.

[0043] The reference unit can improve the accuracy of the reference by referring to customer-related literature when referencing the error pattern database. For example, the reference unit can improve the accuracy of the reference to the error pattern database by referring to customer-related literature. The reference unit can also select the optimal reference method based on customer-related literature. The reference unit can also select the most efficient reference method by referring to customer-related literature. For example, the reference unit can improve the accuracy of the reference to the error pattern database by referring to customer-related literature. The reference unit selects the optimal reference method based on customer-related literature. The reference unit selects the most efficient reference method by referring to customer-related literature. This allows for improved accuracy of the reference by referring to customer-related literature. Some or all of the above processing in the reference unit may be performed using AI, for example, or without using AI.

[0044] The decision-making unit can improve the accuracy of its judgment by considering the interrelationships of actions when determining the likelihood of an inquiry. For example, the decision-making unit analyzes the interrelationships of customer actions and determines the likelihood of an inquiry. The decision-making unit can also set optimal judgment criteria by considering the interrelationships of actions. The decision-making unit can also select the most efficient judgment method based on the interrelationships of actions. For example, the decision-making unit analyzes the interrelationships of customer actions and determines the likelihood of an inquiry. The decision-making unit sets optimal judgment criteria by considering the interrelationships of actions. The decision-making unit selects the most efficient judgment method based on the interrelationships of actions. In this way, the accuracy of the judgment can be improved by considering the interrelationships of actions. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI.

[0045] The decision-making unit can make decisions by considering customer attribute information when determining the likelihood of an inquiry. For example, the decision-making unit can determine the likelihood of an inquiry based on customer attribute information (age, gender, etc.). The decision-making unit can also set optimal decision criteria by considering customer attribute information. The decision-making unit can also select the most efficient decision-making method based on customer attribute information. For example, the decision-making unit can determine the likelihood of an inquiry based on customer attribute information (age, gender, etc.). The decision-making unit can set optimal decision criteria by considering customer attribute information. The decision-making unit can select the most efficient decision-making method based on customer attribute information. This makes it possible to make more appropriate decisions by considering customer attribute information. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI.

[0046] The decision-making unit can make decisions considering the geographical distribution of actions when determining the likelihood of an inquiry. For example, if customer actions are concentrated in a particular region, the decision-making unit will prioritize determining the likelihood of an inquiry related to that region. The decision-making unit can also set optimal decision criteria based on the geographical distribution of actions. The decision-making unit can also select the most efficient decision-making method considering the geographical distribution of actions. For example, if customer actions are concentrated in a particular region, the decision-making unit will prioritize determining the likelihood of an inquiry related to that region. The decision-making unit will set optimal decision criteria based on the geographical distribution of actions. The decision-making unit will select the most efficient decision-making method considering the geographical distribution of actions. This makes it possible to make appropriate decisions specific to a region by considering the geographical distribution of actions. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or not using AI.

[0047] The decision unit can improve the accuracy of its decision when determining queryability by referring to relevant literature for the action. For example, the decision unit can improve the accuracy of its queryability determination by referring to relevant literature for the action. The decision unit can also set optimal decision criteria based on relevant literature for the action. The decision unit can also select the most efficient decision method by referring to relevant literature for the action. For example, the decision unit can improve the accuracy of its queryability determination by referring to relevant literature for the action. The decision unit can set optimal decision criteria based on relevant literature for the action. The decision unit can select the most efficient decision method by referring to relevant literature for the action. In this way, the accuracy of the decision can be improved by referring to relevant literature for the action. Some or all of the above processing in the decision unit may be performed using AI, for example, or without using AI.

[0048] The execution unit can select the optimal execution method by referring to past customer service response data when executing a customer service response. For example, the execution unit can select the optimal execution method based on past successful customer service response data. The execution unit can also select the most efficient execution method by referring to the customer's past customer service response history. The execution unit can also select the most effective execution method by analyzing past customer service response data. For example, the execution unit can select the optimal execution method based on past successful customer service response data. The execution unit can select the most efficient execution method by referring to the customer's past customer service response history. The execution unit can select the most effective execution method by analyzing past customer service response data. In this way, the optimal execution method can be selected by referring to past customer service response data. Some or all of the above processing in the execution unit may be performed using AI, for example, or without using AI.

[0049] The execution unit can apply different execution algorithms depending on the customer action category when performing CS response. For example, the execution unit applies the optimal execution algorithm based on the customer action category. The execution unit can also set different execution algorithms for each customer action category and perform CS response in the most optimal way. The execution unit can also apply the most efficient execution algorithm depending on the customer action category. For example, the execution unit applies the optimal execution algorithm based on the customer action category. The execution unit sets different execution algorithms for each customer action category and performs CS response in the most optimal way. The execution unit applies the most efficient execution algorithm depending on the customer action category. This makes it possible to perform optimal CS response by applying different execution algorithms depending on the customer action category. Some or all of the above processing in the execution unit may be performed using AI, for example, or without using AI.

[0050] The execution unit can determine the execution priority based on when the customer action was submitted when performing a customer service response. For example, the execution unit will prioritize CS responses if the customer action was recently submitted. The execution unit can also determine the optimal execution priority based on when the customer action was submitted. If the customer action is old, the execution unit can also perform CS responses with the normal priority. For example, the execution unit will prioritize CS responses if the customer action was recently submitted. The execution unit will determine the optimal execution priority based on when the customer action was submitted. If the customer action is old, the execution unit will perform CS responses with the normal priority. This enables a quick and appropriate response by determining the execution priority based on when the customer action was submitted. Some or all of the above processing in the execution unit may be performed using AI, for example, or without using AI.

[0051] The execution unit can improve the accuracy of its execution by referring to relevant customer documentation during CS response execution. For example, the execution unit improves the accuracy of CS response execution by referring to relevant customer documentation. The execution unit can also select the optimal execution method based on relevant customer documentation. The execution unit can also select the most efficient execution method by referring to relevant customer documentation. For example, the execution unit improves the accuracy of CS response execution by referring to relevant customer documentation. The execution unit selects the optimal execution method based on relevant customer documentation. The execution unit selects the most efficient execution method by referring to relevant customer documentation. In this way, the accuracy of execution can be improved by referring to relevant customer documentation. Some or all of the above processing in the execution unit may be performed using AI, for example, or without using AI.

[0052] The notification unit can select the optimal notification method by referring to the customer's past notification history when sending a notification. For example, the notification unit selects the optimal notification method based on the customer's past notification history. The notification unit can also analyze the customer's past notification history and select the most efficient notification method. The notification unit can also refer to the customer's past notification history and select the most relevant notification method. For example, the notification unit selects the optimal notification method based on the customer's past notification history. The notification unit analyzes the customer's past notification history and selects the most efficient notification method. The notification unit refers to the customer's past notification history and selects the most relevant notification method. This allows the notification unit to select the optimal notification method by referring to the customer's past notification history. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI.

[0053] The notification unit can customize the notification method based on the customer's current situation when a notification is sent. For example, the notification unit may prioritize voice notifications if the customer is on the go. The notification unit may also prioritize email notifications if the customer is in the office. The notification unit may also prioritize app notifications if the customer is at home. For example, the notification unit may prioritize voice notifications if the customer is on the go. The notification unit may prioritize email notifications if the customer is in the office. The notification unit may prioritize app notifications if the customer is at home. This allows for more appropriate notifications by customizing the notification method based on the customer's current situation. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI.

[0054] The notification unit can select the optimal notification method by considering the customer's geographical location information when sending a notification. For example, if the customer is in a specific region, the notification unit will prioritize notifications related to that region. The notification unit can also prioritize notifications that have occurred in locations close to the customer's current location. The notification unit can also send the most relevant notifications based on the customer's geographical location information. For example, if the customer is in a specific region, the notification unit will prioritize notifications related to that region. The notification unit will prioritize notifications that have occurred in locations close to the customer's current location. The notification unit will send the most relevant notifications based on the customer's geographical location information. In this way, the optimal notification method can be selected by considering the customer's geographical location information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI.

[0055] The notification unit can analyze the customer's social media activity and suggest notification methods when sending notifications. For example, the notification unit can suggest the most suitable notification method based on what the customer has mentioned on social media. The notification unit can also suggest notification methods related to topics of interest based on the customer's social media activity. The notification unit can also analyze the customer's social media activity history and suggest the most relevant notification method. For example, the notification unit can suggest the most suitable notification method based on what the customer has mentioned on social media. The notification unit can suggest notification methods related to topics of interest based on the customer's social media activity. The notification unit can analyze the customer's social media activity history and suggest the most relevant notification method. In this way, the notification unit can suggest the most suitable notification method by analyzing the customer's social media activity. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI.

[0056] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0057] The data acquisition unit can select the optimal acquisition method when acquiring customer actions, taking into account the type of device and usage patterns of the customer. For example, if the customer is using a smartphone, the acquisition unit can prioritize acquiring mobile app usage data. If the customer is using a desktop computer, it can also prioritize acquiring website browsing behavior. Furthermore, if the customer is using a tablet, the acquisition unit can acquire actions while considering tablet-specific operations. This allows for more accurate action acquisition by selecting the optimal acquisition method according to the type of device and usage patterns of the customer.

[0058] The reference unit can select the optimal reference method when referencing the error pattern database, taking into account the customer's past error pattern resolution history. For example, if the reference unit has experienced a similar error pattern in the past, it will prioritize referencing that solution. If the customer is experiencing the error pattern for the first time, it can also refer to general solutions. Furthermore, the reference unit can analyze the customer's past error pattern resolution history and select the most efficient reference method. This allows for the selection of the optimal reference method by considering the customer's past error pattern resolution history.

[0059] The decision-making unit can improve the accuracy of its judgment by considering the frequency of customer actions when determining the likelihood of an inquiry. For example, the decision-making unit can set a high likelihood of an inquiry for actions that customers perform frequently, and a low likelihood for actions that customers perform rarely. Furthermore, the decision-making unit can analyze the frequency of customer actions and set the most efficient judgment criteria. This improves the accuracy of the judgment by considering the frequency of customer actions.

[0060] The execution unit can apply different response methods depending on the type of customer action when performing customer service (CS) responses. For example, if a customer makes a purchase, the execution unit can prioritize providing support related to the purchase. If a customer makes an inquiry, it can also prioritize providing support related to the inquiry. Furthermore, if a customer browses a website, the execution unit can provide support related to browsing. This allows for more effective CS responses by applying the most appropriate response method according to the type of customer action.

[0061] The notification unit can adjust the content of notifications based on the importance of the customer's action. For example, if a customer takes an important action, the notification unit can provide a detailed notification. If a customer takes a general action, it can provide a concise notification. Furthermore, the notification unit can analyze the importance of the customer's action and select the most appropriate notification content. This allows for more effective notifications by adjusting the content according to the importance of the customer's action.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The acquisition unit retrieves customer actions. Customer actions include purchase behavior, inquiry behavior, website browsing behavior, etc. For example, the acquisition unit retrieves actions taken when a customer views products on the website, actions taken when adding products to the cart, and content entered into an inquiry form. Step 2: The reference unit looks up the error pattern database based on the actions obtained by the acquisition unit. The error pattern database contains past error patterns and how to deal with them. The reference unit searches the error pattern database and identifies the relevant error pattern. The error pattern database can also be updated periodically and automatically. Step 3: The decision unit determines query feasibility based on the error pattern referenced by the reference unit. Query feasibility is determined based on the degree of matching of the error pattern and the customer's past query history. For example, the decision unit calculates the degree of matching of the error pattern, references the customer's past query history, and combines these to determine query feasibility. Step 4: The execution unit performs customer service (CS) support if the decision unit determines that there is a possibility of an inquiry. CS support includes telephone support, email support, and chat support. For example, the execution unit may call the customer, send an email, or chat with them. Step 5: The notification unit notifies the customer of the results of the CS response performed by the execution unit. Notifications may include email, SMS, and app notifications. For example, the notification unit may notify the customer of the results via email, SMS, and app notifications.

[0064] (Example of form 2) The customer support system according to an embodiment of the present invention is a system that uses an AI agent to proactively detect customer issues and prevent inquiries. This customer support system can prevent inquiries by acquiring customer actions, referring to an error pattern database, determining the likelihood of an inquiry, executing a customer support response, and notifying the customer of the result. For example, if an error occurs when a customer tries to register as a member, the system will respond in the following steps: An error occurs when the customer tries to register as a member, and an activity log is sent. The proactive customer support system makes a preliminary determination as to whether the activity is likely to result in an inquiry and refers to a pre-registered error pattern database. If it is determined that there is a possibility of an inquiry, the system proceeds to the next step. The AI ​​agent acquires the information necessary for the determination and makes a secondary determination of the likelihood of an inquiry. The error pattern database is referred to again, and if it is determined that there is a possibility of an inquiry, the system proceeds to the next step. The AI ​​agent executes the customer support response and notifies the customer of the solution via a dedicated app. The error pattern database is updated when a customer support representative performs a customer support response. The AI ​​agent can also update it automatically. This mechanism allows for the prediction of signs of an inquiry from the user's actions and status, and enables the implementation of an appropriate approach before the situation escalates into an inquiry. This reduces customer pain points, decreases customer support complaints, and reduces the company's customer support costs. This allows customers, customer support, and the company to build a win-win-win relationship. As a result, the customer support system can proactively detect customer issues and prevent inquiries.

[0065] The customer support system according to this embodiment comprises an acquisition unit, a reference unit, a determination unit, an execution unit, and a notification unit. The acquisition unit acquires customer actions. Customer actions include, but are not limited to, purchase actions, inquiry actions, and website browsing actions. For example, the acquisition unit acquires actions when a customer browses products on the website. The acquisition unit can also acquire actions when a customer adds products to their cart. Furthermore, the acquisition unit can acquire the content entered by the customer in an inquiry form. For example, the acquisition unit acquires actions when a customer browses products on the website in real time. It records actions when a customer adds products to their cart as a log. It saves the content entered by the customer in an inquiry form in a database. The reference unit refers to an error pattern database based on the actions acquired by the acquisition unit. The error pattern database includes, but is not limited to, past error patterns and how to deal with them. For example, the reference unit searches the error pattern database and identifies the relevant error pattern. The reference unit can also periodically update the error pattern database. Furthermore, the reference unit can also automatically update the error pattern database. For example, the reference unit searches the error pattern database and identifies the relevant error pattern. The error pattern database is updated periodically. The error pattern database is updated automatically. The decision unit determines queryability based on the error pattern referenced by the reference unit. Queryability is determined based on, for example, the degree of error pattern matching or the customer's past query history, but is not limited to these examples. The decision unit calculates the degree of error pattern matching and determines queryability. The decision unit can also refer to the customer's past query history and determine queryability. Furthermore, the decision unit can combine the degree of error pattern matching and the customer's past query history to determine queryability. For example, the decision unit calculates the degree of error pattern matching and determines queryability. The customer's past query history is referred to and determines queryability.The likelihood of an inquiry is determined by combining the degree of matching of error patterns with the customer's past inquiry history. The execution unit performs customer service (CS) support if the decision unit determines that an inquiry is likely. CS support includes, but is not limited to, telephone support, email support, and chat support. For example, the execution unit may call the customer to provide support. The execution unit may also send an email to the customer. Furthermore, the execution unit may also chat with the customer. For example, the execution unit may call the customer to provide support. Send an email to the customer to provide support. Chat with the customer. The notification unit notifies the customer of the results of the CS support performed by the execution unit. Notifications include, but are not limited to, email, SMS, and app notifications. For example, the notification unit may notify the customer of the results by email. The notification unit may also notify the customer of the results by SMS. Furthermore, the notification unit may also notify the customer of the results by app notification. For example, the notification unit may notify the customer of the results by email. Notify the customer of the results by SMS. Notify the customer of the results by app notification. As a result, the customer support system according to this embodiment can proactively detect when a customer's problem arises and prevent inquiries.

[0066] The data acquisition unit acquires customer actions. These actions include, but are not limited to, purchase behavior, inquiry behavior, and website browsing behavior. For example, the unit acquires customer behavior when browsing products on a website. It can also acquire customer behavior when adding items to a shopping cart. Furthermore, it can acquire the content entered by customers in inquiry forms. For example, the data acquisition unit acquires customer behavior in real time when browsing products on a website. It logs customer behavior when adding items to a shopping cart. It saves the content entered by customers in inquiry forms to a database. The data acquisition unit uses website tracking codes and sensors to collect this data. Tracking codes record customer behavior in detail and transmit it to the database in real time. For example, it collects detailed behavioral data such as the time a customer spends viewing a specific product page, scrolling behavior within the page, and links clicked. This allows the data acquisition unit to understand customer behavior patterns in detail and analyze customer interests and preferences. The data acquisition unit also integrates with the shopping cart system to record customer behavior when adding items to a cart. The shopping cart system provides the data acquisition unit with information such as the items and quantities added by customers to their cart, as well as the date and time of addition. This allows the data acquisition unit to understand customers' purchasing intent and behavior, and provide support at the appropriate time. Furthermore, the data acquisition unit captures form submission data to obtain the information entered by customers in inquiry forms. Inquiry forms contain information such as the customer's name, email address, and inquiry content, and this data is stored in a database. The data acquisition unit analyzes this data to provide information that enables quick responses to customer problems and questions. In this way, the data acquisition unit can comprehensively collect customer behavior data and accurately understand customer needs and problems.

[0067] The reference unit refers to the error pattern database based on actions acquired by the acquisition unit. The error pattern database includes, but is not limited to, past error patterns and their corresponding solutions. For example, the reference unit searches the error pattern database and identifies the relevant error pattern. The reference unit can also periodically update the error pattern database. Furthermore, the reference unit can automatically update the error pattern database. For example, the reference unit searches the error pattern database and identifies the relevant error pattern. It periodically updates the error pattern database. It automatically updates the error pattern database. The reference unit analyzes customer behavior data provided by the acquisition unit and compares it with the error pattern database. For example, if a customer views a specific product page but leaves without adding it to their cart, the reference unit compares this behavior with the error pattern database and refers to data of customers who have taken similar actions in the past. This allows the reference unit to identify potential problems or obstacles the customer may be facing. To periodically update the error pattern database, the reference unit adds past support history and newly occurring error patterns to the database. This allows the reference unit to quickly identify customer problems based on the latest information and provide appropriate solutions. Furthermore, the reference unit uses machine learning algorithms to automatically update the error pattern database. These algorithms analyze historical data and automatically detect new error patterns and trends. This allows the reference unit to always identify customer problems based on the latest information and provide quick and accurate responses.

[0068] The decision unit determines the likelihood of a query based on the error patterns referenced by the reference unit. Query likelihood is determined, for example, based on the degree of error pattern matching or the customer's past query history. The decision unit may, for example, calculate the degree of error pattern matching and determine the likelihood of a query. It may also refer to the customer's past query history and determine the likelihood of a query. Furthermore, the decision unit may combine the degree of error pattern matching and the customer's past query history to determine the likelihood of a query. For example, the decision unit may calculate the degree of error pattern matching and determine the likelihood of a query. It may refer to the customer's past query history and determine the likelihood of a query. It may combine the degree of error pattern matching and the customer's past query history to determine the likelihood of a query. To calculate the degree of error pattern matching, the decision unit compares customer behavior data provided by the acquisition unit with error pattern data provided by the reference unit. For example, if a customer views a specific product page but leaves without adding it to their cart, the decision unit matches this behavior with the error pattern database and calculates the degree of matching. If the degree of error pattern matching is high, the decision unit determines that the customer is likely to have a problem. The decision unit may also refer to the customer's past query history and determine the likelihood of a query. For example, if a customer has previously inquired about a similar problem, the decision-making unit will determine that the customer is likely to inquire again. Furthermore, the decision-making unit combines the degree of similarity of the error pattern with the customer's past inquiry history to determine the likelihood of another inquiry. This allows the decision-making unit to accurately identify the customer's problem and provide appropriate solutions quickly.

[0069] The execution unit performs customer service (CS) responses when the decision-making unit determines that there is a possibility of an inquiry. CS responses include, but are not limited to, telephone support, email support, and chat support. For example, the execution unit may call the customer to provide support. Alternatively, the execution unit may send an email to the customer. Furthermore, the execution unit may chat with the customer. The execution unit selects the most appropriate CS response method based on the inquiry possibility information provided by the decision-making unit. For example, if the customer has previously preferred telephone support, the execution unit will call the customer. If the customer prefers email support, the execution unit will send an email. Furthermore, if the customer prefers chat support, the execution unit will chat with the customer. The execution unit selects the most appropriate response method based on the content of the customer inquiry and the urgency of the problem, providing a quick and appropriate response. This allows the execution unit to quickly resolve customer problems and improve customer satisfaction.

[0070] The notification unit notifies the customer of the results of the CS response performed by the execution unit. Notifications include, but are not limited to, email, SMS, and app notifications. For example, the notification unit may notify the customer of the results via email. The notification unit may also notify the customer of the results via SMS. Furthermore, the notification unit may also notify the customer of the results via app notification. For example, the notification unit may notify the customer of the results via email. The notification unit may notify the customer of the results via SMS. The notification unit may notify the customer of the results via app notification. Based on the results of the CS response provided by the execution unit, the notification unit provides appropriate notifications to the customer. For example, if a customer makes an inquiry, the notification unit will notify the customer of the results via email. Also, if a customer receives telephone support, the notification unit may notify the customer of the results via SMS. Furthermore, if a customer receives chat support, the notification unit may notify the customer of the results via app notification. The notification unit selects the most suitable notification method according to the customer's notification settings and preferences, and provides notifications quickly and accurately. This allows the notification unit to provide customers with quick and accurate information and improve customer satisfaction.

[0071] The reference unit can automatically update the error pattern database. For example, the reference unit can periodically update the error pattern database. The reference unit can also update the error pattern database in real time. The reference unit can use AI to automatically update the error pattern database. For example, the reference unit can periodically update the error pattern database. The reference unit can update the error pattern database in real time. The reference unit uses AI to automatically update the error pattern database. This allows for responses based on the latest error patterns by automatically updating the error pattern database.

[0072] The acquisition unit can estimate the customer's emotions and adjust the timing of action acquisition based on the estimated emotions. For example, if the customer is stressed, the acquisition unit can acquire an action immediately and respond quickly. If the customer is relaxed, the acquisition unit can also slightly delay acquiring an action and respond at a more natural timing. If the customer is in a hurry, the acquisition unit can also prioritize acquiring an action and respond quickly. For example, if the customer is stressed, the acquisition unit can acquire an action immediately and respond quickly. If the customer is relaxed, the acquisition unit can slightly delay acquiring an action and respond at a more natural timing. If the customer is in a hurry, the acquisition unit can prioritize acquiring an action and respond quickly. This allows for actions to be acquired at a more appropriate time by adjusting the timing of action acquisition according to the customer's 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.

[0073] The acquisition unit can analyze the customer's past action history and select the optimal acquisition method. For example, the acquisition unit prioritizes acquiring actions that the customer has frequently performed in the past. The acquisition unit can also find specific patterns from the customer's past action history and acquire actions based on those patterns. The acquisition unit can also analyze the customer's past action history and select the most efficient acquisition method. For example, the acquisition unit prioritizes acquiring actions that the customer has frequently performed in the past. The acquisition unit finds specific patterns from the customer's past action history and acquires actions based on those patterns. The acquisition unit analyzes the customer's past action history and selects the most efficient acquisition method. This allows the optimal acquisition method to be selected by analyzing the customer's past action history. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI.

[0074] The acquisition unit can filter actions based on the customer's current situation and areas of interest. For example, the acquisition unit prioritizes acquiring information related to actions the customer is currently taking. The acquisition unit can also acquire highly relevant actions based on the customer's areas of interest. The acquisition unit can also acquire the most suitable actions based on the customer's current situation (e.g., time of day and location). For example, the acquisition unit prioritizes acquiring information related to actions the customer is currently taking. The acquisition unit acquires highly relevant actions based on the customer's areas of interest. The acquisition unit acquires the most suitable actions based on the customer's current situation (e.g., time of day and location). This allows for the acquisition of highly relevant actions by filtering based on the customer's current situation and areas of interest. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without AI.

[0075] The acquisition unit can estimate the customer's emotions and determine the priority of actions to take based on the estimated emotions. For example, if the customer is stressed, the acquisition unit will prioritize important actions. If the customer is relaxed, the acquisition unit can also prioritize actions with normal priority. If the customer is in a hurry, the acquisition unit can also prioritize actions that require a quick response. For example, if the customer is stressed, the acquisition unit will prioritize important actions. If the customer is relaxed, the acquisition unit will prioritize actions with normal priority. If the customer is in a hurry, the acquisition unit will prioritize actions that require a quick response. This allows for the priority of important actions by determining the priority of actions according to the customer's emotions. Some or all of the processing described above in the acquisition unit may be performed using AI, for example, or without AI.

[0076] The acquisition unit can prioritize the acquisition of highly relevant actions by considering the customer's geographical location information when acquiring actions. For example, if the customer is in a specific region, the acquisition unit will prioritize the acquisition of actions related to that region. The acquisition unit can also prioritize the acquisition of actions that occurred near the customer's current location. The acquisition unit can also acquire the most relevant actions based on the customer's geographical location information. For example, if the acquisition unit is in a specific region, the acquisition unit will prioritize the acquisition of actions related to that region. The acquisition unit will prioritize the acquisition of actions that occurred near the customer's current location. The acquisition unit will acquire the most relevant actions based on the customer's geographical location information. In this way, by considering the customer's geographical location information, highly relevant actions can be prioritized. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI.

[0077] The acquisition unit can analyze the customer's social media activity and acquire relevant actions when acquiring actions. For example, the acquisition unit can acquire relevant actions based on what the customer has mentioned on social media. The acquisition unit can also acquire actions related to topics of interest from the customer's social media activity. The acquisition unit can also analyze the customer's social media activity history and acquire the most relevant actions. For example, the acquisition unit can acquire relevant actions based on what the customer has mentioned on social media. The acquisition unit can acquire actions related to topics of interest from the customer's social media activity. The acquisition unit can analyze the customer's social media activity history and acquire the most relevant actions. In this way, relevant actions can be acquired by analyzing the customer's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI, for example, or without using AI.

[0078] The reference unit can estimate the customer's emotions and adjust how it references the error pattern database based on the estimated emotions. For example, if the customer is stressed, the reference unit will quickly reference the error pattern database. If the customer is relaxed, the reference unit can also reference the error pattern database in the normal way. If the customer is in a hurry, the reference unit can also prioritize referencing the error pattern database. For example, if the customer is stressed, the reference unit will quickly reference the error pattern database. If the customer is relaxed, the reference unit will reference the error pattern database in the normal way. If the customer is in a hurry, the reference unit will prioritize referencing the error pattern database. This allows for quick and appropriate referencing by adjusting how the error pattern database is referenced according to the customer's 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.

[0079] The reference unit can select the optimal reference method by referring to past error pattern data when referencing the error pattern database. For example, the reference unit can select the optimal reference method based on past error patterns. The reference unit can also analyze the customer's past error pattern data and select the most efficient reference method. The reference unit can also select the most relevant reference method by referring to past error pattern data. For example, the reference unit can select the optimal reference method based on past error patterns. The reference unit can analyze the customer's past error pattern data and select the most efficient reference method. The reference unit can select the most relevant reference method by referring to past error pattern data. In this way, the optimal reference method can be selected by referring to past error pattern data. Some or all of the above processing in the reference unit may be performed using AI, for example, or without using AI.

[0080] The reference unit can apply different reference algorithms depending on the customer's action category when referencing the error pattern database. For example, the reference unit applies the optimal reference algorithm based on the customer's action category. The reference unit can also set different reference algorithms for each customer's action category and reference in the most optimal way. The reference unit can also apply the most efficient reference algorithm depending on the customer's action category. For example, the reference unit applies the optimal reference algorithm based on the customer's action category. The reference unit sets different reference algorithms for each customer's action category and references in the most optimal way. The reference unit applies the most efficient reference algorithm depending on the customer's action category. This makes optimal referencing possible by applying different reference algorithms depending on the customer's action category. Some or all of the above processing in the reference unit may be performed using AI, for example, or without using AI.

[0081] The reference unit can estimate the customer's emotions and adjust the frequency of referencing the error pattern database based on the estimated emotions. For example, if the customer is stressed, the reference unit will refer to the error pattern database frequently. If the customer is relaxed, the reference unit can also refer to the error pattern database at a normal frequency. If the customer is in a hurry, the reference unit can also preferentially refer to the error pattern database. For example, if the customer is stressed, the reference unit will refer to the error pattern database frequently. If the customer is relaxed, the reference unit will refer to the error pattern database at a normal frequency. If the customer is in a hurry, the reference unit will preferentially refer to the error pattern database. This allows for quick and appropriate referencing by adjusting the frequency of referencing the error pattern database according to the customer's 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.

[0082] The reference unit can determine the priority of references to the error pattern database based on when the customer's actions were submitted. For example, the reference unit will prioritize referencing the error pattern database if the customer's actions were recently submitted. The reference unit can also determine the optimal priority of references based on when the customer's actions were submitted. If the customer's actions are older, the reference unit can also refer to the error pattern database with normal priority. For example, the reference unit will prioritize referencing the error pattern database if the customer's actions were recently submitted. The reference unit will determine the optimal priority of references based on when the customer's actions were submitted. If the customer's actions are older, the reference unit will refer to the error pattern database with normal priority. This enables quick and appropriate referencing by determining the priority of references based on when the customer's actions were submitted. Some or all of the above processing in the reference unit may be performed using AI, for example, or not using AI.

[0083] The reference unit can improve the accuracy of the reference by referring to customer-related literature when referencing the error pattern database. For example, the reference unit can improve the accuracy of the reference to the error pattern database by referring to customer-related literature. The reference unit can also select the optimal reference method based on customer-related literature. The reference unit can also select the most efficient reference method by referring to customer-related literature. For example, the reference unit can improve the accuracy of the reference to the error pattern database by referring to customer-related literature. The reference unit selects the optimal reference method based on customer-related literature. The reference unit selects the most efficient reference method by referring to customer-related literature. This allows for improved accuracy of the reference by referring to customer-related literature. Some or all of the above processing in the reference unit may be performed using AI, for example, or without using AI.

[0084] The decision-making unit can estimate the customer's emotions and adjust the criteria for determining the likelihood of an inquiry based on the estimated emotions. For example, if the customer is stressed, the decision-making unit will tighten the criteria for determining the likelihood of an inquiry. If the customer is relaxed, the decision-making unit can also determine the likelihood of an inquiry using normal criteria. If the customer is in a hurry, the decision-making unit can also quickly determine the likelihood of an inquiry. For example, if the customer is stressed, the decision-making unit will tighten the criteria for determining the likelihood of an inquiry. If the customer is relaxed, the decision-making unit will determine the likelihood of an inquiry using normal criteria. If the customer is in a hurry, the decision-making unit can quickly determine the likelihood of an inquiry. This allows for more appropriate decisions by adjusting the criteria for determining the likelihood of an inquiry according to the customer's emotions. Emotion estimation is achieved using emotion estimation functions, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] The decision-making unit can improve the accuracy of its judgment by considering the interrelationships of actions when determining the likelihood of an inquiry. For example, the decision-making unit analyzes the interrelationships of customer actions and determines the likelihood of an inquiry. The decision-making unit can also set optimal judgment criteria by considering the interrelationships of actions. The decision-making unit can also select the most efficient judgment method based on the interrelationships of actions. For example, the decision-making unit analyzes the interrelationships of customer actions and determines the likelihood of an inquiry. The decision-making unit sets optimal judgment criteria by considering the interrelationships of actions. The decision-making unit selects the most efficient judgment method based on the interrelationships of actions. In this way, the accuracy of the judgment can be improved by considering the interrelationships of actions. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI.

[0086] The decision-making unit can make decisions by considering customer attribute information when determining the likelihood of an inquiry. For example, the decision-making unit can determine the likelihood of an inquiry based on customer attribute information (age, gender, etc.). The decision-making unit can also set optimal decision criteria by considering customer attribute information. The decision-making unit can also select the most efficient decision-making method based on customer attribute information. For example, the decision-making unit can determine the likelihood of an inquiry based on customer attribute information (age, gender, etc.). The decision-making unit can set optimal decision criteria by considering customer attribute information. The decision-making unit can select the most efficient decision-making method based on customer attribute information. This makes it possible to make more appropriate decisions by considering customer attribute information. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI.

[0087] The decision unit can estimate the customer's emotions and adjust the order in which it displays the likelihood of an inquiry based on the estimated emotions. For example, if the customer is stressed, the decision unit will prioritize displaying important decisions. If the customer is relaxed, the decision unit can also display decisions in the normal order. If the customer is in a hurry, the decision unit can also prioritize displaying decisions that require immediate attention. For example, if the customer is stressed, the decision unit will prioritize displaying important decisions. If the customer is relaxed, the decision unit will display decisions in the normal order. If the customer is in a hurry, the decision unit will prioritize displaying decisions that require immediate attention. This allows for the priority provision of important information by adjusting the display order of decisions according to the customer's 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.

[0088] The decision-making unit can make decisions considering the geographical distribution of actions when determining the likelihood of an inquiry. For example, if customer actions are concentrated in a particular region, the decision-making unit will prioritize determining the likelihood of an inquiry related to that region. The decision-making unit can also set optimal decision criteria based on the geographical distribution of actions. The decision-making unit can also select the most efficient decision-making method considering the geographical distribution of actions. For example, if customer actions are concentrated in a particular region, the decision-making unit will prioritize determining the likelihood of an inquiry related to that region. The decision-making unit will set optimal decision criteria based on the geographical distribution of actions. The decision-making unit will select the most efficient decision-making method considering the geographical distribution of actions. This makes it possible to make appropriate decisions specific to a region by considering the geographical distribution of actions. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or not using AI.

[0089] The decision unit can improve the accuracy of its decision when determining queryability by referring to relevant literature for the action. For example, the decision unit can improve the accuracy of its queryability determination by referring to relevant literature for the action. The decision unit can also set optimal decision criteria based on relevant literature for the action. The decision unit can also select the most efficient decision method by referring to relevant literature for the action. For example, the decision unit can improve the accuracy of its queryability determination by referring to relevant literature for the action. The decision unit can set optimal decision criteria based on relevant literature for the action. The decision unit can select the most efficient decision method by referring to relevant literature for the action. In this way, the accuracy of the decision can be improved by referring to relevant literature for the action. Some or all of the above processing in the decision unit may be performed using AI, for example, or without using AI.

[0090] The execution unit can estimate the customer's emotions and adjust the customer service response based on the estimated emotions. For example, if the customer is stressed, the execution unit will provide a quick and courteous response. If the customer is relaxed, the execution unit can also provide a standard customer service response. If the customer is in a hurry, the execution unit can complete the response quickly. For example, if the customer is stressed, the execution unit will provide a quick and courteous response. If the customer is relaxed, the execution unit will provide a standard customer service response. If the customer is in a hurry, the execution unit will complete the response quickly. This allows for a more appropriate response by adjusting the customer service response according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The execution unit can select the optimal execution method by referring to past customer service response data when executing a customer service response. For example, the execution unit can select the optimal execution method based on past successful customer service response data. The execution unit can also select the most efficient execution method by referring to the customer's past customer service response history. The execution unit can also select the most effective execution method by analyzing past customer service response data. For example, the execution unit can select the optimal execution method based on past successful customer service response data. The execution unit can select the most efficient execution method by referring to the customer's past customer service response history. The execution unit can select the most effective execution method by analyzing past customer service response data. In this way, the optimal execution method can be selected by referring to past customer service response data. Some or all of the above processing in the execution unit may be performed using AI, for example, or without using AI.

[0092] The execution unit can apply different execution algorithms depending on the customer action category when performing CS response. For example, the execution unit applies the optimal execution algorithm based on the customer action category. The execution unit can also set different execution algorithms for each customer action category and perform CS response in the most optimal way. The execution unit can also apply the most efficient execution algorithm depending on the customer action category. For example, the execution unit applies the optimal execution algorithm based on the customer action category. The execution unit sets different execution algorithms for each customer action category and performs CS response in the most optimal way. The execution unit applies the most efficient execution algorithm depending on the customer action category. This makes it possible to perform optimal CS response by applying different execution algorithms depending on the customer action category. Some or all of the above processing in the execution unit may be performed using AI, for example, or without using AI.

[0093] The execution unit can estimate the customer's emotions and adjust the frequency of customer service (CS) responses based on the estimated emotions. For example, if the customer is stressed, the execution unit will perform CS responses more frequently. If the customer is relaxed, the execution unit can also perform CS responses at a normal frequency. If the customer is in a hurry, the execution unit can also perform CS responses only when a quick response is necessary. This allows for quick and appropriate responses by adjusting the frequency of CS responses according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0094] The execution unit can determine the execution priority based on when the customer action was submitted when performing a customer service response. For example, the execution unit will prioritize CS responses if the customer action was recently submitted. The execution unit can also determine the optimal execution priority based on when the customer action was submitted. If the customer action is old, the execution unit can also perform CS responses with the normal priority. For example, the execution unit will prioritize CS responses if the customer action was recently submitted. The execution unit will determine the optimal execution priority based on when the customer action was submitted. If the customer action is old, the execution unit will perform CS responses with the normal priority. This enables a quick and appropriate response by determining the execution priority based on when the customer action was submitted. Some or all of the above processing in the execution unit may be performed using AI, for example, or without using AI.

[0095] The execution unit can improve the accuracy of its execution by referring to relevant customer documentation during CS response execution. For example, the execution unit improves the accuracy of CS response execution by referring to relevant customer documentation. The execution unit can also select the optimal execution method based on relevant customer documentation. The execution unit can also select the most efficient execution method by referring to relevant customer documentation. For example, the execution unit improves the accuracy of CS response execution by referring to relevant customer documentation. The execution unit selects the optimal execution method based on relevant customer documentation. The execution unit selects the most efficient execution method by referring to relevant customer documentation. In this way, the accuracy of execution can be improved by referring to relevant customer documentation. Some or all of the above processing in the execution unit may be performed using AI, for example, or without using AI.

[0096] The notification unit can estimate the customer's emotions and adjust the way notifications are presented based on those emotions. For example, if the customer is stressed, the notification unit will provide a concise and clear notification. If the customer is relaxed, the notification unit can also provide a detailed notification. If the customer is in a hurry, the notification unit can also provide a notification requiring immediate attention. This allows for more appropriate notifications by adjusting the way notifications are presented according to the customer's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0097] The notification unit can select the optimal notification method by referring to the customer's past notification history when sending a notification. For example, the notification unit selects the optimal notification method based on the customer's past notification history. The notification unit can also analyze the customer's past notification history and select the most efficient notification method. The notification unit can also refer to the customer's past notification history and select the most relevant notification method. For example, the notification unit selects the optimal notification method based on the customer's past notification history. The notification unit analyzes the customer's past notification history and selects the most efficient notification method. The notification unit refers to the customer's past notification history and selects the most relevant notification method. This allows the notification unit to select the optimal notification method by referring to the customer's past notification history. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI.

[0098] The notification unit can customize the notification method based on the customer's current situation when a notification is sent. For example, the notification unit may prioritize voice notifications if the customer is on the go. The notification unit may also prioritize email notifications if the customer is in the office. The notification unit may also prioritize app notifications if the customer is at home. For example, the notification unit may prioritize voice notifications if the customer is on the go. The notification unit may prioritize email notifications if the customer is in the office. The notification unit may prioritize app notifications if the customer is at home. This allows for more appropriate notifications by customizing the notification method based on the customer's current situation. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI.

[0099] The notification unit can estimate the customer's emotions and prioritize notifications based on those emotions. For example, if the customer is stressed, the notification unit will prioritize important notifications. If the customer is relaxed, the notification unit can also prioritize notifications that require immediate attention if the customer is in a hurry. For example, if the notification unit is stressed, it will prioritize important notifications. If the customer is relaxed, it will prioritize notifications that require immediate attention if the customer is in a hurry. This allows important notifications to be prioritized by determining the priority of notifications according to the customer's 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.

[0100] The notification unit can select the optimal notification method by considering the customer's geographical location information when sending a notification. For example, if the customer is in a specific region, the notification unit will prioritize notifications related to that region. The notification unit can also prioritize notifications that have occurred in locations close to the customer's current location. The notification unit can also send the most relevant notifications based on the customer's geographical location information. For example, if the customer is in a specific region, the notification unit will prioritize notifications related to that region. The notification unit will prioritize notifications that have occurred in locations close to the customer's current location. The notification unit will send the most relevant notifications based on the customer's geographical location information. In this way, the optimal notification method can be selected by considering the customer's geographical location information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without using AI.

[0101] The notification unit can analyze the customer's social media activity and suggest notification methods when sending notifications. For example, the notification unit can suggest the most suitable notification method based on what the customer has mentioned on social media. The notification unit can also suggest notification methods related to topics of interest based on the customer's social media activity. The notification unit can also analyze the customer's social media activity history and suggest the most relevant notification method. For example, the notification unit can suggest the most suitable notification method based on what the customer has mentioned on social media. The notification unit can suggest notification methods related to topics of interest based on the customer's social media activity. The notification unit can analyze the customer's social media activity history and suggest the most relevant notification method. In this way, the notification unit can suggest the most suitable notification method by analyzing the customer's social media activity. Some or all of the above processing in the notification unit may be performed using AI, for example, or not using AI.

[0102] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0103] The data acquisition unit can select the optimal acquisition method when acquiring customer actions, taking into account the type of device and usage patterns of the customer. For example, if the customer is using a smartphone, the acquisition unit can prioritize acquiring mobile app usage data. If the customer is using a desktop computer, it can also prioritize acquiring website browsing behavior. Furthermore, if the customer is using a tablet, the acquisition unit can acquire actions while considering tablet-specific operations. This allows for more accurate action acquisition by selecting the optimal acquisition method according to the type of device and usage patterns of the customer.

[0104] The acquisition unit can estimate the customer's emotions and customize how it takes action based on those emotions. For example, if the customer is feeling anxious, the acquisition unit can take action while providing detailed guidance. If the customer is excited, it can take action quickly and move on to the next step. Furthermore, if the customer is calm, the acquisition unit can take action using the standard acquisition method. This allows for more appropriate responses by customizing how action is taken according to the customer's emotions.

[0105] The reference unit can select the optimal reference method when referencing the error pattern database, taking into account the customer's past error pattern resolution history. For example, if the reference unit has experienced a similar error pattern in the past, it will prioritize referencing that solution. If the customer is experiencing the error pattern for the first time, it can also refer to general solutions. Furthermore, the reference unit can analyze the customer's past error pattern resolution history and select the most efficient reference method. This allows for the selection of the optimal reference method by considering the customer's past error pattern resolution history.

[0106] The reference unit can estimate the customer's emotions when referencing the error pattern database and prioritize the references based on those emotions. For example, if the customer is stressed, the reference unit will prioritize referencing error patterns that require quick resolution. If the customer is relaxed, it can refer to the normal priority list. Furthermore, if the customer is in a hurry, the reference unit can also prioritize referencing error patterns that require immediate attention. This allows for quick and appropriate referencing by prioritizing the references according to the customer's emotions.

[0107] The decision-making unit can improve the accuracy of its judgment by considering the frequency of customer actions when determining the likelihood of an inquiry. For example, the decision-making unit can set a high likelihood of an inquiry for actions that customers perform frequently, and a low likelihood for actions that customers perform rarely. Furthermore, the decision-making unit can analyze the frequency of customer actions and set the most efficient judgment criteria. This improves the accuracy of the judgment by considering the frequency of customer actions.

[0108] The decision-making unit can estimate the customer's emotions and adjust how it displays the likelihood of an inquiry based on those emotions. For example, if the customer is stressed, the unit will highlight important decisions. If the customer is relaxed, the unit can display the decisions in the normal way. Furthermore, if the customer is in a hurry, the unit can make decisions requiring immediate attention stand out. This allows for the effective communication of important information by adjusting how decisions are displayed according to the customer's emotions.

[0109] The execution unit can apply different response methods depending on the type of customer action when performing customer service (CS) responses. For example, if a customer makes a purchase, the execution unit can prioritize providing support related to the purchase. If a customer makes an inquiry, it can also prioritize providing support related to the inquiry. Furthermore, if a customer browses a website, the execution unit can provide support related to browsing. This allows for more effective CS responses by applying the most appropriate response method according to the type of customer action.

[0110] The execution unit can estimate the customer's emotions and select the appropriate customer service response based on those emotions. For example, if the customer is stressed, the execution unit will prioritize direct communication methods such as phone calls or chats. If the customer is relaxed, it can also select indirect methods such as emails or app notifications. Furthermore, if the customer is in a hurry, the execution unit can select a method that allows for a quick response. This enables more appropriate customer service by selecting the optimal response method according to the customer's emotions.

[0111] The notification unit can adjust the content of notifications based on the importance of the customer's action. For example, if a customer takes an important action, the notification unit can provide a detailed notification. If a customer takes a general action, it can provide a concise notification. Furthermore, the notification unit can analyze the importance of the customer's action and select the most appropriate notification content. This allows for more effective notifications by adjusting the content according to the importance of the customer's action.

[0112] The notification unit can estimate the customer's emotions and adjust the timing of notifications based on those emotions. For example, if the customer is stressed, the notification unit will send a notification quickly. If the customer is relaxed, the notification can be slightly delayed. Furthermore, if the customer is in a hurry, the notification unit can send a notification immediately. This allows for notifications to be delivered at a more appropriate time by adjusting the timing according to the customer's emotions.

[0113] The following briefly describes the processing flow for example form 2.

[0114] Step 1: The acquisition unit retrieves customer actions. Customer actions include purchase behavior, inquiry behavior, website browsing behavior, etc. For example, the acquisition unit retrieves actions taken when a customer views products on the website, actions taken when adding products to the cart, and content entered into an inquiry form. Step 2: The reference unit looks up the error pattern database based on the actions obtained by the acquisition unit. The error pattern database contains past error patterns and how to deal with them. The reference unit searches the error pattern database and identifies the relevant error pattern. The error pattern database can also be updated periodically and automatically. Step 3: The decision unit determines query feasibility based on the error pattern referenced by the reference unit. Query feasibility is determined based on the degree of matching of the error pattern and the customer's past query history. For example, the decision unit calculates the degree of matching of the error pattern, references the customer's past query history, and combines these to determine query feasibility. Step 4: The execution unit performs customer service (CS) support if the decision unit determines that there is a possibility of an inquiry. CS support includes telephone support, email support, and chat support. For example, the execution unit may call the customer, send an email, or chat with them. Step 5: The notification unit notifies the customer of the results of the CS response performed by the execution unit. Notifications may include email, SMS, and app notifications. For example, the notification unit may notify the customer of the results via email, SMS, and app notifications.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] Each of the multiple elements described above, including the acquisition unit, reference unit, decision unit, execution unit, and notification unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit is implemented by the control unit 46A of the smart device 14 and acquires customer actions. The reference unit is implemented by the identification processing unit 290 of the data processing device 12 and refers to the error pattern database. The decision unit is implemented by the identification processing unit 290 of the data processing device 12 and determines the possibility of querying. The execution unit is implemented by the control unit 46A of the smart device 14 and performs customer service response. The notification unit is implemented by the control unit 46A of the smart device 14 and notifies the customer of the result of the customer service response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0119] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] Each of the multiple elements described above, including the acquisition unit, reference unit, decision unit, execution unit, and notification unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit is implemented by the control unit 46A of the smart glasses 214 and acquires customer actions. The reference unit is implemented by the identification processing unit 290 of the data processing device 12 and refers to the error pattern database. The decision unit is implemented by the identification processing unit 290 of the data processing device 12 and determines query feasibility. The execution unit is implemented by the control unit 46A of the smart glasses 214 and performs customer service response. The notification unit is implemented by the control unit 46A of the smart glasses 214 and notifies the customer of the results of the customer service response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0135] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] Each of the multiple elements described above, including the acquisition unit, reference unit, decision unit, execution unit, and notification unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the acquisition unit is implemented by the control unit 46A of the headset terminal 314 and acquires customer actions. The reference unit is implemented by the identification processing unit 290 of the data processing device 12 and refers to the error pattern database. The decision unit is implemented by the identification processing unit 290 of the data processing device 12 and determines the possibility of querying. The execution unit is implemented by the control unit 46A of the headset terminal 314 and performs customer service response. The notification unit is implemented by the control unit 46A of the headset terminal 314 and notifies the customer of the result of the customer service response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0151] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] Each of the multiple elements described above, including the acquisition unit, reference unit, decision unit, execution unit, and notification unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit is implemented by the control unit 46A of the robot 414 and acquires customer actions. The reference unit is implemented by the identification processing unit 290 of the data processing unit 12 and refers to the error pattern database. The decision unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines query feasibility. The execution unit is implemented by the control unit 46A of the robot 414 and performs customer service response. The notification unit is implemented by the control unit 46A of the robot 414 and notifies the customer of the results of the customer service response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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."

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] (Note 1) The acquisition unit retrieves customer actions, A reference unit that refers to an error pattern database based on the actions obtained by the acquisition unit, A determination unit that determines the possibility of querying based on the error pattern referenced by the aforementioned reference unit, An execution unit that performs CS response when the aforementioned determination unit determines that there is a possibility of inquiry, The system includes a notification unit that notifies the customer of the results of the CS response performed by the execution unit. A system characterized by the following features. (Note 2) The aforementioned reference section is, Automatically update the error pattern database. The system described in Appendix 1, characterized by the features described herein. (Note 3) The acquisition unit is, We estimate customer emotions and adjust the timing of actions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The acquisition unit is, Analyze the customer's past action history and select the optimal method for acquiring that information. The system described in Appendix 1, characterized by the features described herein. (Note 5) The acquisition unit is, When retrieving actions, filtering is performed based on the customer's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 6) The acquisition unit is, Estimate customer emotions and prioritize actions to take based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, When retrieving actions, the system prioritizes retrieving highly relevant actions by considering the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, When capturing an action, we analyze the customer's social media activity and capture relevant actions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reference section is, We estimate customer emotions and adjust how we refer to the error pattern database based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reference section is, When referencing the error pattern database, the system selects the optimal referencing method by referring to past error pattern data. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reference section is, When referencing the error pattern database, different reference algorithms are applied depending on the customer's action category. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reference section is, We estimate customer emotions and adjust the frequency of references to the error pattern database based on the estimated customer emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reference section is, When referencing the error pattern database, the priority of the reference is determined based on when the customer's actions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reference section is, When referencing the error pattern database, we improve the accuracy of the reference by referring to relevant customer documentation. The system described in Appendix 1, characterized by the features described herein. (Note 15) The unit that makes the determination said, We estimate customer sentiment and adjust the criteria for determining the likelihood of an inquiry based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The unit that makes the determination said, When determining the likelihood of an inquiry, consider the interrelationships between actions to improve the accuracy of the decision. The system described in Appendix 1, characterized by the features described herein. (Note 17) The unit that makes the determination said, When determining the likelihood of an inquiry, the customer's attribute information is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 18) The unit that makes the determination said, The system estimates customer sentiment and adjusts the order in which the results of the inquiry likelihood assessment are displayed based on the estimated customer sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The unit that makes the determination said, When determining the likelihood of an inquiry, the geographical distribution of actions should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 20) The unit that makes the determination said, When determining the likelihood of an inquiry, refer to relevant literature related to the action to improve the accuracy of the decision. The system described in Appendix 1, characterized by the features described herein. (Note 21) The execution unit is, We estimate customer emotions and adjust how we implement customer service responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The execution unit is, When performing CS (Customer Satisfaction) support, the optimal execution method is selected by referring to past CS support data. The system described in Appendix 1, characterized by the features described herein. (Note 23) The execution unit is, When performing customer service (CS) support, different execution algorithms are applied depending on the customer's action category. The system described in Appendix 1, characterized by the features described herein. (Note 24) The execution unit is, The system estimates customer emotions and adjusts the frequency of customer service responses based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The execution unit is, When implementing customer support (CS) responses, prioritize actions based on when the customer submitted their actions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The execution unit is, When implementing customer support (CS) measures, we improve the accuracy of the implementation by referring to relevant customer documentation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned notification unit, We estimate customer emotions and adjust the way notifications are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned notification unit, When sending a notification, the system will refer to the customer's past notification history to select the most suitable notification method. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned notification unit, When sending notifications, customize the notification method based on the customer's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned notification unit, It estimates customer emotions and prioritizes notifications based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned notification unit, When sending notifications, the system will select the most suitable notification method, taking into account the customer's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned notification unit, When sending notifications, we analyze the customer's social media activity and suggest notification methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0187] 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 acquisition unit retrieves customer actions, A reference unit that refers to an error pattern database based on the actions obtained by the acquisition unit, A determination unit that determines the possibility of querying based on the error pattern referenced by the aforementioned reference unit, An execution unit that performs CS response when the aforementioned determination unit determines that there is a possibility of inquiry, The system includes a notification unit that notifies the customer of the results of the CS response performed by the execution unit. A system characterized by the following features.

2. The aforementioned reference section is, Automatically update the error pattern database. The system according to feature 1.

3. The acquisition unit is, We estimate customer emotions and adjust the timing of actions based on those estimated emotions. The system according to feature 1.

4. The acquisition unit is, Analyze the customer's past action history and select the optimal method for acquiring that information. The system according to feature 1.

5. The acquisition unit is, When retrieving actions, filtering is performed based on the customer's current situation and areas of interest. The system according to feature 1.

6. The acquisition unit is, Estimate customer emotions and prioritize actions to take based on those estimated emotions. The system according to feature 1.

7. The acquisition unit is, When retrieving actions, the system prioritizes retrieving highly relevant actions by considering the customer's geographical location. The system according to feature 1.

8. The acquisition unit is, When capturing an action, we analyze the customer's social media activity and capture relevant actions. The system according to feature 1.

9. The aforementioned reference section is, We estimate customer emotions and adjust how we refer to the error pattern database based on those estimated emotions. The system according to feature 1.

Images