system
The system addresses repetitive search inefficiencies by automating and personalizing information retrieval through recorded queries, emotion-based adjustments, and generative AI, enhancing user experience and productivity.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- SOFTBANK GROUP CORP
- Filing Date
- 2024-10-11
- Publication Date
- 2026-04-23
AI Technical Summary
Existing information retrieval systems require repetitive and time-consuming search operations, reducing user productivity and failing to provide personalized or emotionally sensitive results.
A system that records user search queries, generates shortcuts, and automates the search process using RPA, integrates emotion engines to adjust queries based on user emotions, and uses generative AI to organize and present results efficiently.
Significantly reduces search effort, enhances user satisfaction by providing personalized and emotionally tailored information, improving productivity and decision-making efficiency.
Smart Images

Figure 2026069098000001_ABST
Abstract
Description
Technical Field
[0001] The technology of the present disclosure relates to a system.
Background Art
[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] In information retrieval, the search operations on a specific website repeatedly performed by many users require time and effort and are factors reducing productivity. There is a need for a system to streamline such repetitive search tasks and enable users to concentrate on more important tasks.
Means for Solving the Problems
[0005] The present invention provides a means for recording the user's initial search query and generating shortcuts based on it. By using these shortcuts to automate the process, a generation agent can automatically collect search results. This reduces the time users spend searching, allowing them to focus on other important tasks. The collected search results are presented to the user in an organized format, improving the efficiency of information retrieval.
[0006] A "user" is an individual or organization that enters a search query on a specific website and attempts to obtain information.
[0007] A "search query" is a word or phrase that a user enters into a search engine to obtain specific information.
[0008] "Means of recording" refers to a function that saves the user's search operations as data and makes them available for use in subsequent processes.
[0009] A "shortcut" is a concise procedure or instruction for a process created to simplify repetitive tasks.
[0010] "Process automation" is a system that uses software to automatically perform repetitive operations.
[0011] A "search result generation agent" is an automated program or system that operates on behalf of a user to retrieve information based on a search query.
[0012] "Means of presentation" refers to functions that display collected information in an easy-to-understand manner for the user. [Brief explanation of the drawing]
[0013] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. <000007!> [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined. <{0000085}}
MODE FOR CARRYING OUT THE INVENTION
[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.
[0015] First, the terms used in the following description will be explained.
[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.
[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.
[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.
[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.
[0020] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."
[0021] [First Embodiment]
[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.
[0023] As shown in Figure 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.
[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).
[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.
[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.
[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.
[0028] 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.
[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.
[0030] As shown in Figure 2, in the data processing device 12, 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.
[0031] The 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.
[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.
[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".
[0034] The system according to the present invention provides a process for recording and automating specific search operations performed by a user. First, the user accesses a specific website using a terminal and enters a search query. The terminal records the user's search query input and related operations for later use. This recorded data is sent to a server, which generates shortcuts for the search operations based on that information.
[0035] This shortcut will be used for subsequent searches, enabling process automation. Specifically, the RPA (Robotic Process Automation) configured on the terminal will use this shortcut to perform an automated search based on the user's new search query. The server collects the search results obtained through the automated search process via a generating agent. The server then analyzes these search results and organizes them in a way that is easy for the user to understand. The organized information is presented to the user through the terminal, allowing the user to efficiently obtain the necessary information.
[0036] As a concrete example, consider a scenario where a user frequently searches for product information. During the initial product information search, the terminal records the user's actions. Subsequently, the server generates a shortcut, and the next time the user searches for a different product, the automated process on the terminal quickly performs the search, and the server accurately organizes and provides the results. This method significantly reduces the effort required for searches, allowing the user to focus on other important tasks.
[0037] The following describes the processing flow.
[0038] Step 1:
[0039] A user accesses a specific website using their device and enters a search query. The device records the user's search query and subsequent actions (e.g., clicking the search button).
[0040] Step 2:
[0041] The terminal sends the search operation data it recorded to the server. The server receives this data and saves it for future use.
[0042] Step 3:
[0043] The server analyzes the received data and generates shortcuts to the search operations performed by the user. These generated shortcuts are simplified procedures that allow for the rapid reproduction of similar searches.
[0044] Step 4:
[0045] The RPA configured on the terminal receives a shortcut sent from the server and builds an automated process based on that shortcut.
[0046] Step 5:
[0047] The next time the user enters a new search query, the RPA on the terminal will use existing shortcuts to automatically perform the search. The user only needs to enter the search query.
[0048] Step 6:
[0049] A generation agent on the server collects search results obtained through automated searches. These results are then analyzed and organized in a way that is most beneficial to the user.
[0050] Step 7:
[0051] The terminal receives organized search results from the server and presents them to the user. This allows the user to efficiently obtain the necessary information and concentrate on other tasks.
[0052] (Example 1)
[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."
[0054] Modern information retrieval requires the efficient and rapid acquisition of necessary information from a wide variety of websites. However, manual information retrieval by users each time is time-consuming and laborious, and organizing search results is dependent on the individual, leading to decreased efficiency. This reduces productivity, so there is a need for methods to automate the information retrieval process and organize and provide the acquired information.
[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.
[0056] In this invention, the server includes means for recording information retrieval requests entered via an information terminal operated by a user, means for constructing an information acquisition procedure based on the recorded information operations, and means for automating the operation flow based on the constructed information acquisition procedure. This makes it possible to streamline the user's search process and quickly obtain the necessary information.
[0057] An "information retrieval request" is an instruction that a user enters via an information terminal in order to obtain specific information.
[0058] An "information terminal" is a type of electronic device used by users to input and receive information, and includes computers and smartphones.
[0059] A "recording device" is a system or tool used to save user actions and input data.
[0060] An "information acquisition procedure" is a set of operational flows or processes designed to efficiently collect specific information based on recorded data.
[0061] A "construction device" is a system that analyzes recorded information to create new procedures and processes.
[0062] "Operation flow automation" refers to a set of steps configured to mechanically and repeatedly perform operations that were previously done manually.
[0063] A "collection mechanism" is a system or tool used to analyze and organize collected information.
[0064] "Analysis" is the process of scrutinizing collected information and extracting the necessary data.
[0065] "Presenting information visually" refers to displaying organized information in a graphical format so that users can easily understand it.
[0066] This invention is a system that enables efficient information retrieval and processing based on an information terminal operated by the user. Specifically, when a user makes a search request through the input device of the information terminal, the terminal records the request and related operations. The recorded data is analyzed using Python, JavaScript (registered trademark), etc., and an information retrieval procedure is constructed. This procedure is stored and managed on a server.
[0067] Information terminals are equipped with RPA (Robotic Process Automation) software to automate operations, which helps to streamline repetitive user actions. Examples of RPA tools include UiPath and Automation Anywhere. This allows the terminal to execute automated workflows when a user searches for different information, enabling it to quickly collect the necessary data.
[0068] The collected data is analyzed by a collection mechanism on the server, and the necessary information is extracted and organized. Using a generative AI model, the data is formatted into a visually easy-to-understand format for the user. This formatted information is then provided to the user through a web browser or application, significantly improving the efficiency of information selection.
[0069] As a concrete example, consider a case where a user is "researching a new product." First, when the user starts a search on their information terminal, the steps are recorded. From the next time onward, the terminal executes an automated process based on the information retrieval procedure generated on the server, and the server quickly organizes and provides the results. This process allows the user to quickly obtain the latest information without any extra effort.
[0070] An example of a prompt message is as follows:
[0071] "Please automate the process of researching new products, and make it manageable and executable on a server."
[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.
[0073] Step 1:
[0074] The user uses an information terminal to enter a specific information retrieval request. The entered search query and user actions such as clicks are recorded on the terminal. This serves as foundational data for analyzing what the user is searching for and how they are pursuing information. The input consists of the user's search queries and action logs, while the output is this recorded data.
[0075] Step 2:
[0076] The terminal sends the recorded data to the server. The server analyzes the received data and constructs an information retrieval procedure. In this process, data aggregation and pattern matching are performed using scripts written in Python or similar languages. The output is the generated information retrieval procedure.
[0077] Step 3:
[0078] When the user searches for information again, the terminal automates the operation flow based on the established information retrieval procedure. Specifically, an RPA tool is used to replicate the user's search operation. The input is the previous procedure, and the output is the automated search results.
[0079] Step 4:
[0080] The server then re-analyzes the data collected through automated processes. It uses generative AI models to extract useful information and format the data to meet specific requirements. For example, it leverages natural language processing techniques to create structured information from unstructured data. The output is visualized information.
[0081] Step 5:
[0082] The user receives information organized and analyzed on the server via their terminal. The information is presented in a dashboard format, allowing the user to quickly and efficiently access the necessary data. Based on the output of prompts, specific actions are taken to support the user's decision-making. The output is visualized data that supports the user's decision-making.
[0083] (Application Example 1)
[0084] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."
[0085] In today's information-saturated environment, there is a need for effective search methods to efficiently obtain product and service information that users frequently access. However, traditional methods involve time-consuming search operations and information gathering, wasting valuable user time. Furthermore, there is a lack of systems that can quickly and appropriately present the information users need, making efficient information presentation, which contributes to faster decision-making, a key challenge.
[0086] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.
[0087] In this invention, the server includes means for recording information requests entered by the user, means for generating abbreviated operations based on the recorded information requests, means for automating processing based on the generated abbreviated operations, means for quickly displaying relevant information for subsequent use based on the user's operation history, and means for collecting information through automated processing and presenting it to the user in an organized manner. This enables the user to quickly and efficiently obtain the necessary information, saving time and accelerating decision-making.
[0088] A "user" refers to an entity that utilizes a particular system or device, and is a human being or a similar entity that performs operations.
[0089] An "information request" is an inquiry or query issued by a user when they want specific data or information.
[0090] "Means of recording" refers to a function that saves entered information and operation details and retains them for later use or analysis.
[0091] A "shortcut operation" is a process that simplifies multiple operations or procedures to enable a series of actions to be performed quickly.
[0092] "Means of generation" refers to functions and methods for creating new data or processes.
[0093] "Process automation" is a technology that makes it possible to mechanically execute processes that would normally be performed manually.
[0094] A "communication terminal" is a hardware device capable of data communication, and includes smartphones and tablets.
[0095] A "data processing device" refers to a computer or server used to manipulate, transform, and store data.
[0096] "Means of organizing and presenting information" refers to methods of analyzing and structuring collected data and displaying it in a format that is easy for users to understand.
[0097] This invention provides a system for users to quickly and efficiently acquire information. This system operates in cooperation with a server and a communication terminal and has the following configuration.
[0098] The server acts as a data processing unit, recording the information requests entered by the user. The recorded information serves as the basis for generating abbreviations to smoothly present search results. These generated abbreviations form the foundation for automating subsequent searches. The abbreviations are automatically generated based on data generated within the server and stored in a database.
[0099] The communication terminal is a user-operated device. Information requests entered on this device are recorded in real time, creating batches that automate specific processes. This process allows for the rapid display of relevant information for subsequent use based on the user's operation history. The communication terminal also serves as a means of presenting organized information to the user; after collecting the information, it visualizes and presents it in an easy-to-understand manner.
[0100] As an example, consider a case where a user searches for "popular gadgets" on their smartphone. This information request is recorded on the device, and a shortened search query is generated by the server. The next time the user opens the app, the latest information related to "popular gadgets" can be instantly presented to the user.
[0101] Using a generative AI model, the system analyzes information in real time and presents appropriate information based on prompts. Based on an example prompt, "Tell me about this week's popular wireless earphones," the server organizes the most relevant information for the user and sends it to their device. This system improves the efficiency of information retrieval, saving time.
[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.
[0103] Step 1:
[0104] The user enters a search query on a communication terminal. The entered information is recorded on the terminal. This input information is stored as data before being sent to the server.
[0105] Step 2:
[0106] The terminal sends the recorded information request to the server. The server stores the received information request in a database and generates abbreviated operations based on this information. The entered information request is stored in the database and used for subsequent searches.
[0107] Step 3:
[0108] The server uses a generative AI model to analyze received information requests and create shortened operations. It receives recorded information requests as input, analyzes them to find the data most relevant to the information the user is looking for, and generates shortened operations as output.
[0109] Step 4:
[0110] After the abbreviated operation is saved in the database, it is sent to the terminal when the user requests the relevant information again. At this point, the terminal executes the abbreviated operation, and from then on, the automated process provides the user with the information they need immediately. This is a concrete example of how the report generation function visually generates reports.
[0111] Step 5:
[0112] When a user requests the latest information using their device, the device receives search results from the server obtained from the generating AI model, organizes the retrieved data, and displays it to the user. It receives shortcut operations and new information requests from the user as input, organizes the data, and presents an easy-to-understand information report as output.
[0113] This series of processes allows users to quickly and efficiently obtain information and provide information based on prompts. The prompt "Tell me about this week's popular wireless earphones" is a specific example of how this process is quickly responded to.
[0114] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.
[0115] The system of this invention integrates an emotion engine to streamline user search operations. The emotion engine recognizes the user's emotional state and adjusts the search process accordingly. When a user enters a search query on a terminal, the terminal records the search and sends it to the server. The server generates shortcuts based on this data to prepare for future automated searches.
[0116] The emotion engine estimates user emotions from their input and interactions, and uses that information to derive the most suitable search results. If the user's emotions are positive, it will present standard search results; if negative, it will prioritize displaying more encouraging and supportive information. This feature provides feedback that matches the user's current emotional state, resulting in a more personalized information retrieval experience.
[0117] For example, if a user searches for "relaxation methods" while feeling stressed, the emotion engine will read the user's emotions and highlight information that is effective for relaxation. On the other hand, if the user is in a good mood, it will actively recommend information for learning new relaxation techniques. This allows users to have a search experience that is linked to their own emotions.
[0118] This system utilizes a generation agent provided by a server to collect search results, which are then analyzed by an emotion engine before being presented to the user via their device. This emotion-based system allows users to access important information with less effort and improve their satisfaction by receiving search results tailored to their own emotions.
[0119] The following describes the processing flow.
[0120] Step 1:
[0121] A user accesses a specific website using their device and enters a search query. The user's search query and related actions are recorded by the device.
[0122] Step 2:
[0123] The device sends the recorded search operation data to the server. The server receives this data and stores it for future use.
[0124] Step 3:
[0125] The server analyzes the received data and generates shortcuts based on the user's search actions. These shortcuts are simplified procedures for quickly reproducing similar searches.
[0126] Step 4:
[0127] The emotion engine configured in the device analyzes the user's input and interactions to estimate their current emotional state.
[0128] Step 5:
[0129] The emotion engine adjusts search queries based on the user's emotional state. For example, if a user is feeling stressed, it prioritizes information about relaxation methods.
[0130] Step 6:
[0131] Using shortcuts generated by the server and sentiment-adjusted queries, the RPA on the terminal automatically executes the search process.
[0132] Step 7:
[0133] A generation agent on the server collects search results gathered by the search process. Optimization results are then generated based on the analysis of the sentiment engine.
[0134] Step 8:
[0135] The device receives organized and optimized search results from the server and presents them to the user. This allows the user to quickly obtain search results that best suit their mood and focus on other tasks.
[0136] (Example 2)
[0137] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".
[0138] In search systems designed for efficient information retrieval, there is a problem in providing information that is sensitive to the user's emotions. Conventional systems present results without considering the user's individual emotional state, which can lead to decreased user satisfaction.
[0139] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.
[0140] In this invention, the server includes means for recording information requests entered by the user, means for generating shortcuts based on the recorded information requests, and means for performing emotion processing to analyze the user's emotional state. This makes it possible to provide results optimized according to the user's emotions.
[0141] An "information request" is a general term for the data or queries that a user enters into a search system.
[0142] A "shortcut" is a shortcut process created to streamline the user's search process.
[0143] "Emotional processing" is a process that analyzes the user's emotions and optimizes the information provided based on the results.
[0144] A "generating agent" is a device or program that has the function of deriving the optimal search results using a specific algorithm or technology.
[0145] A "Central Information Processing Unit" is a primary computer system used for data processing and sentiment analysis across the entire system.
[0146] A "terminal device" is an electronic device that includes input devices for direct user operation.
[0147] This invention is a system that analyzes a user's emotional state based on their information requests and provides optimal search results. The main components of the system include a terminal device that receives information requests from the user, a central information processing device that records and analyzes the information, and a generation agent that generates and provides the results.
[0148] The user enters a search query using a terminal device. This terminal can be a general-purpose computer or smart device, and information is entered via the appropriate interface. The entered information request is sent to the central information processing unit.
[0149] The server acts as a central information processing unit, receiving information requests. Based on the recorded information, this server generates shortcuts and builds the foundation for utilizing generation agents. It also analyzes the user's emotional state from their input using an emotion processing engine. For emotion processing, natural language processing libraries (e.g., NLTK and spaCy) are used to determine whether the user's emotions are positive or negative.
[0150] Based on the analyzed sentiment data, the server utilizes a generative AI model to generate user-optimized search results. This highlights results and information that are relevant to the user's emotional state.
[0151] The terminal device displays search results received from the server to the user. For example, if a user searches for "ways to relieve stress," and negative emotions are detected, content effective for relaxation will be displayed. Conversely, if positive emotions are detected, new relaxation techniques will be recommended.
[0152] An example of a prompt message would be: "The user is experiencing high stress and is searching for relaxation methods. Please suggest a plan that prioritizes providing information effective for relaxation." This system allows users to efficiently obtain a search experience tailored to their emotional state.
[0153] The flow of the specific processing in Example 2 will be explained using Figure 13.
[0154] Step 1:
[0155] The user enters an information request on the terminal. The user enters queries through the interface on the terminal device to obtain specific information or knowledge of interest. For example, they might enter a specific request in text format, such as "a nearby cafe." The entered data is sent from the terminal to the server as an information request.
[0156] Step 2:
[0157] The server receives and records information requests. The server records the received information requests in a database and uses this as basic data for analysis. Specifically, it parses the query content and compares it with past request history stored in the database. This information is used in the sentiment analysis and shortcut generation steps described later.
[0158] Step 3:
[0159] The server analyzes the user's emotional state. Using a natural language processing library, the server analyzes the user's emotions from the information request. It performs text analysis on the input language data and extracts the positive / negative tendencies of keywords. Based on this analysis, it evaluates the user's emotional state. The output identifies the user's emotional state as either positive or negative.
[0160] Step 4:
[0161] The server generates search results based on the user's emotional state. The server utilizes a generative AI model to produce search results that reflect the analyzed emotional information. Specifically, if the emotional state is positive, it prioritizes information offering new experiences; if it's negative, it prioritizes information related to comfort and relaxation. The resulting search results are output as an information set adjusted according to the user's emotional state.
[0162] Step 5:
[0163] The server sends the generated search results to the device. To deliver information that reflects the user's emotional state, the server sends the generated search results to the device as data packets. The transmitted data is visualized in real time for the user, providing personalized feedback.
[0164] Step 6:
[0165] The device displays results optimized for the user. Based on search results received from the server, the device visually displays information relevant to the user. By receiving information customized based on their own emotions, users can enjoy a more satisfying experience.
[0166] (Application Example 2)
[0167] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".
[0168] Traditional search systems often provide uniform search results without considering the user's emotional state, which can lead to decreased user satisfaction. Furthermore, they fail to offer a personalized search experience, hindering users from quickly accessing the information they seek.
[0169] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.
[0170] In this invention, the server includes means for recognizing the user's emotional state, means for adjusting search queries based on the recognized emotions, and means for customizing the information provided. This enables the rapid provision of information appropriate to the user's emotions, resulting in a personalized search experience.
[0171] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's emotions from their facial expressions, voice, input actions, etc., and identify that state.
[0172] "Means of adjusting search queries" refers to technologies that automatically correct or transform search queries entered by users based on the recognized emotional state of the user.
[0173] "Methods for generating shortcuts" are techniques that identify frequently used processes from previously recorded search operations and create shortened paths to simplify them.
[0174] "Means of process automation" refers to technologies that automate a series of steps to efficiently perform search operations based on generated shortcuts.
[0175] "Means for activating generation agents" refers to technologies that activate agents to quickly collect necessary information through automated processes.
[0176] "Means of presenting collected search results to the user" refers to technologies that appropriately organize information collected by a generating agent and present it to the user visually or audibly.
[0177] The system for realizing this invention integrates and functions with numerous components to provide a personalized search experience based on the user's emotions.
[0178] When a user enters a search query, the device uses its built-in emotion recognition capabilities to capture facial expressions and voice via the camera and microphone, and analyze the user's emotional state. This utilizes emotion recognition APIs such as Microsoft® Azure® Face API and Google® Cloud Vision API. The emotional state data is then sent to a server.
[0179] The server performs calculations to adjust the results based on this emotional state and the search query entered by the user. This process incorporates logic to learn patterns from past search history and generate appropriate shortcuts. It also activates a generation agent to quickly gather the necessary information through an automated process.
[0180] Furthermore, the search results obtained from the server are customized according to the user's emotions and presented on the device. When the user is expressing negative emotions, content related to relaxation and support is emphasized, while content encouraging excitement and new experiences is displayed when the user is expressing positive emotions.
[0181] For example, if a user searches for "ways to refresh," the device analyzes their emotions, and the server uses that emotion data to provide information on appropriate ways to refresh. Because users can easily obtain information that matches their interests, the satisfaction of the search experience improves.
[0182] An example of a prompt to input into a generative AI model would be, "Create an algorithm that refines search queries based on the user's emotions and recommends the most suitable products and information." This enables personalized information delivery tailored to that user.
[0183] The flow of a specific process in Application Example 2 will be explained using Figure 14.
[0184] Step 1:
[0185] The device accepts the user's search query input. As the user enters a specific query, the device's camera and microphone capture the user's facial expressions and voice. The input consists of the search query and the captured emotion-related data.
[0186] Step 2:
[0187] The device calls an emotion recognition API and analyzes the emotional state from the captured data. Using Microsoft Azure Face API and Google Cloud Vision API, the user's emotions are classified as "positive," "negative," "neutral," etc. The output is the user's emotional state data.
[0188] Step 3:
[0189] The terminal sends user emotional state data and search queries to the server. This data is input into the server's search process adjustment module. The server receives these inputs and begins the next calculation.
[0190] Step 4:
[0191] The server adjusts the search query based on the emotional state data it receives. It processes the data to add specific keywords or change the search scope according to the user's emotions. The adjusted search query is then output.
[0192] Step 5:
[0193] The server's shortcut generation module generates relevant shortcuts from past history based on the adjusted search query. This data becomes the input for the next automated process. The generated shortcuts are steps to quickly process the query.
[0194] Step 6:
[0195] The server automates the process based on the generated shortcuts. The automated process allows the generating agent to collect the necessary information. This process utilizes efficient data retrieval logic to obtain the required information from various databases and information sources.
[0196] Step 7:
[0197] The server re-evaluates the collected search results and prioritizes the most relevant information based on the user's emotional state. The prioritized search results become the final output and are prepared for transmission to the device.
[0198] Step 8:
[0199] The device presents the search results received from the server to the user. Information is displayed in a way that matches the user's emotions, improving the user's search experience. Here, the user can receive personalized feedback that responds to their emotions.
[0200] 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.
[0201] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0202] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.
[0203] [Second Embodiment]
[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.
[0205] 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.
[0206] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).
[0207] 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.
[0208] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.
[0209] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).
[0210] 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.
[0211] 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 using the processor 28. The storage 32 stores the specific processing program 56.
[0212] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.
[0213] The 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.
[0214] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.
[0215] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".
[0216] The system according to the present invention provides a process for recording and automating specific search operations performed by a user. First, the user accesses a specific website using a terminal and enters a search query. The terminal records the user's search query input and related operations for later use. This recorded data is sent to a server, which generates shortcuts for the search operations based on that information.
[0217] This shortcut will be used for subsequent searches, enabling process automation. Specifically, the RPA (Robotic Process Automation) configured on the terminal will use this shortcut to perform an automated search based on the user's new search query. The server collects the search results obtained through the automated search process via a generating agent. The server then analyzes these search results and organizes them in a way that is easy for the user to understand. The organized information is presented to the user through the terminal, allowing the user to efficiently obtain the necessary information.
[0218] As a concrete example, consider a scenario where a user frequently searches for product information. During the initial product information search, the terminal records the user's actions. Subsequently, the server generates a shortcut, and the next time the user searches for a different product, the automated process on the terminal quickly performs the search, and the server accurately organizes and provides the results. This method significantly reduces the effort required for searches, allowing the user to focus on other important tasks.
[0219] The following describes the processing flow.
[0220] Step 1:
[0221] A user accesses a specific website using their device and enters a search query. The device records the user's search query and subsequent actions (e.g., clicking the search button).
[0222] Step 2:
[0223] The terminal sends the search operation data it recorded to the server. The server receives this data and saves it for future use.
[0224] Step 3:
[0225] The server analyzes the received data and generates shortcuts to the search operations performed by the user. These generated shortcuts are simplified procedures that allow for the rapid reproduction of similar searches.
[0226] Step 4:
[0227] The RPA configured on the terminal receives a shortcut sent from the server and builds an automated process based on that shortcut.
[0228] Step 5:
[0229] The next time the user enters a new search query, the RPA on the terminal will use existing shortcuts to automatically perform the search. The user only needs to enter the search query.
[0230] Step 6:
[0231] A generation agent on the server collects search results obtained through automated searches. These results are then analyzed and organized in a way that is most beneficial to the user.
[0232] Step 7:
[0233] The terminal receives organized search results from the server and presents them to the user. This allows the user to efficiently obtain the necessary information and concentrate on other tasks.
[0234] (Example 1)
[0235] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."
[0236] Modern information retrieval requires the efficient and rapid acquisition of necessary information from a wide variety of websites. However, manual information retrieval by users each time is time-consuming and laborious, and organizing search results is dependent on the individual, leading to decreased efficiency. This reduces productivity, so there is a need for methods to automate the information retrieval process and organize and provide the acquired information.
[0237] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.
[0238] In this invention, the server includes means for recording information retrieval requests entered via an information terminal operated by a user, means for constructing an information acquisition procedure based on the recorded information operations, and means for automating the operation flow based on the constructed information acquisition procedure. This makes it possible to streamline the user's search process and quickly obtain the necessary information.
[0239] An "information retrieval request" is an instruction that a user enters via an information terminal in order to obtain specific information.
[0240] An "information terminal" is a type of electronic device used by users to input and receive information, and includes computers and smartphones.
[0241] A "recording device" is a system or tool used to save user actions and input data.
[0242] An "information acquisition procedure" is a set of operational flows or processes designed to efficiently collect specific information based on recorded data.
[0243] A "construction device" is a system that analyzes recorded information to create new procedures and processes.
[0244] "Operation flow automation" refers to a set of steps configured to mechanically and repeatedly perform operations that were previously done manually.
[0245] A "collection mechanism" is a system or tool used to analyze and organize collected information.
[0246] "Analysis" is the process of scrutinizing collected information and extracting the necessary data.
[0247] "Presenting information visually" refers to displaying organized information in a graphical format so that users can easily understand it.
[0248] This invention is a system that enables efficient information retrieval and processing based on an information terminal operated by the user. Specifically, when a user makes a search request through the input device of the information terminal, the terminal records the request and related operations. The recorded data is analyzed using Python, JavaScript, or other languages to construct an information retrieval procedure. This procedure is stored and managed on a server.
[0249] Information terminals are equipped with RPA (Robotic Process Automation) software to automate operations, which helps to streamline repetitive user actions. Examples of RPA tools include UiPath and Automation Anywhere. This allows the terminal to execute automated workflows when a user searches for different information, enabling it to quickly collect the necessary data.
[0250] The collected data is analyzed by a collection mechanism on the server, and the necessary information is extracted and organized. Using a generative AI model, the data is formatted into a visually easy-to-understand format for the user. This formatted information is then provided to the user through a web browser or application, significantly improving the efficiency of information selection.
[0251] As a concrete example, consider a case where a user is "researching a new product." First, when the user starts a search on their information terminal, the steps are recorded. From the next time onward, the terminal executes an automated process based on the information retrieval procedure generated on the server, and the server quickly organizes and provides the results. This process allows the user to quickly obtain the latest information without any extra effort.
[0252] An example of a prompt message is as follows:
[0253] "Please automate the process of researching new products, and make it manageable and executable on a server."
[0254] The flow of the specific processing in Example 1 will be explained using Figure 11.
[0255] Step 1:
[0256] The user uses an information terminal to enter a specific information retrieval request. The entered search query and user actions such as clicks are recorded on the terminal. This serves as foundational data for analyzing what the user is searching for and how they are pursuing information. The input consists of the user's search queries and action logs, while the output is this recorded data.
[0257] Step 2:
[0258] The terminal sends the recorded data to the server. The server analyzes the received data and constructs an information retrieval procedure. In this process, data aggregation and pattern matching are performed using scripts written in Python or similar languages. The output is the generated information retrieval procedure.
[0259] Step 3:
[0260] When the user searches for information again, the terminal automates the operation flow based on the established information retrieval procedure. Specifically, an RPA tool is used to replicate the user's search operation. The input is the previous procedure, and the output is the automated search results.
[0261] Step 4:
[0262] The server then re-analyzes the data collected through automated processes. It uses generative AI models to extract useful information and format the data to meet specific requirements. For example, it leverages natural language processing techniques to create structured information from unstructured data. The output is visualized information.
[0263] Step 5:
[0264] The user receives information organized and analyzed on the server via their terminal. The information is presented in a dashboard format, allowing the user to quickly and efficiently access the necessary data. Based on the output of prompts, specific actions are taken to support the user's decision-making. The output is visualized data that supports the user's decision-making.
[0265] (Application Example 1)
[0266] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."
[0267] In today's information-saturated environment, there is a need for effective search methods to efficiently obtain product and service information that users frequently access. However, traditional methods involve time-consuming search operations and information gathering, wasting valuable user time. Furthermore, there is a lack of systems that can quickly and appropriately present the information users need, making efficient information presentation, which contributes to faster decision-making, a key challenge.
[0268] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.
[0269] In this invention, the server includes means for recording information requests entered by the user, means for generating abbreviated operations based on the recorded information requests, means for automating processing based on the generated abbreviated operations, means for quickly displaying relevant information for subsequent use based on the user's operation history, and means for collecting information through automated processing and presenting it to the user in an organized manner. This enables the user to quickly and efficiently obtain the necessary information, saving time and accelerating decision-making.
[0270] A "user" refers to an entity that utilizes a particular system or device, and is a human being or a similar entity that performs operations.
[0271] An "information request" is an inquiry or query issued by a user when they want specific data or information.
[0272] "Means of recording" refers to a function that saves entered information and operation details and retains them for later use or analysis.
[0273] A "shortcut operation" is a process that simplifies multiple operations or procedures to enable a series of actions to be performed quickly.
[0274] "Means of generation" refers to functions and methods for creating new data or processes.
[0275] "Process automation" is a technology that makes it possible to mechanically execute processes that would normally be performed manually.
[0276] A "communication terminal" is a hardware device capable of data communication, and includes smartphones and tablets.
[0277] A "data processing device" refers to a computer or server used to manipulate, transform, and store data.
[0278] "Means of organizing and presenting information" refers to methods of analyzing and structuring collected data and displaying it in a format that is easy for users to understand.
[0279] This invention provides a system for users to quickly and efficiently acquire information. This system operates in cooperation with a server and a communication terminal and has the following configuration.
[0280] The server acts as a data processing unit, recording the information requests entered by the user. The recorded information serves as the basis for generating abbreviations to smoothly present search results. These generated abbreviations form the foundation for automating subsequent searches. The abbreviations are automatically generated based on data generated within the server and stored in a database.
[0281] The communication terminal is a user-operated device. Information requests entered on this device are recorded in real time, creating batches that automate specific processes. This process allows for the rapid display of relevant information for subsequent use based on the user's operation history. The communication terminal also serves as a means of presenting organized information to the user; after collecting the information, it visualizes and presents it in an easy-to-understand manner.
[0282] As an example, consider a case where a user searches for "popular gadgets" on their smartphone. This information request is recorded on the device, and a shortened search query is generated by the server. The next time the user opens the app, the latest information related to "popular gadgets" can be instantly presented to the user.
[0283] Using a generative AI model, the system analyzes information in real time and presents appropriate information based on prompts. Based on an example prompt, "Tell me about this week's popular wireless earphones," the server organizes the most relevant information for the user and sends it to their device. This system improves the efficiency of information retrieval, saving time.
[0284] The process flow of the specific process in Application Example 1 will be described using FIG. 12.
[0285] Step 1:
[0286] The user enters a search query on the communication terminal. The entered information is recorded on the terminal. This input information is data that is saved as a preliminary step before being sent to the server.
[0287] Step 2:
[0288] The terminal sends the recorded information request to the server. The server saves the received information request in the database and generates a shortening operation based on this information. The input information request is stored in the database and used for subsequent searches.
[0289] Step 3:
[0290] The server analyzes the received information request using the generated AI model and creates a shortening operation. By receiving and analyzing the information request recorded as input, it finds the data most relevant to the information required by the user and generates a shortening operation as output.
[0291] Step 4:
[0292] After the shortening operation is saved in the database, it is sent to the terminal when the user requests relevant information again. At this time, the terminal executes the shortening operation, and in subsequent times, the information required by the user is immediately provided by an automated process. This is a specific operation where a report is visually generated by the report creation function.
[0293] Step 5:
[0294] When a user requests the latest information using their device, the device receives search results from the server obtained from the generating AI model, organizes the retrieved data, and displays it to the user. It receives shortcut operations and new information requests from the user as input, organizes the data, and presents an easy-to-understand information report as output.
[0295] This series of processes allows users to quickly and efficiently obtain information and provide information based on prompts. The prompt "Tell me about this week's popular wireless earphones" is a specific example of how this process is quickly responded to.
[0296] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.
[0297] The system of this invention integrates an emotion engine to streamline user search operations. The emotion engine recognizes the user's emotional state and adjusts the search process accordingly. When a user enters a search query on a terminal, the terminal records the search and sends it to the server. The server generates shortcuts based on this data to prepare for future automated searches.
[0298] The emotion engine estimates user emotions from their input and interactions, and uses that information to derive the most suitable search results. If the user's emotions are positive, it will present standard search results; if negative, it will prioritize displaying more encouraging and supportive information. This feature provides feedback that matches the user's current emotional state, resulting in a more personalized information retrieval experience.
[0299] As a specific example, when a user searches for "relaxation methods" in a stressed state, the emotion engine reads the user's emotion and emphasizes information effective for relaxation. On the other hand, in a good mood, it actively recommends information for learning new relaxation techniques. As a result, the user can obtain a search experience linked to their own emotions.
[0300] This system utilizes a generation agent provided by a server to collect search results. After analysis by the emotion engine, it presents the results to the user through a terminal. By using this system based on the emotion engine, the user can not only access important information with less effort but also improve their satisfaction by receiving search results according to their emotions.
[0301] The following explains the processing flow.
[0302] Step 1:
[0303] The user uses a terminal to access a specific website and enters a search query. The operations related to the user's search query are recorded by the terminal.
[0304] Step 2:
[0305] The terminal sends the recorded search operation data to the server. The server receives this data and saves it for future use.
[0306] Step 3:
[0307] The server analyzes the received data and generates a shortcut based on the user's search operation. This shortcut is a simplified procedure for quickly reproducing similar searches.
[0308] Step 4:
[0309] The emotion engine configured in the device analyzes the user's input and interactions to estimate their current emotional state.
[0310] Step 5:
[0311] The emotion engine adjusts search queries based on the user's emotional state. For example, if a user is feeling stressed, it prioritizes information about relaxation methods.
[0312] Step 6:
[0313] Using shortcuts generated by the server and sentiment-adjusted queries, the RPA on the terminal automatically executes the search process.
[0314] Step 7:
[0315] A generation agent on the server collects search results gathered by the search process. Optimization results are then generated based on the analysis of the sentiment engine.
[0316] Step 8:
[0317] The device receives organized and optimized search results from the server and presents them to the user. This allows the user to quickly obtain search results that best suit their mood and focus on other tasks.
[0318] (Example 2)
[0319] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".
[0320] In search systems designed for efficient information retrieval, there is a problem in providing information that is sensitive to the user's emotions. Conventional systems present results without considering the user's individual emotional state, which can lead to decreased user satisfaction.
[0321] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.
[0322] In this invention, the server includes means for recording information requests entered by the user, means for generating shortcuts based on the recorded information requests, and means for performing emotion processing to analyze the user's emotional state. This makes it possible to provide results optimized according to the user's emotions.
[0323] An "information request" is a general term for the data or queries that a user enters into a search system.
[0324] A "shortcut" is a shortcut process created to streamline the user's search process.
[0325] "Emotional processing" is a process that analyzes the user's emotions and optimizes the information provided based on the results.
[0326] A "generating agent" is a device or program that has the function of deriving the optimal search results using a specific algorithm or technology.
[0327] A "Central Information Processing Unit" is a primary computer system used for data processing and sentiment analysis across the entire system.
[0328] A "terminal device" is an electronic device that includes input devices for direct user operation.
[0329] This invention is a system that analyzes a user's emotional state based on their information requests and provides optimal search results. The main components of the system include a terminal device that receives information requests from the user, a central information processing device that records and analyzes the information, and a generation agent that generates and provides the results.
[0330] The user enters a search query using a terminal device. This terminal can be a general-purpose computer or smart device, and information is entered via the appropriate interface. The entered information request is sent to the central information processing unit.
[0331] The server acts as a central information processing unit, receiving information requests. Based on the recorded information, this server generates shortcuts and builds the foundation for utilizing generation agents. It also analyzes the user's emotional state from their input using an emotion processing engine. For emotion processing, natural language processing libraries (e.g., NLTK and spaCy) are used to determine whether the user's emotions are positive or negative.
[0332] Based on the analyzed sentiment data, the server utilizes a generative AI model to generate user-optimized search results. This highlights results and information that are relevant to the user's emotional state.
[0333] The terminal device displays search results received from the server to the user. For example, if a user searches for "ways to relieve stress," and negative emotions are detected, content effective for relaxation will be displayed. Conversely, if positive emotions are detected, new relaxation techniques will be recommended.
[0334] An example of a prompt message would be: "The user is experiencing high stress and is searching for relaxation methods. Please suggest a plan that prioritizes providing information effective for relaxation." This system allows users to efficiently obtain a search experience tailored to their emotional state.
[0335] The flow of the specific processing in Example 2 will be explained using Figure 13.
[0336] Step 1:
[0337] The user enters an information request on the terminal. The user enters queries through the interface on the terminal device to obtain specific information or knowledge of interest. For example, they might enter a specific request in text format, such as "a nearby cafe." The entered data is sent from the terminal to the server as an information request.
[0338] Step 2:
[0339] The server receives and records information requests. The server records the received information requests in a database and uses this as basic data for analysis. Specifically, it parses the query content and compares it with past request history stored in the database. This information is used in the sentiment analysis and shortcut generation steps described later.
[0340] Step 3:
[0341] The server analyzes the user's emotional state. Using a natural language processing library, the server analyzes the user's emotions from the information request. It performs text analysis on the input language data and extracts the positive / negative tendencies of keywords. Based on this analysis, it evaluates the user's emotional state. The output identifies the user's emotional state as either positive or negative.
[0342] Step 4:
[0343] The server generates search results based on the user's emotional state. The server utilizes a generative AI model to produce search results that reflect the analyzed emotional information. Specifically, if the emotional state is positive, it prioritizes information offering new experiences; if it's negative, it prioritizes information related to comfort and relaxation. The resulting search results are output as an information set adjusted according to the user's emotional state.
[0344] Step 5:
[0345] The server sends the generated search results to the device. To deliver information that reflects the user's emotional state, the server sends the generated search results to the device as data packets. The transmitted data is visualized in real time for the user, providing personalized feedback.
[0346] Step 6:
[0347] The device displays results optimized for the user. Based on search results received from the server, the device visually displays information relevant to the user. By receiving information customized based on their own emotions, users can enjoy a more satisfying experience.
[0348] (Application Example 2)
[0349] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."
[0350] Traditional search systems often provide uniform search results without considering the user's emotional state, which can lead to decreased user satisfaction. Furthermore, they fail to offer a personalized search experience, hindering users from quickly accessing the information they seek.
[0351] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.
[0352] In this invention, the server includes means for recognizing the user's emotional state, means for adjusting search queries based on the recognized emotions, and means for customizing the information provided. This enables the rapid provision of information appropriate to the user's emotions, resulting in a personalized search experience.
[0353] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's emotions from their facial expressions, voice, input actions, etc., and identify that state.
[0354] "Means of adjusting search queries" refers to technologies that automatically correct or transform search queries entered by users based on the recognized emotional state of the user.
[0355] "Methods for generating shortcuts" are techniques that identify frequently used processes from previously recorded search operations and create shortened paths to simplify them.
[0356] "Means of process automation" refers to technologies that automate a series of steps to efficiently perform search operations based on generated shortcuts.
[0357] "Means for activating generation agents" refers to technologies that activate agents to quickly collect necessary information through automated processes.
[0358] "Means of presenting collected search results to the user" refers to technologies that appropriately organize information collected by a generating agent and present it to the user visually or audibly.
[0359] The system for realizing this invention integrates and functions with numerous components to provide a personalized search experience based on the user's emotions.
[0360] When a user enters a search query, the device uses its built-in emotion recognition capabilities to capture facial expressions and voice through the camera and microphone, and analyze the user's emotional state. This utilizes emotion recognition APIs such as Microsoft Azure Face API and Google Cloud Vision API. The emotional state data is then sent to a server.
[0361] The server performs calculations to adjust the results based on this emotional state and the search query entered by the user. This process incorporates logic to learn patterns from past search history and generate appropriate shortcuts. It also activates a generation agent to quickly gather the necessary information through an automated process.
[0362] Furthermore, the search results obtained from the server are customized according to the user's emotions and presented on the device. When the user is expressing negative emotions, content related to relaxation and support is emphasized, while content encouraging excitement and new experiences is displayed when the user is expressing positive emotions.
[0363] For example, if a user searches for "ways to refresh," the device analyzes their emotions, and the server uses that emotion data to provide information on appropriate ways to refresh. Because users can easily obtain information that matches their interests, the satisfaction of the search experience improves.
[0364] An example of a prompt to input into a generative AI model would be, "Create an algorithm that refines search queries based on the user's emotions and recommends the most suitable products and information." This enables personalized information delivery tailored to that user.
[0365] The flow of a specific process in Application Example 2 will be explained using Figure 14.
[0366] Step 1:
[0367] The device accepts the user's search query input. As the user enters a specific query, the device's camera and microphone capture the user's facial expressions and voice. The input consists of the search query and the captured emotion-related data.
[0368] Step 2:
[0369] The device calls an emotion recognition API and analyzes the emotional state from the captured data. Using Microsoft Azure Face API and Google Cloud Vision API, the user's emotions are classified as "positive," "negative," "neutral," etc. The output is the user's emotional state data.
[0370] Step 3:
[0371] The terminal sends user emotional state data and search queries to the server. This data is input into the server's search process adjustment module. The server receives these inputs and begins the next calculation.
[0372] Step 4:
[0373] The server adjusts the search query based on the emotional state data it receives. It processes the data to add specific keywords or change the search scope according to the user's emotions. The adjusted search query is then output.
[0374] Step 5:
[0375] The server's shortcut generation module generates relevant shortcuts from past history based on the adjusted search query. This data becomes the input for the next automated process. The generated shortcuts are steps to quickly process the query.
[0376] Step 6:
[0377] The server automates the process based on the generated shortcuts. The automated process allows the generating agent to collect the necessary information. This process utilizes efficient data retrieval logic to obtain the required information from various databases and information sources.
[0378] Step 7:
[0379] The server re-evaluates the collected search results and prioritizes the most relevant information based on the user's emotional state. The prioritized search results become the final output and are prepared for transmission to the device.
[0380] Step 8:
[0381] The device presents the search results received from the server to the user. Information is displayed in a way that matches the user's emotions, improving the user's search experience. Here, the user can receive personalized feedback that responds to their emotions.
[0382] 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.
[0383] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0384] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.
[0385] [Third Embodiment]
[0386] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.
[0387] 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.
[0388] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).
[0389] 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.
[0390] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.
[0391] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).
[0392] 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.
[0393] 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.
[0394] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.
[0395] The 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.
[0396] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.
[0397] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".
[0398] The system according to the present invention provides a process for recording and automating specific search operations performed by a user. First, the user accesses a specific website using a terminal and enters a search query. The terminal records the user's search query input and related operations for later use. This recorded data is sent to a server, which generates shortcuts for the search operations based on that information.
[0399] This shortcut will be used for subsequent searches, enabling process automation. Specifically, the RPA (Robotic Process Automation) configured on the terminal will use this shortcut to perform an automated search based on the user's new search query. The server collects the search results obtained through the automated search process via a generating agent. The server then analyzes these search results and organizes them in a way that is easy for the user to understand. The organized information is presented to the user through the terminal, allowing the user to efficiently obtain the necessary information.
[0400] As a concrete example, consider a scenario where a user frequently searches for product information. During the initial product information search, the terminal records the user's actions. Subsequently, the server generates a shortcut, and the next time the user searches for a different product, the automated process on the terminal quickly performs the search, and the server accurately organizes and provides the results. This method significantly reduces the effort required for searches, allowing the user to focus on other important tasks.
[0401] The following describes the processing flow.
[0402] Step 1:
[0403] A user accesses a specific website using their device and enters a search query. The device records the user's search query and subsequent actions (e.g., clicking the search button).
[0404] Step 2:
[0405] The terminal sends the search operation data it recorded to the server. The server receives this data and saves it for future use.
[0406] Step 3:
[0407] The server analyzes the received data and generates shortcuts to the search operations performed by the user. These generated shortcuts are simplified procedures that allow for the rapid reproduction of similar searches.
[0408] Step 4:
[0409] The RPA configured on the terminal receives a shortcut sent from the server and builds an automated process based on that shortcut.
[0410] Step 5:
[0411] The next time the user enters a new search query, the RPA on the terminal will use existing shortcuts to automatically perform the search. The user only needs to enter the search query.
[0412] Step 6:
[0413] A generation agent on the server collects search results obtained through automated searches. These results are then analyzed and organized in a way that is most beneficial to the user.
[0414] Step 7:
[0415] The terminal receives organized search results from the server and presents them to the user. This allows the user to efficiently obtain the necessary information and concentrate on other tasks.
[0416] (Example 1)
[0417] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."
[0418] Modern information retrieval requires the efficient and rapid acquisition of necessary information from a wide variety of websites. However, manual information retrieval by users each time is time-consuming and laborious, and organizing search results is dependent on the individual, leading to decreased efficiency. This reduces productivity, so there is a need for methods to automate the information retrieval process and organize and provide the acquired information.
[0419] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.
[0420] In this invention, the server includes means for recording information retrieval requests entered via an information terminal operated by a user, means for constructing an information acquisition procedure based on the recorded information operations, and means for automating the operation flow based on the constructed information acquisition procedure. This makes it possible to streamline the user's search process and quickly obtain the necessary information.
[0421] An "information retrieval request" is an instruction that a user enters via an information terminal in order to obtain specific information.
[0422] An "information terminal" is a type of electronic device used by users to input and receive information, and includes computers and smartphones.
[0423] A "recording device" is a system or tool used to save user actions and input data.
[0424] An "information acquisition procedure" is a set of operational flows or processes designed to efficiently collect specific information based on recorded data.
[0425] A "construction device" is a system that analyzes recorded information to create new procedures and processes.
[0426] "Operation flow automation" refers to a set of steps configured to mechanically and repeatedly perform operations that were previously done manually.
[0427] A "collection mechanism" is a system or tool used to analyze and organize collected information.
[0428] "Analysis" is the process of scrutinizing collected information and extracting the necessary data.
[0429] "Presenting information visually" refers to displaying organized information in a graphical format so that users can easily understand it.
[0430] This invention is a system that enables efficient information retrieval and processing based on an information terminal operated by the user. Specifically, when a user makes a search request through the input device of the information terminal, the terminal records the request and related operations. The recorded data is analyzed using Python, JavaScript, or other languages to construct an information retrieval procedure. This procedure is stored and managed on a server.
[0431] Information terminals are equipped with RPA (Robotic Process Automation) software to automate operations, which helps to streamline repetitive user actions. Examples of RPA tools include UiPath and Automation Anywhere. This allows the terminal to execute automated workflows when a user searches for different information, enabling it to quickly collect the necessary data.
[0432] The collected data is analyzed by a collection mechanism on the server, and the necessary information is extracted and organized. Using a generative AI model, the data is formatted into a visually easy-to-understand format for the user. This formatted information is then provided to the user through a web browser or application, significantly improving the efficiency of information selection.
[0433] As a concrete example, consider a case where a user is "researching a new product." First, when the user starts a search on their information terminal, the steps are recorded. From the next time onward, the terminal executes an automated process based on the information retrieval procedure generated on the server, and the server quickly organizes and provides the results. This process allows the user to quickly obtain the latest information without any extra effort.
[0434] An example of a prompt message is as follows:
[0435] "Please automate the process of researching new products, and make it manageable and executable on a server."
[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.
[0437] Step 1:
[0438] The user uses an information terminal to enter a specific information retrieval request. The entered search query and user actions such as clicks are recorded on the terminal. This serves as foundational data for analyzing what the user is searching for and how they are pursuing information. The input consists of the user's search queries and action logs, while the output is this recorded data.
[0439] Step 2:
[0440] The terminal sends the recorded data to the server. The server analyzes the received data and constructs an information retrieval procedure. In this process, data aggregation and pattern matching are performed using scripts written in Python or similar languages. The output is the generated information retrieval procedure.
[0441] Step 3:
[0442] When the user searches for information again, the terminal automates the operation flow based on the established information retrieval procedure. Specifically, an RPA tool is used to replicate the user's search operation. The input is the previous procedure, and the output is the automated search results.
[0443] Step 4:
[0444] The server then re-analyzes the data collected through automated processes. It uses generative AI models to extract useful information and format the data to meet specific requirements. For example, it leverages natural language processing techniques to create structured information from unstructured data. The output is visualized information.
[0445] Step 5:
[0446] The user receives information organized and analyzed on the server via their terminal. The information is presented in a dashboard format, allowing the user to quickly and efficiently access the necessary data. Based on the output of prompts, specific actions are taken to support the user's decision-making. The output is visualized data that supports the user's decision-making.
[0447] (Application Example 1)
[0448] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."
[0449] In today's information-saturated environment, there is a need for effective search methods to efficiently obtain product and service information that users frequently access. However, traditional methods involve time-consuming search operations and information gathering, wasting valuable user time. Furthermore, there is a lack of systems that can quickly and appropriately present the information users need, making efficient information presentation, which contributes to faster decision-making, a key challenge.
[0450] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.
[0451] In this invention, the server includes means for recording information requests entered by the user, means for generating abbreviated operations based on the recorded information requests, means for automating processing based on the generated abbreviated operations, means for quickly displaying relevant information for subsequent use based on the user's operation history, and means for collecting information through automated processing and presenting it to the user in an organized manner. This enables the user to quickly and efficiently obtain the necessary information, saving time and accelerating decision-making.
[0452] A "user" refers to an entity that utilizes a particular system or device, and is a human being or a similar entity that performs operations.
[0453] An "information request" is an inquiry or query issued by a user when they want specific data or information.
[0454] "Means of recording" refers to a function that saves entered information and operation details and retains them for later use or analysis.
[0455] A "shortcut operation" is a process that simplifies multiple operations or procedures to enable a series of actions to be performed quickly.
[0456] "Means of generation" refers to functions and methods for creating new data or processes.
[0457] "Process automation" is a technology that makes it possible to mechanically execute processes that would normally be performed manually.
[0458] A "communication terminal" is a hardware device capable of data communication, and includes smartphones and tablets.
[0459] A "data processing device" refers to a computer or server used to manipulate, transform, and store data.
[0460] "Means of organizing and presenting information" refers to methods of analyzing and structuring collected data and displaying it in a format that is easy for users to understand.
[0461] This invention provides a system for users to quickly and efficiently acquire information. This system operates in cooperation with a server and a communication terminal and has the following configuration.
[0462] The server acts as a data processing unit, recording the information requests entered by the user. The recorded information serves as the basis for generating abbreviations to smoothly present search results. These generated abbreviations form the foundation for automating subsequent searches. The abbreviations are automatically generated based on data generated within the server and stored in a database.
[0463] The communication terminal is a user-operated device. Information requests entered on this device are recorded in real time, creating batches that automate specific processes. This process allows for the rapid display of relevant information for subsequent use based on the user's operation history. The communication terminal also serves as a means of presenting organized information to the user; after collecting the information, it visualizes and presents it in an easy-to-understand manner.
[0464] As an example, consider a case where a user searches for "popular gadgets" on their smartphone. This information request is recorded on the device, and a shortened search query is generated by the server. The next time the user opens the app, the latest information related to "popular gadgets" can be instantly presented to the user.
[0465] Using a generative AI model, the system analyzes information in real time and presents appropriate information based on prompts. Based on an example prompt, "Tell me about this week's popular wireless earphones," the server organizes the most relevant information for the user and sends it to their device. This system improves the efficiency of information retrieval, saving time.
[0466] The flow of a specific process in Application Example 1 will be explained using Figure 12.
[0467] Step 1:
[0468] The user enters a search query on a communication terminal. The entered information is recorded on the terminal. This input information is stored as data before being sent to the server.
[0469] Step 2:
[0470] The terminal sends the recorded information request to the server. The server stores the received information request in a database and generates abbreviated operations based on this information. The entered information request is stored in the database and used for subsequent searches.
[0471] Step 3:
[0472] The server uses a generative AI model to analyze received information requests and create shortened operations. It receives recorded information requests as input, analyzes them to find the data most relevant to the information the user is looking for, and generates shortened operations as output.
[0473] Step 4:
[0474] After the abbreviated operation is saved in the database, it is sent to the terminal when the user requests the relevant information again. At this point, the terminal executes the abbreviated operation, and from then on, the automated process provides the user with the information they need immediately. This is a concrete example of how the report generation function visually generates reports.
[0475] Step 5:
[0476] When a user requests the latest information using their device, the device receives search results from the server obtained from the generating AI model, organizes the retrieved data, and displays it to the user. It receives shortcut operations and new information requests from the user as input, organizes the data, and presents an easy-to-understand information report as output.
[0477] This series of processes allows users to quickly and efficiently obtain information and provide information based on prompts. The prompt "Tell me about this week's popular wireless earphones" is a specific example of how this process is quickly responded to.
[0478] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.
[0479] The system of this invention integrates an emotion engine to streamline user search operations. The emotion engine recognizes the user's emotional state and adjusts the search process accordingly. When a user enters a search query on a terminal, the terminal records the search and sends it to the server. The server generates shortcuts based on this data to prepare for future automated searches.
[0480] The emotion engine estimates user emotions from their input and interactions, and uses that information to derive the most suitable search results. If the user's emotions are positive, it will present standard search results; if negative, it will prioritize displaying more encouraging and supportive information. This feature provides feedback that matches the user's current emotional state, resulting in a more personalized information retrieval experience.
[0481] For example, if a user searches for "relaxation methods" while feeling stressed, the emotion engine will read the user's emotions and highlight information that is effective for relaxation. On the other hand, if the user is in a good mood, it will actively recommend information for learning new relaxation techniques. This allows users to have a search experience that is linked to their own emotions.
[0482] This system utilizes a generation agent provided by a server to collect search results, which are then analyzed by an emotion engine before being presented to the user via their device. This emotion-based system allows users to access important information with less effort and improve their satisfaction by receiving search results tailored to their own emotions.
[0483] The following describes the processing flow.
[0484] Step 1:
[0485] A user accesses a specific website using their device and enters a search query. The user's search query and related actions are recorded by the device.
[0486] Step 2:
[0487] The device sends the recorded search operation data to the server. The server receives this data and stores it for future use.
[0488] Step 3:
[0489] The server analyzes the received data and generates shortcuts based on the user's search actions. These shortcuts are simplified procedures for quickly reproducing similar searches.
[0490] Step 4:
[0491] The emotion engine configured in the device analyzes the user's input and interactions to estimate their current emotional state.
[0492] Step 5:
[0493] The emotion engine adjusts search queries based on the user's emotional state. For example, if a user is feeling stressed, it prioritizes information about relaxation methods.
[0494] Step 6:
[0495] Using shortcuts generated by the server and sentiment-adjusted queries, the RPA on the terminal automatically executes the search process.
[0496] Step 7:
[0497] A generation agent on the server collects search results gathered by the search process. Optimization results are then generated based on the analysis of the sentiment engine.
[0498] Step 8:
[0499] The device receives organized and optimized search results from the server and presents them to the user. This allows the user to quickly obtain search results that best suit their mood and focus on other tasks.
[0500] (Example 2)
[0501] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."
[0502] In search systems designed for efficient information retrieval, there is a problem in providing information that is sensitive to the user's emotions. Conventional systems present results without considering the user's individual emotional state, which can lead to decreased user satisfaction.
[0503] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.
[0504] In this invention, the server includes means for recording information requests entered by the user, means for generating shortcuts based on the recorded information requests, and means for performing emotion processing to analyze the user's emotional state. This makes it possible to provide results optimized according to the user's emotions.
[0505] An "information request" is a general term for the data or queries that a user enters into a search system.
[0506] A "shortcut" is a shortcut process created to streamline the user's search process.
[0507] "Emotional processing" is a process that analyzes the user's emotions and optimizes the information provided based on the results.
[0508] A "generating agent" is a device or program that has the function of deriving the optimal search results using a specific algorithm or technology.
[0509] A "Central Information Processing Unit" is a primary computer system used for data processing and sentiment analysis across the entire system.
[0510] A "terminal device" is an electronic device that includes input devices for direct user operation.
[0511] This invention is a system that analyzes a user's emotional state based on their information requests and provides optimal search results. The main components of the system include a terminal device that receives information requests from the user, a central information processing device that records and analyzes the information, and a generation agent that generates and provides the results.
[0512] The user enters a search query using a terminal device. This terminal can be a general-purpose computer or smart device, and information is entered via the appropriate interface. The entered information request is sent to the central information processing unit.
[0513] The server acts as a central information processing unit, receiving information requests. Based on the recorded information, this server generates shortcuts and builds the foundation for utilizing generation agents. It also analyzes the user's emotional state from their input using an emotion processing engine. For emotion processing, natural language processing libraries (e.g., NLTK and spaCy) are used to determine whether the user's emotions are positive or negative.
[0514] Based on the analyzed sentiment data, the server utilizes a generative AI model to generate user-optimized search results. This highlights results and information that are relevant to the user's emotional state.
[0515] The terminal device displays search results received from the server to the user. For example, if a user searches for "ways to relieve stress," and negative emotions are detected, content effective for relaxation will be displayed. Conversely, if positive emotions are detected, new relaxation techniques will be recommended.
[0516] An example of a prompt message would be: "The user is experiencing high stress and is searching for relaxation methods. Please suggest a plan that prioritizes providing information effective for relaxation." This system allows users to efficiently obtain a search experience tailored to their emotional state.
[0517] The flow of the specific processing in Example 2 will be explained using Figure 13.
[0518] Step 1:
[0519] The user enters an information request on the terminal. The user enters queries through the interface on the terminal device to obtain specific information or knowledge of interest. For example, they might enter a specific request in text format, such as "a nearby cafe." The entered data is sent from the terminal to the server as an information request.
[0520] Step 2:
[0521] The server receives and records information requests. The server records the received information requests in a database and uses this as basic data for analysis. Specifically, it parses the query content and compares it with past request history stored in the database. This information is used in the sentiment analysis and shortcut generation steps described later.
[0522] Step 3:
[0523] The server analyzes the user's emotional state. Using a natural language processing library, the server analyzes the user's emotions from the information request. It performs text analysis on the input language data and extracts the positive / negative tendencies of keywords. Based on this analysis, it evaluates the user's emotional state. The output identifies the user's emotional state as either positive or negative.
[0524] Step 4:
[0525] The server generates search results based on the user's emotional state. The server utilizes a generative AI model to produce search results that reflect the analyzed emotional information. Specifically, if the emotional state is positive, it prioritizes information offering new experiences; if it's negative, it prioritizes information related to comfort and relaxation. The resulting search results are output as an information set adjusted according to the user's emotional state.
[0526] Step 5:
[0527] The server sends the generated search results to the device. To deliver information that reflects the user's emotional state, the server sends the generated search results to the device as data packets. The transmitted data is visualized in real time for the user, providing personalized feedback.
[0528] Step 6:
[0529] The device displays results optimized for the user. Based on search results received from the server, the device visually displays information relevant to the user. By receiving information customized based on their own emotions, users can enjoy a more satisfying experience.
[0530] (Application Example 2)
[0531] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."
[0532] Traditional search systems often provide uniform search results without considering the user's emotional state, which can lead to decreased user satisfaction. Furthermore, they fail to offer a personalized search experience, hindering users from quickly accessing the information they seek.
[0533] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.
[0534] In this invention, the server includes means for recognizing the user's emotional state, means for adjusting search queries based on the recognized emotions, and means for customizing the information provided. This enables the rapid provision of information appropriate to the user's emotions, resulting in a personalized search experience.
[0535] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's emotions from their facial expressions, voice, input actions, etc., and identify that state.
[0536] "Means of adjusting search queries" refers to technologies that automatically correct or transform search queries entered by users based on the recognized emotional state of the user.
[0537] "Methods for generating shortcuts" are techniques that identify frequently used processes from previously recorded search operations and create shortened paths to simplify them.
[0538] "Means of process automation" refers to technologies that automate a series of steps to efficiently perform search operations based on generated shortcuts.
[0539] "Means for activating generation agents" refers to technologies that activate agents to quickly collect necessary information through automated processes.
[0540] "Means of presenting collected search results to the user" refers to technologies that appropriately organize information collected by a generating agent and present it to the user visually or audibly.
[0541] The system for realizing this invention integrates and functions with numerous components to provide a personalized search experience based on the user's emotions.
[0542] When a user enters a search query, the device uses its built-in emotion recognition capabilities to capture facial expressions and voice through the camera and microphone, and analyze the user's emotional state. This utilizes emotion recognition APIs such as Microsoft Azure Face API and Google Cloud Vision API. The emotional state data is then sent to a server.
[0543] The server performs calculations to adjust the results based on this emotional state and the search query entered by the user. This process incorporates logic to learn patterns from past search history and generate appropriate shortcuts. It also activates a generation agent to quickly gather the necessary information through an automated process.
[0544] Furthermore, the search results obtained from the server are customized according to the user's emotions and presented on the device. When the user is expressing negative emotions, content related to relaxation and support is emphasized, while content encouraging excitement and new experiences is displayed when the user is expressing positive emotions.
[0545] For example, if a user searches for "ways to refresh," the device analyzes their emotions, and the server uses that emotion data to provide information on appropriate ways to refresh. Because users can easily obtain information that matches their interests, the satisfaction of the search experience improves.
[0546] An example of a prompt to input into a generative AI model would be, "Create an algorithm that refines search queries based on the user's emotions and recommends the most suitable products and information." This enables personalized information delivery tailored to that user.
[0547] The flow of a specific process in Application Example 2 will be explained using Figure 14.
[0548] Step 1:
[0549] The device accepts the user's search query input. As the user enters a specific query, the device's camera and microphone capture the user's facial expressions and voice. The input consists of the search query and the captured emotion-related data.
[0550] Step 2:
[0551] The device calls an emotion recognition API and analyzes the emotional state from the captured data. Using Microsoft Azure Face API and Google Cloud Vision API, the user's emotions are classified as "positive," "negative," "neutral," etc. The output is the user's emotional state data.
[0552] Step 3:
[0553] The terminal sends user emotional state data and search queries to the server. This data is input into the server's search process adjustment module. The server receives these inputs and begins the next calculation.
[0554] Step 4:
[0555] The server adjusts the search query based on the emotional state data it receives. It processes the data to add specific keywords or change the search scope according to the user's emotions. The adjusted search query is then output.
[0556] Step 5:
[0557] The server's shortcut generation module generates relevant shortcuts from past history based on the adjusted search query. This data becomes the input for the next automated process. The generated shortcuts are steps to quickly process the query.
[0558] Step 6:
[0559] The server automates the process based on the generated shortcuts. The automated process allows the generating agent to collect the necessary information. This process utilizes efficient data retrieval logic to obtain the required information from various databases and information sources.
[0560] Step 7:
[0561] The server re-evaluates the collected search results and prioritizes the most relevant information based on the user's emotional state. The prioritized search results become the final output and are prepared for transmission to the device.
[0562] Step 8:
[0563] The device presents the search results received from the server to the user. Information is displayed in a way that matches the user's emotions, improving the user's search experience. Here, the user can receive personalized feedback that responds to their emotions.
[0564] 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.
[0565] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0566] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.
[0567] [Fourth Embodiment]
[0568] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.
[0569] 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.
[0570] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).
[0571] 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.
[0572] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.
[0573] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).
[0574] 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.
[0575] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.
[0576] 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.
[0577] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.
[0578] The 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.
[0579] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.
[0580] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".
[0581] The system according to the present invention provides a process for recording and automating specific search operations performed by a user. First, the user accesses a specific website using a terminal and enters a search query. The terminal records the user's search query input and related operations for later use. This recorded data is sent to a server, which generates shortcuts for the search operations based on that information.
[0582] This shortcut will be used for subsequent searches, enabling process automation. Specifically, the RPA (Robotic Process Automation) configured on the terminal will use this shortcut to perform an automated search based on the user's new search query. The server collects the search results obtained through the automated search process via a generating agent. The server then analyzes these search results and organizes them in a way that is easy for the user to understand. The organized information is presented to the user through the terminal, allowing the user to efficiently obtain the necessary information.
[0583] As a concrete example, consider a scenario where a user frequently searches for product information. During the initial product information search, the terminal records the user's actions. Subsequently, the server generates a shortcut, and the next time the user searches for a different product, the automated process on the terminal quickly performs the search, and the server accurately organizes and provides the results. This method significantly reduces the effort required for searches, allowing the user to focus on other important tasks.
[0584] The following describes the processing flow.
[0585] Step 1:
[0586] A user accesses a specific website using their device and enters a search query. The device records the user's search query and subsequent actions (e.g., clicking the search button).
[0587] Step 2:
[0588] The terminal sends the search operation data it recorded to the server. The server receives this data and saves it for future use.
[0589] Step 3:
[0590] The server analyzes the received data and generates shortcuts to the search operations performed by the user. These generated shortcuts are simplified procedures that allow for the rapid reproduction of similar searches.
[0591] Step 4:
[0592] The RPA configured on the terminal receives a shortcut sent from the server and builds an automated process based on that shortcut.
[0593] Step 5:
[0594] The next time the user enters a new search query, the RPA on the terminal will use existing shortcuts to automatically perform the search. The user only needs to enter the search query.
[0595] Step 6:
[0596] A generation agent on the server collects search results obtained through automated searches. These results are then analyzed and organized in a way that is most beneficial to the user.
[0597] Step 7:
[0598] The terminal receives organized search results from the server and presents them to the user. This allows the user to efficiently obtain the necessary information and concentrate on other tasks.
[0599] (Example 1)
[0600] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".
[0601] Modern information retrieval requires the efficient and rapid acquisition of necessary information from a wide variety of websites. However, manual information retrieval by users each time is time-consuming and laborious, and organizing search results is dependent on the individual, leading to decreased efficiency. This reduces productivity, so there is a need for methods to automate the information retrieval process and organize and provide the acquired information.
[0602] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.
[0603] In this invention, the server includes means for recording information retrieval requests entered via an information terminal operated by a user, means for constructing an information acquisition procedure based on the recorded information operations, and means for automating the operation flow based on the constructed information acquisition procedure. This makes it possible to streamline the user's search process and quickly obtain the necessary information.
[0604] An "information retrieval request" is an instruction that a user enters via an information terminal in order to obtain specific information.
[0605] An "information terminal" is a type of electronic device used by users to input and receive information, and includes computers and smartphones.
[0606] A "recording device" is a system or tool used to save user actions and input data.
[0607] An "information acquisition procedure" is a set of operational flows or processes designed to efficiently collect specific information based on recorded data.
[0608] A "construction device" is a system that analyzes recorded information to create new procedures and processes.
[0609] "Operation flow automation" refers to a set of steps configured to mechanically and repeatedly perform operations that were previously done manually.
[0610] A "collection mechanism" is a system or tool used to analyze and organize collected information.
[0611] "Analysis" is the process of scrutinizing collected information and extracting the necessary data.
[0612] "Presenting information visually" refers to displaying organized information in a graphical format so that users can easily understand it.
[0613] This invention is a system that enables efficient information retrieval and processing based on an information terminal operated by the user. Specifically, when a user makes a search request through the input device of the information terminal, the terminal records the request and related operations. The recorded data is analyzed using Python, JavaScript, or other languages to construct an information retrieval procedure. This procedure is stored and managed on a server.
[0614] Information terminals are equipped with RPA (Robotic Process Automation) software to automate operations, which helps to streamline repetitive user actions. Examples of RPA tools include UiPath and Automation Anywhere. This allows the terminal to execute automated workflows when a user searches for different information, enabling it to quickly collect the necessary data.
[0615] The collected data is analyzed by a collection mechanism on the server, and the necessary information is extracted and organized. Using a generative AI model, the data is formatted into a visually easy-to-understand format for the user. This formatted information is then provided to the user through a web browser or application, significantly improving the efficiency of information selection.
[0616] As a concrete example, consider a case where a user is "researching a new product." First, when the user starts a search on their information terminal, the steps are recorded. From the next time onward, the terminal executes an automated process based on the information retrieval procedure generated on the server, and the server quickly organizes and provides the results. This process allows the user to quickly obtain the latest information without any extra effort.
[0617] An example of a prompt message is as follows:
[0618] "Please automate the process of researching new products, and make it manageable and executable on a server."
[0619] The flow of the specific processing in Example 1 will be explained using Figure 11.
[0620] Step 1:
[0621] The user uses an information terminal to enter a specific information retrieval request. The entered search query and user actions such as clicks are recorded on the terminal. This serves as foundational data for analyzing what the user is searching for and how they are pursuing information. The input consists of the user's search queries and action logs, while the output is this recorded data.
[0622] Step 2:
[0623] The terminal sends the recorded data to the server. The server analyzes the received data and constructs an information retrieval procedure. In this process, data aggregation and pattern matching are performed using scripts written in Python or similar languages. The output is the generated information retrieval procedure.
[0624] Step 3:
[0625] When the user searches for information again, the terminal automates the operation flow based on the established information retrieval procedure. Specifically, an RPA tool is used to replicate the user's search operation. The input is the previous procedure, and the output is the automated search results.
[0626] Step 4:
[0627] The server then re-analyzes the data collected through automated processes. It uses generative AI models to extract useful information and format the data to meet specific requirements. For example, it leverages natural language processing techniques to create structured information from unstructured data. The output is visualized information.
[0628] Step 5:
[0629] The user receives information organized and analyzed on the server via their terminal. The information is presented in a dashboard format, allowing the user to quickly and efficiently access the necessary data. Based on the output of prompts, specific actions are taken to support the user's decision-making. The output is visualized data that supports the user's decision-making.
[0630] (Application Example 1)
[0631] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".
[0632] In today's information-saturated environment, there is a need for effective search methods to efficiently obtain product and service information that users frequently access. However, traditional methods involve time-consuming search operations and information gathering, wasting valuable user time. Furthermore, there is a lack of systems that can quickly and appropriately present the information users need, making efficient information presentation, which contributes to faster decision-making, a key challenge.
[0633] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.
[0634] In this invention, the server includes means for recording information requests entered by the user, means for generating abbreviated operations based on the recorded information requests, means for automating processing based on the generated abbreviated operations, means for quickly displaying relevant information for subsequent use based on the user's operation history, and means for collecting information through automated processing and presenting it to the user in an organized manner. This enables the user to quickly and efficiently obtain the necessary information, saving time and accelerating decision-making.
[0635] A "user" refers to an entity that utilizes a particular system or device, and is a human being or a similar entity that performs operations.
[0636] An "information request" is an inquiry or query issued by a user when they want specific data or information.
[0637] "Means of recording" refers to a function that saves entered information and operation details and retains them for later use or analysis.
[0638] A "shortcut operation" is a process that simplifies multiple operations or procedures to enable a series of actions to be performed quickly.
[0639] "Means of generation" refers to functions and methods for creating new data or processes.
[0640] "Process automation" is a technology that makes it possible to mechanically execute processes that would normally be performed manually.
[0641] A "communication terminal" is a hardware device capable of data communication, and includes smartphones and tablets.
[0642] A "data processing device" refers to a computer or server used to manipulate, transform, and store data.
[0643] "Means of organizing and presenting information" refers to methods of analyzing and structuring collected data and displaying it in a format that is easy for users to understand.
[0644] This invention provides a system for users to quickly and efficiently acquire information. This system operates in cooperation with a server and a communication terminal and has the following configuration.
[0645] The server acts as a data processing unit, recording the information requests entered by the user. The recorded information serves as the basis for generating abbreviations to smoothly present search results. These generated abbreviations form the foundation for automating subsequent searches. The abbreviations are automatically generated based on data generated within the server and stored in a database.
[0646] The communication terminal is a user-operated device. Information requests entered on this device are recorded in real time, creating batches that automate specific processes. This process allows for the rapid display of relevant information for subsequent use based on the user's operation history. The communication terminal also serves as a means of presenting organized information to the user; after collecting the information, it visualizes and presents it in an easy-to-understand manner.
[0647] As an example, consider a case where a user searches for "popular gadgets" on their smartphone. This information request is recorded on the device, and a shortened search query is generated by the server. The next time the user opens the app, the latest information related to "popular gadgets" can be instantly presented to the user.
[0648] Using a generative AI model, the system analyzes information in real time and presents appropriate information based on prompts. Based on an example prompt, "Tell me about this week's popular wireless earphones," the server organizes the most relevant information for the user and sends it to their device. This system improves the efficiency of information retrieval, saving time.
[0649] The flow of a specific process in Application Example 1 will be explained using Figure 12.
[0650] Step 1:
[0651] The user enters a search query on a communication terminal. The entered information is recorded on the terminal. This input information is stored as data before being sent to the server.
[0652] Step 2:
[0653] The terminal sends the recorded information request to the server. The server stores the received information request in a database and generates abbreviated operations based on this information. The entered information request is stored in the database and used for subsequent searches.
[0654] Step 3:
[0655] The server uses a generative AI model to analyze received information requests and create shortened operations. It receives recorded information requests as input, analyzes them to find the data most relevant to the information the user is looking for, and generates shortened operations as output.
[0656] Step 4:
[0657] After the abbreviated operation is saved in the database, it is sent to the terminal when the user requests the relevant information again. At this point, the terminal executes the abbreviated operation, and from then on, the automated process provides the user with the information they need immediately. This is a concrete example of how the report generation function visually generates reports.
[0658] Step 5:
[0659] When a user requests the latest information using their device, the device receives search results from the server obtained from the generating AI model, organizes the retrieved data, and displays it to the user. It receives shortcut operations and new information requests from the user as input, organizes the data, and presents an easy-to-understand information report as output.
[0660] This series of processes allows users to quickly and efficiently obtain information and provide information based on prompts. The prompt "Tell me about this week's popular wireless earphones" is a specific example of how this process is quickly responded to.
[0661] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.
[0662] The system of this invention integrates an emotion engine to streamline user search operations. The emotion engine recognizes the user's emotional state and adjusts the search process accordingly. When a user enters a search query on a terminal, the terminal records the search and sends it to the server. The server generates shortcuts based on this data to prepare for future automated searches.
[0663] The emotion engine estimates user emotions from their input and interactions, and uses that information to derive the most suitable search results. If the user's emotions are positive, it will present standard search results; if negative, it will prioritize displaying more encouraging and supportive information. This feature provides feedback that matches the user's current emotional state, resulting in a more personalized information retrieval experience.
[0664] For example, if a user searches for "relaxation methods" while feeling stressed, the emotion engine will read the user's emotions and highlight information that is effective for relaxation. On the other hand, if the user is in a good mood, it will actively recommend information for learning new relaxation techniques. This allows users to have a search experience that is linked to their own emotions.
[0665] This system utilizes a generation agent provided by a server to collect search results, which are then analyzed by an emotion engine before being presented to the user via their device. This emotion-based system allows users to access important information with less effort and improve their satisfaction by receiving search results tailored to their own emotions.
[0666] The following describes the processing flow.
[0667] Step 1:
[0668] A user accesses a specific website using their device and enters a search query. The user's search query and related actions are recorded by the device.
[0669] Step 2:
[0670] The device sends the recorded search operation data to the server. The server receives this data and stores it for future use.
[0671] Step 3:
[0672] The server analyzes the received data and generates shortcuts based on the user's search actions. These shortcuts are simplified procedures for quickly reproducing similar searches.
[0673] Step 4:
[0674] The emotion engine configured in the device analyzes the user's input and interactions to estimate their current emotional state.
[0675] Step 5:
[0676] The emotion engine adjusts search queries based on the user's emotional state. For example, if a user is feeling stressed, it prioritizes information about relaxation methods.
[0677] Step 6:
[0678] Using shortcuts generated by the server and sentiment-adjusted queries, the RPA on the terminal automatically executes the search process.
[0679] Step 7:
[0680] A generation agent on the server collects search results gathered by the search process. Optimization results are then generated based on the analysis of the sentiment engine.
[0681] Step 8:
[0682] The device receives organized and optimized search results from the server and presents them to the user. This allows the user to quickly obtain search results that best suit their mood and focus on other tasks.
[0683] (Example 2)
[0684] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".
[0685] In search systems designed for efficient information retrieval, there is a problem in providing information that is sensitive to the user's emotions. Conventional systems present results without considering the user's individual emotional state, which can lead to decreased user satisfaction.
[0686] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.
[0687] In this invention, the server includes means for recording information requests entered by the user, means for generating shortcuts based on the recorded information requests, and means for performing emotion processing to analyze the user's emotional state. This makes it possible to provide results optimized according to the user's emotions.
[0688] An "information request" is a general term for the data or queries that a user enters into a search system.
[0689] A "shortcut" is a shortcut process created to streamline the user's search process.
[0690] "Emotional processing" is a process that analyzes the user's emotions and optimizes the information provided based on the results.
[0691] A "generating agent" is a device or program that has the function of deriving the optimal search results using a specific algorithm or technology.
[0692] A "Central Information Processing Unit" is a primary computer system used for data processing and sentiment analysis across the entire system.
[0693] A "terminal device" is an electronic device that includes input devices for direct user operation.
[0694] This invention is a system that analyzes a user's emotional state based on their information requests and provides optimal search results. The main components of the system include a terminal device that receives information requests from the user, a central information processing device that records and analyzes the information, and a generation agent that generates and provides the results.
[0695] The user enters a search query using a terminal device. This terminal can be a general-purpose computer or smart device, and information is entered via the appropriate interface. The entered information request is sent to the central information processing unit.
[0696] The server acts as a central information processing unit, receiving information requests. Based on the recorded information, this server generates shortcuts and builds the foundation for utilizing generation agents. It also analyzes the user's emotional state from their input using an emotion processing engine. For emotion processing, natural language processing libraries (e.g., NLTK and spaCy) are used to determine whether the user's emotions are positive or negative.
[0697] Based on the analyzed sentiment data, the server utilizes a generative AI model to generate user-optimized search results. This highlights results and information that are relevant to the user's emotional state.
[0698] The terminal device displays search results received from the server to the user. For example, if a user searches for "ways to relieve stress," and negative emotions are detected, content effective for relaxation will be displayed. Conversely, if positive emotions are detected, new relaxation techniques will be recommended.
[0699] An example of a prompt message would be: "The user is experiencing high stress and is searching for relaxation methods. Please suggest a plan that prioritizes providing information effective for relaxation." This system allows users to efficiently obtain a search experience tailored to their emotional state.
[0700] The flow of the specific processing in Example 2 will be explained using Figure 13.
[0701] Step 1:
[0702] The user enters an information request on the terminal. The user enters queries through the interface on the terminal device to obtain specific information or knowledge of interest. For example, they might enter a specific request in text format, such as "a nearby cafe." The entered data is sent from the terminal to the server as an information request.
[0703] Step 2:
[0704] The server receives and records information requests. The server records the received information requests in a database and uses this as basic data for analysis. Specifically, it parses the query content and compares it with past request history stored in the database. This information is used in the sentiment analysis and shortcut generation steps described later.
[0705] Step 3:
[0706] The server analyzes the user's emotional state. Using a natural language processing library, the server analyzes the user's emotions from the information request. It performs text analysis on the input language data and extracts the positive / negative tendencies of keywords. Based on this analysis, it evaluates the user's emotional state. The output identifies the user's emotional state as either positive or negative.
[0707] Step 4:
[0708] The server generates search results based on the user's emotional state. The server utilizes a generative AI model to produce search results that reflect the analyzed emotional information. Specifically, if the emotional state is positive, it prioritizes information offering new experiences; if it's negative, it prioritizes information related to comfort and relaxation. The resulting search results are output as an information set adjusted according to the user's emotional state.
[0709] Step 5:
[0710] The server sends the generated search results to the device. To deliver information that reflects the user's emotional state, the server sends the generated search results to the device as data packets. The transmitted data is visualized in real time for the user, providing personalized feedback.
[0711] Step 6:
[0712] The device displays results optimized for the user. Based on search results received from the server, the device visually displays information relevant to the user. By receiving information customized based on their own emotions, users can enjoy a more satisfying experience.
[0713] (Application Example 2)
[0714] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".
[0715] Traditional search systems often provide uniform search results without considering the user's emotional state, which can lead to decreased user satisfaction. Furthermore, they fail to offer a personalized search experience, hindering users from quickly accessing the information they seek.
[0716] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.
[0717] In this invention, the server includes means for recognizing the user's emotional state, means for adjusting search queries based on the recognized emotions, and means for customizing the information provided. This enables the rapid provision of information appropriate to the user's emotions, resulting in a personalized search experience.
[0718] "Means for recognizing a user's emotional state" refers to technologies that analyze a user's emotions from their facial expressions, voice, input actions, etc., and identify that state.
[0719] "Means of adjusting search queries" refers to technologies that automatically correct or transform search queries entered by users based on the recognized emotional state of the user.
[0720] "Methods for generating shortcuts" are techniques that identify frequently used processes from previously recorded search operations and create shortened paths to simplify them.
[0721] "Means of process automation" refers to technologies that automate a series of steps to efficiently perform search operations based on generated shortcuts.
[0722] "Means for activating generation agents" refers to technologies that activate agents to quickly collect necessary information through automated processes.
[0723] "Means of presenting collected search results to the user" refers to technologies that appropriately organize information collected by a generating agent and present it to the user visually or audibly.
[0724] The system for realizing this invention integrates and functions with numerous components to provide a personalized search experience based on the user's emotions.
[0725] When a user enters a search query, the device uses its built-in emotion recognition capabilities to capture facial expressions and voice through the camera and microphone, and analyze the user's emotional state. This utilizes emotion recognition APIs such as Microsoft Azure Face API and Google Cloud Vision API. The emotional state data is then sent to a server.
[0726] The server performs calculations to adjust the results based on this emotional state and the search query entered by the user. This process incorporates logic to learn patterns from past search history and generate appropriate shortcuts. It also activates a generation agent to quickly gather the necessary information through an automated process.
[0727] Furthermore, the search results obtained from the server are customized according to the user's emotions and presented on the device. When the user is expressing negative emotions, content related to relaxation and support is emphasized, while content encouraging excitement and new experiences is displayed when the user is expressing positive emotions.
[0728] For example, if a user searches for "ways to refresh," the device analyzes their emotions, and the server uses that emotion data to provide information on appropriate ways to refresh. Because users can easily obtain information that matches their interests, the satisfaction of the search experience improves.
[0729] An example of a prompt to input into a generative AI model would be, "Create an algorithm that refines search queries based on the user's emotions and recommends the most suitable products and information." This enables personalized information delivery tailored to that user.
[0730] The flow of a specific process in Application Example 2 will be explained using Figure 14.
[0731] Step 1:
[0732] The device accepts the user's search query input. As the user enters a specific query, the device's camera and microphone capture the user's facial expressions and voice. The input consists of the search query and the captured emotion-related data.
[0733] Step 2:
[0734] The device calls an emotion recognition API and analyzes the emotional state from the captured data. Using Microsoft Azure Face API and Google Cloud Vision API, the user's emotions are classified as "positive," "negative," "neutral," etc. The output is the user's emotional state data.
[0735] Step 3:
[0736] The terminal sends user emotional state data and search queries to the server. This data is input into the server's search process adjustment module. The server receives these inputs and begins the next calculation.
[0737] Step 4:
[0738] The server adjusts the search query based on the emotional state data it receives. It processes the data to add specific keywords or change the search scope according to the user's emotions. The adjusted search query is then output.
[0739] Step 5:
[0740] The server's shortcut generation module generates relevant shortcuts from past history based on the adjusted search query. This data becomes the input for the next automated process. The generated shortcuts are steps to quickly process the query.
[0741] Step 6:
[0742] The server automates the process based on the generated shortcuts. The automated process allows the generating agent to collect the necessary information. This process utilizes efficient data retrieval logic to obtain the required information from various databases and information sources.
[0743] Step 7:
[0744] The server re-evaluates the collected search results and prioritizes the most relevant information based on the user's emotional state. The prioritized search results become the final output and are prepared for transmission to the device.
[0745] Step 8:
[0746] The device presents the search results received from the server to the user. Information is displayed in a way that matches the user's emotions, improving the user's search experience. Here, the user can receive personalized feedback that responds to their emotions.
[0747] 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.
[0748] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0749] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.
[0750] 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.
[0751] Figure 9 shows an 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.
[0752] 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.
[0753] 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.
[0754] 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, motorcycles, etc., 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, for example, based 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.
[0755] 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."
[0756] 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.
[0757] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.
[0758] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.
[0759] 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.
[0760] 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.
[0761] 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.
[0762] 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.
[0763] 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.
[0764] 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.
[0765] 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.
[0766] 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 the like 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.
[0767] 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 as being incorporated by reference.
[0768] The following is further disclosed regarding the embodiments described above.
[0769] (Claim 1)
[0770] A means of recording the search queries entered by the user,
[0771] A means of generating shortcuts based on recorded search operations,
[0772] A means of automating processes based on the generated shortcuts,
[0773] A means of launching a generation agent that collects search results through an automated process,
[0774] A means of presenting the collected search results to the user,
[0775] A system that includes this.
[0776] (Claim 2)
[0777] The system according to claim 1, which generates shortcuts on the server.
[0778] (Claim 3)
[0779] The system according to claim 1, which performs process automation at a terminal.
[0780] "Example 1"
[0781] (Claim 1)
[0782] A device that records information retrieval requests entered via an information terminal operated by a user,
[0783] A device that constructs information acquisition procedures based on recorded information manipulation,
[0784] A device that automates the operation flow based on the established information acquisition procedure,
[0785] A device that operates a collection mechanism to analyze the information results obtained by an automated operation flow,
[0786] A device that visually provides the user with the results of the analysis,
[0787] Information processing device including
[0788] (Claim 2)
[0789] The information processing apparatus according to claim 1, wherein the information acquisition procedure is constructed using an information integration processing apparatus.
[0790] (Claim 3)
[0791] The information processing device according to claim 1, which performs operation flow automation on an information terminal.
[0792] "Application Example 1"
[0793] (Claim 1)
[0794] A means of recording the information requests entered by the user,
[0795] A means for generating abbreviated operations based on recorded information requests,
[0796] A means of automating processing based on the generated shortened operations,
[0797] A means of quickly displaying relevant information for subsequent visits based on the user's operation history,
[0798] A means of collecting information through automated processing and presenting it to the user in an organized manner,
[0799] A system that includes this.
[0800] (Claim 2)
[0801] The system according to claim 1, wherein abbreviated operations are generated by a data processing device.
[0802] (Claim 3)
[0803] The system according to claim 1, wherein processing automation is performed at a communication terminal.
[0804] "Example 2 of combining an emotion engine"
[0805] (Claim 1)
[0806] A means of recording the information requests entered by the user,
[0807] A means of generating shortcuts based on recorded information requests,
[0808] A means of performing emotion processing to analyze the user's emotional state,
[0809] A means of utilizing a generation agent to generate optimized results based on emotional state,
[0810] A means of presenting results to the user according to their emotional state,
[0811] A system that includes this.
[0812] (Claim 2)
[0813] The system according to claim 1, wherein a shortcut is generated by a central information processing device.
[0814] (Claim 3)
[0815] The system according to claim 1, wherein process automation is performed using a terminal device.
[0816] "Application example 2 when combining with an emotional engine"
[0817] (Claim 1)
[0818] A means of recognizing the user's emotional state,
[0819] A means of adjusting search queries based on recognized emotions,
[0820] A means of recording the search queries entered by the user,
[0821] A means of generating shortcuts based on recorded search operations,
[0822] A means of automating processes based on the generated shortcuts,
[0823] A means of launching a generation agent that collects search results through an automated process,
[0824] A means of presenting the collected search results to the user,
[0825] A system that includes this.
[0826] (Claim 2)
[0827] The system according to claim 1, wherein a shortcut is generated by an information processing device.
[0828] (Claim 3)
[0829] The system according to claim 1, wherein process automation is performed using a communication device. [Explanation of Symbols]
[0830] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>
Claims
1. A means of recording the search queries entered by the user, A means of generating shortcuts based on recorded search operations, A means of automating processes based on the generated shortcuts, A means of launching a generation agent that collects search results through an automated process, A means of presenting the collected search results to the user, A system that includes this.
2. The system according to claim 1, wherein shortcuts are generated on the server.
3. The system according to claim 1, which performs process automation at a terminal.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A