system

Abstract

The system according to this embodiment aims to improve productivity by automating the search process for specific websites. [Solution] The system according to the embodiment comprises a recording unit, a shortcut creation unit, a program creation unit, and a search result collection unit. The recording unit records the user's search activity to a specific site. The shortcut creation unit creates a shortcut based on the search activity recorded by the recording unit. The program creation unit automatically writes a program such as RPA based on the shortcut created by the shortcut creation unit. The search result collection unit collects search results for subsequent searches based on the program written by the program creation 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0007] The system according to this embodiment can automate the search process for specific websites, thereby improving productivity. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The search agent system according to an embodiment of the present invention is a system for streamlining search operations performed by people working on PCs for specific tools or websites. This search agent system allows users to record their search actions for a specific website once, create a shortcut, and automatically program it using RPA (Robotic Process Automation). This enables the search agent to collect search results with simple operations on subsequent uses. This mechanism allows all users of the search agent to reduce man-hours and improve productivity. For example, a user records their search actions for a specific website once. The user performs a series of search actions, and the search agent records these actions. For example, if a user searches for information about base stations using a specific tool, the search agent records these actions. Next, the search agent creates a shortcut based on the recorded search actions. The search agent formats the recorded operations and automatically programs them using RPA or similar software. This allows users to perform search actions with simple operations on subsequent uses. For example, a user simply enters search information into a chat UI and presses the execute button, and the search agent automatically collects the search results. Furthermore, search agents not only collect search results but also have functions to streamline the search process. For example, when presenting search results, search agents prioritize displaying the information the user needs. They also manage the search history and allow users to refer to past search results. This mechanism allows all users of search agents to reduce workload and improve productivity. For instance, if a business person spends an average of 1.6 hours a day researching, using a search agent can significantly reduce that time. This could result in tens of hours saved annually, equivalent to hundreds of millions to tens of billions of yen in wage savings. Additionally, because search agents are in demand in any company with desk-based work, revenue generation through external sales is also possible. Moreover, search agents are important as a first step towards streamlining the search process using generative AI.The practical application of generation AI agents will enable them to handle even more complex and time-consuming tasks. This will lead to improved business efficiency and increased employee satisfaction. As a result, search agent systems can streamline user search processes and improve productivity.

[0029] The search agent system according to this embodiment comprises a recording unit, a shortcut creation unit, a program creation unit, and a search result collection unit. The recording unit records the user's search actions to a specific site. For example, if a user searches for information about a base station using a specific tool, the recording unit records that search action. The recording unit can record a series of operations performed by a user during a search. For example, the recording unit records a series of operations in which a user enters search keywords, clicks the search button, and views the search results. The shortcut creation unit creates shortcuts based on the search actions recorded by the recording unit. The shortcut creation unit can format the recorded operations and automatically create programs such as RPA. For example, the shortcut creation unit creates desktop shortcuts and browser bookmarks based on the recorded search actions. The program creation unit automatically creates programs such as RPA based on the shortcuts created by the shortcut creation unit. The program creation unit can create programs using specific RPA tools or scripting languages. For example, the program creation unit creates an automation script using a specific RPA tool based on the recorded search actions. The search result collection unit collects search results for subsequent searches based on the programs created by the program creation unit. The search results collection unit enables users to perform searches with simple operations. For example, the search results collection unit can collect search results simply by entering search information into the chat UI and pressing the execute button. As a result, the search agent system according to the embodiment can streamline the user's search process and improve productivity.

[0030] The recording unit records a user's search activity to a specific website. For example, if a user searches for information about base stations using a specific tool, the recording unit will record that search activity. The recording unit can record the entire sequence of actions a user takes in a search. Specifically, the recording unit records the sequence of actions a user takes, such as entering search keywords, clicking the search button, and viewing the search results. To record user actions in detail, the recording unit includes information such as the timing of keyboard input and mouse clicks, and screen transitions. This allows for an accurate reproduction of the steps a user took to perform a search. Furthermore, the recording unit can handle cases where a user uses multiple search engines or websites, recording each search activity individually. For example, if a user searches for the same keyword using different search engines, all operations are recorded so that they can be compared and analyzed later. The recording unit also records environmental information when a user performs a search. For example, it records the type of device used, the browser version, and the network status to improve the reproducibility of the search activity. As a result, the recording unit can record user search activities in detail and accurately, providing the information necessary for subsequent processing.

[0031] The shortcut creation unit creates shortcuts based on search actions recorded by the recording unit. The shortcut creation unit can format the recorded operations and automatically create programs such as RPA. Specifically, the shortcut creation unit creates desktop shortcuts and browser bookmarks based on recorded search actions. For example, if a user frequently searches using a specific keyword, that search action can be saved as a shortcut, allowing the same search to be performed with a single click in the future. The shortcut creation unit also has a function to analyze the user's search actions and suggest the most suitable shortcuts. For example, if a user tends to search using a specific keyword at a specific time of day, the shortcut will be automatically displayed at that time to improve user convenience. Furthermore, the shortcut creation unit can combine multiple search actions into a single shortcut. For example, if a user searches for the same keyword on multiple websites, all of those searches can be combined into a single shortcut, allowing multiple searches to be performed simultaneously with a single click. In this way, the shortcut creation unit can streamline the user's search actions and save time and effort.

[0032] The program creation unit automatically generates RPA and other programs based on shortcuts created by the shortcut creation unit. The program creation unit can create programs using specific RPA tools and scripting languages. Specifically, the program creation unit creates automation scripts using specific RPA tools based on recorded search actions. For example, if a user performs a search using a specific keyword and saves the results in a specific format, the program creation unit generates a script to automate this series of operations. The program creation unit analyzes the user's search actions and designs the optimal automation procedure. For example, it considers page transitions in search results, extraction of specific information, and data saving methods to create an efficient automation script. The program creation unit also has a function to simulate the operation of the generated script and check for errors and malfunctions. This allows users to use the automation script with confidence. Furthermore, the program creation unit improves the script based on user feedback to achieve higher accuracy and efficiency. For example, if a user is not satisfied with a particular search result, the script is modified based on that feedback to improve search results for subsequent searches. In this way, the program creation unit can highly automate the user's search actions and significantly improve work efficiency.

[0033] The search result collection unit collects search results for subsequent searches based on a program created by the program development unit. The search result collection unit enables users to perform searches with simple operations. Specifically, the search result collection unit can collect search results simply by entering search information into the chat UI and pressing the execute button. For example, if a user enters "Search for the latest base station information" into the chat UI and presses the execute button, the search result collection unit automatically executes the program and collects the latest base station information. The search result collection unit also has a function to display the collected search results in an easy-to-understand manner for the user. For example, it can display search results in a list format and highlight important information. Furthermore, the search result collection unit also has a function to save the collected data for later reuse. For example, if a user wants to refer to past search results, the search result collection unit can quickly display the saved data. In addition, the search result collection unit also has a function to learn from the user's search behavior and improve the accuracy of subsequent search results. For example, if a user gives a high rating to a particular search result, the search result collection unit will optimize subsequent search results based on that information. This allows the search result collection unit to streamline the user's search behavior and provide necessary information quickly and accurately.

[0034] The search result collection unit can present the search results. For example, the search result collection unit can present the search results in a list format. The search result collection unit can also present the search results in a grid format. The search result collection unit can also present the search results as thumbnails. By presenting the search results to the user, the efficiency of the search process can be improved. Some or all of the above-described processing in the search result collection unit may be performed using, for example, a generation AI, or without a generation AI. For example, the search result collection unit can input the search results into a generation AI, and the generation AI can present the search results in a list format.

[0035] The search result collection unit manages the history of search activity and can refer to past search results. The search result collection unit manages the history of search activity, such as search keywords, search date and time, and search result click history. By referring to past search results, the search result collection unit allows users to repeat previously performed search activities. The search result collection unit can also prioritize displaying information that the user needs based on past search results. This makes the search activity more efficient by referring to past search results. Some or all of the above processing in the search result collection unit may be performed using, for example, a generation AI, or without a generation AI. For example, the search result collection unit can input past search result data into a generation AI, and the generation AI can present current search results based on past search results.

[0036] The recording unit can record a series of actions performed by a user during a search. For example, the recording unit can record a series of actions such as a user entering search keywords, clicking the search button, and viewing the search results. The recording unit can record detailed actions performed by the user during a search. By recording the series of actions during a search, the recording unit can make subsequent searches more efficient. In this way, recording the user's search actions can make subsequent searches more efficient. Some or all of the above processing in the recording unit may be performed using, for example, a generating AI, or it may be performed without a generating AI. For example, the recording unit can input the series of actions performed by the user into a generating AI, and the generating AI can record those actions.

[0037] The shortcut creation unit can format recorded operations. For example, the shortcut creation unit can format recorded search actions into a specific file format. The shortcut creation unit can also format recorded operations into a specific data structure. The shortcut creation unit can also format recorded operations into a specific template. This makes it easier to create shortcuts by formatting recorded operations. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input recorded operations into a generation AI, and the generation AI can format those operations.

[0038] The program creation unit can automatically create programs such as RPA. The program creation unit can, for example, create automation scripts using a specific RPA tool. The program creation unit can also create programs using a specific scripting language. The program creation unit can automatically create programs based on recorded search actions. This enables the automation of search actions by automatically creating programs. Some or all of the above processes in the program creation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the program creation unit can input recorded search actions into a generation AI, and the generation AI can automatically create a program.

[0039] The search result collection unit can collect search results simply by having the user enter search information into the chat UI and press the execute button. For example, the search result collection unit can collect search results when the user enters search keywords into the chat UI and presses the execute button. The search result collection unit can collect search results with simple operations using the chat UI. The search result collection unit makes it easy for users to perform searches by using the chat UI. As a result, search results can be collected with simple operations using the chat UI. Some or all of the above-described processes in the search result collection unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the search result collection unit can input the search information entered into the chat UI into a generation AI, and the generation AI can collect the search results.

[0040] The recording unit can analyze the user's past search behavior and select the optimal recording method. For example, the recording unit can automatically record the user's frequently performed search behaviors, reducing manual operation. The recording unit can also extract specific patterns from the user's past search behavior and optimize the recording method based on those patterns. The recording unit can also analyze the user's past search behavior and propose the most efficient recording method. In this way, the optimal recording method can be selected by analyzing past search behavior. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the user's past search behavior data into a generative AI, which can then select the optimal recording method.

[0041] The recording unit can filter search activity based on the user's current work situation and areas of interest when recording it. For example, the recording unit can record only search activity related to the project the user is currently working on. The recording unit can also prioritize recording highly relevant search activity based on the user's areas of interest. The recording unit can also filter and record search activity of high importance according to the user's work situation. This allows for the priority recording of important search activity by filtering based on the user's work situation and areas of interest. Some or all of the above processing in the recording unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the recording unit can input the user's work situation data into a generating AI, which can then perform the filtering.

[0042] The recording unit can prioritize recording highly relevant search activities by considering the user's geographical location information when recording search activities. For example, if the user is in a specific region, the recording unit will prioritize recording search activities related to that region. The recording unit can also filter and record highly relevant search activities based on the user's geographical location information. If the user is on the move, the recording unit can also prioritize recording search activities related to the user's current location. This makes search activities more efficient by recording highly relevant search activities based on the user's geographical location information. Some or all of the above processing in the recording unit may be performed using, for example, a generating AI, or without a generating AI. For example, the recording unit can input the user's geographical location information into a generating AI, which can then prioritize recording highly relevant search activities.

[0043] The recording unit can analyze the user's social media activity and record relevant search activities when recording search activity. For example, the recording unit can record relevant search activities based on information shared by the user on social media. The recording unit can also extract topics of interest from the user's social media activity and record search activities related to those topics. The recording unit can also analyze the user's social media activity history and prioritize recording highly relevant search activities. This makes search activity more efficient by recording relevant search activities based on the user's social media activity. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the user's social media activity data into a generative AI, which can then record relevant search activities.

[0044] The shortcut creation unit can adjust the level of detail of a shortcut based on the importance of the search action when creating a shortcut. For example, the shortcut creation unit can create a detailed shortcut for high-importance search actions. It can also create a simple shortcut for low-importance search actions. The shortcut creation unit can also dynamically adjust the level of detail of a shortcut according to the importance of the search action. This allows for the creation of efficient shortcuts by adjusting the level of detail of the shortcut according to the importance of the search action. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input search action importance data into a generation AI, and the generation AI can adjust the level of detail of the shortcut.

[0045] The shortcut creation unit can apply different shortcut creation algorithms depending on the category of the search activity when creating shortcuts. For example, the shortcut creation unit can apply an efficient shortcut creation algorithm to business-related search activities. It can also apply a user-friendly shortcut creation algorithm to entertainment-related search activities. It can also apply a shortcut creation algorithm that provides detailed information to academic-related search activities. By applying a shortcut creation algorithm according to the category of the search activity, efficient shortcuts can be created. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the shortcut creation unit can input search activity category data into a generative AI, and the generative AI can apply a shortcut creation algorithm.

[0046] The shortcut creation unit can determine the priority of shortcuts based on the timing of search actions when creating them. For example, the shortcut creation unit can prioritize creating shortcuts for search actions that the user performs frequently. The shortcut creation unit can also prioritize creating shortcuts for search actions that the user performs during specific time periods. The shortcut creation unit can also dynamically adjust the priority of shortcuts based on the timing of search actions. This allows for the creation of efficient shortcuts by determining the priority of shortcuts based on the timing of search actions. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input search action timing data into a generation AI, which can then determine the priority of shortcuts.

[0047] The shortcut creation unit can adjust the order of shortcuts based on the relevance of search actions when creating shortcuts. For example, the shortcut creation unit can prioritize creating shortcuts for search actions that the user frequently performs. The shortcut creation unit can also prioritize creating shortcuts for highly relevant search actions based on the user's areas of interest. The shortcut creation unit can also dynamically adjust the order of shortcuts based on the relevance of search actions. This allows for the creation of efficient shortcuts by adjusting the order of shortcuts based on the relevance of search actions. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input search relevance data into a generation AI, and the generation AI can adjust the order of shortcuts.

[0048] The program creation unit can improve the accuracy of the program by considering the interrelationships of search actions during program creation. For example, the program creation unit analyzes the interrelationships of search actions and creates an optimal program. The program creation unit can also improve the accuracy of the program based on the interrelationships of search actions. The program creation unit can also create an efficient program by considering the interrelationships of search actions. In this way, the accuracy of the program can be improved by considering the interrelationships of search actions. Some or all of the above processing in the program creation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the program creation unit can input data on the interrelationships of search actions into a generative AI, and the generative AI can improve the accuracy of the program.

[0049] The program creation unit can create a program while considering the attribute information of the person performing the search. For example, the program creation unit can create an optimal program based on the attribute information of the person performing the search. The program creation unit can also improve the accuracy of the program by considering the attribute information of the person performing the search. The program creation unit can also create a customizable program based on the attribute information of the person performing the search. This allows for the creation of an optimal program by considering the attribute information of the person performing the search. Some or all of the above processing in the program creation unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the program creation unit can input the attribute information of the person performing the search into a generating AI, and the generating AI can create an optimal program.

[0050] The program creation unit can create programs while considering the geographical distribution of search activity. For example, the program creation unit can create an optimal program based on the geographical distribution of search activity. The program creation unit can also improve the accuracy of the program by considering the geographical distribution of search activity. The program creation unit can also create an efficient program based on the geographical distribution of search activity. In this way, an optimal program can be created by considering the geographical distribution of search activity. Some or all of the above processing in the program creation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the program creation unit can input geographical distribution data of search activity into a generative AI, and the generative AI can create an optimal program.

[0051] The program creation unit can improve the accuracy of the program by referring to relevant literature for the search activity during program creation. For example, the program creation unit creates an optimal program based on relevant literature for the search activity. The program creation unit can also improve the accuracy of the program by referring to relevant literature for the search activity. The program creation unit can also create an efficient program by considering relevant literature for the search activity. In this way, the accuracy of the program can be improved by referring to relevant literature for the search activity. Some or all of the above processing in the program creation unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the program creation unit can input data on relevant literature for the search activity into a generating AI, and the generating AI can create an optimal program.

[0052] The search result collection unit can predict current search results by referring to past search result data when collecting search results. For example, the search result collection unit predicts current search results based on past search result data. The search result collection unit can also present the optimal search results by referring to past search result data. The search result collection unit can also predict current search results by analyzing past search result data. This allows the current search results to be predicted by referring to past search result data. Some or all of the above processing in the search result collection unit may be performed using, for example, a generation AI, or without a generation AI. For example, the search result collection unit can input past search result data into a generation AI, and the generation AI can predict current search results.

[0053] The search result collection unit can apply different search result collection methods depending on the category of the search activity when collecting search results. For example, the search result collection unit can apply an efficient search result collection method to business-related search activities. It can also apply a user-friendly search result collection method to entertainment-related search activities. It can also apply a search result collection method that provides detailed information to academic-related search activities. By applying different search result collection methods according to the category of the search activity, efficient search results can be provided. Some or all of the above processing in the search result collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the search result collection unit can input search activity category data into a generative AI, and the generative AI can apply a search result collection method.

[0054] The search result collection unit can analyze changes in search results based on the timing of the search activity when collecting search results. For example, the search result collection unit analyzes changes in search results based on the timing of the search activity. The search result collection unit can also present the most suitable search results depending on the timing of the search activity. The search result collection unit can also predict changes in search results, taking into account the timing of the search activity. This allows for the provision of optimal search results by analyzing changes in search results based on the timing of the search activity. Some or all of the above processing in the search result collection unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the search result collection unit can input search activity timing data into a generating AI, which can then analyze changes in search results.

[0055] The search result collection unit can analyze search results by referring to relevant market data related to the search activity when collecting search results. For example, the search result collection unit can present optimal search results based on the relevant market data related to the search activity. The search result collection unit can also analyze search results by referring to relevant market data related to the search activity. The search result collection unit can also provide efficient search results by considering relevant market data related to the search activity. This allows for the provision of optimal search results by referring to relevant market data related to the search activity. Some or all of the above processing in the search result collection unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the search result collection unit can input relevant market data related to the search activity into a generating AI, which can then analyze the search results.

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

[0057] The search agent system can analyze a user's past search behavior and select the optimal recording method. For example, it can automatically record frequently performed searches by the user, reducing manual operation. It can also extract specific patterns from the user's past search behavior and optimize the recording method based on those patterns. It can also analyze the user's past search behavior and suggest the most efficient recording method. In this way, the optimal recording method can be selected by analyzing past search behavior. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the user's past search behavior data into a generative AI, which can then select the optimal recording method.

[0058] The search agent system can prioritize recording highly relevant search activities by considering the user's geographical location. For example, if the user is in a specific region, it can prioritize recording search activities related to that region. It can also filter and record highly relevant search activities based on the user's geographical location. If the user is on the move, it can prioritize recording search activities related to their current location. This improves the efficiency of search activities by recording highly relevant search activities based on the user's geographical location. Some or all of the above processing in the recording unit may be performed using, for example, a generating AI, or without a generating AI. For example, the recording unit can input the user's geographical location information into a generating AI, which can then prioritize recording highly relevant search activities.

[0059] The search agent system can analyze a user's social media activity and record relevant search activities. For example, it can record relevant search activities based on information shared by the user on social media. It can also extract topics of interest from the user's social media activity and record search activities related to those topics. It can also analyze the user's social media activity history and prioritize recording highly relevant search activities. This makes search activities more efficient by recording relevant search activities based on the user's social media activity. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the user's social media activity data into a generative AI, which can then record relevant search activities.

[0060] The search agent system can adjust the level of detail of shortcuts based on the importance of the search activity when creating them. For example, it can create detailed shortcuts for high-importance search activities and simple shortcuts for low-importance search activities. It can also dynamically adjust the level of detail of shortcuts according to the importance of the search activity. This allows for the creation of efficient shortcuts by adjusting the level of detail according to the importance of the search activity. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input search activity importance data into the generation AI, and the generation AI can adjust the level of detail of the shortcuts.

[0061] The search agent system can apply different shortcut creation algorithms depending on the category of the search activity when creating shortcuts. For example, an efficient shortcut creation algorithm can be applied to business-related searches. A user-friendly shortcut creation algorithm can be applied to entertainment-related searches. A shortcut creation algorithm that provides detailed information can be applied to academic searches. By applying a shortcut creation algorithm according to the category of the search activity, efficient shortcuts can be created. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the shortcut creation unit can input search activity category data into a generative AI, and the generative AI can apply a shortcut creation algorithm.

[0062] The search agent system can improve the accuracy of its program by considering the interrelationships of search actions during program creation. For example, it can analyze the interrelationships of search actions and create an optimal program. It can also improve the accuracy of the program based on the interrelationships of search actions. It can also create an efficient program by considering the interrelationships of search actions. In this way, the accuracy of the program can be improved by considering the interrelationships of search actions. Some or all of the above processing in the program creation unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the program creation unit can input data on the interrelationships of search actions into a generative AI, and the generative AI can improve the accuracy of the program.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The recording unit records the user's search activity to a specific site. For example, if a user searches for information about base stations using a specific tool, the recording unit records that search activity. The recording unit can record the sequence of actions a user performs during a search. For example, it can record the sequence of actions a user takes, such as entering search keywords, clicking the search button, and viewing the search results. Step 2: The shortcut creation unit creates shortcuts based on the search actions recorded by the recording unit. The shortcut creation unit formats the recorded operations and can automatically create programs such as RPA. For example, it can create desktop shortcuts and browser bookmarks based on recorded search actions. Step 3: The program creation unit automatically writes RPA or other programs based on the shortcuts created by the shortcut creation unit. The program creation unit can create programs using specific RPA tools or scripting languages. For example, it can create an automation script using a specific RPA tool based on recorded search actions. Step 4: The search result collection unit collects subsequent search results based on the program created by the program creation unit. The search result collection unit enables users to perform searches with simple operations. For example, users can collect search results simply by entering search information into the chat UI and pressing the execute button.

[0065] (Example of form 2) The search agent system according to an embodiment of the present invention is a system for streamlining search operations performed by people working on PCs for specific tools or websites. This search agent system allows users to record their search actions for a specific website once, create a shortcut, and automatically program it using RPA (Robotic Process Automation). This enables the search agent to collect search results with simple operations on subsequent uses. This mechanism allows all users of the search agent to reduce man-hours and improve productivity. For example, a user records their search actions for a specific website once. The user performs a series of search actions, and the search agent records these actions. For example, if a user searches for information about base stations using a specific tool, the search agent records these actions. Next, the search agent creates a shortcut based on the recorded search actions. The search agent formats the recorded operations and automatically programs them using RPA or similar software. This allows users to perform search actions with simple operations on subsequent uses. For example, a user simply enters search information into a chat UI and presses the execute button, and the search agent automatically collects the search results. Furthermore, search agents not only collect search results but also have functions to streamline the search process. For example, when presenting search results, search agents prioritize displaying the information the user needs. They also manage the search history and allow users to refer to past search results. This mechanism allows all users of search agents to reduce workload and improve productivity. For instance, if a business person spends an average of 1.6 hours a day researching, using a search agent can significantly reduce that time. This could result in tens of hours saved annually, equivalent to hundreds of millions to tens of billions of yen in wage savings. Additionally, because search agents are in demand in any company with desk-based work, revenue generation through external sales is also possible. Moreover, search agents are important as a first step towards streamlining the search process using generative AI.The practical application of generation AI agents will enable them to handle even more complex and time-consuming tasks. This will lead to improved business efficiency and increased employee satisfaction. As a result, search agent systems can streamline user search processes and improve productivity.

[0066] The search agent system according to this embodiment comprises a recording unit, a shortcut creation unit, a program creation unit, and a search result collection unit. The recording unit records the user's search actions to a specific site. For example, if a user searches for information about a base station using a specific tool, the recording unit records that search action. The recording unit can record a series of operations performed by a user during a search. For example, the recording unit records a series of operations in which a user enters search keywords, clicks the search button, and views the search results. The shortcut creation unit creates shortcuts based on the search actions recorded by the recording unit. The shortcut creation unit can format the recorded operations and automatically create programs such as RPA. For example, the shortcut creation unit creates desktop shortcuts and browser bookmarks based on the recorded search actions. The program creation unit automatically creates programs such as RPA based on the shortcuts created by the shortcut creation unit. The program creation unit can create programs using specific RPA tools or scripting languages. For example, the program creation unit creates an automation script using a specific RPA tool based on the recorded search actions. The search result collection unit collects search results for subsequent searches based on the programs created by the program creation unit. The search results collection unit enables users to perform searches with simple operations. For example, the search results collection unit can collect search results simply by entering search information into the chat UI and pressing the execute button. As a result, the search agent system according to the embodiment can streamline the user's search process and improve productivity.

[0067] The recording unit records a user's search activity to a specific website. For example, if a user searches for information about base stations using a specific tool, the recording unit will record that search activity. The recording unit can record the entire sequence of actions a user takes in a search. Specifically, the recording unit records the sequence of actions a user takes, such as entering search keywords, clicking the search button, and viewing the search results. To record user actions in detail, the recording unit includes information such as the timing of keyboard input and mouse clicks, and screen transitions. This allows for an accurate reproduction of the steps a user took to perform a search. Furthermore, the recording unit can handle cases where a user uses multiple search engines or websites, recording each search activity individually. For example, if a user searches for the same keyword using different search engines, all operations are recorded so that they can be compared and analyzed later. The recording unit also records environmental information when a user performs a search. For example, it records the type of device used, the browser version, and the network status to improve the reproducibility of the search activity. As a result, the recording unit can record user search activities in detail and accurately, providing the information necessary for subsequent processing.

[0068] The shortcut creation unit creates shortcuts based on search actions recorded by the recording unit. The shortcut creation unit can format the recorded operations and automatically create programs such as RPA. Specifically, the shortcut creation unit creates desktop shortcuts and browser bookmarks based on recorded search actions. For example, if a user frequently searches using a specific keyword, that search action can be saved as a shortcut, allowing the same search to be performed with a single click in the future. The shortcut creation unit also has a function to analyze the user's search actions and suggest the most suitable shortcuts. For example, if a user tends to search using a specific keyword at a specific time of day, the shortcut will be automatically displayed at that time to improve user convenience. Furthermore, the shortcut creation unit can combine multiple search actions into a single shortcut. For example, if a user searches for the same keyword on multiple websites, all of those searches can be combined into a single shortcut, allowing multiple searches to be performed simultaneously with a single click. In this way, the shortcut creation unit can streamline the user's search actions and save time and effort.

[0069] The program creation unit automatically generates RPA and other programs based on shortcuts created by the shortcut creation unit. The program creation unit can create programs using specific RPA tools and scripting languages. Specifically, the program creation unit creates automation scripts using specific RPA tools based on recorded search actions. For example, if a user performs a search using a specific keyword and saves the results in a specific format, the program creation unit generates a script to automate this series of operations. The program creation unit analyzes the user's search actions and designs the optimal automation procedure. For example, it considers page transitions in search results, extraction of specific information, and data saving methods to create an efficient automation script. The program creation unit also has a function to simulate the operation of the generated script and check for errors and malfunctions. This allows users to use the automation script with confidence. Furthermore, the program creation unit improves the script based on user feedback to achieve higher accuracy and efficiency. For example, if a user is not satisfied with a particular search result, the script is modified based on that feedback to improve search results for subsequent searches. In this way, the program creation unit can highly automate the user's search actions and significantly improve work efficiency.

[0070] The search result collection unit collects search results for subsequent searches based on a program created by the program development unit. The search result collection unit enables users to perform searches with simple operations. Specifically, the search result collection unit can collect search results simply by entering search information into the chat UI and pressing the execute button. For example, if a user enters "Search for the latest base station information" into the chat UI and presses the execute button, the search result collection unit automatically executes the program and collects the latest base station information. The search result collection unit also has a function to display the collected search results in an easy-to-understand manner for the user. For example, it can display search results in a list format and highlight important information. Furthermore, the search result collection unit also has a function to save the collected data for later reuse. For example, if a user wants to refer to past search results, the search result collection unit can quickly display the saved data. In addition, the search result collection unit also has a function to learn from the user's search behavior and improve the accuracy of subsequent search results. For example, if a user gives a high rating to a particular search result, the search result collection unit will optimize subsequent search results based on that information. This allows the search result collection unit to streamline the user's search behavior and provide necessary information quickly and accurately.

[0071] The search result collection unit can present the search results. For example, the search result collection unit can present the search results in a list format. The search result collection unit can also present the search results in a grid format. The search result collection unit can also present the search results as thumbnails. By presenting the search results to the user, the efficiency of the search process can be improved. Some or all of the above-described processing in the search result collection unit may be performed using, for example, a generation AI, or without a generation AI. For example, the search result collection unit can input the search results into a generation AI, and the generation AI can present the search results in a list format.

[0072] The search result collection unit manages the history of search activity and can refer to past search results. The search result collection unit manages the history of search activity, such as search keywords, search date and time, and search result click history. By referring to past search results, the search result collection unit allows users to repeat previously performed search activities. The search result collection unit can also prioritize displaying information that the user needs based on past search results. This makes the search activity more efficient by referring to past search results. Some or all of the above processing in the search result collection unit may be performed using, for example, a generation AI, or without a generation AI. For example, the search result collection unit can input past search result data into a generation AI, and the generation AI can present current search results based on past search results.

[0073] The recording unit can record a series of actions performed by a user during a search. For example, the recording unit can record a series of actions such as a user entering search keywords, clicking the search button, and viewing the search results. The recording unit can record detailed actions performed by the user during a search. By recording the series of actions during a search, the recording unit can make subsequent searches more efficient. In this way, recording the user's search actions can make subsequent searches more efficient. Some or all of the above processing in the recording unit may be performed using, for example, a generating AI, or it may be performed without a generating AI. For example, the recording unit can input the series of actions performed by the user into a generating AI, and the generating AI can record those actions.

[0074] The shortcut creation unit can format recorded operations. For example, the shortcut creation unit can format recorded search actions into a specific file format. The shortcut creation unit can also format recorded operations into a specific data structure. The shortcut creation unit can also format recorded operations into a specific template. This makes it easier to create shortcuts by formatting recorded operations. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input recorded operations into a generation AI, and the generation AI can format those operations.

[0075] The program creation unit can automatically create programs such as RPA. The program creation unit can, for example, create automation scripts using a specific RPA tool. The program creation unit can also create programs using a specific scripting language. The program creation unit can automatically create programs based on recorded search actions. This enables the automation of search actions by automatically creating programs. Some or all of the above processes in the program creation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the program creation unit can input recorded search actions into a generation AI, and the generation AI can automatically create a program.

[0076] The search result collection unit can collect search results simply by having the user enter search information into the chat UI and press the execute button. For example, the search result collection unit can collect search results when the user enters search keywords into the chat UI and presses the execute button. The search result collection unit can collect search results with simple operations using the chat UI. The search result collection unit makes it easy for users to perform searches by using the chat UI. As a result, search results can be collected with simple operations using the chat UI. Some or all of the above-described processes in the search result collection unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the search result collection unit can input the search information entered into the chat UI into a generation AI, and the generation AI can collect the search results.

[0077] The recording unit can estimate the user's emotions and adjust the timing of recording search actions based on the estimated emotions. For example, if the user is stressed, the recording unit can automatically record search actions to reduce the user's burden. If the user is relaxed, the recording unit can also prompt manual recording, allowing the user to record detailed operations. If the user is in a hurry, the recording unit can quickly record search actions and supplement details later. This reduces the user's burden by adjusting the recording timing 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 recording unit may be performed using AI or not using AI. For example, the recording unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the recording timing based on the result.

[0078] The recording unit can analyze the user's past search behavior and select the optimal recording method. For example, the recording unit can automatically record the user's frequently performed search behaviors, reducing manual operation. The recording unit can also extract specific patterns from the user's past search behavior and optimize the recording method based on those patterns. The recording unit can also analyze the user's past search behavior and propose the most efficient recording method. In this way, the optimal recording method can be selected by analyzing past search behavior. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the user's past search behavior data into a generative AI, which can then select the optimal recording method.

[0079] The recording unit can filter search activity based on the user's current work situation and areas of interest when recording it. For example, the recording unit can record only search activity related to the project the user is currently working on. The recording unit can also prioritize recording highly relevant search activity based on the user's areas of interest. The recording unit can also filter and record search activity of high importance according to the user's work situation. This allows for the priority recording of important search activity by filtering based on the user's work situation and areas of interest. Some or all of the above processing in the recording unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the recording unit can input the user's work situation data into a generating AI, which can then perform the filtering.

[0080] The recording unit can estimate the user's emotions and determine the priority of search actions to record based on the estimated emotions. For example, if the user is stressed, the recording unit may prioritize recording high-priority search actions. If the user is relaxed, the recording unit may also prioritize recording detailed search actions. If the user is in a hurry, the recording unit may also prioritize recording search actions that can be completed quickly. This allows for the priority recording of important search actions by determining the priority of search actions 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 recording unit may be performed using AI or not using AI. For example, the recording unit can input user emotion data into a generative AI, the generative AI can estimate the emotions, and the priority of search actions can be determined based on the result.

[0081] The recording unit can prioritize recording highly relevant search activities by considering the user's geographical location information when recording search activities. For example, if the user is in a specific region, the recording unit will prioritize recording search activities related to that region. The recording unit can also filter and record highly relevant search activities based on the user's geographical location information. If the user is on the move, the recording unit can also prioritize recording search activities related to the user's current location. This makes search activities more efficient by recording highly relevant search activities based on the user's geographical location information. Some or all of the above processing in the recording unit may be performed using, for example, a generating AI, or without a generating AI. For example, the recording unit can input the user's geographical location information into a generating AI, which can then prioritize recording highly relevant search activities.

[0082] The recording unit can analyze the user's social media activity and record relevant search activities when recording search activity. For example, the recording unit can record relevant search activities based on information shared by the user on social media. The recording unit can also extract topics of interest from the user's social media activity and record search activities related to those topics. The recording unit can also analyze the user's social media activity history and prioritize recording highly relevant search activities. This makes search activity more efficient by recording relevant search activities based on the user's social media activity. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the user's social media activity data into a generative AI, which can then record relevant search activities.

[0083] The shortcut creation unit can estimate the user's emotions and adjust how shortcuts are created based on the estimated emotions. For example, if the user is stressed, the shortcut creation unit can create a simple shortcut to simplify the operation. If the user is relaxed, the shortcut creation unit can also create a detailed shortcut and provide customizable options. If the user is in a hurry, the shortcut creation unit can also create a shortcut that can be accessed quickly. This simplifies the operation by adjusting how shortcuts are created 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 shortcut creation unit may be performed using AI or not using AI. For example, the shortcut creation unit can input user emotion data into a generative AI, the generative AI can estimate the emotion, and adjust how shortcuts are created based on the result.

[0084] The shortcut creation unit can adjust the level of detail of a shortcut based on the importance of the search action when creating a shortcut. For example, the shortcut creation unit can create a detailed shortcut for high-importance search actions. It can also create a simple shortcut for low-importance search actions. The shortcut creation unit can also dynamically adjust the level of detail of a shortcut according to the importance of the search action. This allows for the creation of efficient shortcuts by adjusting the level of detail of the shortcut according to the importance of the search action. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input search action importance data into a generation AI, and the generation AI can adjust the level of detail of the shortcut.

[0085] The shortcut creation unit can apply different shortcut creation algorithms depending on the category of the search activity when creating shortcuts. For example, the shortcut creation unit can apply an efficient shortcut creation algorithm to business-related search activities. It can also apply a user-friendly shortcut creation algorithm to entertainment-related search activities. It can also apply a shortcut creation algorithm that provides detailed information to academic-related search activities. By applying a shortcut creation algorithm according to the category of the search activity, efficient shortcuts can be created. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the shortcut creation unit can input search activity category data into a generative AI, and the generative AI can apply a shortcut creation algorithm.

[0086] The shortcut creation unit can estimate the user's emotions and adjust the length of the shortcut based on the estimated emotions. For example, if the user is stressed, the shortcut creation unit can create a short shortcut to simplify the operation. If the user is relaxed, the shortcut creation unit can also create a detailed shortcut and provide customizable options. If the user is in a hurry, the shortcut creation unit can also create a short shortcut that can be accessed quickly. This simplifies the operation by adjusting the length of the shortcut 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 shortcut creation unit may be performed using AI or not using AI. For example, the shortcut creation unit can input user emotion data into a generative AI, which can estimate the emotion and adjust the length of the shortcut based on the result.

[0087] The shortcut creation unit can determine the priority of shortcuts based on the timing of search actions when creating them. For example, the shortcut creation unit can prioritize creating shortcuts for search actions that the user performs frequently. The shortcut creation unit can also prioritize creating shortcuts for search actions that the user performs during specific time periods. The shortcut creation unit can also dynamically adjust the priority of shortcuts based on the timing of search actions. This allows for the creation of efficient shortcuts by determining the priority of shortcuts based on the timing of search actions. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input search action timing data into a generation AI, which can then determine the priority of shortcuts.

[0088] The shortcut creation unit can adjust the order of shortcuts based on the relevance of search actions when creating shortcuts. For example, the shortcut creation unit can prioritize creating shortcuts for search actions that the user frequently performs. The shortcut creation unit can also prioritize creating shortcuts for highly relevant search actions based on the user's areas of interest. The shortcut creation unit can also dynamically adjust the order of shortcuts based on the relevance of search actions. This allows for the creation of efficient shortcuts by adjusting the order of shortcuts based on the relevance of search actions. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input search relevance data into a generation AI, and the generation AI can adjust the order of shortcuts.

[0089] The program creation unit can estimate the user's emotions and adjust the program creation method based on the estimated user emotions. For example, if the user is stressed, the program creation unit can create a simple program and simplify the operation. If the user is relaxed, the program creation unit can also create a detailed program and provide customizable options. If the user is in a hurry, the program creation unit can also create a program that can be executed quickly. This simplifies the operation by adjusting the program creation 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 program creation unit may be performed using AI or not using AI. For example, the program creation unit can input user emotion data into a generative AI, the generative AI can estimate the emotions, and the program creation method can be adjusted based on the result.

[0090] The program creation unit can improve the accuracy of the program by considering the interrelationships of search actions during program creation. For example, the program creation unit analyzes the interrelationships of search actions and creates an optimal program. The program creation unit can also improve the accuracy of the program based on the interrelationships of search actions. The program creation unit can also create an efficient program by considering the interrelationships of search actions. In this way, the accuracy of the program can be improved by considering the interrelationships of search actions. Some or all of the above processing in the program creation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the program creation unit can input data on the interrelationships of search actions into a generative AI, and the generative AI can improve the accuracy of the program.

[0091] The program creation unit can create a program while considering the attribute information of the person performing the search. For example, the program creation unit can create an optimal program based on the attribute information of the person performing the search. The program creation unit can also improve the accuracy of the program by considering the attribute information of the person performing the search. The program creation unit can also create a customizable program based on the attribute information of the person performing the search. This allows for the creation of an optimal program by considering the attribute information of the person performing the search. Some or all of the above processing in the program creation unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the program creation unit can input the attribute information of the person performing the search into a generating AI, and the generating AI can create an optimal program.

[0092] The program creation unit can estimate the user's emotions and adjust the program's display method based on the estimated emotions. For example, if the user is stressed, the program creation unit can provide a simple and highly visible display method. If the user is relaxed, the program creation unit can also provide a display method that includes detailed information. If the user is in a hurry, the program creation unit can also provide a concise display method. This improves visibility by adjusting the program's 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. The 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 program creation unit may be performed using AI, for example, or without AI. For example, the program creation unit can input user emotion data into the generative AI, the generative AI can estimate the emotions, and the program's display method can be adjusted based on the result.

[0093] The program creation unit can create programs while considering the geographical distribution of search activity. For example, the program creation unit can create an optimal program based on the geographical distribution of search activity. The program creation unit can also improve the accuracy of the program by considering the geographical distribution of search activity. The program creation unit can also create an efficient program based on the geographical distribution of search activity. In this way, an optimal program can be created by considering the geographical distribution of search activity. Some or all of the above processing in the program creation unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the program creation unit can input geographical distribution data of search activity into a generative AI, and the generative AI can create an optimal program.

[0094] The program creation unit can improve the accuracy of the program by referring to relevant literature for the search activity during program creation. For example, the program creation unit creates an optimal program based on relevant literature for the search activity. The program creation unit can also improve the accuracy of the program by referring to relevant literature for the search activity. The program creation unit can also create an efficient program by considering relevant literature for the search activity. In this way, the accuracy of the program can be improved by referring to relevant literature for the search activity. Some or all of the above processing in the program creation unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the program creation unit can input data on relevant literature for the search activity into a generating AI, and the generating AI can create an optimal program.

[0095] The search results collection unit can estimate the user's emotions and adjust the display method of the search results based on the estimated emotions. For example, if the user is stressed, the search results collection unit can provide a simple and highly visible display method. If the user is relaxed, the search results collection unit can also provide a display method that includes detailed information. If the user is in a hurry, the search results collection unit can also provide a concise display method. In this way, visibility can be improved by adjusting the display method of search results 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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the search results collection unit may be performed using AI, for example, or without AI. For example, the search results collection unit can input user emotion data into a generative AI, the generative AI can estimate the emotions, and the display method of the search results can be adjusted based on the result.

[0096] The search result collection unit can predict current search results by referring to past search result data when collecting search results. For example, the search result collection unit predicts current search results based on past search result data. The search result collection unit can also present the optimal search results by referring to past search result data. The search result collection unit can also predict current search results by analyzing past search result data. This allows the current search results to be predicted by referring to past search result data. Some or all of the above processing in the search result collection unit may be performed using, for example, a generation AI, or without a generation AI. For example, the search result collection unit can input past search result data into a generation AI, and the generation AI can predict current search results.

[0097] The search result collection unit can apply different search result collection methods depending on the category of the search activity when collecting search results. For example, the search result collection unit can apply an efficient search result collection method to business-related search activities. It can also apply a user-friendly search result collection method to entertainment-related search activities. It can also apply a search result collection method that provides detailed information to academic-related search activities. By applying different search result collection methods according to the category of the search activity, efficient search results can be provided. Some or all of the above processing in the search result collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the search result collection unit can input search activity category data into a generative AI, and the generative AI can apply a search result collection method.

[0098] The search result collection unit can estimate the user's emotions and adjust the importance of search results based on the estimated emotions. For example, if the user is stressed, the search result collection unit can prioritize displaying high-importance search results. If the user is relaxed, the search result collection unit can also prioritize displaying detailed search results. If the user is in a hurry, the search result collection unit can also prioritize displaying search results that can be accessed quickly. In this way, important search results can be prioritized by adjusting the importance of search results 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 search result collection unit may be performed using AI, for example, or not using AI. For example, the search result collection unit can input user emotion data into a generative AI, the generative AI can estimate the emotions, and the importance of search results can be adjusted based on the result.

[0099] The search result collection unit can analyze changes in search results based on the timing of the search activity when collecting search results. For example, the search result collection unit analyzes changes in search results based on the timing of the search activity. The search result collection unit can also present the most suitable search results depending on the timing of the search activity. The search result collection unit can also predict changes in search results, taking into account the timing of the search activity. This allows for the provision of optimal search results by analyzing changes in search results based on the timing of the search activity. Some or all of the above processing in the search result collection unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the search result collection unit can input search activity timing data into a generating AI, which can then analyze changes in search results.

[0100] The search result collection unit can analyze search results by referring to relevant market data related to the search activity when collecting search results. For example, the search result collection unit can present optimal search results based on the relevant market data related to the search activity. The search result collection unit can also analyze search results by referring to relevant market data related to the search activity. The search result collection unit can also provide efficient search results by considering relevant market data related to the search activity. This allows for the provision of optimal search results by referring to relevant market data related to the search activity. Some or all of the above processing in the search result collection unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the search result collection unit can input relevant market data related to the search activity into a generating AI, which can then analyze the search results.

[0101] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0102] The search agent system can estimate the user's emotions and adjust how search results are displayed based on the estimated emotions. For example, if the user is stressed, a simple and highly visible display method can be provided. If the user is relaxed, a display method including detailed information can be provided. If the user is in a hurry, a display method that gets straight to the point can be provided. This improves visibility by adjusting how search 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 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 search result collection unit may be performed using AI, for example, or not using AI. For example, the search result collection unit can input user emotion data into a generative AI, the generative AI can estimate the emotions, and the display method of the search results can be adjusted based on the result.

[0103] The search agent system can analyze a user's past search behavior and select the optimal recording method. For example, it can automatically record frequently performed searches by the user, reducing manual operation. It can also extract specific patterns from the user's past search behavior and optimize the recording method based on those patterns. It can also analyze the user's past search behavior and suggest the most efficient recording method. In this way, the optimal recording method can be selected by analyzing past search behavior. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the user's past search behavior data into a generative AI, which can then select the optimal recording method.

[0104] The search agent system can estimate the user's emotions and prioritize search actions based on those emotions. For example, if the user is stressed, it can prioritize recording high-priority search actions. If the user is relaxed, it can also prioritize recording detailed search actions. If the user is in a hurry, it can also prioritize recording search actions that can be completed quickly. This allows for the prioritization of important search actions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recording unit may be performed using AI or not. For example, the recording unit can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of search actions based on the result.

[0105] The search agent system can prioritize recording highly relevant search activities by considering the user's geographical location. For example, if the user is in a specific region, it can prioritize recording search activities related to that region. It can also filter and record highly relevant search activities based on the user's geographical location. If the user is on the move, it can prioritize recording search activities related to their current location. This improves the efficiency of search activities by recording highly relevant search activities based on the user's geographical location. Some or all of the above processing in the recording unit may be performed using, for example, a generating AI, or without a generating AI. For example, the recording unit can input the user's geographical location information into a generating AI, which can then prioritize recording highly relevant search activities.

[0106] The search agent system can analyze a user's social media activity and record relevant search activities. For example, it can record relevant search activities based on information shared by the user on social media. It can also extract topics of interest from the user's social media activity and record search activities related to those topics. It can also analyze the user's social media activity history and prioritize recording highly relevant search activities. This makes search activities more efficient by recording relevant search activities based on the user's social media activity. Some or all of the above processing in the recording unit may be performed using, for example, a generative AI, or without a generative AI. For example, the recording unit can input the user's social media activity data into a generative AI, which can then record relevant search activities.

[0107] The search agent system can estimate the user's emotions and adjust how shortcuts are created based on the estimated emotions. For example, if the user is stressed, a simple shortcut can be created to simplify the operation. If the user is relaxed, a more detailed shortcut can be created, offering customizable options. If the user is in a hurry, a shortcut that can be accessed quickly can be created. This simplifies the operation by adjusting how shortcuts are created 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 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 shortcut creation unit may be performed using AI or not. For example, the shortcut creation unit can input user emotion data into the generative AI, which can estimate the emotions and adjust how shortcuts are created based on the result.

[0108] The search agent system can adjust the level of detail of shortcuts based on the importance of the search activity when creating them. For example, it can create detailed shortcuts for high-importance search activities and simple shortcuts for low-importance search activities. It can also dynamically adjust the level of detail of shortcuts according to the importance of the search activity. This allows for the creation of efficient shortcuts by adjusting the level of detail according to the importance of the search activity. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the shortcut creation unit can input search activity importance data into the generation AI, and the generation AI can adjust the level of detail of the shortcuts.

[0109] The search agent system can apply different shortcut creation algorithms depending on the category of the search activity when creating shortcuts. For example, an efficient shortcut creation algorithm can be applied to business-related searches. A user-friendly shortcut creation algorithm can be applied to entertainment-related searches. A shortcut creation algorithm that provides detailed information can be applied to academic searches. By applying a shortcut creation algorithm according to the category of the search activity, efficient shortcuts can be created. Some or all of the above processing in the shortcut creation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the shortcut creation unit can input search activity category data into a generative AI, and the generative AI can apply a shortcut creation algorithm.

[0110] The search agent system can estimate the user's emotions and adjust how the program is created based on the estimated emotions. For example, if the user is stressed, a simple program can be created to simplify the operation. If the user is relaxed, a detailed program can be created with customizable options. If the user is in a hurry, a program that can be executed quickly can be created. This simplifies the operation by adjusting how the program is created 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 program creation unit may be performed using AI, for example, or not using AI. For example, the program creation unit can input user emotion data into the generative AI, the generative AI can estimate the emotions, and the program creation method can be adjusted based on the result.

[0111] The search agent system can improve the accuracy of its program by considering the interrelationships of search actions during program creation. For example, it can analyze the interrelationships of search actions and create an optimal program. It can also improve the accuracy of the program based on the interrelationships of search actions. It can also create an efficient program by considering the interrelationships of search actions. In this way, the accuracy of the program can be improved by considering the interrelationships of search actions. Some or all of the above processing in the program creation unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the program creation unit can input data on the interrelationships of search actions into a generative AI, and the generative AI can improve the accuracy of the program.

[0112] The following briefly describes the processing flow for example form 2.

[0113] Step 1: The recording unit records the user's search activity to a specific site. For example, if a user searches for information about base stations using a specific tool, the recording unit records that search activity. The recording unit can record the sequence of actions a user performs during a search. For example, it can record the sequence of actions a user takes, such as entering search keywords, clicking the search button, and viewing the search results. Step 2: The shortcut creation unit creates shortcuts based on the search actions recorded by the recording unit. The shortcut creation unit formats the recorded operations and can automatically create programs such as RPA. For example, it can create desktop shortcuts and browser bookmarks based on recorded search actions. Step 3: The program creation unit automatically writes RPA or other programs based on the shortcuts created by the shortcut creation unit. The program creation unit can create programs using specific RPA tools or scripting languages. For example, it can create an automation script using a specific RPA tool based on recorded search actions. Step 4: The search result collection unit collects subsequent search results based on the program created by the program creation unit. The search result collection unit enables users to perform searches with simple operations. For example, users can collect search results simply by entering search information into the chat UI and pressing the execute button.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] Each of the multiple elements described above, including the recording unit, shortcut creation unit, program creation unit, and search result collection unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the recording unit is implemented by the control unit 46A of the smart device 14 and records the user's search activity to a specific site. The shortcut creation unit is implemented by the specific processing unit 290 of the data processing device 12 and creates a shortcut based on the recorded search activity. The program creation unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically creates a program such as RPA based on the shortcut. The search result collection unit is implemented by the control unit 46A of the smart device 14 and collects search results for subsequent searches. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0118] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] Each of the multiple elements described above, including the recording unit, shortcut creation unit, program creation unit, and search result collection unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the recording unit is implemented by the control unit 46A of the smart glasses 214 and records the user's search activity to a specific site. The shortcut creation unit is implemented by the specific processing unit 290 of the data processing device 12 and creates a shortcut based on the recorded search activity. The program creation unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically creates a program such as RPA based on the shortcut. The search result collection unit is implemented by the control unit 46A of the smart glasses 214 and collects search results for subsequent searches. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0134] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] Each of the multiple elements described above, including the recording unit, shortcut creation unit, program creation unit, and search result collection unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the recording unit is implemented by the control unit 46A of the headset terminal 314 and records the user's search activity to a specific site. The shortcut creation unit is implemented by the specific processing unit 290 of the data processing device 12 and creates shortcuts based on the recorded search activity. The program creation unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically creates programs such as RPA based on the shortcuts. The search result collection unit is implemented by the control unit 46A of the headset terminal 314 and collects search results for subsequent searches. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0150] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Each of the multiple elements described above, including the recording unit, shortcut creation unit, program creation unit, and search result collection unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the recording unit is implemented by the control unit 46A of the robot 414 and records the user's search activity to a specific site. The shortcut creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates shortcuts based on the recorded search activity. The program creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically creates programs such as RPA based on the shortcuts. The search result collection unit is implemented by the control unit 46A of the robot 414 and collects search results for subsequent searches. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] (Note 1) A recording unit that records the user's search activity to a specific site, A shortcut creation unit creates shortcuts based on the search activity recorded by the recording unit, A program creation unit that automatically creates RPA or other programs based on the shortcuts created by the shortcut creation unit, The system includes a search result collection unit that collects subsequent search results based on a program created by the program creation unit. A system characterized by the following features. (Note 2) The aforementioned search result collection unit, Show search results The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned search result collection unit, Manage your search history and refer to past search results. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned recording unit is The user performs a series of search actions, and these actions are recorded. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned shortcut creation unit, Format the recorded operations. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned program creation unit, Automate the creation of RPA and other programs. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned search result collection unit, Simply enter your search information into the chat UI and press the execute button to collect search results. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned recording unit is The system estimates the user's emotions and adjusts the timing of recording search activity based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned recording unit is Analyze the user's past search behavior and select the optimal recording method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned recording unit is When recording search activity, filtering is performed based on the user's current work situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned recording unit is It estimates the user's emotions and prioritizes search actions to record based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned recording unit is When recording search activity, the system prioritizes recording highly relevant search activity by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned recording unit is When recording search activity, the system analyzes the user's social media activity and records related search activity. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned shortcut creation unit, It estimates the user's emotions and adjusts how shortcuts are created based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned shortcut creation unit, When creating a shortcut, adjust the shortcut's level of detail based on the importance of the search action. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned shortcut creation unit, When creating shortcuts, different shortcut creation algorithms are applied depending on the category of the search activity. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned shortcut creation unit, It estimates the user's emotions and adjusts the length of the shortcut based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned shortcut creation unit, When creating shortcuts, the priority of the shortcuts is determined based on when the search action was performed. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned shortcut creation unit, When creating shortcuts, adjust the order of shortcuts based on the relevance of the search activity. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned program creation unit, It estimates the user's emotions and adjusts how the program is created based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned program creation unit, When creating a program, consider the interrelationships of search actions to improve the program's accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned program creation unit, When creating a program, consider the attribute information of the person performing the search. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned program creation unit, The program estimates the user's emotions and adjusts how it displays information based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned program creation unit, When creating a program, consider the geographical distribution of search activity. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned program creation unit, When creating a program, we improve its accuracy by referring to relevant literature related to the search activity. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned search result collection unit, It estimates the user's sentiment and adjusts how search results are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned search result collection unit, When collecting search results, past search result data is referenced to predict current search results. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned search result collection unit, When collecting search results, different search result collection methods are applied depending on the category of the search activity. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned search result collection unit, It estimates the user's sentiment and adjusts the importance of search results based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned search result collection unit, When collecting search results, analyze how the search results change based on when the search activity was performed. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned search result collection unit, When collecting search results, we analyze the results by referring to relevant market data related to the search activity. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0186] 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 recording unit that records the user's search activity to a specific site, A shortcut creation unit creates shortcuts based on the search activity recorded by the recording unit, A program creation unit that automatically creates RPA or other programs based on the shortcuts created by the shortcut creation unit, The system includes a search result collection unit that collects subsequent search results based on a program created by the program creation unit. A system characterized by the following features.

2. The aforementioned search result collection unit, Manage your search history and refer to past search results. The system according to feature 1.

3. The aforementioned recording unit is The user performs a series of search actions, and these actions are recorded. The system according to feature 1.

4. The shortcut creation unit described above is: Format the recorded operations. The system according to feature 1.

5. The aforementioned program creation unit, Automate the creation of RPA and other programs. The system according to feature 1.

6. The aforementioned search result collection unit, Simply enter your search information into the chat UI and press the execute button to collect search results. The system according to feature 1.

7. The aforementioned recording unit is The system estimates the user's emotions and adjusts the timing of recording search activity based on those estimated emotions. The system according to feature 1.

Images