system

Abstract

The system according to this embodiment aims to learn operation data and identify and optimize efficient workflows. [Solution] The system according to the embodiment comprises a collection unit, a learning unit, a reinforcement learning unit, and a provision unit. The collection unit collects operation data. The learning unit learns the operation data collected by the collection unit and identifies an efficient flow. The reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the learning unit and finds the optimal flow. The provision unit provides the flow optimized by the reinforcement learning unit.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , , ,

[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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, an efficient flow has not been sufficiently identified and optimized based on operation data, and there is room for improvement.

[0005] The system according to the embodiment aims to learn operation data and identify and optimize an efficient flow.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a learning unit, a reinforcement learning unit, and a provision unit. The collection unit collects operation data. The learning unit learns from the operation data collected by the collection unit and identifies an efficient flow. The reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the learning unit and finds the optimal flow. The provision unit provides the flow optimized by the reinforcement learning unit. [Effects of the Invention]

[0007] The system according to this embodiment can learn operation data and identify and optimize efficient workflows. [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 including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

[0017] As shown in FIG. 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 reception 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 reception 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 system according to an embodiment of the present invention is a system that learns the operations of people performing the same response, identifies the most efficient flow, and performs reinforcement learning and flow optimization. This system collects the operations of the same response performed by multiple people, and the AI ​​learns each flow. Next, the AI ​​identifies the most efficient flow from among the learned flows and identifies the differences between flows. Furthermore, it optimizes the flow using reinforcement learning to provide an efficient flow. This mechanism improves the efficiency of responses. For example, the system collects the operations of the same response performed by multiple people. In this process, detailed data such as each person's operation procedure, time, and results are collected. For example, in customer support, data such as each operator's response procedure, response time, and customer satisfaction are collected. This allows for a detailed understanding of each person's flow. Next, the AI ​​learns from the collected data. The AI ​​analyzes the collected data and learns each flow. For example, the AI ​​analyzes each operator's response procedure and identifies which procedure is efficient. This allows for the identification of the most efficient flow. Furthermore, the AI ​​identifies the most efficient flow from among the learned flows and identifies the differences between flows. For example, the AI ​​compares the response procedures of each operator and identifies the differences between efficient and inefficient procedures. This allows for the identification of efficient flows. Finally, reinforcement learning is used to optimize the flow. The AI ​​uses reinforcement learning based on the efficient flow to find an even more optimal flow. For example, the AI ​​performs simulations based on efficient procedures to find the optimal procedure. This improves the efficiency of responses. This mechanism allows the system to learn the operations of people performing the same response, identify the most efficient flow, and perform reinforcement learning and flow optimization. This improves the efficiency of responses and increases business productivity. This allows the system to learn the operations of people performing the same response, identify the most efficient flow, and perform reinforcement learning and flow optimization. This improves the efficiency of responses and increases business productivity.

[0029] The system according to this embodiment comprises a collection unit, a learning unit, a reinforcement learning unit, and a provision unit. The collection unit collects operation data. The collection unit can collect, for example, user click data, input data, operation logs, etc. The collection unit can also collect detailed data such as operation procedures, operation time, results, and feedback. The learning unit learns the operation data collected by the collection unit and identifies an efficient flow. The learning unit can analyze the data using, for example, data mining techniques or statistical analysis techniques to identify an efficient flow. The reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the learning unit to find the optimal flow. The reinforcement learning unit can perform simulations using, for example, the Monte Carlo method or agent-based simulation to find the optimal flow. The provision unit provides the flow optimized by the reinforcement learning unit. The provision unit can provide an optimized flow using, for example, user interface design or notification methods. As a result, the system improves the efficiency of its response by collecting operation data, identifying an efficient flow, performing reinforcement learning, and providing the optimal flow.

[0030] The data collection unit collects operational data. For example, it can collect user click data, input data, and operation logs. Specifically, it collects all interaction data that occurs when a user interacts with a website or application. Click data records in detail which buttons or links the user clicked, the timing and frequency of clicks, etc. Input data collects text and numerical data entered by the user into forms or search bars. Operation logs record in detail the user's operation steps, operation time, operation results, and the circumstances under which errors occurred. Furthermore, the data collection unit can also collect detailed data such as operation steps, operation time, results, and feedback. For example, it can collect the steps and time taken for a user to complete a specific task, the success and failure rates of the task, and feedback comments from the user. This allows the data collection unit to collect comprehensive data on user interactions and provide information necessary for subsequent analysis and learning. The collected data is transmitted in real time to a central database and used in conjunction with other departments and systems. For example, the data collection unit can adjust the frequency and accuracy of data collection to enable flexible responses to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0031] The learning unit learns from the operation data collected by the collection unit and identifies efficient flows. The learning unit can analyze the data using, for example, data mining and statistical analysis techniques to identify efficient flows. Specifically, it preprocesses the collected operation data, performing data cleaning and normalization. Next, it uses data mining techniques to extract patterns and trends from the operation data. For example, it identifies frequently used operation procedures and patterns that reduce operation time. It also uses statistical analysis techniques to analyze the distribution and correlations of the operation data and identify efficient flows. For example, it analyzes the relationship between operation procedures and operation results to identify operation procedures with a high success rate. Furthermore, the learning unit uses machine learning algorithms to build models that predict efficient flows from the operation data. For example, it uses algorithms such as decision trees, random forests, and support vector machines to classify the operation data and identify efficient flows. This allows the learning unit to identify efficient flows based on the collected operation data, thereby improving the overall system efficiency. Moreover, the learning unit continuously evaluates the identified efficient flows and updates the model as needed, ensuring that it always provides efficient flows based on the latest data.

[0032] The reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the learning unit to find the optimal flow. For example, the reinforcement learning unit can find the optimal flow by performing simulations using methods such as Monte Carlo or agent-based simulation. Specifically, using a reinforcement learning algorithm, the agent learns the optimal flow through trial and error. The agent receives a reward for each step of the operation flow and adjusts its actions to maximize that reward. For example, using the Monte Carlo method, the agent simulates multiple operation flows and evaluates the reward for each flow. The flow with the highest reward is identified as the optimal flow. Alternatively, using agent-based simulation, the agent executes the operation flow in a virtual environment to find the optimal flow. This allows the reinforcement learning unit to find an even more optimal flow based on the efficient flow identified by the learning unit. Furthermore, based on the simulation results, the reinforcement learning unit can identify areas for improvement and optimization in the operation flow, thereby improving the overall system efficiency. By continuously performing simulations and optimizing the operation flow, the reinforcement learning unit can always provide the optimal flow based on the latest data.

[0033] The service provider provides a flow optimized by the reinforcement learning unit. For example, the service provider can provide an optimized flow using user interface design and notification methods. Specifically, it designs an intuitive user interface to present the optimized flow clearly to the user. For example, it provides a visual guide showing the operation procedure and a dashboard that displays the progress of the operation in real time. It also provides notifications at appropriate times to make it easier for users to follow the operation flow. For example, it displays a pop-up notification at each step of the operation procedure to guide the user to the next action. Furthermore, the service provider collects user feedback and continuously evaluates the accuracy and effectiveness of the optimized flow. For example, it conducts a survey after the user completes the operation flow to evaluate the difficulty of the operation and satisfaction. The service provider can also reliably transmit information using multiple communication methods. For example, it uses not only user interface notifications but also email, SMS, and push notifications to ensure important information is delivered reliably. This allows the service provider to quickly and reliably provide the optimized flow to users, improving operational efficiency. Furthermore, the data provisioning unit can collect user operation data again and work in conjunction with the data collection unit, learning unit, and reinforcement learning unit to improve the overall system performance.

[0034] The data collection unit can collect detailed data such as operation procedures, operation time, results, and feedback. For example, the data collection unit can collect user click data and input data as a method of recording operation procedures. The data collection unit can also collect operation logs to record operation time. Furthermore, the data collection unit can use surveys and evaluation systems to collect results and feedback. This allows for more accurate learning by collecting detailed data. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user click data into an AI, which can then analyze the data and record the operation procedures.

[0035] The learning unit can analyze the collected data and identify efficient workflows. For example, the learning unit can analyze the data using data mining techniques to identify efficient workflows. It can also analyze the data using statistical analysis techniques to identify efficient workflows. Furthermore, it can analyze the data using machine learning algorithms to identify efficient workflows. Thus, efficient workflows can be identified by analyzing the data. Some or all of the above-described processes in the learning unit may be performed using AI, or they may not. For example, the learning unit can input the collected data into an AI, which can then analyze the data and identify efficient workflows.

[0036] The reinforcement learning unit can find the optimal flow by performing simulations based on an efficient flow. For example, the reinforcement learning unit can find the optimal flow by performing simulations using the Monte Carlo method. It can also find the optimal flow by performing simulations using agent-based simulation. Furthermore, it can find the optimal flow by performing simulations using reinforcement learning algorithms. Thus, the optimal flow can be found through simulation. Some or all of the above-described processes in the reinforcement learning unit may be performed using AI, or they may be performed without AI. For example, the reinforcement learning unit can input an efficient flow into the AI, which can then perform simulations to find the optimal flow.

[0037] The service provider can provide an optimized flow. For example, the service provider can provide an optimized flow using user interface design. The service provider can also provide an optimized flow using notification methods. Furthermore, the service provider can provide an optimized flow using dashboards. This allows for more efficient responses by providing an optimized flow. Some or all of the above processes in the service provider may be performed using AI or not. For example, the service provider can input an optimized flow into an AI, which can then design a user interface and provide the flow.

[0038] The data collection unit can analyze the user's past operation history and select the optimal data collection method when collecting operation data. For example, the data collection unit can prioritize collecting operations that the user has frequently performed in the past. The data collection unit can also focus on collecting data for specific operations from the user's past operation history. Furthermore, the data collection unit can analyze the user's operation history and propose an efficient method for collecting operation data. This allows the optimal data collection method to be selected by analyzing past operation history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's operation history data into an AI, which can then analyze the data and select the optimal data collection method.

[0039] The data collection unit can filter operation data based on the user's current work status and areas of interest. For example, the data collection unit prioritizes collecting operation data related to the task the user is currently performing. The data collection unit can also filter and collect relevant operation data based on the user's areas of interest. Furthermore, the data collection unit can grasp the user's work status in real time and collect the most relevant operation data. This allows for the collection of highly relevant data by filtering based on the current work status and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user work status data into AI, which can then filter the data to collect the most relevant operation data.

[0040] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location when collecting operation data. For example, if the user is in a specific region, the data collection unit will prioritize the collection of operation data related to that region. The data collection unit can also filter and collect highly relevant operation data based on the user's location information. Furthermore, if the user is on the move, the data collection unit can collect the most relevant operation data based on their current location. This allows for the collection of highly relevant data by considering geographical location information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's location data into an AI, which can then analyze the data and collect highly relevant operation data.

[0041] The data collection unit can analyze the user's social media activity and collect relevant data when collecting operational data. For example, the data collection unit can analyze the content of the user's social media posts and collect relevant operational data. The data collection unit can also collect operational data related to the user's interests based on the user's social media activity history. Furthermore, the data collection unit can collect relevant operational data by referring to the activities of the user's social media followers and friends. In this way, relevant data can be collected by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's social media data into AI, and the AI ​​can analyze the data and collect relevant operational data.

[0042] The learning unit can adjust the level of detail during learning based on the importance of the operation data. For example, the learning unit will perform detailed learning for operation data with high importance. It can also perform simplified learning for operation data with low importance. Furthermore, the learning unit can determine the priority of learning according to the importance of the operation data. This allows for efficient learning by adjusting the level of detail based on the importance of the operation data. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the importance of the operation data into the AI, and the AI ​​can analyze the data and adjust the level of detail of learning.

[0043] The learning unit can apply different learning algorithms depending on the category of the operation data during training. For example, the learning unit can apply a natural language processing algorithm to customer support operation data. It can also apply a machine learning algorithm to technical support operation data. Furthermore, it can apply a data mining algorithm to sales support operation data. By applying different learning algorithms depending on the category of operation data, more appropriate learning becomes possible. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the category of operation data into the AI, and the AI ​​can analyze the data and apply an appropriate learning algorithm.

[0044] The learning unit can determine the learning priority based on the timing of operation data collection during the learning process. For example, the learning unit prioritizes learning the most recent operation data. It can also prioritize the latest data while referring to past operation data. Furthermore, the learning unit can dynamically adjust the learning priority according to the timing of operation data collection. This makes it possible to prioritize learning based on the timing of operation data collection, thereby emphasizing the latest data. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the timing of operation data collection into the AI, and the AI ​​can analyze the data to determine the learning priority.

[0045] The learning unit can adjust the learning order based on the relevance of the operation data during learning. For example, the learning unit prioritizes learning highly relevant operation data. It can also postpone learning less relevant operation data. Furthermore, the learning unit can dynamically adjust the learning order according to the relevance of the operation data. This allows for efficient learning by adjusting the learning order based on the relevance of the operation data. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the relevance of the operation data into the AI, and the AI ​​can analyze the data and adjust the learning order.

[0046] The reinforcement learning unit can improve the accuracy of reinforcement learning by considering the interrelationships of the manipulated data during reinforcement learning. For example, the reinforcement learning unit can analyze the interrelationships of the manipulated data and perform reinforcement learning based on the related data. The reinforcement learning unit can also adjust the reinforcement learning algorithm by considering the interrelationships of the manipulated data. Furthermore, the reinforcement learning unit can provide reinforcement learning feedback based on the interrelationships of the manipulated data. As a result, the accuracy of reinforcement learning is improved by considering the interrelationships of the manipulated data. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input the interrelationships of the manipulated data into the AI, and the AI ​​can analyze the data to improve the accuracy of reinforcement learning.

[0047] The reinforcement learning unit can perform reinforcement learning while considering the attribute information of the data submitter. For example, the reinforcement learning unit can adjust the reinforcement learning criteria by considering the data submitter's years of experience. It can also adjust the reinforcement learning algorithm by considering the data submitter's job title. Furthermore, the reinforcement learning unit can provide reinforcement learning feedback by considering the data submitter's skill level. This allows for more appropriate reinforcement learning by considering the submitter's attribute information. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input the data submitter's attribute information into AI, and the AI ​​can analyze the data and perform reinforcement learning.

[0048] The reinforcement learning unit can perform reinforcement learning while considering the geographical distribution of the manipulation data. For example, the reinforcement learning unit can analyze the geographical distribution of the manipulation data and perform reinforcement learning while considering the characteristics of each region. The reinforcement learning unit can also adjust the reinforcement learning algorithm based on the geographical distribution of the manipulation data. Furthermore, the reinforcement learning unit can provide reinforcement learning feedback while considering the geographical distribution of the manipulation data. This makes it possible to perform reinforcement learning that is tailored to the characteristics of each region by considering the geographical distribution. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input the geographical distribution of the manipulation data into the AI, and the AI ​​can analyze the data and perform reinforcement learning.

[0049] The reinforcement learning unit can improve the accuracy of reinforcement learning by referring to relevant literature on the manipulation data during reinforcement learning. For example, the reinforcement learning unit can refer to relevant literature on the manipulation data and perform reinforcement learning based on the latest knowledge. The reinforcement learning unit can also adjust the reinforcement learning algorithm based on the relevant literature on the manipulation data. Furthermore, the reinforcement learning unit can provide reinforcement learning feedback considering the relevant literature on the manipulation data. This makes it possible to perform reinforcement learning based on the latest knowledge by referring to relevant literature. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input relevant literature on the manipulation data into AI, and the AI ​​can analyze the literature to improve the accuracy of reinforcement learning.

[0050] The service provider can provide the optimal flow by referring to the user's past operation history at the time of delivery. For example, the service provider can prioritize providing flows that the user has frequently used in the past. The service provider can also analyze the user's past operation history and suggest the optimal flow. Furthermore, the service provider can provide an efficient flow based on the user's operation history. In this way, the optimal flow can be provided by referring to past operation history. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's operation history data into AI, and the AI ​​can analyze the data to provide the optimal flow.

[0051] The service provider can provide the optimal workflow at the time of delivery, taking into account the user's current work status. For example, the service provider can prioritize providing workflows related to the work the user is currently performing. The service provider can also grasp the user's work status in real time and provide the optimal workflow. Furthermore, the service provider can provide efficient workflows according to the user's work status. In this way, the service provider can provide the optimal workflow by taking into account the current work status. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user work status data into AI, and the AI ​​can analyze the data to provide the optimal workflow.

[0052] The service provider can provide an optimal flow by considering the user's device information at the time of delivery. For example, if the user is using a smartphone, the service provider can provide a flow that matches the screen size. Furthermore, if the user is using a tablet, the service provider can provide a flow optimized for a larger screen. In addition, if the user is using a desktop, the service provider can provide a detailed flow. This allows for the provision of an optimal flow by considering device information. Some or all of the above processing in the service provider may be performed using AI, or not. For example, the service provider can input the user's device information into an AI, which can then analyze the data to provide an optimal flow.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The data collection unit can acquire and collect the user's biometric information along with the user's operation data. For example, it can acquire biometric information such as the user's heart rate and skin electrical response and collect it in association with the operation data. The data collection unit can also monitor the user's biometric information in real time and temporarily stop collecting operation data if an abnormality is detected. Furthermore, the data collection unit can adjust the frequency of operation data collection based on the user's biometric information. This allows for more accurate data collection by taking the user's biometric information into consideration.

[0055] The reinforcement learning unit, when performing simulations based on an efficient flow, can refer to the user's past operation history and consider past successes and failures. For example, it can prioritize incorporating previously successful procedures into the simulation. It can also exclude previously failed procedures from the simulation. Furthermore, it can adjust the simulation parameters based on past operation history. This allows for more accurate simulations by considering past operation history.

[0056] The data collection unit can adjust its collection method when collecting operation data, taking into account the user's device information. For example, if the user is using a smartphone, the frequency of operation data collection can be increased. If the user is using a tablet, a collection method optimized for the larger screen can be adopted. Furthermore, if the user is using a desktop computer, detailed operation data can be collected. This allows for the selection of the optimal collection method by considering device information.

[0057] The learning unit can adjust its learning algorithm when analyzing collected operation data, taking into account the user's geographical location. For example, it can prioritize learning operation data from a specific region. It can also adjust the learning algorithm considering the characteristics of each region. Furthermore, it can determine the learning priority based on geographical location information. This makes it possible to perform learning tailored to the characteristics of each region by considering geographical location information.

[0058] The service provider can refer to the user's past operation history when providing optimized flows and prioritize providing flows that have been used in the past. For example, it can prioritize providing flows that the user has frequently used in the past. It can also prioritize providing flows that have been successful in the past. Furthermore, it can suggest the optimal flow based on past operation history. In this way, the optimal flow can be provided by referring to past operation history.

[0059] The data collection unit can analyze the user's social media activity and collect relevant data when collecting operational data. For example, it can analyze the content of the user's social media posts and collect relevant operational data. It can also collect operational data related to the user's interests based on their social media activity history. Furthermore, it can collect relevant operational data by referring to the activities of the user's social media followers and friends. In this way, relevant data can be collected by analyzing social media activity.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The collection unit collects operation data. The collection unit can collect, for example, user click data, input data, and operation logs. It can also collect detailed data such as operation procedures, operation time, results, and feedback. Step 2: The learning unit learns from the operational data collected by the collection unit and identifies efficient workflows. The learning unit can analyze the data using, for example, data mining techniques or statistical analysis techniques to identify efficient workflows. Step 3: The reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the learning unit to find the optimal flow. The reinforcement learning unit can find the optimal flow by performing simulations, for example, using the Monte Carlo method or agent-based simulation. Step 4: The provider unit provides the optimized flow, which is then optimized by the reinforcement learning unit. The provider unit can, for example, provide an optimized flow using user interface design and notification methods.

[0062] (Example of form 2) The system according to an embodiment of the present invention is a system that learns the operations of people performing the same response, identifies the most efficient flow, and performs reinforcement learning and flow optimization. This system collects the operations of the same response performed by multiple people, and the AI ​​learns each flow. Next, the AI ​​identifies the most efficient flow from among the learned flows and identifies the differences between flows. Furthermore, it optimizes the flow using reinforcement learning to provide an efficient flow. This mechanism improves the efficiency of responses. For example, the system collects the operations of the same response performed by multiple people. In this process, detailed data such as each person's operation procedure, time, and results are collected. For example, in customer support, data such as each operator's response procedure, response time, and customer satisfaction are collected. This allows for a detailed understanding of each person's flow. Next, the AI ​​learns from the collected data. The AI ​​analyzes the collected data and learns each flow. For example, the AI ​​analyzes each operator's response procedure and identifies which procedure is efficient. This allows for the identification of the most efficient flow. Furthermore, the AI ​​identifies the most efficient flow from among the learned flows and identifies the differences between flows. For example, the AI ​​compares the response procedures of each operator and identifies the differences between efficient and inefficient procedures. This allows for the identification of efficient flows. Finally, reinforcement learning is used to optimize the flow. The AI ​​uses reinforcement learning based on the efficient flow to find an even more optimal flow. For example, the AI ​​performs simulations based on efficient procedures to find the optimal procedure. This improves the efficiency of responses. This mechanism allows the system to learn the operations of people performing the same response, identify the most efficient flow, and perform reinforcement learning and flow optimization. This improves the efficiency of responses and increases business productivity. This allows the system to learn the operations of people performing the same response, identify the most efficient flow, and perform reinforcement learning and flow optimization. This improves the efficiency of responses and increases business productivity.

[0063] The system according to this embodiment comprises a collection unit, a learning unit, a reinforcement learning unit, and a provision unit. The collection unit collects operation data. The collection unit can collect, for example, user click data, input data, operation logs, etc. The collection unit can also collect detailed data such as operation procedures, operation time, results, and feedback. The learning unit learns the operation data collected by the collection unit and identifies an efficient flow. The learning unit can analyze the data using, for example, data mining techniques or statistical analysis techniques to identify an efficient flow. The reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the learning unit to find the optimal flow. The reinforcement learning unit can perform simulations using, for example, the Monte Carlo method or agent-based simulation to find the optimal flow. The provision unit provides the flow optimized by the reinforcement learning unit. The provision unit can provide an optimized flow using, for example, user interface design or notification methods. As a result, the system improves the efficiency of its response by collecting operation data, identifying an efficient flow, performing reinforcement learning, and providing the optimal flow.

[0064] The data collection unit collects operational data. For example, it can collect user click data, input data, and operation logs. Specifically, it collects all interaction data that occurs when a user interacts with a website or application. Click data records in detail which buttons or links the user clicked, the timing and frequency of clicks, etc. Input data collects text and numerical data entered by the user into forms or search bars. Operation logs record in detail the user's operation steps, operation time, operation results, and the circumstances under which errors occurred. Furthermore, the data collection unit can also collect detailed data such as operation steps, operation time, results, and feedback. For example, it can collect the steps and time taken for a user to complete a specific task, the success and failure rates of the task, and feedback comments from the user. This allows the data collection unit to collect comprehensive data on user interactions and provide information necessary for subsequent analysis and learning. The collected data is transmitted in real time to a central database and used in conjunction with other departments and systems. For example, the data collection unit can adjust the frequency and accuracy of data collection to enable flexible responses to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0065] The learning unit learns from the operation data collected by the collection unit and identifies efficient flows. The learning unit can analyze the data using, for example, data mining and statistical analysis techniques to identify efficient flows. Specifically, it preprocesses the collected operation data, performing data cleaning and normalization. Next, it uses data mining techniques to extract patterns and trends from the operation data. For example, it identifies frequently used operation procedures and patterns that reduce operation time. It also uses statistical analysis techniques to analyze the distribution and correlations of the operation data and identify efficient flows. For example, it analyzes the relationship between operation procedures and operation results to identify operation procedures with a high success rate. Furthermore, the learning unit uses machine learning algorithms to build models that predict efficient flows from the operation data. For example, it uses algorithms such as decision trees, random forests, and support vector machines to classify the operation data and identify efficient flows. This allows the learning unit to identify efficient flows based on the collected operation data, thereby improving the overall system efficiency. Moreover, the learning unit continuously evaluates the identified efficient flows and updates the model as needed, ensuring that it always provides efficient flows based on the latest data.

[0066] The reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the learning unit to find the optimal flow. For example, the reinforcement learning unit can find the optimal flow by performing simulations using methods such as Monte Carlo or agent-based simulation. Specifically, using a reinforcement learning algorithm, the agent learns the optimal flow through trial and error. The agent receives a reward for each step of the operation flow and adjusts its actions to maximize that reward. For example, using the Monte Carlo method, the agent simulates multiple operation flows and evaluates the reward for each flow. The flow with the highest reward is identified as the optimal flow. Alternatively, using agent-based simulation, the agent executes the operation flow in a virtual environment to find the optimal flow. This allows the reinforcement learning unit to find an even more optimal flow based on the efficient flow identified by the learning unit. Furthermore, based on the simulation results, the reinforcement learning unit can identify areas for improvement and optimization in the operation flow, thereby improving the overall system efficiency. By continuously performing simulations and optimizing the operation flow, the reinforcement learning unit can always provide the optimal flow based on the latest data.

[0067] The service provider provides a flow optimized by the reinforcement learning unit. For example, the service provider can provide an optimized flow using user interface design and notification methods. Specifically, it designs an intuitive user interface to present the optimized flow clearly to the user. For example, it provides a visual guide showing the operation procedure and a dashboard that displays the progress of the operation in real time. It also provides notifications at appropriate times to make it easier for users to follow the operation flow. For example, it displays a pop-up notification at each step of the operation procedure to guide the user to the next action. Furthermore, the service provider collects user feedback and continuously evaluates the accuracy and effectiveness of the optimized flow. For example, it conducts a survey after the user completes the operation flow to evaluate the difficulty of the operation and satisfaction. The service provider can also reliably transmit information using multiple communication methods. For example, it uses not only user interface notifications but also email, SMS, and push notifications to ensure important information is delivered reliably. This allows the service provider to quickly and reliably provide the optimized flow to users, improving operational efficiency. Furthermore, the data provisioning unit can collect user operation data again and work in conjunction with the data collection unit, learning unit, and reinforcement learning unit to improve the overall system performance.

[0068] The data collection unit can collect detailed data such as operation procedures, operation time, results, and feedback. For example, the data collection unit can collect user click data and input data as a method of recording operation procedures. The data collection unit can also collect operation logs to record operation time. Furthermore, the data collection unit can use surveys and evaluation systems to collect results and feedback. This allows for more accurate learning by collecting detailed data. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user click data into an AI, which can then analyze the data and record the operation procedures.

[0069] The learning unit can analyze the collected data and identify efficient workflows. For example, the learning unit can analyze the data using data mining techniques to identify efficient workflows. It can also analyze the data using statistical analysis techniques to identify efficient workflows. Furthermore, it can analyze the data using machine learning algorithms to identify efficient workflows. Thus, efficient workflows can be identified by analyzing the data. Some or all of the above-described processes in the learning unit may be performed using AI, or they may not. For example, the learning unit can input the collected data into an AI, which can then analyze the data and identify efficient workflows.

[0070] The reinforcement learning unit can find the optimal flow by performing simulations based on an efficient flow. For example, the reinforcement learning unit can find the optimal flow by performing simulations using the Monte Carlo method. It can also find the optimal flow by performing simulations using agent-based simulation. Furthermore, it can find the optimal flow by performing simulations using reinforcement learning algorithms. Thus, the optimal flow can be found through simulation. Some or all of the above-described processes in the reinforcement learning unit may be performed using AI, or they may be performed without AI. For example, the reinforcement learning unit can input an efficient flow into the AI, which can then perform simulations to find the optimal flow.

[0071] The service provider can provide an optimized flow. For example, the service provider can provide an optimized flow using user interface design. The service provider can also provide an optimized flow using notification methods. Furthermore, the service provider can provide an optimized flow using dashboards. This allows for more efficient responses by providing an optimized flow. Some or all of the above processes in the service provider may be performed using AI or not. For example, the service provider can input an optimized flow into an AI, which can then design a user interface and provide the flow.

[0072] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, if the user is stressed, the data collection unit can temporarily stop collecting data and resume it when the user is relaxed. The data collection unit can also collect data when the user is focused, obtaining more detailed data. Furthermore, if the user is tired, the data collection unit can reduce the frequency of data collection and resume it after a break. This allows for more appropriate data collection by adjusting the timing of data collection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI, which can then estimate the emotions and adjust the timing of data collection.

[0073] The data collection unit can analyze the user's past operation history and select the optimal data collection method when collecting operation data. For example, the data collection unit can prioritize collecting operations that the user has frequently performed in the past. The data collection unit can also focus on collecting data for specific operations from the user's past operation history. Furthermore, the data collection unit can analyze the user's operation history and propose an efficient method for collecting operation data. This allows the optimal data collection method to be selected by analyzing past operation history. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's operation history data into an AI, which can then analyze the data and select the optimal data collection method.

[0074] The data collection unit can filter operation data based on the user's current work status and areas of interest. For example, the data collection unit prioritizes collecting operation data related to the task the user is currently performing. The data collection unit can also filter and collect relevant operation data based on the user's areas of interest. Furthermore, the data collection unit can grasp the user's work status in real time and collect the most relevant operation data. This allows for the collection of highly relevant data by filtering based on the current work status and areas of interest. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user work status data into AI, which can then filter the data to collect the most relevant operation data.

[0075] The data collection unit can estimate the user's emotions and determine the priority of the operation data to be collected based on the estimated user emotions. For example, if the user is stressed, the data collection unit will postpone the collection of less important operation data. Conversely, if the user is relaxed, the data collection unit can prioritize the collection of more important operation data. Furthermore, if the user is in a hurry, the data collection unit can prioritize operation data that can be collected quickly. In this way, important data can be collected preferentially by determining priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI, which can estimate the emotions and determine the priority of the operation data.

[0076] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location when collecting operation data. For example, if the user is in a specific region, the data collection unit will prioritize the collection of operation data related to that region. The data collection unit can also filter and collect highly relevant operation data based on the user's location information. Furthermore, if the user is on the move, the data collection unit can collect the most relevant operation data based on their current location. This allows for the collection of highly relevant data by considering geographical location information. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's location data into an AI, which can then analyze the data and collect highly relevant operation data.

[0077] The data collection unit can analyze the user's social media activity and collect relevant data when collecting operational data. For example, the data collection unit can analyze the content of the user's social media posts and collect relevant operational data. The data collection unit can also collect operational data related to the user's interests based on the user's social media activity history. Furthermore, the data collection unit can collect relevant operational data by referring to the activities of the user's social media followers and friends. In this way, relevant data can be collected by analyzing social media activity. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the user's social media data into AI, and the AI ​​can analyze the data and collect relevant operational data.

[0078] The learning unit can estimate the user's emotions and adjust the learning presentation based on the estimated emotions. For example, if the user is relaxed, the learning unit can provide a learning method that includes detailed explanations. If the user is in a hurry, the learning unit can also provide a concise learning method that gets straight to the point. Furthermore, if the user is excited, the learning unit can provide a learning method that includes visually stimulating effects. This allows for more effective learning by adjusting the learning presentation according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input user emotion data into an AI, which can estimate the emotions and adjust the learning presentation.

[0079] The learning unit can adjust the level of detail during learning based on the importance of the operation data. For example, the learning unit will perform detailed learning for operation data with high importance. It can also perform simplified learning for operation data with low importance. Furthermore, the learning unit can determine the priority of learning according to the importance of the operation data. This allows for efficient learning by adjusting the level of detail based on the importance of the operation data. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the importance of the operation data into the AI, and the AI ​​can analyze the data and adjust the level of detail of learning.

[0080] The learning unit can apply different learning algorithms depending on the category of the operation data during training. For example, the learning unit can apply a natural language processing algorithm to customer support operation data. It can also apply a machine learning algorithm to technical support operation data. Furthermore, it can apply a data mining algorithm to sales support operation data. By applying different learning algorithms depending on the category of operation data, more appropriate learning becomes possible. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the category of operation data into the AI, and the AI ​​can analyze the data and apply an appropriate learning algorithm.

[0081] The learning unit can estimate the user's emotions and adjust the length of the learning session based on the estimated emotions. For example, if the user is relaxed, the learning unit can provide a longer learning session. If the user is in a hurry, the learning unit can also provide a shorter learning session. Furthermore, if the user is excited, the learning unit can provide a learning session of an appropriate length to maintain concentration. By adjusting the length of the learning session according to the user's emotions, more effective learning becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input user emotion data into an AI, which can estimate the emotions and adjust the length of the learning session.

[0082] The learning unit can determine the learning priority based on the timing of operation data collection during the learning process. For example, the learning unit prioritizes learning the most recent operation data. It can also prioritize the latest data while referring to past operation data. Furthermore, the learning unit can dynamically adjust the learning priority according to the timing of operation data collection. This makes it possible to prioritize learning based on the timing of operation data collection, thereby emphasizing the latest data. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the timing of operation data collection into the AI, and the AI ​​can analyze the data to determine the learning priority.

[0083] The learning unit can adjust the learning order based on the relevance of the operation data during learning. For example, the learning unit prioritizes learning highly relevant operation data. It can also postpone learning less relevant operation data. Furthermore, the learning unit can dynamically adjust the learning order according to the relevance of the operation data. This allows for efficient learning by adjusting the learning order based on the relevance of the operation data. Some or all of the above processing in the learning unit may be performed using AI or not. For example, the learning unit can input the relevance of the operation data into the AI, and the AI ​​can analyze the data and adjust the learning order.

[0084] The reinforcement learning unit can estimate the user's emotions and adjust the reinforcement learning criteria based on the estimated emotions. For example, if the user is relaxed, the reinforcement learning unit can provide detailed feedback and loosen the reinforcement learning criteria. Conversely, if the user is in a hurry, the reinforcement learning unit can provide rapid feedback and tighten the reinforcement learning criteria. Furthermore, if the user is excited, the reinforcement learning unit can provide visually stimulating feedback and adjust the reinforcement learning criteria. This allows for more effective reinforcement learning by adjusting the criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AIs include, but are not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input user emotion data into an AI, which can estimate the emotion and adjust the reinforcement learning criteria.

[0085] The reinforcement learning unit can improve the accuracy of reinforcement learning by considering the interrelationships of the manipulated data during reinforcement learning. For example, the reinforcement learning unit can analyze the interrelationships of the manipulated data and perform reinforcement learning based on the related data. The reinforcement learning unit can also adjust the reinforcement learning algorithm by considering the interrelationships of the manipulated data. Furthermore, the reinforcement learning unit can provide reinforcement learning feedback based on the interrelationships of the manipulated data. As a result, the accuracy of reinforcement learning is improved by considering the interrelationships of the manipulated data. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input the interrelationships of the manipulated data into the AI, and the AI ​​can analyze the data to improve the accuracy of reinforcement learning.

[0086] The reinforcement learning unit can perform reinforcement learning while considering the attribute information of the data submitter. For example, the reinforcement learning unit can adjust the reinforcement learning criteria by considering the data submitter's years of experience. It can also adjust the reinforcement learning algorithm by considering the data submitter's job title. Furthermore, the reinforcement learning unit can provide reinforcement learning feedback by considering the data submitter's skill level. This allows for more appropriate reinforcement learning by considering the submitter's attribute information. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input the data submitter's attribute information into AI, and the AI ​​can analyze the data and perform reinforcement learning.

[0087] The reinforcement learning unit can estimate the user's emotions and adjust the order in which it displays the reinforcement learning results based on the estimated emotions. For example, if the user is relaxed, the reinforcement learning unit can display detailed results in a sequential order. If the user is in a hurry, the reinforcement learning unit can prioritize displaying results that summarize the key points. Furthermore, if the user is excited, the reinforcement learning unit can display visually stimulating results in a sequential order. This allows for more effective feedback by adjusting the order in which results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input user emotion data into an AI, which can estimate the emotions and adjust the order in which results are displayed.

[0088] The reinforcement learning unit can perform reinforcement learning while considering the geographical distribution of the manipulation data. For example, the reinforcement learning unit can analyze the geographical distribution of the manipulation data and perform reinforcement learning while considering the characteristics of each region. The reinforcement learning unit can also adjust the reinforcement learning algorithm based on the geographical distribution of the manipulation data. Furthermore, the reinforcement learning unit can provide reinforcement learning feedback while considering the geographical distribution of the manipulation data. This makes it possible to perform reinforcement learning that is tailored to the characteristics of each region by considering the geographical distribution. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input the geographical distribution of the manipulation data into the AI, and the AI ​​can analyze the data and perform reinforcement learning.

[0089] The reinforcement learning unit can improve the accuracy of reinforcement learning by referring to relevant literature on the manipulation data during reinforcement learning. For example, the reinforcement learning unit can refer to relevant literature on the manipulation data and perform reinforcement learning based on the latest knowledge. The reinforcement learning unit can also adjust the reinforcement learning algorithm based on the relevant literature on the manipulation data. Furthermore, the reinforcement learning unit can provide reinforcement learning feedback considering the relevant literature on the manipulation data. This makes it possible to perform reinforcement learning based on the latest knowledge by referring to relevant literature. Some or all of the above processing in the reinforcement learning unit may be performed using AI or not. For example, the reinforcement learning unit can input relevant literature on the manipulation data into AI, and the AI ​​can analyze the literature to improve the accuracy of reinforcement learning.

[0090] The service provider can estimate the user's emotions and adjust the display method of the flow based on the estimated emotions. For example, if the user is relaxed, the service provider can display a detailed flow. If the user is in a hurry, the service provider can also display a concise flow that gets straight to the point. Furthermore, if the user is excited, the service provider can display a visually stimulating flow. This allows for the provision of a more effective flow by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user emotion data into AI, which can estimate the emotions and adjust the flow display method.

[0091] The service provider can provide the optimal flow by referring to the user's past operation history at the time of delivery. For example, the service provider can prioritize providing flows that the user has frequently used in the past. The service provider can also analyze the user's past operation history and suggest the optimal flow. Furthermore, the service provider can provide an efficient flow based on the user's operation history. In this way, the optimal flow can be provided by referring to past operation history. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input the user's operation history data into AI, and the AI ​​can analyze the data to provide the optimal flow.

[0092] The service provider can provide the optimal workflow at the time of delivery, taking into account the user's current work status. For example, the service provider can prioritize providing workflows related to the work the user is currently performing. The service provider can also grasp the user's work status in real time and provide the optimal workflow. Furthermore, the service provider can provide efficient workflows according to the user's work status. In this way, the service provider can provide the optimal workflow by taking into account the current work status. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user work status data into AI, and the AI ​​can analyze the data to provide the optimal workflow.

[0093] The service provider can estimate the user's emotions and determine the priority of the flows to be provided based on the estimated emotions. For example, if the user is stressed, the service provider may postpone providing less important flows. Conversely, if the user is relaxed, the service provider may prioritize providing more important flows. Furthermore, if the user is in a hurry, the service provider may prioritize flows that can be provided quickly. In this way, important flows can be prioritized by determining priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input user emotion data into an AI, which can estimate the emotions and determine the priority of the flows.

[0094] The service provider can provide an optimal flow by considering the user's device information at the time of delivery. For example, if the user is using a smartphone, the service provider can provide a flow that matches the screen size. Furthermore, if the user is using a tablet, the service provider can provide a flow optimized for a larger screen. In addition, if the user is using a desktop, the service provider can provide a detailed flow. This allows for the provision of an optimal flow by considering device information. Some or all of the above processing in the service provider may be performed using AI, or not. For example, the service provider can input the user's device information into an AI, which can then analyze the data to provide an optimal flow.

[0095] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0096] The data collection unit can acquire and collect the user's biometric information along with the user's operation data. For example, it can acquire biometric information such as the user's heart rate and skin electrical response and collect it in association with the operation data. The data collection unit can also monitor the user's biometric information in real time and temporarily stop collecting operation data if an abnormality is detected. Furthermore, the data collection unit can adjust the frequency of operation data collection based on the user's biometric information. This allows for more accurate data collection by taking the user's biometric information into consideration.

[0097] The learning unit can estimate the user's emotions when analyzing collected operational data and adjust its learning algorithm based on those emotions. For example, if the user is stressed, the learning unit will prioritize learning steps to reduce stress. If the user is relaxed, the learning unit can focus on learning efficient steps. Furthermore, if the user is excited, the learning unit can learn visually stimulating steps. By adjusting the learning algorithm according to the user's emotions, more effective learning becomes possible.

[0098] The reinforcement learning unit, when performing simulations based on an efficient flow, can refer to the user's past operation history and consider past successes and failures. For example, it can prioritize incorporating previously successful procedures into the simulation. It can also exclude previously failed procedures from the simulation. Furthermore, it can adjust the simulation parameters based on past operation history. This allows for more accurate simulations by considering past operation history.

[0099] The service provider can estimate the user's emotions when providing an optimized flow and adjust the content of the flow based on those emotions. For example, if the user is stressed, a concise and easy-to-understand flow can be provided. If the user is relaxed, a flow with detailed explanations can be provided. Furthermore, if the user is excited, a visually stimulating flow can be provided. By adjusting the content of the flow according to the user's emotions, a more effective flow can be provided.

[0100] The data collection unit can adjust its collection method when collecting operation data, taking into account the user's device information. For example, if the user is using a smartphone, the frequency of operation data collection can be increased. If the user is using a tablet, a collection method optimized for the larger screen can be adopted. Furthermore, if the user is using a desktop computer, detailed operation data can be collected. This allows for the selection of the optimal collection method by considering device information.

[0101] The learning unit can adjust its learning algorithm when analyzing collected operation data, taking into account the user's geographical location. For example, it can prioritize learning operation data from a specific region. It can also adjust the learning algorithm considering the characteristics of each region. Furthermore, it can determine the learning priority based on geographical location information. This makes it possible to perform learning tailored to the characteristics of each region by considering geographical location information.

[0102] The reinforcement learning unit can estimate the user's emotions when performing simulations based on an efficient flow, and adjust the simulation parameters based on the estimated emotions. For example, if the user is stressed, the difficulty of the simulation can be lowered. Conversely, if the user is relaxed, the difficulty of the simulation can be increased. Furthermore, if the user is excited, a visually stimulating simulation can be performed. In this way, adjusting the simulation parameters according to the user's emotions makes it possible to perform more effective simulations.

[0103] The service provider can refer to the user's past operation history when providing optimized flows and prioritize providing flows that have been used in the past. For example, it can prioritize providing flows that the user has frequently used in the past. It can also prioritize providing flows that have been successful in the past. Furthermore, it can suggest the optimal flow based on past operation history. In this way, the optimal flow can be provided by referring to past operation history.

[0104] The data collection unit can analyze the user's social media activity and collect relevant data when collecting operational data. For example, it can analyze the content of the user's social media posts and collect relevant operational data. It can also collect operational data related to the user's interests based on their social media activity history. Furthermore, it can collect relevant operational data by referring to the activities of the user's social media followers and friends. In this way, relevant data can be collected by analyzing social media activity.

[0105] The service provider can estimate the user's emotions when providing an optimized flow and prioritize the flow based on those emotions. For example, if the user is stressed, less important flows can be postponed. Conversely, if the user is relaxed, more important flows can be prioritized. Furthermore, if the user is in a hurry, flows that can be delivered quickly can be prioritized. In this way, important flows can be prioritized by determining priorities according to the user's emotions.

[0106] The following briefly describes the processing flow for example form 2.

[0107] Step 1: The collection unit collects operation data. The collection unit can collect, for example, user click data, input data, and operation logs. It can also collect detailed data such as operation procedures, operation time, results, and feedback. Step 2: The learning unit learns from the operational data collected by the collection unit and identifies efficient workflows. The learning unit can analyze the data using, for example, data mining techniques or statistical analysis techniques to identify efficient workflows. Step 3: The reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the learning unit to find the optimal flow. The reinforcement learning unit can find the optimal flow by performing simulations, for example, using the Monte Carlo method or agent-based simulation. Step 4: The provider unit provides the optimized flow, which is then optimized by the reinforcement learning unit. The provider unit can, for example, provide an optimized flow using user interface design and notification methods.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] Each of the multiple elements described above, including the collection unit, learning unit, reinforcement learning unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects user click data and operation logs. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data to identify an efficient flow. The reinforcement learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs simulations based on the efficient flow to find the optimal flow. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the optimized flow through the user interface. 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.

[0112] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0117] 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).

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] Each of the multiple elements described above, including the collection unit, learning unit, reinforcement learning unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects user click data and operation logs. The learning unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the collected data to identify an efficient flow. The reinforcement learning unit is implemented by the identification processing unit 290 of the data processing unit 12 and performs simulations based on the efficient flow to find the optimal flow. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the optimized flow through the user interface. 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.

[0128] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] Each of the multiple elements described above, including the collection unit, learning unit, reinforcement learning unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects user click data and operation logs. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data to identify an efficient flow. The reinforcement learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs simulations based on the efficient flow to find the optimal flow. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides the optimized flow through the user interface. 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.

[0144] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] Each of the multiple elements described above, including the collection unit, learning unit, reinforcement learning unit, and provision unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects user click data and operation logs. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data to identify an efficient flow. The reinforcement learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs simulations based on the efficient flow to find the optimal flow. The provision unit is implemented by the control unit 46A of the robot 414 and provides the optimized flow through the user interface. 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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."

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] (Note 1) A data collection unit that collects operational data, A learning unit learns from the operation data collected by the aforementioned collection unit and identifies an efficient flow, A reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the aforementioned learning unit to find the optimal flow, The system comprises a providing unit that provides a flow optimized by the reinforcement learning unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is Collect detailed data such as operating procedures, operating time, results, and feedback. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned learning unit, Analyze the collected data to identify efficient workflows. The system described in Appendix 1, characterized by the features described herein. (Note 4) The reinforcement learning unit, We conduct simulations based on efficient workflows to find the optimal workflow. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, Provides an optimized flow The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of collecting operational data based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting operation data, the system analyzes the user's past operation history to select the optimal collection method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is When collecting operational data, filtering is performed based on the user's current work status and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is It estimates the user's emotions and determines the priority of interaction data to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When collecting operational data, the system prioritizes collecting highly relevant data by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting operational data, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning model's representation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned learning unit, During training, adjust the level of detail based on the importance of the operational data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned learning unit, During training, different learning algorithms are applied depending on the category of the manipulated data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned learning unit, It estimates the user's emotions and adjusts the length of the learning process based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned learning unit, During training, the training priority is determined based on when the operational data was collected. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned learning unit, During training, the order of learning is adjusted based on the relevance of the manipulated data. The system described in Appendix 1, characterized by the features described herein. (Note 18) The reinforcement learning unit, It estimates the user's emotions and adjusts the reinforcement learning criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The reinforcement learning unit, When performing reinforcement learning, consider the interrelationships between the manipulated data to improve the accuracy of the reinforcement learning process. The system described in Appendix 1, characterized by the features described herein. (Note 20) The reinforcement learning unit, When performing reinforcement learning, consider the attribute information of the person who submitted the manipulation data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The reinforcement learning unit, It estimates the user's emotions and adjusts the order in which it displays the reinforcement learning results based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The reinforcement learning unit, When performing reinforcement learning, consider the geographical distribution of the manipulated data. The system described in Appendix 1, characterized by the features described herein. (Note 23) The reinforcement learning unit, During reinforcement learning, we improve the accuracy of reinforcement learning by referring to relevant literature on the manipulated data. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, It estimates the user's emotions and adjusts how the provided flow is displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, When providing the service, the system will refer to the user's past operation history to provide the optimal flow. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing the service, we will provide the optimal flow considering the user's current work status. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of the flow to be delivered based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, When providing the service, we will provide the optimal flow considering the user's device information. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0180] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A data collection unit that collects operational data, A learning unit learns from the operation data collected by the aforementioned collection unit and identifies an efficient flow, A reinforcement learning unit performs reinforcement learning based on the efficient flow identified by the aforementioned learning unit to find the optimal flow, The system comprises a providing unit that provides a flow optimized by the reinforcement learning unit. A system characterized by the following features.

2. The aforementioned collection unit is Collect detailed data such as operating procedures, operating time, results, and feedback. The system according to feature 1.

3. The aforementioned learning unit, Analyze the collected data to identify efficient workflows. The system according to feature 1.

4. The reinforcement learning unit, We conduct simulations based on efficient workflows to find the optimal workflow. The system according to feature 1.

5. The aforementioned supply unit is, Provides an optimized flow The system according to feature 1.

6. The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of collecting operational data based on the estimated emotions. The system according to feature 1.

7. The aforementioned collection unit is When collecting operation data, the system analyzes the user's past operation history to select the optimal collection method. The system according to feature 1.

8. The aforementioned collection unit is When collecting operational data, filtering is performed based on the user's current work status and areas of interest. The system according to feature 1.

Images